Diff of the two buildlogs: -- --- b1/build.log 2025-02-26 21:49:39.216455609 +0000 +++ b2/build.log 2025-02-26 22:52:19.370548386 +0000 @@ -1,6 +1,6 @@ I: pbuilder: network access will be disabled during build -I: Current time: Wed Feb 26 08:48:41 -12 2025 -I: pbuilder-time-stamp: 1740602921 +I: Current time: Wed Apr 1 18:12:41 +14 2026 +I: pbuilder-time-stamp: 1775016761 I: Building the build Environment I: extracting base tarball [/var/cache/pbuilder/trixie-reproducible-base.tgz] I: copying local configuration @@ -25,52 +25,84 @@ dpkg-source: info: applying auto-gitignore I: Not using root during the build. I: Installing the build-deps -I: user script /srv/workspace/pbuilder/1847806/tmp/hooks/D02_print_environment starting +I: user script /srv/workspace/pbuilder/673649/tmp/hooks/D01_modify_environment starting +debug: Running on ionos5-amd64. +I: Changing host+domainname to test build reproducibility +I: Adding a custom variable just for the fun of it... +I: Changing /bin/sh to bash +'/bin/sh' -> '/bin/bash' +lrwxrwxrwx 1 root root 9 Apr 1 04:13 /bin/sh -> /bin/bash +I: Setting pbuilder2's login shell to /bin/bash +I: Setting pbuilder2's GECOS to second user,second room,second work-phone,second home-phone,second other +I: user script /srv/workspace/pbuilder/673649/tmp/hooks/D01_modify_environment finished +I: user script /srv/workspace/pbuilder/673649/tmp/hooks/D02_print_environment starting I: set - BUILDDIR='/build/reproducible-path' - BUILDUSERGECOS='first user,first room,first work-phone,first home-phone,first other' - BUILDUSERNAME='pbuilder1' - BUILD_ARCH='amd64' - DEBIAN_FRONTEND='noninteractive' - DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=20 ' - DISTRIBUTION='trixie' - HOME='/root' - HOST_ARCH='amd64' + BASH=/bin/sh + BASHOPTS=checkwinsize:cmdhist:complete_fullquote:extquote:force_fignore:globasciiranges:globskipdots:hostcomplete:interactive_comments:patsub_replacement:progcomp:promptvars:sourcepath + BASH_ALIASES=() + BASH_ARGC=() + BASH_ARGV=() + BASH_CMDS=() + BASH_LINENO=([0]="12" [1]="0") + BASH_LOADABLES_PATH=/usr/local/lib/bash:/usr/lib/bash:/opt/local/lib/bash:/usr/pkg/lib/bash:/opt/pkg/lib/bash:. + BASH_SOURCE=([0]="/tmp/hooks/D02_print_environment" [1]="/tmp/hooks/D02_print_environment") + BASH_VERSINFO=([0]="5" [1]="2" [2]="37" [3]="1" [4]="release" [5]="x86_64-pc-linux-gnu") + BASH_VERSION='5.2.37(1)-release' + BUILDDIR=/build/reproducible-path + BUILDUSERGECOS='second user,second room,second work-phone,second home-phone,second other' + BUILDUSERNAME=pbuilder2 + BUILD_ARCH=amd64 + DEBIAN_FRONTEND=noninteractive + DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=42 ' + DIRSTACK=() + DISTRIBUTION=trixie + EUID=0 + FUNCNAME=([0]="Echo" [1]="main") + GROUPS=() + HOME=/root + HOSTNAME=i-capture-the-hostname + HOSTTYPE=x86_64 + HOST_ARCH=amd64 IFS=' ' - INVOCATION_ID='7ffb9a4fa4b84b51a1fc442e27ad8d31' - LANG='C' - LANGUAGE='en_US:en' - LC_ALL='C' - MAIL='/var/mail/root' - OPTIND='1' - PATH='/usr/sbin:/usr/bin:/sbin:/bin:/usr/games' - PBCURRENTCOMMANDLINEOPERATION='build' - PBUILDER_OPERATION='build' - PBUILDER_PKGDATADIR='/usr/share/pbuilder' - PBUILDER_PKGLIBDIR='/usr/lib/pbuilder' - PBUILDER_SYSCONFDIR='/etc' - PPID='1847806' - PS1='# ' - PS2='> ' + INVOCATION_ID=f73f8563d4cc4cefb849885209e3d2e9 + LANG=C + LANGUAGE=et_EE:et + LC_ALL=C + MACHTYPE=x86_64-pc-linux-gnu + MAIL=/var/mail/root + OPTERR=1 + OPTIND=1 + OSTYPE=linux-gnu + PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path + PBCURRENTCOMMANDLINEOPERATION=build + PBUILDER_OPERATION=build + PBUILDER_PKGDATADIR=/usr/share/pbuilder + PBUILDER_PKGLIBDIR=/usr/lib/pbuilder + PBUILDER_SYSCONFDIR=/etc + PIPESTATUS=([0]="0") + POSIXLY_CORRECT=y + PPID=673649 PS4='+ ' - PWD='/' - SHELL='/bin/bash' - SHLVL='2' - SUDO_COMMAND='/usr/bin/timeout -k 18.1h 18h /usr/bin/ionice -c 3 /usr/bin/nice /usr/sbin/pbuilder --build --configfile /srv/reproducible-results/rbuild-debian/r-b-build.B5dsHxRP/pbuilderrc_qrYb --distribution trixie --hookdir /etc/pbuilder/first-build-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/trixie-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.B5dsHxRP/b1 --logfile b1/build.log librsb_1.3.0.2+dfsg-7.dsc' - SUDO_GID='110' - SUDO_UID='105' - SUDO_USER='jenkins' - TERM='unknown' - TZ='/usr/share/zoneinfo/Etc/GMT+12' - USER='root' - _='/usr/bin/systemd-run' - http_proxy='http://46.16.76.132:3128' + PWD=/ + SHELL=/bin/bash + SHELLOPTS=braceexpand:errexit:hashall:interactive-comments:posix + SHLVL=3 + SUDO_COMMAND='/usr/bin/timeout -k 24.1h 24h /usr/bin/ionice -c 3 /usr/bin/nice -n 11 /usr/bin/unshare --uts -- /usr/sbin/pbuilder --build --configfile /srv/reproducible-results/rbuild-debian/r-b-build.B5dsHxRP/pbuilderrc_bpmx --distribution trixie --hookdir /etc/pbuilder/rebuild-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/trixie-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.B5dsHxRP/b2 --logfile b2/build.log librsb_1.3.0.2+dfsg-7.dsc' + SUDO_GID=110 + SUDO_UID=105 + SUDO_USER=jenkins + TERM=unknown + TZ=/usr/share/zoneinfo/Etc/GMT-14 + UID=0 + USER=root + _='I: set' + http_proxy=http://213.165.73.152:3128 I: uname -a - Linux ionos1-amd64 6.1.0-31-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.1.128-1 (2025-02-07) x86_64 GNU/Linux + Linux i-capture-the-hostname 6.12.9+bpo-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.12.9-1~bpo12+1 (2025-01-19) x86_64 GNU/Linux I: ls -l /bin - lrwxrwxrwx 1 root root 7 Nov 22 14:40 /bin -> usr/bin -I: user script /srv/workspace/pbuilder/1847806/tmp/hooks/D02_print_environment finished + lrwxrwxrwx 1 root root 7 Nov 22 2024 /bin -> usr/bin +I: user script /srv/workspace/pbuilder/673649/tmp/hooks/D02_print_environment finished -> Attempting to satisfy build-dependencies -> Creating pbuilder-satisfydepends-dummy package Package: pbuilder-satisfydepends-dummy @@ -296,7 +328,7 @@ Get: 178 http://deb.debian.org/debian trixie/main amd64 libltdl-dev amd64 2.5.4-3 [167 kB] Get: 179 http://deb.debian.org/debian trixie/main amd64 libhwloc-dev amd64 2.12.0-1 [255 kB] Get: 180 http://deb.debian.org/debian trixie/main amd64 zlib1g-dev amd64 1:1.3.dfsg+really1.3.1-1+b1 [920 kB] -Fetched 382 MB in 20s (18.9 MB/s) +Fetched 382 MB in 16s (24.1 MB/s) Preconfiguring packages ... Selecting previously unselected package liblocale-gettext-perl. (Reading database ... (Reading database ... 5% (Reading database ... 10% (Reading database ... 15% (Reading database ... 20% (Reading database ... 25% (Reading database ... 30% (Reading database ... 35% (Reading database ... 40% (Reading database ... 45% (Reading database ... 50% (Reading database ... 55% (Reading database ... 60% (Reading database ... 65% (Reading database ... 70% (Reading database ... 75% (Reading database ... 80% (Reading database ... 85% (Reading database ... 90% (Reading database ... 95% (Reading database ... 100% (Reading database ... 19799 files and directories currently installed.) @@ -894,8 +926,8 @@ Setting up tzdata (2025a-2) ... Current default time zone: 'Etc/UTC' -Local time is now: Wed Feb 26 20:53:28 UTC 2025. -Universal Time is now: Wed Feb 26 20:53:28 UTC 2025. +Local time is now: Wed Apr 1 04:15:08 UTC 2026. +Universal Time is now: Wed Apr 1 04:15:08 UTC 2026. Run 'dpkg-reconfigure tzdata' if you wish to change it. Setting up libfontenc1:amd64 (1:1.1.8-1+b2) ... @@ -1062,7 +1094,11 @@ Building tag database... -> Finished parsing the build-deps I: Building the package -I: Running cd /build/reproducible-path/librsb-1.3.0.2+dfsg/ && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games" HOME="/nonexistent/first-build" dpkg-buildpackage -us -uc -b && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games" HOME="/nonexistent/first-build" dpkg-genchanges -S > ../librsb_1.3.0.2+dfsg-7_source.changes +I: user script /srv/workspace/pbuilder/673649/tmp/hooks/A99_set_merged_usr starting +Not re-configuring usrmerge for trixie +I: user script /srv/workspace/pbuilder/673649/tmp/hooks/A99_set_merged_usr finished +hostname: Name or service not known +I: Running cd /build/reproducible-path/librsb-1.3.0.2+dfsg/ && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path" HOME="/nonexistent/second-build" dpkg-buildpackage -us -uc -b && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path" HOME="/nonexistent/second-build" dpkg-genchanges -S > ../librsb_1.3.0.2+dfsg-7_source.changes dpkg-buildpackage: info: source package librsb dpkg-buildpackage: info: source version 1.3.0.2+dfsg-7 dpkg-buildpackage: info: source distribution unstable @@ -1082,62 +1118,62 @@ dh binary dh_update_autotools_config dh_autoreconf -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found libtoolize: putting auxiliary files in '.'. libtoolize: copying file './ltmain.sh' libtoolize: putting macros in AC_CONFIG_MACRO_DIRS, 'm4'. @@ -1179,90 +1215,90 @@ libtoolize: copying file 'm4/ltsugar.m4' libtoolize: copying file 'm4/ltversion.m4' libtoolize: copying file 'm4/lt~obsolete.m4' -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found configure.ac:66: installing './compile' configure.ac:65: installing './missing' Makefile.am: installing './depcomp' @@ -1448,7 +1484,7 @@ checking for m4... m4 checking for gmake... gmake checking for ggrep... /usr/bin/grep -checking for bash... /bin/bash +checking for bash... /bin/sh checking for gsed... /usr/bin/sed checking for cmp... cmp checking for basename... basename @@ -1565,7 +1601,7 @@ configure: It appears that Fortran programs can be linked without using the Fortran linker. configure: Using OPENMP_CFLAGS ok for linking an OpenMP program: adding it to LIBS. checking if your have a usable getrusage() ... 1 -checking for /bin/bash... /bin/bash +checking for /bin/sh... /bin/sh configure: Will not use Google Test. configure: You seem to not have GNU Octave or have disabled 'int' type. Part of the test suite will not be generated. If you want more testing capabilities, you should enable the 'int' type as well. checking that generated files are newer than configure... done @@ -1587,7 +1623,7 @@ config.status: executing depfiles commands config.status: executing libtool commands === configuring in librsbpp (/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether sleep supports fractional seconds... yes checking filesystem timestamp resolution... 0.01 @@ -1712,7 +1748,7 @@ configure: Will not use Google Test. checking whether you have std::thread... yes checking whether you have std::mutex... yes -/bin/bash +/bin/sh checking that generated files are newer than configure... done configure: creating ./config.status config.status: creating Makefile @@ -1721,7 +1757,7 @@ config.status: executing libtool commands configure: Successfully created a Makefile. === configuring in rsblib (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether sleep supports fractional seconds... yes checking filesystem timestamp resolution... 0.01 @@ -1833,7 +1869,7 @@ checking for filesystem... yes checking for main in -lstdc++fs... yes configure: Assuming you are yet to build librsb.la. (set LIBS= -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la) -/bin/bash +/bin/sh checking that generated files are newer than configure... done configure: creating ./config.status config.status: creating Makefile @@ -1843,7 +1879,7 @@ config.status: executing libtool commands configure: Created a Makefile. === configuring in rsbtest (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether sleep supports fractional seconds... yes checking filesystem timestamp resolution... 0.01 @@ -1957,7 +1993,7 @@ checking for filesystem... yes checking for rsb_lib_init... no checking for dd... yes -/bin/bash +/bin/sh /usr/bin/timeout checking that generated files are newer than configure... done configure: creating ./config.status @@ -1989,7 +2025,7 @@ ARFLAGS : cru M4 : m4 MAKE : gmake - BASH : /bin/bash + BASH : /bin/sh OCTAVE : false DOXYGEN : doxygen HELP2MAN : help2man @@ -2008,7 +2044,7 @@ Supported I/O functionality level : "7" vs "7" Interface Error Verbosity : "0" vs "0" Internals Error Verbosity : "0" vs "0" - Memory hierarchy info, detected : "L2:16/64/512K,L1:2/64/64K" + Memory hierarchy info, detected : "L2:16/64/4096K,L1:8/64/32K" Memory hierarchy info, selected : "" Maximum of supported threads : "128" Build Fortran examples : "yes" vs "yes" @@ -2038,31 +2074,31 @@ blhc: ignore-line-regexp: ^.*CC.*: gcc blhc: ignore-line-regexp: ^.*LD.*: /usr/bin/ld.* dh_auto_build - make -j20 + make -j42 make[2]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' gmake all-recursive gmake[3]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' Making all in librsbpp gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp.o rsbpp.cpp -/bin/bash ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_coo.lo rsbpp_coo.cpp -/bin/bash ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_csr.lo rsbpp_csr.cpp +/bin/sh ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_coo.lo rsbpp_coo.cpp +/bin/sh ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_csr.lo rsbpp_csr.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbtt.o rsbtt.cpp gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -c -o rsbct.o rsbct.c -libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_csr.cpp -fPIC -DPIC -o .libs/rsbpp_csr.o libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -fPIC -DPIC -o .libs/rsbpp_coo.o +libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_csr.cpp -fPIC -DPIC -o .libs/rsbpp_csr.o libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -o rsbpp_coo.o >/dev/null 2>&1 libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_csr.cpp -o rsbpp_csr.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o librsbpp.la rsbpp_coo.lo rsbpp_csr.lo -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o librsbpp.la rsbpp_coo.lo rsbpp_csr.lo -lpthread -lstdc++fs libtool: link: ar cr .libs/librsbpp.a .libs/rsbpp_coo.o .libs/rsbpp_csr.o libtool: link: ranlib .libs/librsbpp.a libtool: link: ( cd ".libs" && rm -f "librsbpp.la" && ln -s "../librsbpp.la" "librsbpp.la" ) -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbpp rsbpp.o librsbpp.la -lpthread -lstdc++fs -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbtt rsbtt.o librsbpp.la -lpthread -lstdc++fs -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbct rsbct.o librsbpp.la -lpthread -lstdc++fs -libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbpp rsbpp.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbpp rsbpp.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbtt rsbtt.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbct rsbct.o librsbpp.la -lpthread -lstdc++fs libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbct rsbct.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbtt rsbtt.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp +libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbpp rsbpp.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' @@ -2080,208 +2116,246 @@ gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsbench-rsb_libspblas_tests.o `test -f 'rsb_libspblas_tests.c' || echo './'`rsb_libspblas_tests.c g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -c -o rsb_dummy.o rsb_dummy.cpp gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o ch2icfb-ch2icfb.o `test -f 'ch2icfb.c' || echo './'`ch2icfb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_stropts.lo `test -f 'rsb_stropts.c' || echo './'`rsb_stropts.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_strmif.lo `test -f 'rsb_strmif.c' || echo './'`rsb_strmif.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_unroll.lo `test -f 'rsb_unroll.c' || echo './'`rsb_unroll.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_lb.lo `test -f 'rsb_krnl_lb.c' || echo './'`rsb_krnl_lb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_permute.lo `test -f 'rsb_permute.c' || echo './'`rsb_permute.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mergesort.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_mergesort.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_permute.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_permute.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_stropts.lo `test -f 'rsb_stropts.c' || echo './'`rsb_stropts.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_strmif.lo `test -f 'rsb_strmif.c' || echo './'`rsb_strmif.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_unroll.lo `test -f 'rsb_unroll.c' || echo './'`rsb_unroll.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_lb.lo `test -f 'rsb_krnl_lb.c' || echo './'`rsb_krnl_lb.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_permute.lo `test -f 'rsb_permute.c' || echo './'`rsb_permute.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo `test -f 'rsb_krnl_bcss_spsv_u.c' || echo './'`rsb_krnl_bcss_spsv_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo `test -f 'rsb_krnl_bcss_spmv_u.c' || echo './'`rsb_krnl_bcss_spmv_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo `test -f 'rsb_krnl_bcss_misc_u.c' || echo './'`rsb_krnl_bcss_misc_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo `test -f 'rsb_krnl_bcoo_spmv_u.c' || echo './'`rsb_krnl_bcoo_spmv_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss.lo `test -f 'rsb_krnl_bcss.c' || echo './'`rsb_krnl_bcss.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spmv.lo `test -f 'rsb_spmv.c' || echo './'`rsb_spmv.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_ompio.lo `test -f 'rsb_ompio.c' || echo './'`rsb_ompio.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spgemm_csr.lo `test -f 'rsb_spgemm_csr.c' || echo './'`rsb_spgemm_csr.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mio.lo `test -f 'rsb_mio.c' || echo './'`rsb_mio.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_op.lo `test -f 'rsb_op.c' || echo './'`rsb_op.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_bio.lo `test -f 'rsb_bio.c' || echo './'`rsb_bio.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_set.lo `test -f 'rsb_set.c' || echo './'`rsb_set.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo.lo `test -f 'rsb_coo.c' || echo './'`rsb_coo.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_csr.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_lb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_lb.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_stropts.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_vb.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_unroll.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_unroll.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_bench.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_strmif.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo `test -f 'rsb_krnl_bcss_spsv_u.c' || echo './'`rsb_krnl_bcss_spsv_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo `test -f 'rsb_krnl_bcss_spmv_u.c' || echo './'`rsb_krnl_bcss_spmv_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo `test -f 'rsb_krnl_bcss_misc_u.c' || echo './'`rsb_krnl_bcss_misc_u.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_lb.c -o librsb_nounroll_la-rsb_krnl_lb.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_unroll.c -o librsb_nounroll_la-rsb_unroll.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -o librsb_nounroll_la-rsb_stropts.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_permute.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_permute.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_unroll.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_unroll.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_l.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_stropts.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo `test -f 'rsb_krnl_bcoo_spmv_u.c' || echo './'`rsb_krnl_bcoo_spmv_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss.lo `test -f 'rsb_krnl_bcss.c' || echo './'`rsb_krnl_bcss.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spmv.lo `test -f 'rsb_spmv.c' || echo './'`rsb_spmv.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_l.c -o librsb_nounroll_la-rsb_krnl_bcss_l.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spmv.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_merge.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_merge.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_ompio.lo `test -f 'rsb_ompio.c' || echo './'`rsb_ompio.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -o librsb_nounroll_la-rsb_strmif.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_u.c -o librsb_nounroll_la-rsb_krnl_bcss_u.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spgemm_csr.lo `test -f 'rsb_spgemm_csr.c' || echo './'`rsb_spgemm_csr.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_ompio.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_ompio.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -o librsb_nounroll_la-rsb_krnl_bcss.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm_csr.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spgemm_csr.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_util.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -o librsb_nounroll_la-rsb_bench.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spsum_misc.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_prec.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_prec.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mio.lo `test -f 'rsb_mio.c' || echo './'`rsb_mio.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_ompio.c -o librsb_nounroll_la-rsb_ompio.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_bio.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spsum_misc.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_ompio.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_ompio.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_is.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mio.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_permute.c -o librsb_nounroll_la-rsb_permute.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_op.lo `test -f 'rsb_op.c' || echo './'`rsb_op.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_merge.c -o librsb_nounroll_la-rsb_merge.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm_csr.c -o librsb_nounroll_la-rsb_spgemm_csr.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_bio.lo `test -f 'rsb_bio.c' || echo './'`rsb_bio.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_prec.c -o librsb_nounroll_la-rsb_prec.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_op.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_op.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_bio.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_op.c -o librsb_base_la-rsb_op.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_set.lo `test -f 'rsb_set.c' || echo './'`rsb_set.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -o librsb_base_la-rsb_bio.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo.lo `test -f 'rsb_coo.c' || echo './'`rsb_coo.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_util.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_strmif.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_bench.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mergesort.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_mergesort.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_get.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_get.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mio.c -o librsb_base_la-rsb_mio.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_csr.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_set.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_set.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_symm.lo `test -f 'rsb_coo_symm.c' || echo './'`rsb_coo_symm.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_idx.lo `test -f 'rsb_idx.c' || echo './'`rsb_idx.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_merge.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_merge.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spmv.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_set.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_set.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm_csr.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spgemm_csr.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_op.c -o librsb_base_la-rsb_op.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_symm.lo `test -f 'rsb_coo_symm.c' || echo './'`rsb_coo_symm.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -o librsb_base_la-rsb_bio.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_check.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_check.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srt.lo `test -f 'rsb_srt.c' || echo './'`rsb_srt.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr.c -o librsb_base_la-rsb_csr.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_u.c -o librsb_nounroll_la-rsb_krnl_bcss_u.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_symm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_symm.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_set.c -o librsb_base_la-rsb_set.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_lb.c -o librsb_nounroll_la-rsb_krnl_lb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -o librsb_nounroll_la-rsb_stropts.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr.c -o librsb_base_la-rsb_csr.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_idx.lo `test -f 'rsb_idx.c' || echo './'`rsb_idx.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_unroll.c -o librsb_nounroll_la-rsb_unroll.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_ompio.c -o librsb_nounroll_la-rsb_ompio.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_l.c -o librsb_nounroll_la-rsb_krnl_bcss_l.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -o librsb_nounroll_la-rsb_krnl_bcss.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srt.lo `test -f 'rsb_srt.c' || echo './'`rsb_srt.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_idx.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_idx.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srt.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srtp.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srtp.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_check.c -o librsb_base_la-rsb_coo_check.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_test_accuracy.lo `test -f 'rsb_test_accuracy.c' || echo './'`rsb_test_accuracy.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_src.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_src.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_clone.lo `test -f 'rsb_clone.c' || echo './'`rsb_clone.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec.lo `test -f 'rsb_rec.c' || echo './'`rsb_rec.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_render.lo `test -f 'rsb_render.c' || echo './'`rsb_render.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_symm.c -o librsb_base_la-rsb_coo_symm.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_test_accuracy.lo `test -f 'rsb_test_accuracy.c' || echo './'`rsb_test_accuracy.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_clone.lo `test -f 'rsb_clone.c' || echo './'`rsb_clone.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_clone.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_clone.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_test_accuracy.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_test_accuracy.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec.lo `test -f 'rsb_rec.c' || echo './'`rsb_rec.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srtp.c -o librsb_base_la-rsb_srtp.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_render.lo `test -f 'rsb_render.c' || echo './'`rsb_render.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_check.c -o librsb_base_la-rsb_coo_check.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_msort_up.lo `test -f 'rsb_msort_up.c' || echo './'`rsb_msort_up.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_blas_stuff.lo `test -f 'rsb_blas_stuff.c' || echo './'`rsb_blas_stuff.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_clone.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_clone.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_gen.lo `test -f 'rsb_gen.c' || echo './'`rsb_gen.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_set.c -o librsb_base_la-rsb_set.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_msort_up.lo `test -f 'rsb_msort_up.c' || echo './'`rsb_msort_up.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_get.c -o librsb_base_la-rsb_get.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_render.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_render.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_idx.c -o librsb_base_la-rsb_idx.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -o librsb_base_la-rsb_srt.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_msort_up.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_msort_up.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_test_accuracy.c -o librsb_base_la-rsb_test_accuracy.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_eps.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_eps.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_msort_up.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_msort_up.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_sys.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_sys.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_blas_stuff.lo `test -f 'rsb_blas_stuff.c' || echo './'`rsb_blas_stuff.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_render.c -o librsb_base_la-rsb_render.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_clone.c -o librsb_base_la-rsb_clone.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_gen.lo `test -f 'rsb_gen.c' || echo './'`rsb_gen.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_blas_stuff.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_msort_up.c -o librsb_base_la-rsb_msort_up.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rsb.lo `test -f 'rsb_rsb.c' || echo './'`rsb_rsb.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_gen.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_gen.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rsb.lo `test -f 'rsb_rsb.c' || echo './'`rsb_rsb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_err.lo `test -f 'rsb_err.c' || echo './'`rsb_err.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm_csr.c -o librsb_nounroll_la-rsb_spgemm_csr.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_merge.c -o librsb_nounroll_la-rsb_merge.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_err.lo `test -f 'rsb_err.c' || echo './'`rsb_err.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_perf.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_perf.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_sys.c -o librsb_base_la-rsb_sys.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rsb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rsb.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_prec.c -o librsb_nounroll_la-rsb_prec.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_err.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_err.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_render.c -o librsb_base_la-rsb_render.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_msort_up.c -o librsb_base_la-rsb_msort_up.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -o librsb_nounroll_la-rsb_strmif.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_test_accuracy.c -o librsb_base_la-rsb_test_accuracy.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_tune.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_sys.c -o librsb_base_la-rsb_sys.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srtp.c -o librsb_base_la-rsb_srtp.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_err.c -o librsb_base_la-rsb_err.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_do.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_do.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec.c -o librsb_base_la-rsb_rec.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_internals.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_internals.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_garbage.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_err.c -o librsb_base_la-rsb_err.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rsb.c -o librsb_base_la-rsb_rsb.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -o librsb_base_la-rsb_srt.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_perf.c -o librsb_base_la-rsb_perf.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mmio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mmio.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_internals.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_internals.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rsb.c -o librsb_base_la-rsb_rsb.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_gen.c -o librsb_base_la-rsb_gen.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -o librsb_base_la-rsb_garbage.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_do.c -o librsb_base_la-rsb_do.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mmio.c -o librsb_base_la-rsb_mmio.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_partition.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_partition.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mbw.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mbw.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_clone.c -o librsb_base_la-rsb_clone.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spgemm.lo `test -f 'rsb_spgemm.c' || echo './'`rsb_spgemm.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_limiter.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_limiter.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_partition.c -o librsb_base_la-rsb_partition.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spgemm.lo `test -f 'rsb_spgemm.c' || echo './'`rsb_spgemm.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mbw.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mbw.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_fpb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_fpb.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spgemm.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_swt.lo `test -f 'rsb_swt.c' || echo './'`rsb_swt.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_lock.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_lock.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_idx.c -o librsb_base_la-rsb_idx.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mio.c -o librsb_base_la-rsb_mio.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsum.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_gen.c -o librsb_base_la-rsb_gen.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_swt.lo `test -f 'rsb_swt.c' || echo './'`rsb_swt.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsv.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_init.lo `test -f 'rsb_init.c' || echo './'`rsb_init.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_dump.lo `test -f 'rsb_dump.c' || echo './'`rsb_dump.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_lock.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_lock.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_swt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_swt.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_init.lo `test -f 'rsb_init.c' || echo './'`rsb_init.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_dump.lo `test -f 'rsb_dump.c' || echo './'`rsb_dump.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_limiter.c -o librsb_base_la-rsb_limiter.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum.c -o librsb_base_la-rsb_spsum.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -o librsb_base_la-rsb_tune.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_init.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_init.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_lock.c -o librsb_base_la-rsb_lock.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm.c -o librsb_base_la-rsb_spgemm.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_swt.c -o librsb_base_la-rsb_swt.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mbw.c -o librsb_base_la-rsb_mbw.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_partition.c -o librsb_base_la-rsb_partition.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_cpmv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_cpmv.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_user.lo `test -f 'rsb_user.c' || echo './'`rsb_user.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -o librsb_base_la-rsb_garbage.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_get.c -o librsb_base_la-rsb_get.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_user.lo `test -f 'rsb_user.c' || echo './'`rsb_user.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_limiter.c -o librsb_base_la-rsb_limiter.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_lock.c -o librsb_base_la-rsb_lock.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -o librsb_nounroll_la-rsb_bench.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo2rec.lo `test -f 'rsb_coo2rec.c' || echo './'`rsb_coo2rec.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_asm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_asm.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum.c -o librsb_base_la-rsb_spsum.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2coo.lo `test -f 'rsb_rec2coo.c' || echo './'`rsb_rec2coo.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2csr.lo `test -f 'rsb_rec2csr.c' || echo './'`rsb_rec2csr.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_user.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_user.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_init.c -o librsb_base_la-rsb_init.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_dump.c -o librsb_base_la-rsb_dump.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo2rec.lo `test -f 'rsb_coo2rec.c' || echo './'`rsb_coo2rec.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsv.c -o librsb_base_la-rsb_spsv.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo2rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo2rec.o +/bin/sh ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_permute.c -o librsb_nounroll_la-rsb_permute.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2csr.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr2coo.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_do.c -o librsb_base_la-rsb_do.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2coo.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mmio.c -o librsb_base_la-rsb_mmio.o >/dev/null 2>&1 +gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.o rsb_blas_sparse.F90 +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o ch2icfb ch2icfb-ch2icfb.o -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -fPIC -DPIC -o .libs/rsb_libspblas_handle.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -fPIC -DPIC -o .libs/rsb_libspblas.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_swt.c -o librsb_base_la-rsb_swt.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_asm.c -o librsb_base_la-rsb_asm.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2coo.lo `test -f 'rsb_rec2coo.c' || echo './'`rsb_rec2coo.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2csr.lo `test -f 'rsb_rec2csr.c' || echo './'`rsb_rec2csr.c +libtool: warning: '-version-info' is ignored for programs +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2csr.c -o librsb_base_la-rsb_rec2csr.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_dump.c -o librsb_base_la-rsb_dump.o >/dev/null 2>&1 +libtool: link: gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_init.c -o librsb_base_la-rsb_init.o >/dev/null 2>&1 +if test -f ./rsb_types.h -a ! -f ./rsb_types.h ; then cp -pv ./rsb_types.h ./rsb_types.h ; fi # out-of-dir behaviour varies between installations +if test -f ch2icfb ; then if SED=/usr/bin/sed GREP=/usr/bin/grep /bin/sh ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsv.c -o librsb_base_la-rsb_spsv.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.lo rsb.F90 +gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.o rsb.F90 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_user.c -o librsb_base_la-rsb_user.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm.c -o librsb_base_la-rsb_spgemm.o >/dev/null 2>&1 +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -fPIC -o .libs/rsb.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2coo.c -o librsb_base_la-rsb_rec2coo.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec.c -o librsb_base_la-rsb_rec.o >/dev/null 2>&1 +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -o rsb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mbw.c -o librsb_base_la-rsb_mbw.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo2rec.c -o librsb_base_la-rsb_coo2rec.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -o librsb_base_la-rsb_tune.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.o >/dev/null 2>&1 +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_spblas.la rsb_libspblas_handle.lo rsb_libspblas.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +libtool: warning: '-version-info/-version-number' is ignored for convenience libraries +libtool: link: ar cr .libs/librsb_spblas.a .libs/rsb_libspblas_handle.o .libs/rsb_libspblas.o +libtool: link: ranlib .libs/librsb_spblas.a +libtool: link: ( cd ".libs" && rm -f "librsb_spblas.la" && ln -s "../librsb_spblas.la" "librsb_spblas.la" ) +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_base.la librsb_base_la-rsb_is.lo librsb_base_la-rsb_mio.lo librsb_base_la-rsb_op.lo librsb_base_la-rsb_bio.lo librsb_base_la-rsb_get.lo librsb_base_la-rsb_set.lo librsb_base_la-rsb_coo.lo librsb_base_la-rsb_csr.lo librsb_base_la-rsb_coo_check.lo librsb_base_la-rsb_coo_symm.lo librsb_base_la-rsb_idx.lo librsb_base_la-rsb_srt.lo librsb_base_la-rsb_srtp.lo librsb_base_la-rsb_src.lo librsb_base_la-rsb_test_accuracy.lo librsb_base_la-rsb_clone.lo librsb_base_la-rsb_rec.lo librsb_base_la-rsb_render.lo librsb_base_la-rsb_eps.lo librsb_base_la-rsb_msort_up.lo librsb_base_la-rsb_sys.lo librsb_base_la-rsb_blas_stuff.lo librsb_base_la-rsb_gen.lo librsb_base_la-rsb_perf.lo librsb_base_la-rsb_rsb.lo librsb_base_la-rsb_err.lo librsb_base_la-rsb_tune.lo librsb_base_la-rsb_do.lo librsb_base_la-rsb_internals.lo librsb_base_la-rsb_garbage.lo librsb_base_la-rsb_mmio.lo librsb_base_la-rsb_partition.lo librsb_base_la-rsb_mbw.lo librsb_base_la-rsb_limiter.lo librsb_base_la-rsb_fpb.lo librsb_base_la-rsb_spgemm.lo librsb_base_la-rsb_spsum.lo librsb_base_la-rsb_spsv.lo librsb_base_la-rsb_lock.lo librsb_base_la-rsb_swt.lo librsb_base_la-rsb_init.lo librsb_base_la-rsb_dump.lo librsb_base_la-rsb_cpmv.lo librsb_base_la-rsb_asm.lo librsb_base_la-rsb_user.lo librsb_base_la-rsb_coo2rec.lo librsb_base_la-rsb_rec2coo.lo librsb_base_la-rsb_rec2csr.lo librsb_base_la-rsb_csr2coo.lo rsb_blas_sparse.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +libtool: warning: '-version-info/-version-number' is ignored for convenience libraries +libtool: link: ar cr .libs/librsb_base.a .libs/librsb_base_la-rsb_is.o .libs/librsb_base_la-rsb_mio.o .libs/librsb_base_la-rsb_op.o .libs/librsb_base_la-rsb_bio.o .libs/librsb_base_la-rsb_get.o .libs/librsb_base_la-rsb_set.o .libs/librsb_base_la-rsb_coo.o .libs/librsb_base_la-rsb_csr.o .libs/librsb_base_la-rsb_coo_check.o .libs/librsb_base_la-rsb_coo_symm.o .libs/librsb_base_la-rsb_idx.o .libs/librsb_base_la-rsb_srt.o .libs/librsb_base_la-rsb_srtp.o .libs/librsb_base_la-rsb_src.o .libs/librsb_base_la-rsb_test_accuracy.o .libs/librsb_base_la-rsb_clone.o .libs/librsb_base_la-rsb_rec.o .libs/librsb_base_la-rsb_render.o .libs/librsb_base_la-rsb_eps.o .libs/librsb_base_la-rsb_msort_up.o .libs/librsb_base_la-rsb_sys.o .libs/librsb_base_la-rsb_blas_stuff.o .libs/librsb_base_la-rsb_gen.o .libs/librsb_base_la-rsb_perf.o .libs/librsb_base_la-rsb_rsb.o .libs/librsb_base_la-rsb_err.o .libs/librsb_base_la-rsb_tune.o .libs/librsb_base_la-rsb_do.o .libs/librsb_base_la-rsb_internals.o .libs/librsb_base_la-rsb_garbage.o .libs/librsb_base_la-rsb_mmio.o .libs/librsb_base_la-rsb_partition.o .libs/librsb_base_la-rsb_mbw.o .libs/librsb_base_la-rsb_limiter.o .libs/librsb_base_la-rsb_fpb.o .libs/librsb_base_la-rsb_spgemm.o .libs/librsb_base_la-rsb_spsum.o .libs/librsb_base_la-rsb_spsv.o .libs/librsb_base_la-rsb_lock.o .libs/librsb_base_la-rsb_swt.o .libs/librsb_base_la-rsb_init.o .libs/librsb_base_la-rsb_dump.o .libs/librsb_base_la-rsb_cpmv.o .libs/librsb_base_la-rsb_asm.o .libs/librsb_base_la-rsb_user.o .libs/librsb_base_la-rsb_coo2rec.o .libs/librsb_base_la-rsb_rec2coo.o .libs/librsb_base_la-rsb_rec2csr.o .libs/librsb_base_la-rsb_csr2coo.o .libs/rsb_blas_sparse.o +libtool: link: ranlib .libs/librsb_base.a +libtool: link: ( cd ".libs" && rm -f "librsb_base.la" && ln -s "../librsb_base.la" "librsb_base.la" ) rsb_test_matops.c: In function 'rsb__main_block_partitioned_spmv_sxsa': rsb_test_matops.c:214:41: warning: '%s' directive writing up to 2047 bytes into a region of size 1011 [-Wformat-overflow=] 214 | rsb__sprintf(dst,"%s%s_%s_%.0lf_%s%s" "%s%s%s" "%s%s" "%s",pp?pp:"",h,rsb__getenv_nnr("HOSTNAME"),rsb_time(),buf,ap?ap:"", @@ -2300,45 +2374,8 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 32 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2coo.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2csr.o -/bin/bash ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr2coo.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -fPIC -DPIC -o .libs/rsb_libspblas_handle.o -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.c -gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.o rsb_blas_sparse.F90 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2csr.c -o librsb_base_la-rsb_rec2csr.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -fPIC -DPIC -o .libs/rsb_libspblas.o -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o ch2icfb ch2icfb-ch2icfb.o -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2coo.c -o librsb_base_la-rsb_rec2coo.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.o >/dev/null 2>&1 -libtool: warning: '-version-info' is ignored for programs -libtool: link: gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -if test -f ./rsb_types.h -a ! -f ./rsb_types.h ; then cp -pv ./rsb_types.h ./rsb_types.h ; fi # out-of-dir behaviour varies between installations -if test -f ch2icfb ; then if SED=/usr/bin/sed GREP=/usr/bin/grep /bin/bash ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo2rec.c -o librsb_base_la-rsb_coo2rec.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.lo rsb.F90 -gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.o rsb.F90 -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -fPIC -o .libs/rsb.o -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -o rsb.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_base.la librsb_base_la-rsb_is.lo librsb_base_la-rsb_mio.lo librsb_base_la-rsb_op.lo librsb_base_la-rsb_bio.lo librsb_base_la-rsb_get.lo librsb_base_la-rsb_set.lo librsb_base_la-rsb_coo.lo librsb_base_la-rsb_csr.lo librsb_base_la-rsb_coo_check.lo librsb_base_la-rsb_coo_symm.lo librsb_base_la-rsb_idx.lo librsb_base_la-rsb_srt.lo librsb_base_la-rsb_srtp.lo librsb_base_la-rsb_src.lo librsb_base_la-rsb_test_accuracy.lo librsb_base_la-rsb_clone.lo librsb_base_la-rsb_rec.lo librsb_base_la-rsb_render.lo librsb_base_la-rsb_eps.lo librsb_base_la-rsb_msort_up.lo librsb_base_la-rsb_sys.lo librsb_base_la-rsb_blas_stuff.lo librsb_base_la-rsb_gen.lo librsb_base_la-rsb_perf.lo librsb_base_la-rsb_rsb.lo librsb_base_la-rsb_err.lo librsb_base_la-rsb_tune.lo librsb_base_la-rsb_do.lo librsb_base_la-rsb_internals.lo librsb_base_la-rsb_garbage.lo librsb_base_la-rsb_mmio.lo librsb_base_la-rsb_partition.lo librsb_base_la-rsb_mbw.lo librsb_base_la-rsb_limiter.lo librsb_base_la-rsb_fpb.lo librsb_base_la-rsb_spgemm.lo librsb_base_la-rsb_spsum.lo librsb_base_la-rsb_spsv.lo librsb_base_la-rsb_lock.lo librsb_base_la-rsb_swt.lo librsb_base_la-rsb_init.lo librsb_base_la-rsb_dump.lo librsb_base_la-rsb_cpmv.lo librsb_base_la-rsb_asm.lo librsb_base_la-rsb_user.lo librsb_base_la-rsb_coo2rec.lo librsb_base_la-rsb_rec2coo.lo librsb_base_la-rsb_rec2csr.lo librsb_base_la-rsb_csr2coo.lo rsb_blas_sparse.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -libtool: warning: '-version-info/-version-number' is ignored for convenience libraries -libtool: link: ar cr .libs/librsb_base.a .libs/librsb_base_la-rsb_is.o .libs/librsb_base_la-rsb_mio.o .libs/librsb_base_la-rsb_op.o .libs/librsb_base_la-rsb_bio.o .libs/librsb_base_la-rsb_get.o .libs/librsb_base_la-rsb_set.o .libs/librsb_base_la-rsb_coo.o .libs/librsb_base_la-rsb_csr.o .libs/librsb_base_la-rsb_coo_check.o .libs/librsb_base_la-rsb_coo_symm.o .libs/librsb_base_la-rsb_idx.o .libs/librsb_base_la-rsb_srt.o .libs/librsb_base_la-rsb_srtp.o .libs/librsb_base_la-rsb_src.o .libs/librsb_base_la-rsb_test_accuracy.o .libs/librsb_base_la-rsb_clone.o .libs/librsb_base_la-rsb_rec.o .libs/librsb_base_la-rsb_render.o .libs/librsb_base_la-rsb_eps.o .libs/librsb_base_la-rsb_msort_up.o .libs/librsb_base_la-rsb_sys.o .libs/librsb_base_la-rsb_blas_stuff.o .libs/librsb_base_la-rsb_gen.o .libs/librsb_base_la-rsb_perf.o .libs/librsb_base_la-rsb_rsb.o .libs/librsb_base_la-rsb_err.o .libs/librsb_base_la-rsb_tune.o .libs/librsb_base_la-rsb_do.o .libs/librsb_base_la-rsb_internals.o .libs/librsb_base_la-rsb_garbage.o .libs/librsb_base_la-rsb_mmio.o .libs/librsb_base_la-rsb_partition.o .libs/librsb_base_la-rsb_mbw.o .libs/librsb_base_la-rsb_limiter.o .libs/librsb_base_la-rsb_fpb.o .libs/librsb_base_la-rsb_spgemm.o .libs/librsb_base_la-rsb_spsum.o .libs/librsb_base_la-rsb_spsv.o .libs/librsb_base_la-rsb_lock.o .libs/librsb_base_la-rsb_swt.o .libs/librsb_base_la-rsb_init.o .libs/librsb_base_la-rsb_dump.o .libs/librsb_base_la-rsb_cpmv.o .libs/librsb_base_la-rsb_asm.o .libs/librsb_base_la-rsb_user.o .libs/librsb_base_la-rsb_coo2rec.o .libs/librsb_base_la-rsb_rec2coo.o .libs/librsb_base_la-rsb_rec2csr.o .libs/librsb_base_la-rsb_csr2coo.o .libs/rsb_blas_sparse.o -libtool: link: ranlib .libs/librsb_base.a -libtool: link: ( cd ".libs" && rm -f "librsb_base.la" && ln -s "../librsb_base.la" "librsb_base.la" ) -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_spblas.la rsb_libspblas_handle.lo rsb_libspblas.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -libtool: warning: '-version-info/-version-number' is ignored for convenience libraries -libtool: link: ar cr .libs/librsb_spblas.a .libs/rsb_libspblas_handle.o .libs/rsb_libspblas.o -libtool: link: ranlib .libs/librsb_spblas.a -libtool: link: ( cd ".libs" && rm -f "librsb_spblas.la" && ln -s "../librsb_spblas.la" "librsb_spblas.la" ) libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -o librsb_nounroll_la-rsb_util.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl.c -o librsb_nounroll_la-rsb_krnl.o >/dev/null 2>&1 rsb_test_matops.c: In function 'rsb__main_block_partitioned_spsv_sxsx': rsb_test_matops.c:214:41: warning: '%s' directive writing up to 2047 bytes into a region of size 1011 [-Wformat-overflow=] 214 | rsb__sprintf(dst,"%s%s_%s_%.0lf_%s%s" "%s%s%s" "%s%s" "%s",pp?pp:"",h,rsb__getenv_nnr("HOSTNAME"),rsb_time(),buf,ap?ap:"", @@ -2353,7 +2390,6 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 32 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl.c -o librsb_nounroll_la-rsb_krnl.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.o >/dev/null 2>&1 rsb_test_matops.c: In function 'rsb__main_block_partitioned_mat_stats': rsb_test_matops.c:214:41: warning: '%s' directive writing up to 2047 bytes into a region of size 1011 [-Wformat-overflow=] @@ -2371,12 +2407,12 @@ | ~~~~~~~~~~~~~~~~~ libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_nounroll.la librsb_nounroll_la-rsb_stropts.lo librsb_nounroll_la-rsb_strmif.lo librsb_nounroll_la-rsb_unroll.lo librsb_nounroll_la-rsb_krnl_vb.lo librsb_nounroll_la-rsb_krnl_lb.lo librsb_nounroll_la-rsb_krnl.lo librsb_nounroll_la-rsb_bench.lo librsb_nounroll_la-rsb_mergesort.lo librsb_nounroll_la-rsb_permute.lo librsb_nounroll_la-rsb_krnl_bcss_l.lo librsb_nounroll_la-rsb_krnl_bcss_u.lo librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss.lo librsb_nounroll_la-rsb_spmv.lo librsb_nounroll_la-rsb_merge.lo librsb_nounroll_la-rsb_ompio.lo librsb_nounroll_la-rsb_util.lo librsb_nounroll_la-rsb_spgemm_csr.lo librsb_nounroll_la-rsb_spsum_misc.lo librsb_nounroll_la-rsb_prec.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_nounroll.la librsb_nounroll_la-rsb_stropts.lo librsb_nounroll_la-rsb_strmif.lo librsb_nounroll_la-rsb_unroll.lo librsb_nounroll_la-rsb_krnl_vb.lo librsb_nounroll_la-rsb_krnl_lb.lo librsb_nounroll_la-rsb_krnl.lo librsb_nounroll_la-rsb_bench.lo librsb_nounroll_la-rsb_mergesort.lo librsb_nounroll_la-rsb_permute.lo librsb_nounroll_la-rsb_krnl_bcss_l.lo librsb_nounroll_la-rsb_krnl_bcss_u.lo librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss.lo librsb_nounroll_la-rsb_spmv.lo librsb_nounroll_la-rsb_merge.lo librsb_nounroll_la-rsb_ompio.lo librsb_nounroll_la-rsb_util.lo librsb_nounroll_la-rsb_spgemm_csr.lo librsb_nounroll_la-rsb_spsum_misc.lo librsb_nounroll_la-rsb_prec.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_nounroll.a .libs/librsb_nounroll_la-rsb_stropts.o .libs/librsb_nounroll_la-rsb_strmif.o .libs/librsb_nounroll_la-rsb_unroll.o .libs/librsb_nounroll_la-rsb_krnl_vb.o .libs/librsb_nounroll_la-rsb_krnl_lb.o .libs/librsb_nounroll_la-rsb_krnl.o .libs/librsb_nounroll_la-rsb_bench.o .libs/librsb_nounroll_la-rsb_mergesort.o .libs/librsb_nounroll_la-rsb_permute.o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss.o .libs/librsb_nounroll_la-rsb_spmv.o .libs/librsb_nounroll_la-rsb_merge.o .libs/librsb_nounroll_la-rsb_ompio.o .libs/librsb_nounroll_la-rsb_util.o .libs/librsb_nounroll_la-rsb_spgemm_csr.o .libs/librsb_nounroll_la-rsb_spsum_misc.o .libs/librsb_nounroll_la-rsb_prec.o libtool: link: ranlib .libs/librsb_nounroll.a libtool: link: ( cd ".libs" && rm -f "librsb_nounroll.la" && ln -s "../librsb_nounroll.la" "librsb_nounroll.la" ) -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/x86_64-linux-gnu rsb.lo librsb_nounroll.la librsb_base.la librsb_spblas.la /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/librsbpp.la -lstdc++ -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/x86_64-linux-gnu rsb.lo librsb_nounroll.la librsb_base.la librsb_spblas.la /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/librsbpp.la -lstdc++ -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: gcc -shared -fPIC -DPIC .libs/rsb.o -Wl,--whole-archive ./.libs/librsb_nounroll.a ./.libs/librsb_base.a ./.libs/librsb_spblas.a /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/.libs/librsbpp.a -Wl,--no-whole-archive -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lpthread -lstdc++fs -lstdc++ -lhwloc -lz -lgfortran -lm -lquadmath -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Werror=format-security -O3 -Wl,-z -Wl,relro -fopenmp -fopenmp -Wl,-soname -Wl,librsb.so.0 -o .libs/librsb.so.0.0.0 libtool: link: (cd ".libs" && rm -f "librsb.so.0" && ln -s "librsb.so.0.0.0" "librsb.so.0") libtool: link: (cd ".libs" && rm -f "librsb.so" && ln -s "librsb.so.0.0.0" "librsb.so") @@ -2388,7 +2424,7 @@ libtool: link: ranlib .libs/librsb.a libtool: link: rm -fr .libs/librsb.lax libtool: link: ( cd ".libs" && rm -f "librsb.la" && ln -s "../librsb.la" "librsb.la" ) -/bin/bash ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -no-undefined -version-info 0:0:0 -Wl,-z,relro -o rsbench rsbench-rsbench.o rsbench-rsb_test_matops.o rsbench-rsb_mkl.o rsbench-rsb_genmm.o rsbench-rsb_mmls.o rsbench-rsb_pr.o rsbench-rsb_pcnt.o rsbench-rsb_failure_tests.o rsbench-rsb_libspblas_tests.o rsb_dummy.o librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -no-undefined -version-info 0:0:0 -Wl,-z,relro -o rsbench rsbench-rsbench.o rsbench-rsb_test_matops.o rsbench-rsb_mkl.o rsbench-rsb_genmm.o rsbench-rsb_mmls.o rsbench-rsb_pr.o rsbench-rsb_pcnt.o rsbench-rsb_failure_tests.o rsbench-rsb_libspblas_tests.o rsb_dummy.o librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info' is ignored for programs libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/rsbench rsbench-rsbench.o rsbench-rsb_test_matops.o rsbench-rsb_mkl.o rsbench-rsb_genmm.o rsbench-rsb_mmls.o rsbench-rsb_pr.o rsbench-rsb_pcnt.o rsbench-rsb_failure_tests.o rsbench-rsb_libspblas_tests.o rsb_dummy.o -fopenmp ./.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' @@ -2405,27 +2441,27 @@ gfortran -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -I.. -I.. -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o fortran.o fortran.F90 gfortran -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -I.. -I.. -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o fortran_rsb_fi.o fortran_rsb_fi.F90 g++ -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -c -o cplusplus.o cplusplus.cpp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello hello.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o io-spblas io-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o backsolve backsolve.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o transpose transpose.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello-spblas hello-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o power power.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran_rsb_fi fortran_rsb_fi.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o autotune autotune.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran fortran.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o transpose transpose.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o io-spblas io-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello hello.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o power power.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o backsolve backsolve.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello-spblas hello-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran_rsb_fi fortran_rsb_fi.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o autotune autotune.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran fortran.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/transpose transpose.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/hello-spblas hello-spblas.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/hello hello.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/io-spblas io-spblas.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/power power.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/backsolve backsolve.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/io-spblas io-spblas.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o snippets snippets.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/hello-spblas hello-spblas.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/fortran_rsb_fi fortran_rsb_fi.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/fortran fortran.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/autotune autotune.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o cplusplus cplusplus.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o snippets snippets.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/fortran fortran.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/snippets snippets.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o cplusplus cplusplus.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/cplusplus cplusplus.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/14 -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/14/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' Making all in scripts @@ -2444,11 +2480,11 @@ gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/doc' /usr/bin/mkdir -p man /usr/bin/mkdir -p man -SOURCE_DATE_EPOCH=1735736461 \ +gmake makedox +SOURCE_DATE_EPOCH=1767178861 \ help2man --name="benchmark and test for librsb" --no-info ../rsbench | /usr/bin/sed 's/January //g' > man/rsbench.1 -SOURCE_DATE_EPOCH=1735736461 \ +SOURCE_DATE_EPOCH=1767178861 \ help2man --name="provide configuration information for librsb" --no-info /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb-config | /usr/bin/sed 's/January //g' > man/librsb-config.1 -gmake makedox gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/doc' DOXYGEN_PROJECT_NUMBER=1.3.0.2 doxygen Doxyfile || echo "are you sure you have doxygen installed ?" warning: Tag 'HTML_TIMESTAMP' at line 1513 of file 'Doxyfile' has become obsolete. @@ -3159,13 +3195,13 @@ g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rgt-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rgt_ne-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rgt_rv-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' Making all in examples @@ -3180,25 +3216,25 @@ g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o mtx2bin.o mtx2bin.cpp g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o render.o render.cpp g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o span.o span.cpp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib/examples' gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' @@ -3208,7 +3244,7 @@ gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' g++ -DHAVE_CONFIG_H -I. -I/build/reproducible-path/librsb-1.3.0.2+dfsg -Wdate-time -D_FORTIFY_SOURCE=2 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rsbtest.o rsbtest.cpp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lstdc++fs -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lstdc++fs -lstdc++fs libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lstdc++fs -fopenmp gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' @@ -3284,7 +3320,7 @@ gmake[3]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' gmake mtests -C . gmake[3]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' -srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/bash -ex ./scripts/readme-tests.sh +srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/sh -ex ./scripts/readme-tests.sh + test x/build/reproducible-path/librsb-1.3.0.2+dfsg = x + ./rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx -qH -R -n1,4 -T z --verbose --nrhs 1,2 --by-rows # --bench option implies -qH -R --write-performance-record --want-mkl-autotune --mkl-benchmark --types : --split-experimental 6 --merge-experimental 6 --also-transpose --sort-filenames-list --want-memory-benchmark @@ -3294,15 +3330,15 @@ Adding matrix file: /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx # Sorting matrices list (use --no-sort-filenames-list to prevent this) # Using matrices: A.mtx -# beginning run at 1740605485 +# beginning run at 1775018864 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx -qH -R -n1,4 -T z --verbose --nrhs 1,2 --by-rows # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -# average timer granularity: 6.51e-08 s -# Will write a final performance record to file rsbench_pr__1740605485_gcc-14.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1740605485_gcc-14.2-1,4th.rpr.tmp +# average timer granularity: 4.08e-08 s +# Will write a final performance record to file rsbench_pr__1775018864_gcc-14.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1775018864_gcc-14.2-1,4th.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -3341,67 +3377,67 @@ # env: SLURM_NTASKS is not set # env: SLURM_STEP_TASKS_PER_NODE is not set # env: SLURM_TASKS_PER_NODE is not set -# detected hostname: ionos1-amd64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 1 (each --verbose occurrence counts +1) # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 5.517s +# Memory benchmark took 7.925s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 8 samples (2240 bytes). -# Cache block size total 524288 bytes, per-thread 26214 bytes -# so far, program took 5.520s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . +# Cache block size total 4194304 bytes, per-thread 99864 bytes +# so far, program took 7.927s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . # Using 1 threads # reading A.mtx (184 bytes / 1 MiB / 6 nnz / 3 rows / 3 columns / 1 MiB COO) as type Z... -# file input of A.mtx took 0.00 s (6 nnz, 34904 nnz/s ) (1.07 MB/s ) -#pre-sorting (6 elements) took 0.0363839 s -#weeding duplicates (to 6 elements) took 5.00679e-06 s (and check, 2.86102e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 63873 nnz/s ) (1.96 MB/s ) +#pre-sorting (6 elements) took 0.0245659 s +#weeding duplicates (to 6 elements) took 3.09944e-06 s (and check, 1.90735e-06 s ) # multi-nrhs benchmarking (1,2) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads -# Constructed matrix (took 0.104s): (3 x 3)[0x557fc701bd50]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Constructed matrix (took 0.064s): (3 x 3)[0x55e1e4c86e60]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (1 th.) took 0.04795s; avg 0.01598s ( +/- 0.14/ 0.09 %); best 0.01596s; worst 0.016s; std dev. 1.641e-05 (taking best). -Reference operation time is 0.0159609 s (0.006015 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01596 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 3.004e-05s, ~1.311e-05s of computing time (of which 1.907e-06s sorting, 3.815e-06s analysis) -3 iterations (1 th.) took 3.004e-05s; avg 1.001e-05s ( +/- 99.30/190.48 %); best 7.011e-08s; worst 2.909e-05s; std dev. 1.349e-05 (taking best). -Reference operation time is 7.0107e-08 s (1369 Mflops) with 1 threads. -After merge step 1: tpop: 7.011e-08 s ~Mflops: 1369.336 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 227665.363x: 0.01596s -> 7.011e-08s, so taking this instance. +3 iterations (1 th.) took 0.03092s; avg 0.01031s ( +/- 10.38/ 19.25 %); best 0.009236s; worst 0.01229s; std dev. 0.001404 (taking best). +Reference operation time is 0.00923586 s (0.01039 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.009236 Mflops: 0.010) +Merge (3 -> 1 leaves) took w.c.t. of 4.506e-05s, ~1.311e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) +3 iterations (1 th.) took 4.315e-05s; avg 1.438e-05s ( +/- 99.74/193.37 %); best 3.73e-08s; worst 4.22e-05s; std dev. 1.967e-05 (taking best). +Reference operation time is 3.73006e-08 s (2574 Mflops) with 1 threads. +After merge step 1: tpop: 3.73e-08 s ~Mflops: 2573.686 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 247606.264x: 0.009236s -> 3.73e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.05597s (of which 3.409e-05s partitioning, 0s I/O); computing times: 1.311e-05s in par. loops, 1.907e-06s sorting, 3.815e-06s analyzing) -Total merge + benchmarking process took 0.05597s, equivalent to 798323.4/3.5 new/old ops (0.1038s for 2 clones -- as 1481292.3/6.5 ops, or 740646.1/3.3 ops per clone), SPEEDUP of 227665.363x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 227665.363x (0.01596s -> 7.011e-08s), will amortize in 3.5 ops by saving 0.01596s per op. -In 1 tuning rounds (tot. 0.15s, 0.1s for constructor, 2 clones) obtained a SPEEDUP of 22766436.3% (2.277e+05x) (from 0.006015 to 1369 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03564s (of which 5.007e-05s partitioning, 0s I/O); computing times: 1.311e-05s in par. loops, 1.907e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.03564s, equivalent to 955372.3/3.9 new/old ops (0.08644s for 2 clones -- as 2317468.8/9.4 ops, or 1158734.4/4.7 ops per clone), SPEEDUP of 247606.264x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 247606.264x (0.009236s -> 3.73e-08s), will amortize in 3.9 ops by saving 0.009236s per op. +In 1 tuning rounds (tot. 0.12s, 0.086s for constructor, 2 clones) obtained a SPEEDUP of 24760526.4% (2.476e+05x) (from 0.01039 to 2574 Mflops). #pr: updating sample at index 1 (0^th of 8), 0^th touch for (0,0,0,0,0,0,0). -First run of RSB Autotuner took 0.151988 s (1.596e-02 s -> 7.011e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.117619 s (9.236e-03 s -> 3.730e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.799971 s and estimated a speedup of 1.000000 x (7.011e-08 s -> 7.011e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.732109 s and estimated a speedup of 1.000000 x (3.730e-08 s -> 3.730e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.023860 0.047915 0.071775 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.071775 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.023860 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.047915 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 1 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 1 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.071775 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000001 0.015583 0.020808 0.036391 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.036392 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.015583 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.020808 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 1 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 1 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.036391 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 1 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 %:RSB_SUBDIVISION_SCALING:A.mtx S N 1 3 3 6 1.00 %:RSB_SHUFFLE_SCALING:A.mtx S N 1 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 1 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 1 3 3 6 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 1 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 1 3 3 6 28 48 36 @@ -3410,47 +3446,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.140s): (3 x 3)[0x557fc701bd50]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Constructed matrix (took 0.094s): (3 x 3)[0x55e1e4c86e60]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.1 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (4 th.) took 0.07199s; avg 0.024s ( +/- 0.04/ 0.02 %); best 0.02399s; worst 0.024s; std dev. 6.357e-06 (taking best). -Reference operation time is 0.023988 s (0.004002 Mflops) with 4 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.02399 Mflops: 0.004) -Merge (3 -> 1 leaves) took w.c.t. of 3.099e-05s, ~9.06e-06s of computing time (of which 2.861e-06s sorting, 7.153e-06s analysis) -3 iterations (4 th.) took 8.106e-06s; avg 2.702e-06s ( +/- 97.41/164.71 %); best 7.011e-08s; worst 7.153e-06s; std dev. 3.171e-06 (taking best). -Reference operation time is 7.0107e-08 s (1369 Mflops) with 4 threads. -After merge step 1: tpop: 7.011e-08 s ~Mflops: 1369.336 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 342162.897x: 0.02399s -> 7.011e-08s, so taking this instance. +3 iterations (4 th.) took 0.04228s; avg 0.01409s ( +/- 45.50/ 25.80 %); best 0.007681s; worst 0.01773s; std dev. 0.004549 (taking best). +Reference operation time is 0.00768113 s (0.0125 Mflops) with 4 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.007681 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 2.599e-05s, ~7.868e-06s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) +3 iterations (4 th.) took 1.001e-05s; avg 3.338e-06s ( +/- 98.88/171.43 %); best 3.73e-08s; worst 9.06e-06s; std dev. 4.065e-06 (taking best). +Reference operation time is 3.73006e-08 s (2574 Mflops) with 4 threads. +After merge step 1: tpop: 3.73e-08 s ~Mflops: 2573.686 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 205925.216x: 0.007681s -> 3.73e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.07217s (of which 3.505e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 2.861e-06s sorting, 7.153e-06s analyzing) -Total merge + benchmarking process took 0.07217s, equivalent to 1029396.4/3.0 new/old ops (0.1434s for 2 clones -- as 2045961.6/6.0 ops, or 1022980.8/3.0 ops per clone), SPEEDUP of 342162.897x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 342162.897x (0.02399s -> 7.011e-08s), will amortize in 3.0 ops by saving 0.02399s per op. -In 1 tuning rounds (tot. 0.22s, 0.14s for constructor, 2 clones) obtained a SPEEDUP of 34216189.7% (3.422e+05x) (from 0.004002 to 1369 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03038s (of which 2.909e-05s partitioning, 0s I/O); computing times: 7.868e-06s in par. loops, 2.146e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.03038s, equivalent to 814464.7/4.0 new/old ops (0.08635s for 2 clones -- as 2314982.4/11.2 ops, or 1157491.2/5.6 ops per clone), SPEEDUP of 205925.216x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 205925.216x (0.007681s -> 3.73e-08s), will amortize in 4.0 ops by saving 0.007681s per op. +In 1 tuning rounds (tot. 0.13s, 0.086s for constructor, 2 clones) obtained a SPEEDUP of 20592421.6% (2.059e+05x) (from 0.0125 to 2574 Mflops). #pr: updating sample at index 5 (1^th of 8), 0^th touch for (0,1,0,0,0,0,0). -First run of RSB Autotuner took 0.215586 s (2.399e-02 s -> 7.011e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.128788 s (7.681e-03 s -> 3.730e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.852527 s and estimated a speedup of 1.000000 x (7.011e-08 s -> 7.011e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.680276 s and estimated a speedup of 1.000000 x (3.730e-08 s -> 3.730e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.031628 0.059744 0.091372 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.091372 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.031628 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.059744 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.029421 0.038408 0.067829 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.067829 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.029421 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.038408 %:ROW_MAJOR_SORT_TIME:A.mtx S N 4 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.091372 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 inf +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.067829 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 4 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.79 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.79 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.75 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.80 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.75 0.80 0.79 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.54 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.54 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.53 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.54 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 inf 0.53 0.54 0.54 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 4 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 4 3 3 6 28 48 36 @@ -3459,50 +3495,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.1038 1e+09 1e+09 +%operation:A.mtx 0.0642068 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.02386 0 0.047915 +%constructor:A.mtx 9.53674e-07 0.015583 0 0.020808 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,2) -- now using nrhs 2. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads -# Constructed matrix (took 0.103s): (3 x 3)[0x557fc701bd50]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Constructed matrix (took 0.077s): (3 x 3)[0x55e1e4c86e60]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (1 th.) took 0.04798s; avg 0.01599s ( +/- 0.08/ 0.09 %); best 0.01598s; worst 0.01601s; std dev. 1.11e-05 (taking best). -Reference operation time is 0.015981 s (0.01201 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01598 Mflops: 0.012) -Merge (3 -> 1 leaves) took w.c.t. of 2.909e-05s, ~1.097e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) -3 iterations (1 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 95.80/142.86 %); best 7.011e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). -Reference operation time is 7.0107e-08 s (2739 Mflops) with 1 threads. -After merge step 1: tpop: 7.011e-08 s ~Mflops: 2738.672 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 227951.029x: 0.01598s -> 7.011e-08s, so taking this instance. +3 iterations (1 th.) took 0.04404s; avg 0.01468s ( +/- 23.33/ 14.66 %); best 0.01126s; worst 0.01683s; std dev. 0.002448 (taking best). +Reference operation time is 0.011255 s (0.01706 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01126 Mflops: 0.017) +Merge (3 -> 1 leaves) took w.c.t. of 2.384e-05s, ~7.868e-06s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) +3 iterations (1 th.) took 1.001e-05s; avg 3.338e-06s ( +/- 98.88/171.43 %); best 3.73e-08s; worst 9.06e-06s; std dev. 4.065e-06 (taking best). +Reference operation time is 3.73006e-08 s (5147 Mflops) with 1 threads. +After merge step 1: tpop: 3.73e-08 s ~Mflops: 5147.372 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 301738.575x: 0.01126s -> 3.73e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04815s (of which 3.314e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 1.907e-06s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.04815s, equivalent to 686822.0/3.0 new/old ops (0.09598s for 2 clones -- as 1369063.1/6.0 ops, or 684531.5/3.0 ops per clone), SPEEDUP of 227951.029x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 227951.029x (0.01598s -> 7.011e-08s), will amortize in 3.0 ops by saving 0.01598s per op. -In 1 tuning rounds (tot. 0.14s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 22795002.9% (2.28e+05x) (from 0.01201 to 2739 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04413s (of which 2.789e-05s partitioning, 0s I/O); computing times: 7.868e-06s in par. loops, 1.907e-06s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.04413s, equivalent to 1183036.1/3.9 new/old ops (0.09143s for 2 clones -- as 2451140.9/8.1 ops, or 1225570.5/4.1 ops per clone), SPEEDUP of 301738.575x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 301738.575x (0.01126s -> 3.73e-08s), will amortize in 3.9 ops by saving 0.01125s per op. +In 1 tuning rounds (tot. 0.14s, 0.091s for constructor, 2 clones) obtained a SPEEDUP of 30173757.5% (3.017e+05x) (from 0.01706 to 5147 Mflops). #pr: updating sample at index 3 (2^th of 8), 0^th touch for (0,0,0,0,1,0,0). -First run of RSB Autotuner took 0.144125 s (1.598e-02 s -> 7.011e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.135627 s (1.126e-02 s -> 3.730e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.831704 s and estimated a speedup of 1.000000 x (7.011e-08 s -> 7.011e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.777904 s and estimated a speedup of 1.000000 x (3.730e-08 s -> 3.730e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.031405 0.036213 0.067618 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.067618 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.031405 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.036213 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.019551 0.031999 0.051550 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.051550 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.019551 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.031999 %:ROW_MAJOR_SORT_TIME:A.mtx S N 1 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 1 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.067618 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.051550 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 1 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 @@ -3517,47 +3553,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.080s): (3 x 3)[0x557fc701bd50]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Constructed matrix (took 0.095s): (3 x 3)[0x55e1e4c86e60]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.1 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (4 th.) took 0.04395s; avg 0.01465s ( +/- 18.00/ 9.19 %); best 0.01201s; worst 0.016s; std dev. 0.001865 (taking best). -Reference operation time is 0.012013 s (0.01598 Mflops) with 4 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01201 Mflops: 0.016) -Merge (3 -> 1 leaves) took w.c.t. of 3.099e-05s, ~9.06e-06s of computing time (of which 1.907e-06s sorting, 5.96e-06s analysis) -3 iterations (4 th.) took 9.06e-06s; avg 3.02e-06s ( +/- 97.68/168.42 %); best 7.011e-08s; worst 8.106e-06s; std dev. 3.618e-06 (taking best). -Reference operation time is 7.0107e-08 s (2739 Mflops) with 4 threads. -After merge step 1: tpop: 7.011e-08 s ~Mflops: 2738.672 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 171351.811x: 0.01201s -> 7.011e-08s, so taking this instance. +3 iterations (4 th.) took 0.04398s; avg 0.01466s ( +/- 33.04/ 45.61 %); best 0.009817s; worst 0.02135s; std dev. 0.004885 (taking best). +Reference operation time is 0.00981688 s (0.01956 Mflops) with 4 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.009817 Mflops: 0.020) +Merge (3 -> 1 leaves) took w.c.t. of 2.599e-05s, ~8.821e-06s of computing time (of which 3.099e-06s sorting, 5.007e-06s analysis) +3 iterations (4 th.) took 9.06e-06s; avg 3.02e-06s ( +/- 98.76/168.42 %); best 3.73e-08s; worst 8.106e-06s; std dev. 3.618e-06 (taking best). +Reference operation time is 3.73006e-08 s (5147 Mflops) with 4 threads. +After merge step 1: tpop: 3.73e-08 s ~Mflops: 5147.372 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 263183.126x: 0.009817s -> 3.73e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.06402s (of which 3.505e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 1.907e-06s sorting, 5.96e-06s analyzing) -Total merge + benchmarking process took 0.06402s, equivalent to 913205.2/5.3 new/old ops (0.09989s for 2 clones -- as 1424849.5/8.3 ops, or 712424.8/4.2 ops per clone), SPEEDUP of 171351.811x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 171351.811x (0.01201s -> 7.011e-08s), will amortize in 5.3 ops by saving 0.01201s per op. -In 1 tuning rounds (tot. 0.14s, 0.1s for constructor, 2 clones) obtained a SPEEDUP of 17135081.1% (1.714e+05x) (from 0.01598 to 2739 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03813s (of which 2.909e-05s partitioning, 0s I/O); computing times: 8.821e-06s in par. loops, 3.099e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.03813s, equivalent to 1022128.5/3.9 new/old ops (0.0804s for 2 clones -- as 2155334.0/8.2 ops, or 1077667.0/4.1 ops per clone), SPEEDUP of 263183.126x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 263183.126x (0.009817s -> 3.73e-08s), will amortize in 3.9 ops by saving 0.009817s per op. +In 1 tuning rounds (tot. 0.12s, 0.08s for constructor, 2 clones) obtained a SPEEDUP of 26318212.6% (2.632e+05x) (from 0.01956 to 5147 Mflops). #pr: updating sample at index 7 (3^th of 8), 0^th touch for (0,1,0,0,1,0,0). -First run of RSB Autotuner took 0.144037 s (1.201e-02 s -> 7.011e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.124539 s (9.817e-03 s -> 3.730e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.863882 s and estimated a speedup of 1.000000 x (7.011e-08 s -> 7.011e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.759476 s and estimated a speedup of 1.000000 x (3.730e-08 s -> 3.730e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.027649 0.031998 0.059647 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.059647 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.027649 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.031998 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.023233 0.044560 0.067793 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.067793 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.023233 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.044560 %:ROW_MAJOR_SORT_TIME:A.mtx S N 4 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.059647 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.067793 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 4 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.13 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.13 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 1.14 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.13 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 1.14 1.13 1.13 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.76 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.76 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.84 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.72 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.84 0.72 0.76 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 4 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 4 3 3 6 28 48 36 @@ -3566,184 +3602,184 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.103375 1e+09 1e+09 +%operation:A.mtx 0.0773561 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.031405 0 0.0362129 +%constructor:A.mtx 0 0.019551 0 0.0319991 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 10.297s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.004s/0.000s . +# so far, program took 12.050s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.456s/0.000s . getrusage() stats: -ru_maxrss: 11 (maximum resident set size -- MB) -ru_stime : 0.107s (system CPU time used) -ru_utime : 65.62s (user CPU time used) +ru_maxrss: 26 (maximum resident set size -- MB) +ru_stime : 0.4631s (system CPU time used) +ru_utime : 48.53s (user CPU time used) # benchmarking terminated --- finalizing run. # ====== BEGIN Total summary record. #pr: ======== Limiting to nrhs=1: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 1369.34 1.596e-02 0.000e+00 7.011e-08 0.000e+00 1.520e-01 3.82e+00 2.29e+00 1 9.60e-05 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 1369.34 2.399e-02 0.000e+00 7.011e-08 0.000e+00 2.156e-01 3.82e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 2573.69 9.236e-03 0.000e+00 3.730e-08 0.000e+00 1.176e-01 7.18e+00 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 2573.69 7.681e-03 0.000e+00 3.730e-08 0.000e+00 1.288e-01 7.18e+00 2.29e+00 1 9.60e-05 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 28491313.0 % faster, avg. sp. ratio 284914.130x, max sp. ratio 342162.897x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2621521.9/2167944.2/3075099.5/5243043.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 9.0/ 9.5/ 18.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 9.0, max. 9.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 22676474.0 % faster, avg. sp. ratio 226765.740x, max sp. ratio 247606.264x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 3302991.4/3153275.8/3452706.9/6605982.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.8/ 12.7/ 16.8/ 29.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 14.8, min. 12.7, max. 16.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.138/ 3.138/ 3.138,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 7.645/ 3.823/ 3.823,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.898/ 5.898/ 5.898,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.370/ 7.185/ 7.185,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.292/ 2.292/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.18 s, min 0.15 s, max 0.22 s, tot 0.37 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.18 s, min 0.15 s, max 0.22 s, tot 0.37 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.369e+03, min 1.369e+03, max 1.369e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 5.008e-03, min 4.002e-03, max 6.015e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 7.011e-08s, min 7.011e-08s, max 7.011e-08s, tot 1.402e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.997e-02s, min 1.596e-02s, max 2.399e-02s, tot 3.995e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.340e+00 3.340e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.664e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.12 s, min 0.12 s, max 0.13 s, tot 0.25 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.12 s, min 0.12 s, max 0.13 s, tot 0.25 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.574e+03, min 2.574e+03, max 2.574e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.145e-02, min 1.039e-02, max 1.250e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.730e-08s, min 3.730e-08s, max 3.730e-08s, tot 7.460e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.458e-03s, min 7.681e-03s, max 9.236e-03s, tot 1.692e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.383e+00 2.383e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.577e+00 #pr: ======== Limiting to nrhs=2: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 2738.67 1.598e-02 0.000e+00 7.011e-08 0.000e+00 1.441e-01 5.88e+00 1.65e+00 1 1.92e-04 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 2738.67 1.201e-02 0.000e+00 7.011e-08 0.000e+00 1.440e-01 5.88e+00 1.65e+00 1 1.92e-04 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 5147.37 1.126e-02 0.000e+00 3.730e-08 0.000e+00 1.356e-01 1.10e+01 1.65e+00 1 1.92e-04 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 5147.37 9.817e-03 0.000e+00 3.730e-08 0.000e+00 1.245e-01 1.10e+01 1.65e+00 1 1.92e-04 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 19965042.0 % faster, avg. sp. ratio 199651.420x, max sp. ratio 227951.029x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2055157.3/2054528.1/2055786.4/4110314.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.5/ 9.0/ 12.0/ 21.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.5, min. 9.0, max. 12.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 28245985.0 % faster, avg. sp. ratio 282460.850x, max sp. ratio 301738.575x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 3487424.1/3338791.9/3636056.2/6974848.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.4/ 12.1/ 12.7/ 24.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.4, min. 12.1, max. 12.7 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.507/ 4.507/ 4.507,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 11.753/ 5.877/ 5.877,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.472/ 8.472/ 8.472,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 22.091/ 11.045/ 11.045,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.646/ 1.646/ 1.646) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.14 s, min 0.14 s, max 0.14 s, tot 0.29 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.14 s, max 0.14 s, tot 0.29 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.739e+03, min 2.739e+03, max 2.739e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.400e-02, min 1.201e-02, max 1.598e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 7.011e-08s, min 7.011e-08s, max 7.011e-08s, tot 1.402e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.400e-02s, min 1.201e-02s, max 1.598e-02s, tot 2.799e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.325e+00 2.325e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.664e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.26 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.26 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 5.147e+03, min 5.147e+03, max 5.147e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.831e-02, min 1.706e-02, max 1.956e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.730e-08s, min 3.730e-08s, max 3.730e-08s, tot 7.460e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.054e-02s, min 9.817e-03s, max 1.126e-02s, tot 2.107e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.659e+00 1.659e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.577e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=N: #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 1369.34 1.596e-02 0.000e+00 7.011e-08 0.000e+00 1.520e-01 3.82e+00 2.29e+00 1 9.60e-05 -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 2738.67 1.598e-02 0.000e+00 7.011e-08 0.000e+00 1.441e-01 5.88e+00 1.65e+00 1 1.92e-04 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 1369.34 2.399e-02 0.000e+00 7.011e-08 0.000e+00 2.156e-01 3.82e+00 2.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 2738.67 1.201e-02 0.000e+00 7.011e-08 0.000e+00 1.440e-01 5.88e+00 1.65e+00 1 1.92e-04 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 2573.69 9.236e-03 0.000e+00 3.730e-08 0.000e+00 1.176e-01 7.18e+00 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 5147.37 1.126e-02 0.000e+00 3.730e-08 0.000e+00 1.356e-01 1.10e+01 1.65e+00 1 1.92e-04 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 2573.69 7.681e-03 0.000e+00 3.730e-08 0.000e+00 1.288e-01 7.18e+00 2.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 5147.37 9.817e-03 0.000e+00 3.730e-08 0.000e+00 1.245e-01 1.10e+01 1.65e+00 1 1.92e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 24228177.5 % faster, avg. sp. ratio 242282.775x, max sp. ratio 342162.897x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2338339.6/2054528.1/3075099.5/9353358.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.9/ 9.0/ 12.0/ 39.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.9, min. 9.0, max. 12.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 25461229.5 % faster, avg. sp. ratio 254613.295x, max sp. ratio 301738.575x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 3395207.7/3153275.8/3636056.2/13580830.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.6/ 12.1/ 16.8/ 54.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.6, min. 12.1, max. 16.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.823/ 3.138/ 4.507,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 19.399/ 3.823/ 5.877,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.185/ 5.898/ 8.472,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 36.461/ 7.185/ 11.045,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.969/ 1.646/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 2 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.16 s, min 0.14 s, max 0.22 s, tot 0.66 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.16 s, min 0.14 s, max 0.22 s, tot 0.66 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.054e+03, min 1.369e+03, max 2.739e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 9.503e-03, min 4.002e-03, max 1.598e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 7.011e-08s, min 7.011e-08s, max 7.011e-08s, tot 2.804e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.699e-02s, min 1.201e-02s, max 2.399e-02s, tot 6.794e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.325e+00 3.340e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.664e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.51 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.51 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.861e+03, min 2.574e+03, max 5.147e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.488e-02, min 1.039e-02, max 1.956e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.730e-08s, min 3.730e-08s, max 3.730e-08s, tot 1.492e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.497e-03s, min 7.681e-03s, max 1.126e-02s, tot 3.799e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.659e+00 2.383e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.577e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to both transA=N and nrhs=1: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 1369.34 1.596e-02 0.000e+00 7.011e-08 0.000e+00 1.520e-01 3.82e+00 2.29e+00 1 9.60e-05 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 1369.34 2.399e-02 0.000e+00 7.011e-08 0.000e+00 2.156e-01 3.82e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 2573.69 9.236e-03 0.000e+00 3.730e-08 0.000e+00 1.176e-01 7.18e+00 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 2573.69 7.681e-03 0.000e+00 3.730e-08 0.000e+00 1.288e-01 7.18e+00 2.29e+00 1 9.60e-05 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 28491313.0 % faster, avg. sp. ratio 284914.130x, max sp. ratio 342162.897x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2621521.9/2167944.2/3075099.5/5243043.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 9.0/ 9.5/ 18.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 9.0, max. 9.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 22676474.0 % faster, avg. sp. ratio 226765.740x, max sp. ratio 247606.264x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 3302991.4/3153275.8/3452706.9/6605982.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.8/ 12.7/ 16.8/ 29.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 14.8, min. 12.7, max. 16.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.138/ 3.138/ 3.138,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 7.645/ 3.823/ 3.823,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.898/ 5.898/ 5.898,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.370/ 7.185/ 7.185,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.292/ 2.292/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.18 s, min 0.15 s, max 0.22 s, tot 0.37 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.18 s, min 0.15 s, max 0.22 s, tot 0.37 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.369e+03, min 1.369e+03, max 1.369e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 5.008e-03, min 4.002e-03, max 6.015e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 7.011e-08s, min 7.011e-08s, max 7.011e-08s, tot 1.402e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.997e-02s, min 1.596e-02s, max 2.399e-02s, tot 3.995e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.340e+00 3.340e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.664e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.12 s, min 0.12 s, max 0.13 s, tot 0.25 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.12 s, min 0.12 s, max 0.13 s, tot 0.25 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.574e+03, min 2.574e+03, max 2.574e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.145e-02, min 1.039e-02, max 1.250e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.730e-08s, min 3.730e-08s, max 3.730e-08s, tot 7.460e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.458e-03s, min 7.681e-03s, max 9.236e-03s, tot 1.692e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.383e+00 2.383e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.577e+00 #pr: ======== Limiting to both transA=N and nrhs=2: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 2738.67 1.598e-02 0.000e+00 7.011e-08 0.000e+00 1.441e-01 5.88e+00 1.65e+00 1 1.92e-04 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 2738.67 1.201e-02 0.000e+00 7.011e-08 0.000e+00 1.440e-01 5.88e+00 1.65e+00 1 1.92e-04 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 5147.37 1.126e-02 0.000e+00 3.730e-08 0.000e+00 1.356e-01 1.10e+01 1.65e+00 1 1.92e-04 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 5147.37 9.817e-03 0.000e+00 3.730e-08 0.000e+00 1.245e-01 1.10e+01 1.65e+00 1 1.92e-04 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 19965042.0 % faster, avg. sp. ratio 199651.420x, max sp. ratio 227951.029x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2055157.3/2054528.1/2055786.4/4110314.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.5/ 9.0/ 12.0/ 21.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.5, min. 9.0, max. 12.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 28245985.0 % faster, avg. sp. ratio 282460.850x, max sp. ratio 301738.575x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 3487424.1/3338791.9/3636056.2/6974848.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.4/ 12.1/ 12.7/ 24.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.4, min. 12.1, max. 12.7 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.507/ 4.507/ 4.507,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 11.753/ 5.877/ 5.877,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.472/ 8.472/ 8.472,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 22.091/ 11.045/ 11.045,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.646/ 1.646/ 1.646) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.14 s, min 0.14 s, max 0.14 s, tot 0.29 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.14 s, max 0.14 s, tot 0.29 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.739e+03, min 2.739e+03, max 2.739e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.400e-02, min 1.201e-02, max 1.598e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 7.011e-08s, min 7.011e-08s, max 7.011e-08s, tot 1.402e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.400e-02s, min 1.201e-02s, max 1.598e-02s, tot 2.799e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.325e+00 2.325e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.664e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.26 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.26 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 5.147e+03, min 5.147e+03, max 5.147e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.831e-02, min 1.706e-02, max 1.956e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.730e-08s, min 3.730e-08s, max 3.730e-08s, tot 7.460e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.054e-02s, min 9.817e-03s, max 1.126e-02s, tot 2.107e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.659e+00 1.659e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.577e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 4) matched the dump criteria -- skipping dump round. @@ -3754,44 +3790,44 @@ #pr: ======== All results (not limiting) #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 1369.34 1.596e-02 0.000e+00 7.011e-08 0.000e+00 1.520e-01 3.82e+00 2.29e+00 1 9.60e-05 -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 2738.67 1.598e-02 0.000e+00 7.011e-08 0.000e+00 1.441e-01 5.88e+00 1.65e+00 1 1.92e-04 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 1369.34 2.399e-02 0.000e+00 7.011e-08 0.000e+00 2.156e-01 3.82e+00 2.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 2738.67 1.201e-02 0.000e+00 7.011e-08 0.000e+00 1.440e-01 5.88e+00 1.65e+00 1 1.92e-04 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 2573.69 9.236e-03 0.000e+00 3.730e-08 0.000e+00 1.176e-01 7.18e+00 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 5147.37 1.126e-02 0.000e+00 3.730e-08 0.000e+00 1.356e-01 1.10e+01 1.65e+00 1 1.92e-04 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 2573.69 7.681e-03 0.000e+00 3.730e-08 0.000e+00 1.288e-01 7.18e+00 2.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 5147.37 9.817e-03 0.000e+00 3.730e-08 0.000e+00 1.245e-01 1.10e+01 1.65e+00 1 1.92e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 24228177.5 % faster, avg. sp. ratio 242282.775x, max sp. ratio 342162.897x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2338339.6/2054528.1/3075099.5/9353358.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.9/ 9.0/ 12.0/ 39.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.9, min. 9.0, max. 12.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 25461229.5 % faster, avg. sp. ratio 254613.295x, max sp. ratio 301738.575x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 3395207.7/3153275.8/3636056.2/13580830.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.6/ 12.1/ 16.8/ 54.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.6, min. 12.1, max. 16.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.823/ 3.138/ 4.507,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 19.399/ 3.823/ 5.877,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.185/ 5.898/ 8.472,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 36.461/ 7.185/ 11.045,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.969/ 1.646/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 2 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.16 s, min 0.14 s, max 0.22 s, tot 0.66 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.16 s, min 0.14 s, max 0.22 s, tot 0.66 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.054e+03, min 1.369e+03, max 2.739e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 9.503e-03, min 4.002e-03, max 1.598e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 7.011e-08s, min 7.011e-08s, max 7.011e-08s, tot 2.804e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.699e-02s, min 1.201e-02s, max 2.399e-02s, tot 6.794e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.325e+00 3.340e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.664e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.51 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.51 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.861e+03, min 2.574e+03, max 5.147e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.488e-02, min 1.039e-02, max 1.956e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.730e-08s, min 3.730e-08s, max 3.730e-08s, tot 1.492e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.497e-03s, min 7.681e-03s, max 1.126e-02s, tot 3.799e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.659e+00 2.383e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.577e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) -#pr: Record collection took 3.84 s. +#pr: Record collection took 3.29 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 5261 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 5314 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1740605485_gcc-14.2-1,4th.rpr -# Removing the temporary record file rsbench_pr__1740605485_gcc-14.2-1,4th.rpr.tmp. -# terminating run at 1740605495 (after 10.3s of w.c.t.) +#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1775018864_gcc-14.2-1,4th.rpr +# Removing the temporary record file rsbench_pr__1775018864_gcc-14.2-1,4th.rpr.tmp. +# terminating run at 1775018877 (after 12.0s of w.c.t.) + ./rsbench -oa -Ob --help /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench is a swiss army knife for testing the library functionality and performance. You can use it to perform sparse matrix - unitary vector multiplication, specifying the blocking parameters, the times to perform multiplication. @@ -4045,45 +4081,67 @@ Written by michelemartone_AT_users_DOT_sourceforge_DOT_net. + ./rsbench -I -cache block size : 26214 -hwloc size of cache level 1: 65536 -hwloc size of cache level 2: 524288 -detected max available cores/threads : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 -detected max OpenMP procs : 20 +cache block size : 99864 +hwloc size of cache level 1: 32768 +hwloc size of cache level 2: 4194304 +detected max available cores/threads : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 +detected max OpenMP procs : 42 detected 2 levels of cache -L1 size: 65536 -L2 size: 524288 +L1 size: 32768 +L2 size: 4194304 sysconf() : 4096 bytes per pagesize -sysconf() : 20586515 physical pages -sysconf() : 84322365440 bytes (80416 MB) of physical memory -sysconf() : 4600027 available (free) physical pages -sysconf() : 18841710592 available (free) physical memory -sysconf() , processors : 64 -sysconf() , processors online : 20 -sysconf() : level 1 cache size 65536 -sysconf() : level 1 cache associativity 2 +sysconf() : 20582908 physical pages +sysconf() : 84307591168 bytes (80401 MB) of physical memory +sysconf() : 11949126 available (free) physical pages +sysconf() : 48943620096 available (free) physical memory +sysconf() , processors : 128 +sysconf() , processors online : 42 +sysconf() : level 1 cache size 32768 +sysconf() : level 1 cache associativity 8 sysconf() : level 1 cache line size 64 -sysconf() : level 2 cache size 524288 -sysconf() : level 2 cache associativity 16 +sysconf() : level 2 cache size 2097152 +sysconf() : level 2 cache associativity 8 sysconf() : level 2 cache line size 64 sysconf() : no level 3 cache sysconf() : no level 4 cache @@ -4105,30 +4163,33 @@ RSB_SUBM_IDX_MARKER : 2147483647 RSB_MAX_ALLOCATABLE_MEMORY_CHUNK: 18446744073709551615 timing min delta (if negative, don't complain with us) : 0 s -timing granularity : 6.00934e-08 s +timing granularity : 3.35574e-08 s CFLAGS : -g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 CXXFLAGS : -g -O2 -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp CC : gcc -memhinfo : L2:16/64/512K,L1:2/64/64K -detected free memory : 18841710592 -detected total memory : 84322365440 -for array sized 524288 elems, took 0.000590086 s for linear search and 0 s for binary search for element 524287, in 122 tries, for a total of 0.100390 s (ignore this:127926028) -for array sized 524288 elems, took 0.000283957 s for linear search and 0 s for binary search for element 262143, in 299 tries, for a total of 0.100303 s (ignore this:284687542) -for array sized 524288 elems, took 0.000145912 s for linear search and 0 s for binary search for element 131071, in 589 tries, for a total of 0.100077 s (ignore this:439089180) -for array sized 524288 elems, took 7.48634e-05 s for linear search and 0 s for binary search for element 65535, in 1186 tries, for a total of 0.100016 s (ignore this:594538200) -for array sized 524288 elems, took 4.07696e-05 s for linear search and 0 s for binary search for element 32767, in 2342 tries, for a total of 0.100049 s (ignore this:748018828) -for array sized 524288 elems, took 1.97887e-05 s for linear search and 0 s for binary search for element 16383, in 4636 tries, for a total of 0.100011 s (ignore this:899922004) -for array sized 524288 elems, took 9.77516e-06 s for linear search and 0 s for binary search for element 8191, in 9192 tries, for a total of 0.100008 s (ignore this:1050505348) -for array sized 524288 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 4095, in 18022 tries, for a total of 0.100002 s (ignore this:1198105528) -for array sized 524288 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 2047, in 34970 tries, for a total of 0.100001 s (ignore this:1341272708) -for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 1023, in 65123 tries, for a total of 0.100000 s (ignore this:1474514366) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 511, in 115953 tries, for a total of 0.100000 s (ignore this:1593018332) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 188952 tries, for a total of 0.100000 s (ignore this:1689383852) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 277758 tries, for a total of 0.100001 s (ignore this:1759934384) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 357758 tries, for a total of 0.100000 s (ignore this:1805011892) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 415518 tries, for a total of 0.100000 s (ignore this:1830774008) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 463771 tries, for a total of 0.100000 s (ignore this:1844687138) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 487567 tries, for a total of 0.100001 s (ignore this:1851513076) +memhinfo : L2:16/64/4M,L1:8/64/32K +detected free memory : 48943620096 +detected total memory : 84307591168 +for array sized 4194304 elems, took 0.00230098 s for linear search and 0 s for binary search for element 4194303, in 37 tries, for a total of 0.102560 s (ignore this:310378422) +for array sized 4194304 elems, took 0.000787973 s for linear search and 0 s for binary search for element 2097151, in 61 tries, for a total of 0.102140 s (ignore this:566230844) +for array sized 4194304 elems, took 0.000362873 s for linear search and 0 s for binary search for element 1048575, in 185 tries, for a total of 0.100296 s (ignore this:954203594) +for array sized 4194304 elems, took 0.00018096 s for linear search and 0 s for binary search for element 524287, in 350 tries, for a total of 0.100004 s (ignore this:1321204494) +for array sized 4194304 elems, took 8.98838e-05 s for linear search and 0 s for binary search for element 262143, in 766 tries, for a total of 0.100072 s (ignore this:1722807570) +for array sized 4194304 elems, took 4.48227e-05 s for linear search and 0 s for binary search for element 131071, in 1515 tries, for a total of 0.100017 s (ignore this:2119952700) +for array sized 4194304 elems, took 2.19345e-05 s for linear search and 0 s for binary search for element 65535, in 2756 tries, for a total of 0.100035 s (ignore this:-1813785676) +for array sized 4194304 elems, took 1.09673e-05 s for linear search and 0 s for binary search for element 32767, in 6086 tries, for a total of 0.100002 s (ignore this:-1414945752) +for array sized 4194304 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 16383, in 12103 tries, for a total of 0.100004 s (ignore this:-1018378854) +for array sized 4194304 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 8191, in 22214 tries, for a total of 0.100001 s (ignore this:-654469106) +for array sized 4194304 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 4095, in 41872 tries, for a total of 0.100001 s (ignore this:-311537426) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 2047, in 80114 tries, for a total of 0.100001 s (ignore this:16449290) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 150197 tries, for a total of 0.100001 s (ignore this:323752352) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 511, in 113613 tries, for a total of 0.135346 s (ignore this:439864838) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 255, in 23482 tries, for a total of 0.533327 s (ignore this:451840658) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 127, in 527690 tries, for a total of 0.100001 s (ignore this:585873918) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 63, in 756222 tries, for a total of 0.100000 s (ignore this:681157890) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 31, in 868581 tries, for a total of 0.100000 s (ignore this:735009912) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 15, in 837502 tries, for a total of 0.100000 s (ignore this:760134972) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 7, in 798060 tries, for a total of 0.100001 s (ignore this:771307812) + ./rsbench -C /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench version: 1.3.0 format switches:br @@ -4155,7 +4216,7 @@ RSB_CONST_MAX_SUPPORTED_CORES:128 RSB_BLAS_MATRICES_MAX:2147482623 RSB_CONST_MIN_NNZ_PER_ROW_FOR_COO_SWITCH:2 -RSB_USER_SET_MEM_HIERARCHY_INFO:L2:16/64/512K,L1:2/64/64K +RSB_USER_SET_MEM_HIERARCHY_INFO:L2:16/64/4096K,L1:8/64/32K RSB_MAX_VALUE_FOR_TYPE(rsb_half_idx_t):65535 RSB_IOLEVEL:7 LIBRSBPP support: on. @@ -4175,17 +4236,17 @@ Adding matrix file: /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx # Sorting matrices list (use --no-sort-filenames-list to prevent this) # Using matrices: A.mtx -# beginning run at 1740605498 +# beginning run at 1775018880 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx --verbose --nrhs 1,4 --by-rows # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -# User did not specify threads; assuming 1. Environment provides max 20 threads; this build supports max 128. -# User did not specify threads; assuming 1. Environment provides max 20 threads; this build supports max 128. -# average timer granularity: 6.69e-08 s -# Will write a final performance record to file rsbench_pr__1740605498_gcc-14.2.rpr and periodic checkpoints to rsbench_pr__1740605498_gcc-14.2.rpr.tmp +# User did not specify threads; assuming 1. Environment provides max 42 threads; this build supports max 128. +# User did not specify threads; assuming 1. Environment provides max 42 threads; this build supports max 128. +# average timer granularity: 3.35e-08 s +# Will write a final performance record to file rsbench_pr__1775018880_gcc-14.2.rpr and periodic checkpoints to rsbench_pr__1775018880_gcc-14.2.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -4224,835 +4285,839 @@ # env: SLURM_NTASKS is not set # env: SLURM_STEP_TASKS_PER_NODE is not set # env: SLURM_TASKS_PER_NODE is not set -# detected hostname: ionos1-amd64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 1 (each --verbose occurrence counts +1) # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 5.514s +# Memory benchmark took 6.114s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 16 samples (4480 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). -# Cache block size total 524288 bytes, per-thread 26214 bytes -# so far, program took 5.517s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . +# Cache block size total 4194304 bytes, per-thread 99864 bytes +# so far, program took 6.116s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . # reading A.mtx (184 bytes / 1 MiB / 6 nnz / 3 rows / 3 columns / 1 MiB COO) as type D... -# file input of A.mtx took 0.00 s (6 nnz, 24291 nnz/s ) (0.74 MB/s ) -#pre-sorting (6 elements) took 0.0289619 s -#weeding duplicates (to 6 elements) took 4.05312e-06 s (and check, 2.86102e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 52103 nnz/s ) (1.60 MB/s ) +#pre-sorting (6 elements) took 0.0175629 s +#weeding duplicates (to 6 elements) took 1.90735e-06 s (and check, 2.14577e-06 s ) # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 20 threads -# Constructed matrix (took 0.112s): (3 x 3)[0x55b775766590]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 42 threads +# Constructed matrix (took 0.093s): (3 x 3)[0x55b78ac76660]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (20 th.) took 0.06098s; avg 0.02033s ( +/- 21.23/ 18.11 %); best 0.01601s; worst 0.02401s; std dev. 0.003295 (taking best). -Reference operation time is 0.016011 s (0.001499 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01601 Mflops: 0.001) -Merge (3 -> 1 leaves) took w.c.t. of 4.792e-05s, ~1.597e-05s of computing time (of which 9.537e-07s sorting, 7.153e-06s analysis) -3 iterations (20 th.) took 4.506e-05s; avg 1.502e-05s ( +/- 99.54/192.06 %); best 6.87e-08s; worst 4.387e-05s; std dev. 2.04e-05 (taking best). -Reference operation time is 6.87003e-08 s (349.3 Mflops) with 20 threads. -After merge step 1: tpop: 6.87e-08 s ~Mflops: 349.343 nsubm:1 otn:20 -Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 233055.700x: 0.01601s -> 6.87e-08s, so taking this instance. +3 iterations (42 th.) took 0.05374s; avg 0.01791s ( +/- 26.02/ 25.36 %); best 0.01325s; worst 0.02245s; std dev. 0.003758 (taking best). +Reference operation time is 0.0132511 s (0.001811 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01325 Mflops: 0.002) +Merge (3 -> 1 leaves) took w.c.t. of 3.004e-05s, ~9.775e-06s of computing time (of which 9.537e-07s sorting, 6.199e-06s analysis) +3 iterations (42 th.) took 2.408e-05s; avg 8.027e-06s ( +/- 99.58/185.15 %); best 3.395e-08s; worst 2.289e-05s; std dev. 1.052e-05 (taking best). +Reference operation time is 3.39508e-08 s (706.9 Mflops) with 42 threads. +After merge step 1: tpop: 3.395e-08 s ~Mflops: 706.905 nsubm:1 otn:42 +Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 390301.966x: 0.01325s -> 3.395e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.06394s (of which 5.388e-05s partitioning, 0s I/O); computing times: 1.597e-05s in par. loops, 9.537e-07s sorting, 7.153e-06s analyzing) -Total merge + benchmarking process took 0.06394s, equivalent to 930678.5/4.0 new/old ops (0.1226s for 2 clones -- as 1784435.2/7.7 ops, or 892217.6/3.8 ops per clone), SPEEDUP of 233055.700x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 233055.700x (0.01601s -> 6.87e-08s), will amortize in 4.0 ops by saving 0.01601s per op. -In 1 tuning rounds (tot. 0.18s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 23305470.0% (2.331e+05x) (from 0.001499 to 349.3 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03196s (of which 3.409e-05s partitioning, 0s I/O); computing times: 9.775e-06s in par. loops, 9.537e-07s sorting, 6.199e-06s analyzing) +Total merge + benchmarking process took 0.03196s, equivalent to 941243.0/2.4 new/old ops (0.07721s for 2 clones -- as 2274080.1/5.8 ops, or 1137040.0/2.9 ops per clone), SPEEDUP of 390301.966x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 390301.966x (0.01325s -> 3.395e-08s), will amortize in 2.4 ops by saving 0.01325s per op. +In 1 tuning rounds (tot. 0.13s, 0.077s for constructor, 2 clones) obtained a SPEEDUP of 39030096.6% (3.903e+05x) (from 0.001811 to 706.9 Mflops). #pr: updating sample at index 1 (0^th of 16), 0^th touch for (0,0,0,0,0,0,0). -First run of RSB Autotuner took 0.183995 s (1.601e-02 s -> 6.870e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.131151 s (1.325e-02 s -> 3.395e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.915903 s and estimated a speedup of 1.000000 x (6.870e-08 s -> 6.870e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.64103 s and estimated a speedup of 1.000000 x (3.395e-08 s -> 3.395e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.7320508075688772 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.039549 0.039989 0.079538 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.079538 -%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.039549 -%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.039989 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.079538 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.034833 0.028073 0.062906 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.062906 +%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.034833 +%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.028073 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.062906 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] -%operation:A.mtx 0.111541 1e+09 1e+09 -%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] -%constructor:A.mtx 0 0.0395489 0 0.039989 +%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] +%operation:A.mtx 0.0926471 1e+09 1e+09 +%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] +%constructor:A.mtx 0 0.0348332 0 0.0280731 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 20 threads -# Constructed matrix (took 0.100s): (3 x 3)[0x55b775766590]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 42 threads +# Constructed matrix (took 0.076s): (3 x 3)[0x55b78ac79520]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (20 th.) took 0.048s; avg 0.016s ( +/- 0.16/ 0.10 %); best 0.01597s; worst 0.01602s; std dev. 1.833e-05 (taking best). -Reference operation time is 0.015974 s (0.00601 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01597 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 2.503e-05s, ~1.001e-05s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (20 th.) took 1.907e-05s; avg 6.358e-06s ( +/- 98.92/185.00 %); best 6.87e-08s; worst 1.812e-05s; std dev. 8.326e-06 (taking best). -Reference operation time is 6.87003e-08 s (1397 Mflops) with 20 threads. -After merge step 1: tpop: 6.87e-08 s ~Mflops: 1397.374 nsubm:1 otn:20 -Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 232517.786x: 0.01597s -> 6.87e-08s, so taking this instance. +3 iterations (42 th.) took 1.326s; avg 0.4419s ( +/- 98.20/195.08 %); best 0.007946s; worst 1.304s; std dev. 0.6096 (taking best). +Reference operation time is 0.00794601 s (0.01208 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.007946 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 2.599e-05s, ~7.868e-06s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) +3 iterations (42 th.) took 8.106e-06s; avg 2.702e-06s ( +/- 98.74/164.71 %); best 3.395e-08s; worst 7.153e-06s; std dev. 3.171e-06 (taking best). +Reference operation time is 3.39508e-08 s (2828 Mflops) with 42 threads. +After merge step 1: tpop: 3.395e-08 s ~Mflops: 2827.621 nsubm:1 otn:42 +Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 234044.944x: 0.007946s -> 3.395e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.048s (of which 3.004e-05s partitioning, 0s I/O); computing times: 1.001e-05s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.048s, equivalent to 698670.8/3.0 new/old ops (0.09589s for 2 clones -- as 1395759.2/6.0 ops, or 697879.6/3.0 ops per clone), SPEEDUP of 232517.786x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 232517.786x (0.01597s -> 6.87e-08s), will amortize in 3.0 ops by saving 0.01597s per op. -In 1 tuning rounds (tot. 0.14s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 23251678.6% (2.325e+05x) (from 0.00601 to 1397 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.05819s (of which 2.909e-05s partitioning, 0s I/O); computing times: 7.868e-06s in par. loops, 2.146e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.05819s, equivalent to 1714094.1/7.3 new/old ops (0.0962s for 2 clones -- as 2833658.7/12.1 ops, or 1416829.4/6.1 ops per clone), SPEEDUP of 234044.944x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 234044.944x (0.007946s -> 3.395e-08s), will amortize in 7.3 ops by saving 0.007946s per op. +In 1 tuning rounds (tot. 1.4s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 23404394.4% (2.34e+05x) (from 0.01208 to 2828 Mflops). #pr: updating sample at index 9 (1^th of 16), 0^th touch for (0,0,0,0,1,0,0). -First run of RSB Autotuner took 0.144024 s (1.597e-02 s -> 6.870e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 1.42214 s (7.946e-03 s -> 3.395e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.767939 s and estimated a speedup of 1.000000 x (6.870e-08 s -> 6.870e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.643781 s and estimated a speedup of 1.000000 x (3.395e-08 s -> 3.395e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.7320508075688772 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.035575 0.031993 0.067568 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.067568 -%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.035575 -%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.031993 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.067568 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.022875 0.027119 0.049994 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.049994 +%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.022875 +%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.027119 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.049994 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] -%operation:A.mtx 0.0995488 1e+09 1e+09 -%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] -%constructor:A.mtx 0 0.0355752 0 0.0319929 +%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] +%operation:A.mtx 0.07582 1e+09 1e+09 +%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] +%constructor:A.mtx 0 0.0228748 0 0.0271192 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 7.923s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.012s/0.000s . +# so far, program took 9.263s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.838s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.05502s (system CPU time used) -ru_utime : 33.8s (user CPU time used) +ru_maxrss: 22 (maximum resident set size -- MB) +ru_stime : 0.3107s (system CPU time used) +ru_utime : 27.81s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). -# Cache block size total 524288 bytes, per-thread 26214 bytes -# so far, program took 7.923s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.012s/0.000s . +# Cache block size total 4194304 bytes, per-thread 99864 bytes +# so far, program took 9.263s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.838s/0.000s . # Reusing type converted (D->S) arrays from last iteration instead of reloading matrix file. # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 20 threads -# Constructed matrix (took 0.103s): (3 x 3)[0x55b775766590]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 42 threads +# Constructed matrix (took 0.083s): (3 x 3)[0x55b78ac79520]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (20 th.) took 0.048s; avg 0.016s ( +/- 0.03/ 0.03 %); best 0.01599s; worst 0.016s; std dev. 4.216e-06 (taking best). -Reference operation time is 0.0159938 s (0.001501 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01599 Mflops: 0.002) -Merge (3 -> 1 leaves) took w.c.t. of 2.694e-05s, ~1.001e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) -3 iterations (20 th.) took 3.409e-05s; avg 1.136e-05s ( +/- 99.40/189.51 %); best 6.87e-08s; worst 3.29e-05s; std dev. 1.524e-05 (taking best). -Reference operation time is 6.87003e-08 s (349.3 Mflops) with 20 threads. -After merge step 1: tpop: 6.87e-08 s ~Mflops: 349.343 nsubm:1 otn:20 -Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 232805.830x: 0.01599s -> 6.87e-08s, so taking this instance. +3 iterations (42 th.) took 0.05156s; avg 0.01719s ( +/- 17.30/ 21.82 %); best 0.01421s; worst 0.02094s; std dev. 0.0028 (taking best). +Reference operation time is 0.014215 s (0.001688 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01421 Mflops: 0.002) +Merge (3 -> 1 leaves) took w.c.t. of 2.909e-05s, ~1.001e-05s of computing time (of which 1.192e-06s sorting, 5.007e-06s analysis) +3 iterations (42 th.) took 3.099e-05s; avg 1.033e-05s ( +/- 99.67/188.46 %); best 3.395e-08s; worst 2.98e-05s; std dev. 1.378e-05 (taking best). +Reference operation time is 3.39508e-08 s (706.9 Mflops) with 42 threads. +After merge step 1: tpop: 3.395e-08 s ~Mflops: 706.905 nsubm:1 otn:42 +Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 418693.820x: 0.01421s -> 3.395e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.048s (of which 3.195e-05s partitioning, 0s I/O); computing times: 1.001e-05s in par. loops, 1.907e-06s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.048s, equivalent to 698715.9/3.0 new/old ops (0.09585s for 2 clones -- as 1395235.1/6.0 ops, or 697617.6/3.0 ops per clone), SPEEDUP of 232805.830x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 232805.830x (0.01599s -> 6.87e-08s), will amortize in 3.0 ops by saving 0.01599s per op. -In 1 tuning rounds (tot. 0.14s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 23280483.0% (2.328e+05x) (from 0.001501 to 349.3 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1013s (of which 3.314e-05s partitioning, 0s I/O); computing times: 1.001e-05s in par. loops, 1.192e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.1013s, equivalent to 2983174.2/7.1 new/old ops (0.1401s for 2 clones -- as 4125491.6/9.9 ops, or 2062745.8/4.9 ops per clone), SPEEDUP of 418693.820x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 418693.820x (0.01421s -> 3.395e-08s), will amortize in 7.1 ops by saving 0.01421s per op. +In 1 tuning rounds (tot. 0.19s, 0.14s for constructor, 2 clones) obtained a SPEEDUP of 41869282.0% (4.187e+05x) (from 0.001688 to 706.9 Mflops). #pr: updating sample at index 3 (2^th of 16), 0^th touch for (0,0,0,0,0,1,0). -First run of RSB Autotuner took 0.144322 s (1.599e-02 s -> 6.870e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.191918 s (1.421e-02 s -> 3.395e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.71891 s and estimated a speedup of 1.000000 x (6.870e-08 s -> 6.870e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.45497 s and estimated a speedup of 1.000000 x (3.395e-08 s -> 3.395e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.73205078 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.039341 0.032003 0.071344 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.071344 -%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.039341 -%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.032003 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.071344 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.038287 0.014330 0.052617 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.052617 +%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.038287 +%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.014330 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.052617 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 96 -%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 96 +%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] -%operation:A.mtx 0.103356 1e+09 1e+09 -%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] -%constructor:A.mtx 0 0.039341 0 0.0320029 +%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] +%operation:A.mtx 0.082649 1e+09 1e+09 +%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] +%constructor:A.mtx 0 0.0382869 0 0.0143299 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 20 threads -# Constructed matrix (took 0.091s): (3 x 3)[0x55b775766590]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 42 threads +# Constructed matrix (took 0.144s): (3 x 3)[0x55b78ac79520]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (20 th.) took 0.04799s; avg 0.016s ( +/- 0.05/ 0.04 %); best 0.01599s; worst 0.016s; std dev. 5.776e-06 (taking best). -Reference operation time is 0.0159888 s (0.006004 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01599 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 2.193e-05s, ~6.914e-06s of computing time (of which 1.192e-06s sorting, 4.053e-06s analysis) -3 iterations (20 th.) took 2.599e-05s; avg 8.663e-06s ( +/- 99.21/188.99 %); best 6.87e-08s; worst 2.503e-05s; std dev. 1.158e-05 (taking best). -Reference operation time is 6.87003e-08 s (1397 Mflops) with 20 threads. -After merge step 1: tpop: 6.87e-08 s ~Mflops: 1397.374 nsubm:1 otn:20 -Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 232732.952x: 0.01599s -> 6.87e-08s, so taking this instance. +3 iterations (42 th.) took 0.08904s; avg 0.02968s ( +/- 34.73/ 44.80 %); best 0.01937s; worst 0.04298s; std dev. 0.009866 (taking best). +Reference operation time is 0.019372 s (0.004956 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01937 Mflops: 0.005) +Merge (3 -> 1 leaves) took w.c.t. of 2.885e-05s, ~1.097e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) +3 iterations (42 th.) took 3.886e-05s; avg 1.295e-05s ( +/- 92.64/185.28 %); best 9.537e-07s; worst 3.695e-05s; std dev. 1.697e-05 (taking best). +Reference operation time is 9.53674e-07 s (100.7 Mflops) with 42 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:42 +Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 20313.000x: 0.01937s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03609s (of which 2.599e-05s partitioning, 0s I/O); computing times: 6.914e-06s in par. loops, 1.192e-06s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.03609s, equivalent to 525341.0/2.3 new/old ops (0.07224s for 2 clones -- as 1051594.7/4.5 ops, or 525797.3/2.3 ops per clone), SPEEDUP of 232732.952x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 232732.952x (0.01599s -> 6.87e-08s), will amortize in 2.3 ops by saving 0.01599s per op. -In 1 tuning rounds (tot. 0.12s, 0.072s for constructor, 2 clones) obtained a SPEEDUP of 23273195.2% (2.327e+05x) (from 0.006004 to 1397 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.07877s (of which 3.29e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 1.907e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.07877s, equivalent to 82592.2/4.1 new/old ops (0.1536s for 2 clones -- as 161017.5/7.9 ops, or 80508.8/4.0 ops per clone), SPEEDUP of 20313.000x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 20313.000x (0.01937s -> 9.537e-07s), will amortize in 4.1 ops by saving 0.01937s per op. +In 1 tuning rounds (tot. 0.24s, 0.15s for constructor, 2 clones) obtained a SPEEDUP of 2031200.0% (2.031e+04x) (from 0.004956 to 100.7 Mflops). #pr: updating sample at index 11 (3^th of 16), 0^th touch for (0,0,0,0,1,1,0). -First run of RSB Autotuner took 0.120495 s (1.599e-02 s -> 6.870e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.242938 s (1.937e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.567854 s and estimated a speedup of 1.000000 x (6.870e-08 s -> 6.870e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.813307 s and estimated a speedup of 1.000000 x (3.395e-08 s -> 3.395e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.73205078 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.027299 0.031998 0.059297 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.059297 -%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.027299 -%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.031998 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.059297 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.053728 0.049367 0.103095 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.103095 +%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.053728 +%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.049367 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.103095 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 96 -%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 96 +%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] -%operation:A.mtx 0.0909181 1e+09 1e+09 -%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] -%constructor:A.mtx 0 0.0272992 0 0.0319979 +%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] +%operation:A.mtx 0.143589 1e+09 1e+09 +%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] +%constructor:A.mtx 0 0.0537281 0 0.049367 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 9.827s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.563s/0.000s . +# so far, program took 12.423s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.541s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.08289s (system CPU time used) -ru_utime : 63.25s (user CPU time used) +ru_maxrss: 22 (maximum resident set size -- MB) +ru_stime : 0.4746s (system CPU time used) +ru_utime : 46.96s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was S). -# Cache block size total 524288 bytes, per-thread 26214 bytes -# so far, program took 9.827s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.563s/0.000s . +# Cache block size total 4194304 bytes, per-thread 99864 bytes +# so far, program took 12.423s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.541s/0.000s . # Reusing type converted (S->C) arrays from last iteration instead of reloading matrix file. # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 20 threads -# Constructed matrix (took 0.104s): (3 x 3)[0x55b7757698a0]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 42 threads +# Constructed matrix (took 0.137s): (3 x 3)[0x55b78ac79520]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (20 th.) took 0.04797s; avg 0.01599s ( +/- 0.07/ 0.06 %); best 0.01598s; worst 0.016s; std dev. 8.287e-06 (taking best). -Reference operation time is 0.0159781 s (0.006008 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01598 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 2.813e-05s, ~8.106e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (20 th.) took 2.694e-05s; avg 8.98e-06s ( +/- 99.23/189.38 %); best 6.87e-08s; worst 2.599e-05s; std dev. 1.203e-05 (taking best). -Reference operation time is 6.87003e-08 s (1397 Mflops) with 20 threads. -After merge step 1: tpop: 6.87e-08 s ~Mflops: 1397.374 nsubm:1 otn:20 -Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 232576.783x: 0.01598s -> 6.87e-08s, so taking this instance. +3 iterations (42 th.) took 0.125s; avg 0.04166s ( +/- 29.76/ 34.31 %); best 0.02927s; worst 0.05596s; std dev. 0.01098 (taking best). +Reference operation time is 0.0292671 s (0.00328 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.02927 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 2.885e-05s, ~9.06e-06s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) +3 iterations (42 th.) took 3.409e-05s; avg 1.136e-05s ( +/- 91.61/181.12 %); best 9.537e-07s; worst 3.195e-05s; std dev. 1.456e-05 (taking best). +Reference operation time is 9.53674e-07 s (100.7 Mflops) with 42 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:42 +Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 30688.750x: 0.02927s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04814s (of which 3.099e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 9.537e-07s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.04814s, equivalent to 700739.2/3.0 new/old ops (0.09592s for 2 clones -- as 1396210.3/6.0 ops, or 698105.2/3.0 ops per clone), SPEEDUP of 232576.783x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 232576.783x (0.01598s -> 6.87e-08s), will amortize in 3.0 ops by saving 0.01598s per op. -In 1 tuning rounds (tot. 0.14s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 23257578.3% (2.326e+05x) (from 0.006008 to 1397 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.12s (of which 3.195e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 2.146e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.12s, equivalent to 125875.2/4.1 new/old ops (0.2578s for 2 clones -- as 270310.2/8.8 ops, or 135155.1/4.4 ops per clone), SPEEDUP of 30688.750x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 30688.750x (0.02927s -> 9.537e-07s), will amortize in 4.1 ops by saving 0.02927s per op. +In 1 tuning rounds (tot. 0.38s, 0.26s for constructor, 2 clones) obtained a SPEEDUP of 3068775.0% (3.069e+04x) (from 0.00328 to 100.7 Mflops). #pr: updating sample at index 5 (4^th of 16), 0^th touch for (0,0,0,0,0,2,0). -First run of RSB Autotuner took 0.144062 s (1.598e-02 s -> 6.870e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.382982 s (2.927e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.775781 s and estimated a speedup of 1.000000 x (6.870e-08 s -> 6.870e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 2.1827 s and estimated a speedup of 1.000000 x (3.395e-08 s -> 3.395e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.73205078 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.039739 0.032007 0.071746 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.071746 -%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.039739 -%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.032007 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.071746 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.040045 0.039493 0.079538 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.079538 +%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.040045 +%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.039493 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.079538 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] -%operation:A.mtx 0.103753 1e+09 1e+09 -%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] -%constructor:A.mtx 0 0.0397389 0 0.032007 +%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] +%operation:A.mtx 0.137319 1e+09 1e+09 +%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] +%constructor:A.mtx 0 0.0400448 0 0.0394931 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 20 threads -# Constructed matrix (took 0.056s): (3 x 3)[0x55b7757698a0]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 42 threads +# Constructed matrix (took 0.249s): (3 x 3)[0x55b78ac79520]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (20 th.) took 0.03602s; avg 0.01201s ( +/- 33.16/ 33.20 %); best 0.008025s; worst 0.01599s; std dev. 0.003252 (taking best). -Reference operation time is 0.00802517 s (0.04785 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.008025 Mflops: 0.048) -Merge (3 -> 1 leaves) took w.c.t. of 2.098e-05s, ~7.153e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) -3 iterations (20 th.) took 2.384e-05s; avg 7.947e-06s ( +/- 88.00/176.00 %); best 9.537e-07s; worst 2.193e-05s; std dev. 9.89e-06 (taking best). -Reference operation time is 9.53674e-07 s (402.7 Mflops) with 20 threads. -After merge step 1: tpop: 9.537e-07 s ~Mflops: 402.653 nsubm:1 otn:20 -Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 8415.000x: 0.008025s -> 9.537e-07s, so taking this instance. +3 iterations (42 th.) took 0.1308s; avg 0.04361s ( +/- 22.95/ 14.34 %); best 0.0336s; worst 0.04987s; std dev. 0.007151 (taking best). +Reference operation time is 0.033602 s (0.01143 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.0336 Mflops: 0.011) +Merge (3 -> 1 leaves) took w.c.t. of 2.599e-05s, ~8.106e-06s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) +3 iterations (42 th.) took 2.718e-05s; avg 9.06e-06s ( +/- 99.63/186.84 %); best 3.395e-08s; worst 2.599e-05s; std dev. 1.198e-05 (taking best). +Reference operation time is 3.39508e-08 s (1.131e+04 Mflops) with 42 threads. +After merge step 1: tpop: 3.395e-08 s ~Mflops: 11310.483 nsubm:1 otn:42 +Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 989726.124x: 0.0336s -> 3.395e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03195s (of which 2.408e-05s partitioning, 0s I/O); computing times: 7.153e-06s in par. loops, 9.537e-07s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.03195s, equivalent to 33504.2/4.0 new/old ops (0.06382s for 2 clones -- as 66922.0/8.0 ops, or 33461.0/4.0 ops per clone), SPEEDUP of 8415.000x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 8415.000x (0.008025s -> 9.537e-07s), will amortize in 4.0 ops by saving 0.008024s per op. -In 1 tuning rounds (tot. 0.1s, 0.064s for constructor, 2 clones) obtained a SPEEDUP of 841400.0% (8415x) (from 0.04785 to 402.7 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.09276s (of which 2.909e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 2.146e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.09276s, equivalent to 2732155.9/2.8 new/old ops (0.2152s for 2 clones -- as 6337198.0/6.4 ops, or 3168599.0/3.2 ops per clone), SPEEDUP of 989726.124x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 989726.124x (0.0336s -> 3.395e-08s), will amortize in 2.8 ops by saving 0.0336s per op. +In 1 tuning rounds (tot. 0.35s, 0.22s for constructor, 2 clones) obtained a SPEEDUP of 98972512.4% (9.897e+05x) (from 0.01143 to 1.131e+04 Mflops). #pr: updating sample at index 13 (5^th of 16), 0^th touch for (0,0,0,0,1,2,0). -First run of RSB Autotuner took 0.100004 s (8.025e-03 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.346171 s (3.360e-02 s -> 3.395e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.503942 s and estimated a speedup of 1.000000 x (6.870e-08 s -> 6.870e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 3.80756 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.73205078 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.019571 0.016002 0.035573 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.035573 -%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.019571 -%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.016002 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.035573 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.096037 0.079906 0.175943 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.175943 +%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.096037 +%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.079906 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.175943 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] -%operation:A.mtx 0.055594 1e+09 1e+09 -%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] -%constructor:A.mtx 0 0.0195711 0 0.0160019 +%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] +%operation:A.mtx 0.248808 1e+09 1e+09 +%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] +%constructor:A.mtx 0 0.0960371 0 0.079906 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 11.611s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.087s/0.000s . +# so far, program took 20.022s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 12.261s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.09082s (system CPU time used) -ru_utime : 94.1s (user CPU time used) +ru_maxrss: 22 (maximum resident set size -- MB) +ru_stime : 0.6929s (system CPU time used) +ru_utime : 71.81s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was C). -# Cache block size total 524288 bytes, per-thread 26214 bytes -# so far, program took 11.611s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.087s/0.000s . +# Cache block size total 4194304 bytes, per-thread 99864 bytes +# so far, program took 20.023s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 12.261s/0.000s . # Reusing type converted (C->Z) arrays from last iteration instead of reloading matrix file. # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 20 threads -# Constructed matrix (took 0.056s): (3 x 3)[0x55b7757698a0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 42 threads +# Constructed matrix (took 0.316s): (3 x 3)[0x55b78ac79520]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (20 th.) took 0.05063s; avg 0.01688s ( +/- 28.74/ 33.93 %); best 0.01203s; worst 0.0226s; std dev. 0.004362 (taking best). -Reference operation time is 0.0120258 s (0.007983 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01203 Mflops: 0.008) -Merge (3 -> 1 leaves) took w.c.t. of 3.29e-05s, ~1.001e-05s of computing time (of which 2.861e-06s sorting, 7.153e-06s analysis) -3 iterations (20 th.) took 3.409e-05s; avg 1.136e-05s ( +/- 91.61/181.12 %); best 9.537e-07s; worst 3.195e-05s; std dev. 1.456e-05 (taking best). -Reference operation time is 9.53674e-07 s (100.7 Mflops) with 20 threads. -After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:20 -Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 12610.000x: 0.01203s -> 9.537e-07s, so taking this instance. +3 iterations (42 th.) took 0.1495s; avg 0.04982s ( +/- 1.46/ 1.78 %); best 0.04909s; worst 0.05071s; std dev. 0.0006677 (taking best). +Reference operation time is 0.049094 s (0.001955 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.04909 Mflops: 0.002) +Merge (3 -> 1 leaves) took w.c.t. of 2.599e-05s, ~1.001e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) +3 iterations (42 th.) took 3.099e-05s; avg 1.033e-05s ( +/- 99.67/190.77 %); best 3.395e-08s; worst 3.004e-05s; std dev. 1.394e-05 (taking best). +Reference operation time is 3.39508e-08 s (2828 Mflops) with 42 threads. +After merge step 1: tpop: 3.395e-08 s ~Mflops: 2827.621 nsubm:1 otn:42 +Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 1446032.303x: 0.04909s -> 3.395e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04396s (of which 3.886e-05s partitioning, 0s I/O); computing times: 1.001e-05s in par. loops, 2.861e-06s sorting, 7.153e-06s analyzing) -Total merge + benchmarking process took 0.04396s, equivalent to 46099.5/3.7 new/old ops (0.07721s for 2 clones -- as 80965.8/6.4 ops, or 40482.9/3.2 ops per clone), SPEEDUP of 12610.000x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 12610.000x (0.01203s -> 9.537e-07s), will amortize in 3.7 ops by saving 0.01202s per op. -In 1 tuning rounds (tot. 0.13s, 0.077s for constructor, 2 clones) obtained a SPEEDUP of 1260900.0% (1.261e+04x) (from 0.007983 to 100.7 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.154s (of which 2.98e-05s partitioning, 0s I/O); computing times: 1.001e-05s in par. loops, 1.907e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.154s, equivalent to 4537324.4/3.1 new/old ops (0.2786s for 2 clones -- as 8204873.6/5.7 ops, or 4102436.8/2.8 ops per clone), SPEEDUP of 1446032.303x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 1446032.303x (0.04909s -> 3.395e-08s), will amortize in 3.1 ops by saving 0.04909s per op. +In 1 tuning rounds (tot. 0.43s, 0.28s for constructor, 2 clones) obtained a SPEEDUP of 144603130.3% (1.446e+06x) (from 0.001955 to 2828 Mflops). #pr: updating sample at index 7 (6^th of 16), 0^th touch for (0,0,0,0,0,3,0). -First run of RSB Autotuner took 0.128034 s (1.203e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.428232 s (4.909e-02 s -> 3.395e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.747959 s and estimated a speedup of 1.000000 x (6.870e-08 s -> 6.870e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 2.29305 s and estimated a speedup of 1.000000 x (3.395e-08 s -> 3.395e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.023559 0.015993 0.039552 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.039552 -%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.023559 -%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.015993 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.039552 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.125514 0.085819 0.211333 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.211333 +%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.125514 +%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.085819 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.211333 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 276 -%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 276 +%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] -%operation:A.mtx 0.055568 1e+09 1e+09 -%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] -%constructor:A.mtx 0 0.0235591 0 0.0159931 +%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] +%operation:A.mtx 0.31645 1e+09 1e+09 +%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] +%constructor:A.mtx 0 0.125514 0 0.085819 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 20 threads -# Constructed matrix (took 0.104s): (3 x 3)[0x55b7757698a0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 42 threads +# Constructed matrix (took 0.205s): (3 x 3)[0x55b78ac79520]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (20 th.) took 0.04802s; avg 0.01601s ( +/- 0.05/ 0.07 %); best 0.016s; worst 0.01602s; std dev. 8.095e-06 (taking best). -Reference operation time is 0.0159991 s (0.024 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.016 Mflops: 0.024) -Merge (3 -> 1 leaves) took w.c.t. of 2.289e-05s, ~7.153e-06s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) -3 iterations (20 th.) took 7.868e-06s; avg 2.623e-06s ( +/- 97.38/163.64 %); best 6.87e-08s; worst 6.914e-06s; std dev. 3.059e-06 (taking best). -Reference operation time is 6.87003e-08 s (5589 Mflops) with 20 threads. -After merge step 1: tpop: 6.87e-08 s ~Mflops: 5589.494 nsubm:1 otn:20 -Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 232882.179x: 0.016s -> 6.87e-08s, so taking this instance. +3 iterations (42 th.) took 0.141s; avg 0.04701s ( +/- 9.52/ 14.60 %); best 0.04253s; worst 0.05387s; std dev. 0.004927 (taking best). +Reference operation time is 0.0425339 s (0.009028 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.04253 Mflops: 0.009) +Merge (3 -> 1 leaves) took w.c.t. of 2.789e-05s, ~9.06e-06s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) +3 iterations (42 th.) took 1.097e-05s; avg 3.656e-06s ( +/- 99.07/173.91 %); best 3.395e-08s; worst 1.001e-05s; std dev. 4.512e-06 (taking best). +Reference operation time is 3.39508e-08 s (1.131e+04 Mflops) with 42 threads. +After merge step 1: tpop: 3.395e-08 s ~Mflops: 11310.483 nsubm:1 otn:42 +Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 1252808.989x: 0.04253s -> 3.395e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04796s (of which 2.599e-05s partitioning, 0s I/O); computing times: 7.153e-06s in par. loops, 1.907e-06s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.04796s, equivalent to 698146.8/3.0 new/old ops (0.09583s for 2 clones -- as 1394839.5/6.0 ops, or 697419.7/3.0 ops per clone), SPEEDUP of 232882.179x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 232882.179x (0.016s -> 6.87e-08s), will amortize in 3.0 ops by saving 0.016s per op. -In 1 tuning rounds (tot. 0.14s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 23288117.9% (2.329e+05x) (from 0.024 to 5589 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.136s (of which 3.195e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 1.907e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.136s, equivalent to 4006383.4/3.2 new/old ops (0.2453s for 2 clones -- as 7226594.1/5.8 ops, or 3613297.1/2.9 ops per clone), SPEEDUP of 1252808.989x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 1252808.989x (0.04253s -> 3.395e-08s), will amortize in 3.2 ops by saving 0.04253s per op. +In 1 tuning rounds (tot. 0.39s, 0.25s for constructor, 2 clones) obtained a SPEEDUP of 125280798.9% (1.253e+06x) (from 0.009028 to 1.131e+04 Mflops). #pr: updating sample at index 15 (7^th of 16), 0^th touch for (0,0,0,0,1,3,0). -First run of RSB Autotuner took 0.143981 s (1.600e-02 s -> 6.870e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.386847 s (4.253e-02 s -> 3.395e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.779879 s and estimated a speedup of 1.000000 x (6.870e-08 s -> 6.870e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 5.39617 s and estimated a speedup of 1.000000 x (3.395e-08 s -> 3.395e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.039595 0.032000 0.071595 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.071595 -%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.039595 -%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.032000 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.071595 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.081377 0.057594 0.138971 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.138971 +%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.081377 +%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.057594 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.138971 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 276 -%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 276 +%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] -%operation:A.mtx 0.103614 1e+09 1e+09 -%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] -%constructor:A.mtx 0 0.0395949 0 0.0320001 +%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] +%operation:A.mtx 0.205025 1e+09 1e+09 +%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] +%constructor:A.mtx 0 0.081377 0 0.0575938 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 13.731s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 6.887s/0.000s . +# so far, program took 29.519s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 20.765s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.1186s (system CPU time used) -ru_utime : 129s (user CPU time used) +ru_maxrss: 22 (maximum resident set size -- MB) +ru_stime : 0.8853s (system CPU time used) +ru_utime : 93.3s (user CPU time used) # benchmarking terminated --- finalizing run. # ====== BEGIN Total summary record. #pr: ======== Limiting to type D: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 349.34 1.601e-02 0.000e+00 6.870e-08 0.000e+00 1.840e-01 2.15e+00 5.17e+00 1 2.40e-05 -pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.597e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 5.30e+00 2.79e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 706.91 1.325e-02 0.000e+00 3.395e-08 0.000e+00 1.312e-01 4.36e+00 5.17e+00 1 2.40e-05 +pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2827.62 7.946e-03 0.000e+00 3.395e-08 0.000e+00 1.422e+00 1.07e+01 2.79e+00 1 9.60e-05 #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 23278574.3 % faster, avg. sp. ratio 232786.743x, max sp. ratio 233055.700x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2387319.1/2096411.6/2678226.6/4774638.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.3/ 9.0/ 11.5/ 20.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.3, min. 9.0, max. 11.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 31217245.5 % faster, avg. sp. ratio 312173.455x, max sp. ratio 390301.966x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 22875684.7/3862970.5/41888398.9/45751369.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 94.4/ 9.9/179.0/188.9 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 94.4, min. 9.9, max. 179.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 16/ 16/ 16) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 48/ 48/ 48) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.853/ 1.805/ 3.901,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 7.453/ 2.154/ 5.298,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.773/ 3.652/ 7.894,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 15.081/ 4.359/ 10.721,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 3.979/ 2.792/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.16 s, min 0.14 s, max 0.18 s, tot 0.33 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.16 s, min 0.14 s, max 0.18 s, tot 0.33 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.734e+02, min 3.493e+02, max 1.397e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.754e-03, min 1.499e-03, max 6.010e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 6.870e-08s, min 6.870e-08s, max 6.870e-08s, tot 1.374e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.599e-02s, min 1.597e-02s, max 1.601e-02s, tot 3.199e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.573e+00 5.561e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.78 s, min 0.13 s, max 1.42 s, tot 1.55 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.78 s, min 0.13 s, max 1.42 s, tot 1.55 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.767e+03, min 7.069e+02, max 2.828e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.946e-03, min 1.811e-03, max 1.208e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.395e-08s, min 3.395e-08s, max 3.395e-08s, tot 6.790e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.060e-02s, min 7.946e-03s, max 1.325e-02s, tot 2.120e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.706e+00 3.687e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type S: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 349.34 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.443e-01 1.28e+00 3.17e+00 1 2.40e-05 -pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.205e-01 2.85e+00 1.54e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 706.91 1.421e-02 0.000e+00 3.395e-08 0.000e+00 1.919e-01 2.59e+00 3.17e+00 1 2.40e-05 +pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 100.66 1.937e-02 0.000e+00 9.537e-07 0.000e+00 2.429e-01 2.06e-01 1.54e+00 1 9.60e-05 #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 23276839.1 % faster, avg. sp. ratio 232769.391x, max sp. ratio 232805.830x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1927334.7/1753919.8/2100749.6/3854669.4 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 8.3/ 7.5/ 9.0/ 16.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 8.3, min. 7.5, max. 9.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 21950241.0 % faster, avg. sp. ratio 219503.410x, max sp. ratio 418693.820x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2953781.0/254739.0/5652823.0/5907562.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.0/ 12.5/ 13.5/ 26.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.0, min. 12.5, max. 13.5 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 8/ 8/ 8) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 24/ 24/ 24) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.630/ 1.106/ 2.154,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 4.134/ 1.281/ 2.853,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.197/ 0.155/ 2.239,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.798/ 0.206/ 2.592,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.354/ 1.542/ 3.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.26 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.13 s, min 0.12 s, max 0.14 s, tot 0.26 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.734e+02, min 3.493e+02, max 1.397e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.752e-03, min 1.501e-03, max 6.004e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 6.870e-08s, min 6.870e-08s, max 6.870e-08s, tot 1.374e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.599e-02s, min 1.599e-02s, max 1.599e-02s, tot 3.198e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.659e+00 9.073e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.22 s, min 0.19 s, max 0.24 s, tot 0.43 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.22 s, min 0.19 s, max 0.24 s, tot 0.43 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.038e+02, min 1.007e+02, max 7.069e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.322e-03, min 1.688e-03, max 4.956e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 4.938e-07s, min 3.395e-08s, max 9.537e-07s, tot 9.876e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.679e-02s, min 1.421e-02s, max 1.937e-02s, tot 3.359e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.015e+00 8.676e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.424e-01 x, min 1.424e-01 x, max 1.424e-01 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type C: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.598e-02 0.000e+00 6.870e-08 0.000e+00 1.441e-01 2.15e+00 1.29e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 8.025e-03 0.000e+00 9.537e-07 0.000e+00 1.000e-01 3.82e-01 6.98e-01 1 3.84e-04 +pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 100.66 2.927e-02 0.000e+00 9.537e-07 0.000e+00 3.830e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 11310.48 3.360e-02 0.000e+00 3.395e-08 0.000e+00 3.462e-01 1.07e+01 6.98e-01 1 3.84e-04 #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 12049489.1 % faster, avg. sp. ratio 120495.891x, max sp. ratio 232576.783x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1100912.6/104861.8/2096963.4/2201825.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.7/ 9.0/ 12.5/ 21.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.7, min. 9.0, max. 12.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 51020643.7 % faster, avg. sp. ratio 510207.437x, max sp. ratio 989726.124x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 5298917.9/401585.8/10196250.0/10597835.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.7/ 10.3/ 13.1/ 23.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.7, min. 10.3, max. 13.1 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 16/ 16/ 16) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 48/ 48/ 48) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.043/ 0.281/ 1.805,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.536/ 0.382/ 2.154,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.012/ 0.130/ 7.894,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.877/ 0.155/ 10.721,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 0.995/ 0.698/ 1.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.12 s, min 0.10 s, max 0.14 s, tot 0.24 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.12 s, min 0.10 s, max 0.14 s, tot 0.24 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 9.000e+02, min 4.027e+02, max 1.397e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.693e-02, min 6.008e-03, max 4.785e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.112e-07s, min 6.870e-08s, max 9.537e-07s, tot 1.022e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.200e-02s, min 8.025e-03s, max 1.598e-02s, tot 2.400e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.561e+00 3.572e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.882e-01 x, min 2.882e-01 x, max 2.882e-01 x (1 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.36 s, min 0.35 s, max 0.38 s, tot 0.73 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.36 s, min 0.35 s, max 0.38 s, tot 0.73 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 5.706e+03, min 1.007e+02, max 1.131e+04 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.354e-03, min 3.280e-03, max 1.143e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 4.938e-07s, min 3.395e-08s, max 9.537e-07s, tot 9.876e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.143e-02s, min 2.927e-02s, max 3.360e-02s, tot 6.287e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.706e+00 1.036e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.124e+02 x, min 1.124e+02 x, max 1.124e+02 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type Z: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.203e-02 0.000e+00 9.537e-07 0.000e+00 1.280e-01 2.81e-01 2.29e+00 1 9.60e-05 -pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 5589.49 1.600e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 1.02e+01 1.32e+00 1 3.84e-04 +pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2827.62 4.909e-02 0.000e+00 3.395e-08 0.000e+00 4.282e-01 7.89e+00 2.29e+00 1 9.60e-05 +pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11310.48 4.253e-02 0.000e+00 3.395e-08 0.000e+00 3.868e-01 2.06e+01 1.32e+00 1 3.84e-04 #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 12274509.0 % faster, avg. sp. ratio 122746.090x, max sp. ratio 232882.179x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1115018.5/134253.5/2095783.4/2230036.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.8/ 9.0/ 10.6/ 19.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.8, min. 9.0, max. 10.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 134941964.6 % faster, avg. sp. ratio 1349420.646x, max sp. ratio 1446032.303x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12003827.2/11394339.9/12613314.6/24007654.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 8.9/ 8.7/ 9.1/ 17.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 8.9, min. 8.7, max. 9.1 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.813/ 0.231/ 7.394,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.470/ 0.281/ 10.189,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 10.721/ 6.480/ 14.963,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 28.512/ 7.894/ 20.618,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.807/ 1.323/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.14 s, min 0.13 s, max 0.14 s, tot 0.27 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.13 s, max 0.14 s, tot 0.27 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.845e+03, min 1.007e+02, max 5.589e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.599e-02, min 7.983e-03, max 2.400e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.112e-07s, min 6.870e-08s, max 9.537e-07s, tot 1.022e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.401e-02s, min 1.203e-02s, max 1.600e-02s, tot 2.802e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.357e+00 4.351e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 5.553e+01 x, min 5.553e+01 x, max 5.553e+01 x (1 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.41 s, min 0.39 s, max 0.43 s, tot 0.82 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.41 s, min 0.39 s, max 0.43 s, tot 0.82 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 7.069e+03, min 2.828e+03, max 1.131e+04 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.492e-03, min 1.955e-03, max 9.028e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.395e-08s, min 3.395e-08s, max 3.395e-08s, tot 6.790e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.581e-02s, min 4.253e-02s, max 4.909e-02s, tot 9.163e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.999e-01 2.078e+00 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds memory bandwidth --- is this a tiny matrix ? +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to nrhs=1: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 349.34 1.601e-02 0.000e+00 6.870e-08 0.000e+00 1.840e-01 2.15e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 349.34 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.443e-01 1.28e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.598e-02 0.000e+00 6.870e-08 0.000e+00 1.441e-01 2.15e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.203e-02 0.000e+00 9.537e-07 0.000e+00 1.280e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 706.91 1.325e-02 0.000e+00 3.395e-08 0.000e+00 1.312e-01 4.36e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 706.91 1.421e-02 0.000e+00 3.395e-08 0.000e+00 1.919e-01 2.59e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 100.66 2.927e-02 0.000e+00 9.537e-07 0.000e+00 3.830e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2827.62 4.909e-02 0.000e+00 3.395e-08 0.000e+00 4.282e-01 7.89e+00 2.29e+00 1 9.60e-05 #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 17776107.8 % faster, avg. sp. ratio 177762.078x, max sp. ratio 233055.700x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1752548.3/134253.5/2678226.6/7010193.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.0/ 9.0/ 11.5/ 40.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.0, min. 9.0, max. 11.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 57142821.0 % faster, avg. sp. ratio 571429.210x, max sp. ratio 1446032.303x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 5632673.5/401585.8/12613314.6/22530693.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.3/ 8.7/ 13.5/ 45.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.3, min. 8.7, max. 13.5 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.237/ 0.231/ 1.805,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.871/ 0.281/ 2.154,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.125/ 0.130/ 6.480,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 15.000/ 0.155/ 7.894,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.979/ 1.292/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.15 s, min 0.13 s, max 0.18 s, tot 0.60 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.15 s, min 0.13 s, max 0.18 s, tot 0.60 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.492e+02, min 1.007e+02, max 1.397e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.248e-03, min 1.499e-03, max 7.983e-03 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.899e-07s, min 6.870e-08s, max 9.537e-07s, tot 1.160e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.500e-02s, min 1.203e-02s, max 1.601e-02s, tot 6.001e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.561e+00 4.351e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.28 s, min 0.13 s, max 0.43 s, tot 1.13 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.28 s, min 0.13 s, max 0.43 s, tot 1.13 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.086e+03, min 1.007e+02, max 2.828e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.184e-03, min 1.688e-03, max 3.280e-03 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.639e-07s, min 3.395e-08s, max 9.537e-07s, tot 1.056e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.646e-02s, min 1.325e-02s, max 4.909e-02s, tot 1.058e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.078e+00 1.036e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 #pr: ======== Limiting to nrhs=4: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.597e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 5.30e+00 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.205e-01 2.85e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 8.025e-03 0.000e+00 9.537e-07 0.000e+00 1.000e-01 3.82e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 5589.49 1.600e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 1.02e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2827.62 7.946e-03 0.000e+00 3.395e-08 0.000e+00 1.422e+00 1.07e+01 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 100.66 1.937e-02 0.000e+00 9.537e-07 0.000e+00 2.429e-01 2.06e-01 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 11310.48 3.360e-02 0.000e+00 3.395e-08 0.000e+00 3.462e-01 1.07e+01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11310.48 4.253e-02 0.000e+00 3.395e-08 0.000e+00 3.868e-01 2.06e+01 1.32e+00 1 3.84e-04 #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 17663597.9 % faster, avg. sp. ratio 176636.979x, max sp. ratio 232882.179x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1512744.2/104861.8/2096411.6/6050976.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.5/ 7.5/ 12.5/ 38.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.5, min. 7.5, max. 12.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 62422226.4 % faster, avg. sp. ratio 624223.264x, max sp. ratio 1252808.989x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 15933431.9/254739.0/41888398.9/63733727.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 52.7/ 9.1/179.0/210.9 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 52.7, min. 9.1, max. 179.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.433/ 0.281/ 7.394,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.722/ 0.382/ 10.189,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.726/ 0.155/ 14.963,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 42.266/ 0.206/ 20.618,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.589/ 0.698/ 2.792) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.13 s, min 0.10 s, max 0.14 s, tot 0.51 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.13 s, min 0.10 s, max 0.14 s, tot 0.51 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.197e+03, min 4.027e+02, max 5.589e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.097e-02, min 6.004e-03, max 4.785e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.899e-07s, min 6.870e-08s, max 9.537e-07s, tot 1.160e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.400e-02s, min 8.025e-03s, max 1.600e-02s, tot 5.599e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.357e+00 3.572e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.595e+01 x, min 2.882e-01 x, max 5.553e+01 x (4 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.60 s, min 0.24 s, max 1.42 s, tot 2.40 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.60 s, min 0.24 s, max 1.42 s, tot 2.40 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.387e+03, min 1.007e+02, max 1.131e+04 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 9.373e-03, min 4.956e-03, max 1.208e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.639e-07s, min 3.395e-08s, max 9.537e-07s, tot 1.056e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.586e-02s, min 7.946e-03s, max 4.253e-02s, tot 1.035e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.999e-01 8.676e+01 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds memory bandwidth --- is this a tiny matrix ? +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.013e+01 x, min 1.424e-01 x, max 1.124e+02 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=N: #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 349.34 1.601e-02 0.000e+00 6.870e-08 0.000e+00 1.840e-01 2.15e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 349.34 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.443e-01 1.28e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.598e-02 0.000e+00 6.870e-08 0.000e+00 1.441e-01 2.15e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.203e-02 0.000e+00 9.537e-07 0.000e+00 1.280e-01 2.81e-01 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.597e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 5.30e+00 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.205e-01 2.85e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 8.025e-03 0.000e+00 9.537e-07 0.000e+00 1.000e-01 3.82e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 5589.49 1.600e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 1.02e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 706.91 1.325e-02 0.000e+00 3.395e-08 0.000e+00 1.312e-01 4.36e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 706.91 1.421e-02 0.000e+00 3.395e-08 0.000e+00 1.919e-01 2.59e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 100.66 2.927e-02 0.000e+00 9.537e-07 0.000e+00 3.830e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2827.62 4.909e-02 0.000e+00 3.395e-08 0.000e+00 4.282e-01 7.89e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2827.62 7.946e-03 0.000e+00 3.395e-08 0.000e+00 1.422e+00 1.07e+01 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 100.66 1.937e-02 0.000e+00 9.537e-07 0.000e+00 2.429e-01 2.06e-01 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 11310.48 3.360e-02 0.000e+00 3.395e-08 0.000e+00 3.462e-01 1.07e+01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11310.48 4.253e-02 0.000e+00 3.395e-08 0.000e+00 3.868e-01 2.06e+01 1.32e+00 1 3.84e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 8 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 17719852.9 % faster, avg. sp. ratio 177199.529x, max sp. ratio 233055.700x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1632646.2/104861.8/2678226.6/13061169.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.8/ 7.5/ 12.5/ 78.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.8, min. 7.5, max. 12.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 59782523.7 % faster, avg. sp. ratio 597826.237x, max sp. ratio 1446032.303x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10783052.7/254739.0/41888398.9/86264421.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 32.0/ 8.7/179.0/256.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 32.0, min. 8.7, max. 179.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.335/ 0.231/ 7.394,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.593/ 0.281/ 10.189,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.426/ 0.130/ 14.963,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 57.267/ 0.155/ 20.618,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.284/ 0.698/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 8 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /8 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.14 s, min 0.10 s, max 0.18 s, tot 1.11 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.10 s, max 0.18 s, tot 1.11 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.373e+03, min 1.007e+02, max 5.589e+03 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.261e-02, min 1.499e-03, max 4.785e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 2.899e-07s, min 6.870e-08s, max 9.537e-07s, tot 2.320e-06s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.450e-02s, min 8.025e-03s, max 1.601e-02s, tot 1.160e-01s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.357e+00 4.351e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.595e+01 x, min 2.882e-01 x, max 5.553e+01 x (4 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.44 s, min 0.13 s, max 1.42 s, tot 3.53 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.44 s, min 0.13 s, max 1.42 s, tot 3.53 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.736e+03, min 1.007e+02, max 1.131e+04 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.779e-03, min 1.688e-03, max 1.208e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 2.639e-07s, min 3.395e-08s, max 9.537e-07s, tot 2.111e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.616e-02s, min 7.946e-03s, max 4.909e-02s, tot 2.093e-01s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.999e-01 1.036e+02 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds memory bandwidth --- is this a tiny matrix ? +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.013e+01 x, min 1.424e-01 x, max 1.124e+02 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to both transA=N and nrhs=1: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 349.34 1.601e-02 0.000e+00 6.870e-08 0.000e+00 1.840e-01 2.15e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 349.34 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.443e-01 1.28e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.598e-02 0.000e+00 6.870e-08 0.000e+00 1.441e-01 2.15e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.203e-02 0.000e+00 9.537e-07 0.000e+00 1.280e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 706.91 1.325e-02 0.000e+00 3.395e-08 0.000e+00 1.312e-01 4.36e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 706.91 1.421e-02 0.000e+00 3.395e-08 0.000e+00 1.919e-01 2.59e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 100.66 2.927e-02 0.000e+00 9.537e-07 0.000e+00 3.830e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2827.62 4.909e-02 0.000e+00 3.395e-08 0.000e+00 4.282e-01 7.89e+00 2.29e+00 1 9.60e-05 #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 17776107.8 % faster, avg. sp. ratio 177762.078x, max sp. ratio 233055.700x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1752548.3/134253.5/2678226.6/7010193.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.0/ 9.0/ 11.5/ 40.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.0, min. 9.0, max. 11.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 57142821.0 % faster, avg. sp. ratio 571429.210x, max sp. ratio 1446032.303x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 5632673.5/401585.8/12613314.6/22530693.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.3/ 8.7/ 13.5/ 45.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.3, min. 8.7, max. 13.5 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.237/ 0.231/ 1.805,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.871/ 0.281/ 2.154,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.125/ 0.130/ 6.480,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 15.000/ 0.155/ 7.894,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.979/ 1.292/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.15 s, min 0.13 s, max 0.18 s, tot 0.60 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.15 s, min 0.13 s, max 0.18 s, tot 0.60 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.492e+02, min 1.007e+02, max 1.397e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.248e-03, min 1.499e-03, max 7.983e-03 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.899e-07s, min 6.870e-08s, max 9.537e-07s, tot 1.160e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.500e-02s, min 1.203e-02s, max 1.601e-02s, tot 6.001e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.561e+00 4.351e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.28 s, min 0.13 s, max 0.43 s, tot 1.13 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.28 s, min 0.13 s, max 0.43 s, tot 1.13 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.086e+03, min 1.007e+02, max 2.828e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.184e-03, min 1.688e-03, max 3.280e-03 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.639e-07s, min 3.395e-08s, max 9.537e-07s, tot 1.056e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.646e-02s, min 1.325e-02s, max 4.909e-02s, tot 1.058e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.078e+00 1.036e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 #pr: ======== Limiting to both transA=N and nrhs=4: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.597e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 5.30e+00 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.205e-01 2.85e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 8.025e-03 0.000e+00 9.537e-07 0.000e+00 1.000e-01 3.82e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 5589.49 1.600e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 1.02e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2827.62 7.946e-03 0.000e+00 3.395e-08 0.000e+00 1.422e+00 1.07e+01 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 100.66 1.937e-02 0.000e+00 9.537e-07 0.000e+00 2.429e-01 2.06e-01 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 11310.48 3.360e-02 0.000e+00 3.395e-08 0.000e+00 3.462e-01 1.07e+01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11310.48 4.253e-02 0.000e+00 3.395e-08 0.000e+00 3.868e-01 2.06e+01 1.32e+00 1 3.84e-04 #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 17663597.9 % faster, avg. sp. ratio 176636.979x, max sp. ratio 232882.179x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1512744.2/104861.8/2096411.6/6050976.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.5/ 7.5/ 12.5/ 38.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.5, min. 7.5, max. 12.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 62422226.4 % faster, avg. sp. ratio 624223.264x, max sp. ratio 1252808.989x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 15933431.9/254739.0/41888398.9/63733727.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 52.7/ 9.1/179.0/210.9 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 52.7, min. 9.1, max. 179.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.433/ 0.281/ 7.394,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.722/ 0.382/ 10.189,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.726/ 0.155/ 14.963,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 42.266/ 0.206/ 20.618,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.589/ 0.698/ 2.792) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.13 s, min 0.10 s, max 0.14 s, tot 0.51 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.13 s, min 0.10 s, max 0.14 s, tot 0.51 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.197e+03, min 4.027e+02, max 5.589e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.097e-02, min 6.004e-03, max 4.785e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.899e-07s, min 6.870e-08s, max 9.537e-07s, tot 1.160e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.400e-02s, min 8.025e-03s, max 1.600e-02s, tot 5.599e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.357e+00 3.572e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.595e+01 x, min 2.882e-01 x, max 5.553e+01 x (4 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.60 s, min 0.24 s, max 1.42 s, tot 2.40 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.60 s, min 0.24 s, max 1.42 s, tot 2.40 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.387e+03, min 1.007e+02, max 1.131e+04 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 9.373e-03, min 4.956e-03, max 1.208e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.639e-07s, min 3.395e-08s, max 9.537e-07s, tot 1.056e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.586e-02s, min 7.946e-03s, max 4.253e-02s, tot 1.035e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.999e-01 8.676e+01 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds memory bandwidth --- is this a tiny matrix ? +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.013e+01 x, min 1.424e-01 x, max 1.124e+02 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 8) matched the dump criteria -- skipping dump round. #pr: ======== Limiting to both transA=T and nrhs=1: @@ -5062,62 +5127,63 @@ #pr: ======== All results (not limiting) #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 349.34 1.601e-02 0.000e+00 6.870e-08 0.000e+00 1.840e-01 2.15e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 349.34 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.443e-01 1.28e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.598e-02 0.000e+00 6.870e-08 0.000e+00 1.441e-01 2.15e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.203e-02 0.000e+00 9.537e-07 0.000e+00 1.280e-01 2.81e-01 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.597e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 5.30e+00 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 1397.37 1.599e-02 0.000e+00 6.870e-08 0.000e+00 1.205e-01 2.85e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 8.025e-03 0.000e+00 9.537e-07 0.000e+00 1.000e-01 3.82e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 5589.49 1.600e-02 0.000e+00 6.870e-08 0.000e+00 1.440e-01 1.02e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 706.91 1.325e-02 0.000e+00 3.395e-08 0.000e+00 1.312e-01 4.36e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 706.91 1.421e-02 0.000e+00 3.395e-08 0.000e+00 1.919e-01 2.59e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 100.66 2.927e-02 0.000e+00 9.537e-07 0.000e+00 3.830e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2827.62 4.909e-02 0.000e+00 3.395e-08 0.000e+00 4.282e-01 7.89e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2827.62 7.946e-03 0.000e+00 3.395e-08 0.000e+00 1.422e+00 1.07e+01 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 100.66 1.937e-02 0.000e+00 9.537e-07 0.000e+00 2.429e-01 2.06e-01 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 11310.48 3.360e-02 0.000e+00 3.395e-08 0.000e+00 3.462e-01 1.07e+01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11310.48 4.253e-02 0.000e+00 3.395e-08 0.000e+00 3.868e-01 2.06e+01 1.32e+00 1 3.84e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 8 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 17719852.9 % faster, avg. sp. ratio 177199.529x, max sp. ratio 233055.700x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1632646.2/104861.8/2678226.6/13061169.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.8/ 7.5/ 12.5/ 78.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.8, min. 7.5, max. 12.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 59782523.7 % faster, avg. sp. ratio 597826.237x, max sp. ratio 1446032.303x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10783052.7/254739.0/41888398.9/86264421.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 32.0/ 8.7/179.0/256.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 32.0, min. 8.7, max. 179.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.335/ 0.231/ 7.394,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.593/ 0.281/ 10.189,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.426/ 0.130/ 14.963,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 57.267/ 0.155/ 20.618,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.284/ 0.698/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 8 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /8 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.14 s, min 0.10 s, max 0.18 s, tot 1.11 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.10 s, max 0.18 s, tot 1.11 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.373e+03, min 1.007e+02, max 5.589e+03 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.261e-02, min 1.499e-03, max 4.785e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 2.899e-07s, min 6.870e-08s, max 9.537e-07s, tot 2.320e-06s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.450e-02s, min 8.025e-03s, max 1.601e-02s, tot 1.160e-01s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.357e+00 4.351e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.633e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.595e+01 x, min 2.882e-01 x, max 5.553e+01 x (4 samples, the non-min-nrhs ones) -#pr: Record collection took 7.35 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.44 s, min 0.13 s, max 1.42 s, tot 3.53 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.44 s, min 0.13 s, max 1.42 s, tot 3.53 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.736e+03, min 1.007e+02, max 1.131e+04 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.779e-03, min 1.688e-03, max 1.208e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 2.639e-07s, min 3.395e-08s, max 9.537e-07s, tot 2.111e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.616e-02s, min 7.946e-03s, max 4.909e-02s, tot 2.093e-01s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.999e-01 1.036e+02 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds memory bandwidth --- is this a tiny matrix ? +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.625e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.013e+01 x, min 1.424e-01 x, max 1.124e+02 x (4 samples, the non-min-nrhs ones) +#pr: Record collection took 17.71 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 5261 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 5314 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1740605498_gcc-14.2.rpr -# Removing the temporary record file rsbench_pr__1740605498_gcc-14.2.rpr.tmp. -# terminating run at 1740605511 (after 13.9s of w.c.t.) -srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/bash ./scripts/doc-tests.sh +#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1775018880_gcc-14.2.rpr +# Removing the temporary record file rsbench_pr__1775018880_gcc-14.2.rpr.tmp. +# terminating run at 1775018909 (after 29.5s of w.c.t.) +srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/sh ./scripts/doc-tests.sh + set -o pipefail + test x/build/reproducible-path/librsb-1.3.0.2+dfsg = x -+ grep '^.\{71,\}' + cat /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/autotune.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/backsolve.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/hello-spblas.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/hello.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/io-spblas.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/power.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/snippets.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/transpose.c ++ grep '^.\{71,\}' + true -+ cat /build/reproducible-path/librsb-1.3.0.2+dfsg/README + grep '^[^ ].\{80,\}' ++ cat /build/reproducible-path/librsb-1.3.0.2+dfsg/README + true -++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h ++ wc -l -+ test 63 -ge 61 ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h ++ test 63 -ge 61 ++ wc -c +++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h + test 2014 -ge 1966 ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h ++ wc -l @@ -5158,7 +5224,7 @@ type char codes:D S C Z gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' if test /build/reproducible-path/librsb-1.3.0.2+dfsg != /build/reproducible-path/librsb-1.3.0.2+dfsg ; then cp /build/reproducible-path/librsb-1.3.0.2+dfsg/pd.mtx /build/reproducible-path/librsb-1.3.0.2+dfsg/vf.mtx /build/reproducible-path/librsb-1.3.0.2+dfsg/examples ; fi -( PATH="/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games" /bin/bash /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/bench.sh; ) +( PATH="/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path" /bin/sh /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/bench.sh; ) + which rsbench /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench + BRF=test.rpr @@ -5168,15 +5234,15 @@ Will invoke autotuning for ~10.000000 s x 1 rounds, specifying verbosity=0 and threads=0. (>0 means no structure tuning; 0 means only structure tuning, <0 means tuning of both with (negated) thread count suggestion). # Requested no transposition. # performance record file set to: test.rpr -# beginning run at 1740605512 +# beginning run at 1775018910 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench --lower 100 --as-symmetric --types : -n 1 --notranspose --compare-competitors --verbose --verbose --write-performance-record=test.rpr # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -# average timer granularity: 5.84e-08 s +# average timer granularity: 3.65e-08 s # Will write a final performance record to file test.rpr and periodic checkpoints to test.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -5215,15 +5281,15 @@ # env: SLURM_NTASKS is not set # env: SLURM_STEP_TASKS_PER_NODE is not set # env: SLURM_TASKS_PER_NODE is not set -# detected hostname: ionos1-amd64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 2 (each --verbose occurrence counts +1) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5235,40 +5301,40 @@ # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 5.353s +# Memory benchmark took 8.979s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 4 samples (1120 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). -# Cache block size total 524288 bytes, per-thread 26214 bytes -# so far, program took 5.356s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . +# Cache block size total 4194304 bytes, per-thread 99864 bytes +# so far, program took 8.980s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.403e-01 s (100.00 %) - analyzed arrays in 4.045e-02 s (28.82 %) - cleaned-up arrays in 1.717e-05 s (0.01 %) - deduplicated arrays in 1.287e-05 s (0.01 %) + converted COO to RSB in 3.452e-01 s (100.00 %) + analyzed arrays in 9.706e-02 s (28.12 %) + cleaned-up arrays in 1.192e-05 s (0.00 %) + deduplicated arrays in 1.216e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.783e-02 s (48.33 %) - memory allocations took 2.789e-05 s (0.02 %) - leafs setup took 1.287e-05 s (0.01 %) - halfword conversion took 3.200e-02 s (22.80 %) -Built (100 x 100)[0x565522ee28c0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' -# Constructed matrix (took 0.141s): (100 x 100)[0x565522ee28c0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + shuffled partitions in 1.554e-01 s (45.01 %) + memory allocations took 2.575e-05 s (0.01 %) + leafs setup took 1.311e-05 s (0.00 %) + halfword conversion took 9.272e-02 s (26.86 %) +Built (100 x 100)[0x5632942cd8f0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' +# Constructed matrix (took 0.345s): (100 x 100)[0x5632942cd8f0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 100 x 100, type D, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz. Parameters: verbosity:2 mintimes:3 maxtimes:10 mindt:0 maxdt:3 Saved plot to test-tuning-lower-100x100-5050nz--D-N-1--base.eps # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5279,11 +5345,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5294,11 +5360,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5308,16 +5374,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.05292s; avg 0.01764s ( +/- 9.65/ 13.44 %); best 0.01594s; worst 0.02001s; std dev. 0.001729 (taking best). -Reference operation time is 0.015939 s (1.267 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type D, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.01594 Mflops: 1.267) -Merge (3 -> 1 leaves) took w.c.t. of 0.0001261s, ~9.298e-05s of computing time (of which 4.601e-05s sorting, 1.001e-05s analysis) +3 iterations (1 th.) took 0.1661s; avg 0.05538s ( +/- 24.51/ 34.85 %); best 0.04181s; worst 0.07468s; std dev. 0.01402 (taking best). +Reference operation time is 0.0418069 s (0.4832 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type D, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.04181 Mflops: 0.483) +Merge (3 -> 1 leaves) took w.c.t. of 9.68e-05s, ~6.509e-05s of computing time (of which 2.503e-05s sorting, 1.097e-05s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5328,11 +5394,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5342,14 +5408,14 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 3.791e-05s; avg 1.264e-05s ( +/- 20.75/ 41.51 %); best 1.001e-05s; worst 1.788e-05s; std dev. 3.709e-06 (taking best). -Reference operation time is 1.00136e-05 s (2017 Mflops) with 1 threads. +3 iterations (1 th.) took 4.506e-05s; avg 1.502e-05s ( +/- 20.63/ 39.68 %); best 1.192e-05s; worst 2.098e-05s; std dev. 4.216e-06 (taking best). +Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5359,25 +5425,25 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -After merge step 1: tpop: 1.001e-05 s ~Mflops: 2017.260 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1591.738x: 0.01594s -> 1.001e-05s, so taking this instance. +After merge step 1: tpop: 1.192e-05 s ~Mflops: 1694.499 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 3507.020x: 0.04181s -> 1.192e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1872s (of which 0.000133s partitioning, 0.1111s I/O); computing times: 9.298e-05s in par. loops, 4.601e-05s sorting, 1.001e-05s analyzing) -Total merge + benchmarking process took 0.1872s, equivalent to 18695.4/11.7 new/old ops (0.1229s for 2 clones -- as 12269.5/7.7 ops, or 6134.8/3.9 ops per clone), SPEEDUP of 1591.738x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1591.738x (0.01594s -> 1.001e-05s), will amortize in 11.8 ops by saving 0.01593s per op. -In 1 tuning rounds (tot. 0.29s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 159073.8% (1592x) (from 1.267 to 2017 Mflops). Employed 0.1s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.5115s (of which 0.000104s partitioning, 0.3275s I/O); computing times: 6.509e-05s in par. loops, 2.503e-05s sorting, 1.097e-05s analyzing) +Total merge + benchmarking process took 0.5115s, equivalent to 42908.7/12.2 new/old ops (0.3192s for 2 clones -- as 26780.0/7.6 ops, or 13390.0/3.8 ops per clone), SPEEDUP of 3507.020x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 3507.020x (0.04181s -> 1.192e-05s), will amortize in 12.2 ops by saving 0.0418s per op. +In 1 tuning rounds (tot. 0.81s, 0.32s for constructor, 2 clones) obtained a SPEEDUP of 350602.0% (3507x) (from 0.4832 to 1694 Mflops). Employed 0.27s for I/O of matrix plots. #pr: updating sample at index 1 (0^th of 4), 0^th touch for (0,0,0,0,0,0,0). -First run of RSB Autotuner took 0.388179 s (1.594e-02 s -> 1.001e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 1.08374 s (4.181e-02 s -> 1.192e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type D, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5388,11 +5454,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5403,13 +5469,13 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success Started tuning inner round: will search for an optimal matrix instance. -Starting with requested 0 threads ; current default 1 ; at most 20. +Starting with requested 0 threads ; current default 1 ; at most 42. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5420,11 +5486,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5434,27 +5500,27 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 9.108e-05s; avg 3.036e-05s ( +/- 70.16/137.17 %); best 9.06e-06s; worst 7.2e-05s; std dev. 2.945e-05 (taking best). -Reference operation time is 9.05991e-06 s (2230 Mflops) with 1 threads. +3 iterations (1 th.) took 4.601e-05s; avg 1.534e-05s ( +/- 34.72/ 63.21 %); best 1.001e-05s; worst 2.503e-05s; std dev. 6.867e-06 (taking best). +Reference operation time is 1.00136e-05 s (2017 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 8.773e-02 s (100.00 %) - analyzed arrays in 4.334e-02 s (49.40 %) - cleaned-up arrays in 1.407e-05 s (0.02 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 1.889e-01 s (100.00 %) + analyzed arrays in 7.135e-02 s (37.77 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.433e-02 s (50.53 %) - memory allocations took 6.914e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.502e-05 s (0.02 %) -Built (100 x 100)[0x565522eee310]{D} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' -Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 20). -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 1.175e-01 s (62.21 %) + memory allocations took 5.722e-06 s (0.00 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 1.407e-05 s (0.01 %) +Built (100 x 100)[0x5632942dc640]{D} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' +Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 42). +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5465,12 +5531,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5481,22 +5547,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.268e-01 s (100.00 %) - analyzed arrays in 3.082e-02 s (24.30 %) - cleaned-up arrays in 1.311e-05 s (0.01 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 3.169e-01 s (100.00 %) + analyzed arrays in 8.635e-02 s (27.25 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.256e-02 s (41.44 %) - memory allocations took 8.106e-06 s (0.01 %) - leafs setup took 5.960e-06 s (0.00 %) - halfword conversion took 4.341e-02 s (34.23 %) -Built (100 x 100)[0x565522ee2c10]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 1.286e-01 s (40.60 %) + memory allocations took 7.153e-06 s (0.00 %) + leafs setup took 6.914e-06 s (0.00 %) + halfword conversion took 1.018e-01 s (32.14 %) +Built (100 x 100)[0x5632942cdc20]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5507,11 +5573,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5522,11 +5588,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5536,16 +5602,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0486s; avg 0.0162s ( +/- 3.67/ 5.62 %); best 0.01561s; worst 0.01711s; std dev. 0.0006543 (taking best). -Reference operation time is 0.0156069 s (1.294 Mflops) with 1 threads. -Challenging best inner round reference (9.05991e-06 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0156069 s/0 threads (speedup 0.000580507 x), same?n. +3 iterations (1 th.) took 0.1559s; avg 0.05195s ( +/- 31.69/ 34.37 %); best 0.03549s; worst 0.06981s; std dev. 0.01405 (taking best). +Reference operation time is 0.03549 s (0.5692 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.03549 s/0 threads (speedup 0.000282152 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5556,12 +5622,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5572,22 +5638,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.588e-01 s (100.00 %) - analyzed arrays in 5.871e-02 s (36.96 %) - cleaned-up arrays in 1.192e-05 s (0.01 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 2.475e-01 s (100.00 %) + analyzed arrays in 7.265e-02 s (29.35 %) + cleaned-up arrays in 1.001e-05 s (0.00 %) + deduplicated arrays in 1.192e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.236e-02 s (20.37 %) - memory allocations took 1.907e-05 s (0.01 %) - leafs setup took 8.821e-06 s (0.01 %) - halfword conversion took 6.772e-02 s (42.63 %) -Built (100 x 100)[0x565522ee3720]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 12, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 8.928e-02 s (36.07 %) + memory allocations took 7.153e-06 s (0.00 %) + leafs setup took 1.001e-05 s (0.00 %) + halfword conversion took 8.551e-02 s (34.55 %) +Built (100 x 100)[0x5632942ce610]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 10, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5598,11 +5664,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5613,11 +5679,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5627,16 +5693,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.05069s; avg 0.0169s ( +/- 11.27/ 15.99 %); best 0.01499s; worst 0.0196s; std dev. 0.001963 (taking best). -Reference operation time is 0.0149939 s (1.347 Mflops) with 1 threads. -Challenging best inner round reference (9.05991e-06 s/1 threads) with: subdivision 0.5, 12 leaves, 2.217 bytes/nz, 0.0149939 s/0 threads (speedup 0.000604239 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 17 subms, 12 lsubms, 2.2170 bpnz +3 iterations (1 th.) took 0.1241s; avg 0.04137s ( +/- 22.37/ 12.60 %); best 0.03212s; worst 0.04659s; std dev. 0.006562 (taking best). +Reference operation time is 0.0321188 s (0.6289 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.0321188 s/0 threads (speedup 0.000311767 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 14 subms, 10 lsubms, 2.2059 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5647,12 +5713,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5663,22 +5729,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.292e-01 s (100.00 %) - analyzed arrays in 5.165e-02 s (39.96 %) - cleaned-up arrays in 1.812e-05 s (0.01 %) - deduplicated arrays in 1.693e-05 s (0.01 %) + converted COO to RSB in 2.424e-01 s (100.00 %) + analyzed arrays in 6.560e-02 s (27.06 %) + cleaned-up arrays in 1.597e-05 s (0.01 %) + deduplicated arrays in 1.001e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.803e-02 s (37.16 %) - memory allocations took 2.098e-05 s (0.02 %) - leafs setup took 1.502e-05 s (0.01 %) - halfword conversion took 2.949e-02 s (22.82 %) -Built (100 x 100)[0x565522eee430]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 27, symflags:'LS' + shuffled partitions in 8.809e-02 s (36.33 %) + memory allocations took 1.597e-05 s (0.01 %) + leafs setup took 1.001e-05 s (0.00 %) + halfword conversion took 8.869e-02 s (36.59 %) +Built (100 x 100)[0x5632942dc760]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5689,11 +5755,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5704,11 +5770,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5718,16 +5784,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.05827s; avg 0.01942s ( +/- 18.02/ 17.11 %); best 0.01592s; worst 0.02275s; std dev. 0.002788 (taking best). -Reference operation time is 0.015923 s (1.269 Mflops) with 1 threads. -Challenging best inner round reference (9.05991e-06 s/1 threads) with: subdivision 1, 27 leaves, 2.328 bytes/nz, 0.015923 s/0 threads (speedup 0.000568982 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 37 subms, 27 lsubms, 2.3279 bpnz +3 iterations (1 th.) took 0.1289s; avg 0.04297s ( +/- 19.14/ 21.23 %); best 0.03475s; worst 0.05209s; std dev. 0.007109 (taking best). +Reference operation time is 0.0347459 s (0.5814 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.0347459 s/0 threads (speedup 0.000288194 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 30 subms, 22 lsubms, 2.2947 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5738,12 +5804,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5754,22 +5820,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.399e-01 s (100.00 %) - analyzed arrays in 5.580e-02 s (39.90 %) - cleaned-up arrays in 1.812e-05 s (0.01 %) - deduplicated arrays in 1.502e-05 s (0.01 %) + converted COO to RSB in 2.845e-01 s (100.00 %) + analyzed arrays in 1.058e-01 s (37.18 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.402e-02 s (31.48 %) - memory allocations took 2.193e-05 s (0.02 %) - leafs setup took 1.693e-05 s (0.01 %) - halfword conversion took 3.996e-02 s (28.57 %) -Built (100 x 100)[0x565522f150a0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 58, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 8.552e-02 s (30.06 %) + memory allocations took 1.502e-05 s (0.01 %) + leafs setup took 1.192e-05 s (0.00 %) + halfword conversion took 9.313e-02 s (32.74 %) +Built (100 x 100)[0x563294303400]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 48, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5780,11 +5846,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5795,11 +5861,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5809,16 +5875,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.05576s; avg 0.01859s ( +/- 35.64/ 33.61 %); best 0.01196s; worst 0.02483s; std dev. 0.005261 (taking best). -Reference operation time is 0.0119612 s (1.689 Mflops) with 1 threads. -Challenging best inner round reference (9.05991e-06 s/1 threads) with: subdivision 2, 58 leaves, 2.472 bytes/nz, 0.0119612 s/0 threads (speedup 0.00075744 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 79 subms, 58 lsubms, 2.4721 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +3 iterations (1 th.) took 0.1287s; avg 0.0429s ( +/- 23.93/ 22.52 %); best 0.03263s; worst 0.05256s; std dev. 0.008146 (taking best). +Reference operation time is 0.0326302 s (0.6191 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 2, 48 leaves, 2.434 bytes/nz, 0.0326302 s/0 threads (speedup 0.000306881 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 66 subms, 48 lsubms, 2.4341 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5829,12 +5895,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5845,22 +5911,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.158e-01 s (100.00 %) - analyzed arrays in 5.616e-02 s (48.48 %) - cleaned-up arrays in 1.597e-05 s (0.01 %) - deduplicated arrays in 1.311e-05 s (0.01 %) + converted COO to RSB in 2.748e-01 s (100.00 %) + analyzed arrays in 1.026e-01 s (37.33 %) + cleaned-up arrays in 5.960e-06 s (0.00 %) + deduplicated arrays in 6.914e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.160e-02 s (27.28 %) - memory allocations took 2.599e-05 s (0.02 %) - leafs setup took 2.217e-05 s (0.02 %) - halfword conversion took 2.799e-02 s (24.16 %) -Built (100 x 100)[0x565522f150a0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 120, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 9.177e-02 s (33.40 %) + memory allocations took 1.526e-05 s (0.01 %) + leafs setup took 1.693e-05 s (0.01 %) + halfword conversion took 8.038e-02 s (29.25 %) +Built (100 x 100)[0x563294303400]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 102, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5871,11 +5937,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5886,11 +5952,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5900,17 +5966,17 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.05541s; avg 0.01847s ( +/- 13.05/ 8.28 %); best 0.01606s; worst 0.02s; std dev. 0.001724 (taking best). -Reference operation time is 0.0160608 s (1.258 Mflops) with 1 threads. -Challenging best inner round reference (9.05991e-06 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.0160608 s/0 threads (speedup 0.0005641 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 162 subms, 120 lsubms, 2.7255 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 2229.6 Mflops. +3 iterations (1 th.) took 0.142s; avg 0.04734s ( +/- 17.87/ 18.17 %); best 0.03888s; worst 0.05594s; std dev. 0.006966 (taking best). +Reference operation time is 0.0388758 s (0.5196 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 4, 102 leaves, 2.654 bytes/nz, 0.0388758 s/0 threads (speedup 0.000257579 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 138 subms, 102 lsubms, 2.6543 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 2017.26 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5920,23 +5986,23 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 1.03164 s (eq. to 1e+05/ 1e+05 old/new op.times), gained local/global speedup 1 x (9.05991e-06 : 9.05991e-06) / 1 x (9.05991e-06 : 9.05991e-06). This is not amortizable ! +Last tuner inner round (1 of 1) took 2.23737 s (eq. to 2e+05/ 2e+05 old/new op.times), gained local/global speedup 1 x (1.00136e-05 : 1.00136e-05) / 1 x (1.00136e-05 : 1.00136e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 1s, 0.76s for constructor, 0 clones) obtained NO speedup (best stays 2230 Mflops). -Second run of RSB Autotuner took 1.03183 s and estimated a speedup of 1.000000 x (9.060e-06 s -> 9.060e-06 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 2.2s, 1.6s for constructor, 0 clones) obtained NO speedup (best stays 2017 Mflops). +Second run of RSB Autotuner took 2.23744 s and estimated a speedup of 1.000000 x (1.001e-05 s -> 1.001e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:100 #norm:10 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.040446 0.067829 0.108275 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.108275 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.040446 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.067829 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.097064 0.155387 0.252451 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.252451 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.097064 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.155387 %:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000000 %:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.108275 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.252451 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 @@ -5951,45 +6017,45 @@ %:SM_MINMAXAVGNNZ:lower-100x100-5050nz S N 1 100 100 5050 5050 5050 5050 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[1] -%operation:lower-100x100-5050nz 0.140348 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.345234 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0404458 0 0.0678291 -# so far, program took 7.029s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.420s/0.000s . +%constructor:lower-100x100-5050nz 0 0.097064 0 0.155387 +# so far, program took 12.944s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.321s/0.000s . getrusage() stats: -ru_maxrss: 11 (maximum resident set size -- MB) -ru_stime : 0.07926s (system CPU time used) -ru_utime : 21.99s (user CPU time used) +ru_maxrss: 20 (maximum resident set size -- MB) +ru_stime : 0.2665s (system CPU time used) +ru_utime : 15.49s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). -# Cache block size total 524288 bytes, per-thread 524288 bytes -# so far, program took 7.029s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.420s/0.000s . +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# so far, program took 12.945s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.321s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.353e-01 s (100.00 %) - analyzed arrays in 2.730e-02 s (20.18 %) - cleaned-up arrays in 1.621e-05 s (0.01 %) - deduplicated arrays in 1.287e-05 s (0.01 %) + converted COO to RSB in 2.678e+00 s (100.00 %) + analyzed arrays in 6.351e-02 s (2.37 %) + cleaned-up arrays in 1.001e-05 s (0.00 %) + deduplicated arrays in 1.287e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.592e-02 s (56.12 %) - memory allocations took 9.060e-06 s (0.01 %) - leafs setup took 6.914e-06 s (0.01 %) - halfword conversion took 3.201e-02 s (23.66 %) -Built (100 x 100)[0x565522eee430]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' -# Constructed matrix (took 0.135s): (100 x 100)[0x565522eee430]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + shuffled partitions in 2.562e+00 s (95.65 %) + memory allocations took 9.060e-06 s (0.00 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 5.289e-02 s (1.97 %) +Built (100 x 100)[0x5632942dc760]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' +# Constructed matrix (took 2.678s): (100 x 100)[0x5632942dc760]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 100 x 100, type S, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz. Parameters: verbosity:2 mintimes:3 maxtimes:10 mindt:0 maxdt:3 Saved plot to test-tuning-lower-100x100-5050nz--S-N-1--base.eps # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6000,11 +6066,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6015,11 +6081,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6029,16 +6095,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.04396s; avg 0.01465s ( +/- 45.32/ 36.18 %); best 0.008012s; worst 0.01995s; std dev. 0.004966 (taking best). -Reference operation time is 0.00801182 s (2.521 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type S, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.008012 Mflops: 2.521) -Merge (3 -> 1 leaves) took w.c.t. of 9.99e-05s, ~8.488e-05s of computing time (of which 3.195e-05s sorting, 4.053e-06s analysis) +3 iterations (1 th.) took 0.1502s; avg 0.05006s ( +/- 3.41/ 3.76 %); best 0.04835s; worst 0.05194s; std dev. 0.001471 (taking best). +Reference operation time is 0.0483479 s (0.4178 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type S, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.04835 Mflops: 0.418) +Merge (3 -> 1 leaves) took w.c.t. of 8.798e-05s, ~6.7e-05s of computing time (of which 3.099e-05s sorting, 5.96e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6049,11 +6115,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6063,14 +6129,14 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 4.101e-05s; avg 1.367e-05s ( +/- 5.81/ 2.91 %); best 1.287e-05s; worst 1.407e-05s; std dev. 5.62e-07 (taking best). -Reference operation time is 1.28746e-05 s (1569 Mflops) with 1 threads. +3 iterations (1 th.) took 4.005e-05s; avg 1.335e-05s ( +/- 25.00/ 42.86 %); best 1.001e-05s; worst 1.907e-05s; std dev. 4.065e-06 (taking best). +Reference operation time is 1.00136e-05 s (2017 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6080,25 +6146,25 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -After merge step 1: tpop: 1.287e-05 s ~Mflops: 1568.980 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 622.296x: 0.008012s -> 1.287e-05s, so taking this instance. +After merge step 1: tpop: 1.001e-05 s ~Mflops: 2017.260 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 4828.238x: 0.04835s -> 1.001e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.5007s (of which 0.0001049s partitioning, 0.4521s I/O); computing times: 8.488e-05s in par. loops, 3.195e-05s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.5007s, equivalent to 38889.9/62.5 new/old ops (0.1033s for 2 clones -- as 8020.4/12.9 ops, or 4010.2/6.4 ops per clone), SPEEDUP of 622.296x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 622.296x (0.008012s -> 1.287e-05s), will amortize in 62.6 ops by saving 0.007999s per op. -In 1 tuning rounds (tot. 0.6s, 0.1s for constructor, 2 clones) obtained a SPEEDUP of 62129.6% (622.3x) (from 2.521 to 1569 Mflops). Employed 0.36s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.4251s (of which 9.203e-05s partitioning, 0.2674s I/O); computing times: 6.7e-05s in par. loops, 3.099e-05s sorting, 5.96e-06s analyzing) +Total merge + benchmarking process took 0.4251s, equivalent to 42449.3/8.8 new/old ops (0.2541s for 2 clones -- as 25378.9/5.3 ops, or 12689.5/2.6 ops per clone), SPEEDUP of 4828.238x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 4828.238x (0.04835s -> 1.001e-05s), will amortize in 8.8 ops by saving 0.04834s per op. +In 1 tuning rounds (tot. 0.67s, 0.25s for constructor, 2 clones) obtained a SPEEDUP of 482723.8% (4828x) (from 0.4178 to 2017 Mflops). Employed 0.2s for I/O of matrix plots. #pr: updating sample at index 2 (1^th of 4), 0^th touch for (0,0,0,0,0,1,0). -First run of RSB Autotuner took 0.956701 s (8.012e-03 s -> 1.287e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.868755 s (4.835e-02 s -> 1.001e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type S, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6109,11 +6175,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6124,13 +6190,13 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success Started tuning inner round: will search for an optimal matrix instance. -Starting with requested 0 threads ; current default 1 ; at most 20. +Starting with requested 0 threads ; current default 1 ; at most 42. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6141,11 +6207,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6155,27 +6221,27 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 6.104e-05s; avg 2.035e-05s ( +/- 56.64/107.42 %); best 8.821e-06s; worst 4.22e-05s; std dev. 1.546e-05 (taking best). -Reference operation time is 8.82149e-06 s (2290 Mflops) with 1 threads. +3 iterations (1 th.) took 4.506e-05s; avg 1.502e-05s ( +/- 20.63/ 39.68 %); best 1.192e-05s; worst 2.098e-05s; std dev. 4.216e-06 (taking best). +Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 9.086e-02 s (100.00 %) - analyzed arrays in 3.048e-02 s (33.55 %) - cleaned-up arrays in 1.502e-05 s (0.02 %) - deduplicated arrays in 1.287e-05 s (0.01 %) + converted COO to RSB in 1.251e-01 s (100.00 %) + analyzed arrays in 5.703e-02 s (45.58 %) + cleaned-up arrays in 1.216e-05 s (0.01 %) + deduplicated arrays in 1.478e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.033e-02 s (66.40 %) - memory allocations took 8.106e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.00 %) - halfword conversion took 6.914e-06 s (0.01 %) -Built (100 x 100)[0x565522eee310]{S} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' -Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 20). -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 6.369e-02 s (50.90 %) + memory allocations took 4.352e-03 s (3.48 %) + leafs setup took 5.007e-06 s (0.00 %) + halfword conversion took 9.060e-06 s (0.01 %) +Built (100 x 100)[0x5632942dc640]{S} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' +Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 42). +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6186,12 +6252,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6202,22 +6268,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.716e-01 s (100.00 %) - analyzed arrays in 4.762e-02 s (27.75 %) - cleaned-up arrays in 1.502e-05 s (0.01 %) - deduplicated arrays in 1.287e-05 s (0.01 %) + converted COO to RSB in 9.299e-02 s (100.00 %) + analyzed arrays in 5.346e-02 s (57.48 %) + cleaned-up arrays in 8.821e-06 s (0.01 %) + deduplicated arrays in 1.812e-05 s (0.02 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.795e-02 s (39.61 %) - memory allocations took 9.060e-06 s (0.01 %) - leafs setup took 9.060e-06 s (0.01 %) - halfword conversion took 5.595e-02 s (32.61 %) -Built (100 x 100)[0x565522ee3a60]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' + shuffled partitions in 3.949e-02 s (42.46 %) + memory allocations took 6.914e-06 s (0.01 %) + leafs setup took 5.960e-06 s (0.01 %) + halfword conversion took 8.106e-06 s (0.01 %) +Built (100 x 100)[0x5632942ce610]{S} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6228,11 +6294,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6243,11 +6309,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6257,16 +6323,15 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0556s; avg 0.01853s ( +/- 16.02/ 28.73 %); best 0.01556s; worst 0.02386s; std dev. 0.003773 (taking best). -Reference operation time is 0.015563 s (1.298 Mflops) with 1 threads. -Challenging best inner round reference (8.82149e-06 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.015563 s/0 threads (speedup 0.000566824 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +3 iterations (1 th.) took 5.794e-05s; avg 1.931e-05s ( +/- 48.15/ 91.36 %); best 1.001e-05s; worst 3.695e-05s; std dev. 1.248e-05 (taking best). +Reference operation time is 1.00136e-05 s (2017 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 1.00136e-05 s/0 threads (speedup 1.19048 x), same?n. +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6277,12 +6342,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6293,22 +6358,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 9.983e-02 s (100.00 %) - analyzed arrays in 3.187e-02 s (31.92 %) - cleaned-up arrays in 1.597e-05 s (0.02 %) - deduplicated arrays in 1.502e-05 s (0.02 %) + converted COO to RSB in 2.256e-01 s (100.00 %) + analyzed arrays in 5.255e-02 s (23.30 %) + cleaned-up arrays in 8.821e-06 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.851e-02 s (28.55 %) - memory allocations took 1.216e-05 s (0.01 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 3.941e-02 s (39.47 %) -Built (100 x 100)[0x565522ee3a60]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 8, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 7.539e-02 s (33.42 %) + memory allocations took 9.060e-06 s (0.00 %) + leafs setup took 8.821e-06 s (0.00 %) + halfword conversion took 9.760e-02 s (43.26 %) +Built (100 x 100)[0x5632942dc760]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 6, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6319,11 +6384,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6334,11 +6399,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6348,16 +6413,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.05558s; avg 0.01853s ( +/- 35.93/ 27.60 %); best 0.01187s; worst 0.02364s; std dev. 0.004927 (taking best). -Reference operation time is 0.0118699 s (1.702 Mflops) with 1 threads. -Challenging best inner round reference (8.82149e-06 s/1 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 0.0118699 s/0 threads (speedup 0.000743181 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 11 subms, 8 lsubms, 2.1846 bpnz +3 iterations (1 th.) took 0.1127s; avg 0.03757s ( +/- 36.49/ 26.01 %); best 0.02386s; worst 0.04734s; std dev. 0.009981 (taking best). +Reference operation time is 0.02386 s (0.8466 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/0 threads) with: subdivision 0.5, 6 leaves, 2.163 bytes/nz, 0.02386 s/0 threads (speedup 0.000419681 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 8 subms, 6 lsubms, 2.1632 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6368,12 +6433,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6384,22 +6449,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.678e-01 s (100.00 %) - analyzed arrays in 6.383e-02 s (38.04 %) - cleaned-up arrays in 1.478e-05 s (0.01 %) - deduplicated arrays in 1.311e-05 s (0.01 %) + converted COO to RSB in 2.512e-01 s (100.00 %) + analyzed arrays in 6.913e-02 s (27.51 %) + cleaned-up arrays in 1.001e-05 s (0.00 %) + deduplicated arrays in 1.192e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.799e-02 s (28.60 %) - memory allocations took 2.480e-05 s (0.01 %) - leafs setup took 1.383e-05 s (0.01 %) - halfword conversion took 5.592e-02 s (33.32 %) -Built (100 x 100)[0x565522eee430]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 19, symflags:'LS' + shuffled partitions in 8.302e-02 s (33.04 %) + memory allocations took 7.868e-06 s (0.00 %) + leafs setup took 1.097e-05 s (0.00 %) + halfword conversion took 9.906e-02 s (39.43 %) +Built (100 x 100)[0x5632942dc760]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 16, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6410,11 +6475,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6425,11 +6490,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6439,16 +6504,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0661s; avg 0.02203s ( +/- 27.43/ 44.87 %); best 0.01599s; worst 0.03192s; std dev. 0.007049 (taking best). -Reference operation time is 0.0159891 s (1.263 Mflops) with 1 threads. -Challenging best inner round reference (8.82149e-06 s/1 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 0.0159891 s/0 threads (speedup 0.00055172 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 26 subms, 19 lsubms, 2.2725 bpnz +3 iterations (1 th.) took 0.1172s; avg 0.03905s ( +/- 12.22/ 11.76 %); best 0.03428s; worst 0.04364s; std dev. 0.003826 (taking best). +Reference operation time is 0.0342791 s (0.5893 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/0 threads) with: subdivision 1, 16 leaves, 2.25 bytes/nz, 0.0342791 s/0 threads (speedup 0.000292119 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 22 subms, 16 lsubms, 2.2503 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6459,12 +6524,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6475,22 +6540,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.649e-01 s (100.00 %) - analyzed arrays in 6.886e-02 s (41.76 %) - cleaned-up arrays in 1.502e-05 s (0.01 %) - deduplicated arrays in 1.311e-05 s (0.01 %) + converted COO to RSB in 1.997e-01 s (100.00 %) + analyzed arrays in 8.623e-02 s (43.17 %) + cleaned-up arrays in 8.821e-06 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.799e-02 s (29.11 %) - memory allocations took 2.885e-05 s (0.02 %) - leafs setup took 1.502e-05 s (0.01 %) - halfword conversion took 4.796e-02 s (29.09 %) -Built (100 x 100)[0x565522f014e0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 42, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 3.955e-02 s (19.80 %) + memory allocations took 1.431e-05 s (0.01 %) + leafs setup took 1.192e-05 s (0.01 %) + halfword conversion took 7.392e-02 s (37.01 %) +Built (100 x 100)[0x5632942dc760]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6501,11 +6566,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6516,11 +6581,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6530,16 +6595,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.06398s; avg 0.02133s ( +/- 25.42/ 49.98 %); best 0.01591s; worst 0.03198s; std dev. 0.007537 (taking best). -Reference operation time is 0.0159051 s (1.27 Mflops) with 1 threads. -Challenging best inner round reference (8.82149e-06 s/1 threads) with: subdivision 2, 42 leaves, 2.399 bytes/nz, 0.0159051 s/0 threads (speedup 0.000554631 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 58 subms, 42 lsubms, 2.3992 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +3 iterations (1 th.) took 0.07536s; avg 0.02512s ( +/- 8.70/ 11.48 %); best 0.02293s; worst 0.028s; std dev. 0.002128 (taking best). +Reference operation time is 0.022934 s (0.8808 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/0 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.022934 s/0 threads (speedup 0.000436627 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6550,12 +6615,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6566,22 +6631,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.031e-01 s (100.00 %) - analyzed arrays in 7.509e-02 s (36.96 %) - cleaned-up arrays in 1.407e-05 s (0.01 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 2.025e-01 s (100.00 %) + analyzed arrays in 6.538e-02 s (32.29 %) + cleaned-up arrays in 1.192e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.407e-02 s (31.54 %) - memory allocations took 2.384e-05 s (0.01 %) - leafs setup took 3.099e-05 s (0.02 %) - halfword conversion took 6.390e-02 s (31.45 %) -Built (100 x 100)[0x565522f014e0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 90, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 7.121e-02 s (35.17 %) + memory allocations took 1.693e-05 s (0.01 %) + leafs setup took 1.597e-05 s (0.01 %) + halfword conversion took 6.582e-02 s (32.51 %) +Built (100 x 100)[0x5632942fe510]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 78, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6592,11 +6657,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6607,11 +6672,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6621,17 +6686,17 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.09599s; avg 0.032s ( +/- 0.01/ 0.02 %); best 0.03199s; worst 0.032s; std dev. 4.019e-06 (taking best). -Reference operation time is 0.0319939 s (0.6314 Mflops) with 1 threads. -Challenging best inner round reference (8.82149e-06 s/1 threads) with: subdivision 4, 90 leaves, 2.604 bytes/nz, 0.0319939 s/0 threads (speedup 0.000275724 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 122 subms, 90 lsubms, 2.6044 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 2289.86 Mflops. +3 iterations (1 th.) took 0.1079s; avg 0.03598s ( +/- 30.42/ 22.76 %); best 0.02504s; worst 0.04417s; std dev. 0.008051 (taking best). +Reference operation time is 0.0250371 s (0.8068 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/0 threads) with: subdivision 4, 78 leaves, 2.556 bytes/nz, 0.0250371 s/0 threads (speedup 0.00039995 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 106 subms, 78 lsubms, 2.5560 bpnz +Best sparse multiply performance with subdivision multiplier of 0.25: 2017.26 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6641,23 +6706,23 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 1.23974 s (eq. to 1e+05/ 1e+05 old/new op.times), gained local/global speedup 1 x (8.82149e-06 : 8.82149e-06) / 1 x (8.82149e-06 : 8.82149e-06). This is not amortizable ! -Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 1.2s, 0.9s for constructor, 0 clones) obtained NO speedup (best stays 2290 Mflops). -Second run of RSB Autotuner took 1.23992 s and estimated a speedup of 1.000000 x (8.821e-06 s -> 8.821e-06 s per op) in same matrix (1 -> 1 lsubm) +Last tuner inner round (1 of 1) took 1.51308 s (eq. to 1e+05/ 2e+05 old/new op.times), gained local/global speedup 1.19048 x (1.19209e-05 : 1.00136e-05) / 1.19048 x (1.19209e-05 : 1.00136e-05). This is amortizable in 793290 op.times. +In 1 tuning rounds (tot. 1.5s, 1.1s for constructor, 0 clones) obtained a SPEEDUP of 19.0% (1.19x) (from 1694 to 2017 Mflops). +Second run of RSB Autotuner took 1.51316 s and estimated a speedup of 1.190476 x (1.192e-05 s -> 1.001e-05 s per op) in new matrix (1 -> 1 lsubm) +RSB Autotuner suggested a new matrix: freeing the old one. #min:1 #max:1 #sum:100 #norm:10 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.027296 0.075916 0.103212 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.103212 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.027296 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.075916 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.063515 2.561572 2.625087 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 2.625087 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.063515 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 2.561572 %:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000000 %:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.103212 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 2.625087 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 @@ -6672,45 +6737,45 @@ %:SM_MINMAXAVGNNZ:lower-100x100-5050nz S N 1 100 100 5050 5050 5050 5050 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[1] -%operation:lower-100x100-5050nz 0.135268 1e+09 1e+09 +%operation:lower-100x100-5050nz 2.67802 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0272958 0 0.0759161 -# so far, program took 9.509s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.617s/0.000s . +%constructor:lower-100x100-5050nz 0 0.0635149 0 2.56157 +# so far, program took 18.179s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.703s/0.000s . getrusage() stats: -ru_maxrss: 11 (maximum resident set size -- MB) -ru_stime : 0.103s (system CPU time used) -ru_utime : 40.19s (user CPU time used) +ru_maxrss: 20 (maximum resident set size -- MB) +ru_stime : 3.398s (system CPU time used) +ru_utime : 30.72s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was D). -# Cache block size total 524288 bytes, per-thread 524288 bytes -# so far, program took 9.509s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.617s/0.000s . +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# so far, program took 18.179s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.703s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.599e-01 s (100.00 %) - analyzed arrays in 3.192e-02 s (19.96 %) - cleaned-up arrays in 1.311e-05 s (0.01 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 2.715e-01 s (100.00 %) + analyzed arrays in 6.931e-02 s (25.53 %) + cleaned-up arrays in 1.192e-05 s (0.00 %) + deduplicated arrays in 1.216e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.011e-02 s (50.09 %) - memory allocations took 1.788e-05 s (0.01 %) - leafs setup took 7.153e-06 s (0.00 %) - halfword conversion took 4.784e-02 s (29.91 %) -Built (100 x 100)[0x565522eee430]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' -# Constructed matrix (took 0.160s): (100 x 100)[0x565522eee430]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + shuffled partitions in 1.374e-01 s (50.59 %) + memory allocations took 8.106e-06 s (0.00 %) + leafs setup took 6.914e-06 s (0.00 %) + halfword conversion took 6.481e-02 s (23.87 %) +Built (100 x 100)[0x5632942dc760]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' +# Constructed matrix (took 0.272s): (100 x 100)[0x5632942dc760]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 100 x 100, type C, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz. Parameters: verbosity:2 mintimes:3 maxtimes:10 mindt:0 maxdt:3 Saved plot to test-tuning-lower-100x100-5050nz--C-N-1--base.eps # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6721,11 +6786,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6736,11 +6801,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6750,16 +6815,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.07196s; avg 0.02399s ( +/- 49.76/ 49.70 %); best 0.01205s; worst 0.03591s; std dev. 0.00974 (taking best). -Reference operation time is 0.0120509 s (6.705 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type C, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.01205 Mflops: 6.705) -Merge (3 -> 1 leaves) took w.c.t. of 0.000169s, ~0.000139s of computing time (of which 8.202e-05s sorting, 8.821e-06s analysis) +3 iterations (1 th.) took 0.1074s; avg 0.03579s ( +/- 28.81/ 25.02 %); best 0.02548s; worst 0.04474s; std dev. 0.007922 (taking best). +Reference operation time is 0.0254769 s (3.171 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type C, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.02548 Mflops: 3.171) +Merge (3 -> 1 leaves) took w.c.t. of 8.988e-05s, ~6.986e-05s of computing time (of which 2.885e-05s sorting, 5.007e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6770,11 +6835,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6784,14 +6849,14 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.000144s; avg 4.8e-05s ( +/- 27.48/ 46.03 %); best 3.481e-05s; worst 7.01e-05s; std dev. 1.572e-05 (taking best). -Reference operation time is 3.48091e-05 s (2321 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001318s; avg 4.395e-05s ( +/- 9.40/ 16.09 %); best 3.982e-05s; worst 5.102e-05s; std dev. 5.025e-06 (taking best). +Reference operation time is 3.98159e-05 s (2029 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6801,25 +6866,25 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -After merge step 1: tpop: 3.481e-05 s ~Mflops: 2321.231 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 346.199x: 0.01205s -> 3.481e-05s, so taking this instance. +After merge step 1: tpop: 3.982e-05 s ~Mflops: 2029.340 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 639.868x: 0.02548s -> 3.982e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.2202s (of which 0.000174s partitioning, 0.1322s I/O); computing times: 0.000139s in par. loops, 8.202e-05s sorting, 8.821e-06s analyzing) -Total merge + benchmarking process took 0.2202s, equivalent to 6324.6/18.3 new/old ops (0.1795s for 2 clones -- as 5156.3/14.9 ops, or 2578.2/7.4 ops per clone), SPEEDUP of 346.199x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 346.199x (0.01205s -> 3.481e-05s), will amortize in 18.3 ops by saving 0.01202s per op. -In 1 tuning rounds (tot. 0.39s, 0.18s for constructor, 2 clones) obtained a SPEEDUP of 34519.9% (346.2x) (from 6.705 to 2321 Mflops). Employed 0.26s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.3345s (of which 9.489e-05s partitioning, 0.2255s I/O); computing times: 6.986e-05s in par. loops, 2.885e-05s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.3345s, equivalent to 8400.3/13.1 new/old ops (0.2503s for 2 clones -- as 6285.9/9.8 ops, or 3142.9/4.9 ops per clone), SPEEDUP of 639.868x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 639.868x (0.02548s -> 3.982e-05s), will amortize in 13.1 ops by saving 0.02544s per op. +In 1 tuning rounds (tot. 0.58s, 0.25s for constructor, 2 clones) obtained a SPEEDUP of 63886.8% (639.9x) (from 3.171 to 2029 Mflops). Employed 0.25s for I/O of matrix plots. #pr: updating sample at index 3 (2^th of 4), 0^th touch for (0,0,0,0,0,2,0). -First run of RSB Autotuner took 0.648221 s (1.205e-02 s -> 3.481e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.837386 s (2.548e-02 s -> 3.982e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type C, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6830,11 +6895,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6845,13 +6910,13 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success Started tuning inner round: will search for an optimal matrix instance. -Starting with requested 0 threads ; current default 1 ; at most 20. +Starting with requested 0 threads ; current default 1 ; at most 42. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6862,11 +6927,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6876,27 +6941,27 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001149s; avg 3.831e-05s ( +/- 21.58/ 38.17 %); best 3.004e-05s; worst 5.293e-05s; std dev. 1.037e-05 (taking best). -Reference operation time is 3.00407e-05 s (2690 Mflops) with 1 threads. +3 iterations (1 th.) took 0.000124s; avg 4.133e-05s ( +/- 10.58/ 15.96 %); best 3.695e-05s; worst 4.792e-05s; std dev. 4.746e-06 (taking best). +Reference operation time is 3.69549e-05 s (2186 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 9.055e-02 s (100.00 %) - analyzed arrays in 4.254e-02 s (46.97 %) - cleaned-up arrays in 1.311e-05 s (0.01 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 1.315e-01 s (100.00 %) + analyzed arrays in 4.725e-02 s (35.95 %) + cleaned-up arrays in 1.001e-05 s (0.01 %) + deduplicated arrays in 1.097e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.796e-02 s (52.96 %) - memory allocations took 6.914e-06 s (0.01 %) - leafs setup took 7.868e-06 s (0.01 %) - halfword conversion took 1.907e-05 s (0.02 %) -Built (100 x 100)[0x565522eee310]{C} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' -Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 20). -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 8.416e-02 s (64.02 %) + memory allocations took 5.960e-06 s (0.00 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 1.001e-05 s (0.01 %) +Built (100 x 100)[0x5632942dc640]{C} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' +Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 42). +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6907,12 +6972,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6923,22 +6988,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.239e-01 s (100.00 %) - analyzed arrays in 3.587e-02 s (28.96 %) - cleaned-up arrays in 1.311e-05 s (0.01 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 2.382e-01 s (100.00 %) + analyzed arrays in 6.373e-02 s (26.76 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 9.775e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.792e-02 s (38.69 %) - memory allocations took 1.097e-05 s (0.01 %) - leafs setup took 9.060e-06 s (0.01 %) - halfword conversion took 4.001e-02 s (32.31 %) -Built (100 x 100)[0x565522eee430]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 9.048e-02 s (37.99 %) + memory allocations took 6.437e-06 s (0.00 %) + leafs setup took 5.007e-06 s (0.00 %) + halfword conversion took 8.391e-02 s (35.23 %) +Built (100 x 100)[0x5632942ce610]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6949,11 +7014,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6964,11 +7029,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6978,16 +7043,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0715s; avg 0.02383s ( +/- 1.42/ 0.79 %); best 0.02349s; worst 0.02402s; std dev. 0.0002402 (taking best). -Reference operation time is 0.023494 s (3.439 Mflops) with 1 threads. -Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.023494 s/0 threads (speedup 0.00127866 x), same?n. +3 iterations (1 th.) took 0.151s; avg 0.05033s ( +/- 23.11/ 15.53 %); best 0.0387s; worst 0.05815s; std dev. 0.008386 (taking best). +Reference operation time is 0.038698 s (2.088 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.038698 s/0 threads (speedup 0.000954957 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6998,12 +7063,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7014,22 +7079,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.558e-01 s (100.00 %) - analyzed arrays in 5.975e-02 s (38.35 %) - cleaned-up arrays in 1.812e-05 s (0.01 %) - deduplicated arrays in 1.502e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 4.802e-02 s (30.82 %) - memory allocations took 1.597e-05 s (0.01 %) - leafs setup took 1.097e-05 s (0.01 %) - halfword conversion took 4.797e-02 s (30.79 %) -Built (100 x 100)[0x565522eee430]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 12, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + converted COO to RSB in 2.261e-01 s (100.00 %) + analyzed arrays in 7.190e-02 s (31.80 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 9.060e-06 s (0.00 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.180e-02 s (36.18 %) + memory allocations took 8.821e-06 s (0.00 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 7.236e-02 s (32.00 %) +Built (100 x 100)[0x5632942ce610]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 10, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7040,11 +7105,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7055,11 +7120,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7069,16 +7134,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.08742s; avg 0.02914s ( +/- 17.56/ 21.59 %); best 0.02402s; worst 0.03543s; std dev. 0.004731 (taking best). -Reference operation time is 0.0240228 s (3.363 Mflops) with 1 threads. -Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 0.5, 12 leaves, 2.217 bytes/nz, 0.0240228 s/0 threads (speedup 0.00125051 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 17 subms, 12 lsubms, 2.2170 bpnz +3 iterations (1 th.) took 0.1084s; avg 0.03612s ( +/- 33.20/ 20.95 %); best 0.02413s; worst 0.04369s; std dev. 0.008576 (taking best). +Reference operation time is 0.024132 s (3.348 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.024132 s/0 threads (speedup 0.00153136 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 14 subms, 10 lsubms, 2.2059 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7089,12 +7154,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7105,22 +7170,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.478e-01 s (100.00 %) - analyzed arrays in 6.791e-02 s (45.94 %) - cleaned-up arrays in 1.192e-05 s (0.01 %) - deduplicated arrays in 1.216e-05 s (0.01 %) + converted COO to RSB in 2.335e-01 s (100.00 %) + analyzed arrays in 4.961e-02 s (21.25 %) + cleaned-up arrays in 1.001e-05 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.990e-02 s (26.99 %) - memory allocations took 1.597e-05 s (0.01 %) - leafs setup took 1.788e-05 s (0.01 %) - halfword conversion took 3.996e-02 s (27.03 %) -Built (100 x 100)[0x565522eee430]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 27, symflags:'LS' + shuffled partitions in 8.838e-02 s (37.85 %) + memory allocations took 7.868e-06 s (0.00 %) + leafs setup took 7.868e-06 s (0.00 %) + halfword conversion took 9.547e-02 s (40.89 %) +Built (100 x 100)[0x5632942dc760]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7131,11 +7196,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7146,11 +7211,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7160,16 +7225,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.06749s; avg 0.0225s ( +/- 28.91/ 40.03 %); best 0.01599s; worst 0.0315s; std dev. 0.006574 (taking best). -Reference operation time is 0.0159919 s (5.053 Mflops) with 1 threads. -Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 1, 27 leaves, 2.328 bytes/nz, 0.0159919 s/0 threads (speedup 0.00187849 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 37 subms, 27 lsubms, 2.3279 bpnz +3 iterations (1 th.) took 0.1422s; avg 0.04742s ( +/- 3.70/ 5.92 %); best 0.04566s; worst 0.05022s; std dev. 0.002006 (taking best). +Reference operation time is 0.0456591 s (1.77 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.0456591 s/0 threads (speedup 0.000809366 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 30 subms, 22 lsubms, 2.2947 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7180,12 +7245,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7196,22 +7261,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.519e-01 s (100.00 %) - analyzed arrays in 6.386e-02 s (42.04 %) - cleaned-up arrays in 1.192e-05 s (0.01 %) - deduplicated arrays in 1.121e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 5.223e-02 s (34.38 %) - memory allocations took 1.907e-05 s (0.01 %) - leafs setup took 1.311e-05 s (0.01 %) - halfword conversion took 3.577e-02 s (23.55 %) -Built (100 x 100)[0x565522f150a0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 58, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + converted COO to RSB in 3.107e-01 s (100.00 %) + analyzed arrays in 1.225e-01 s (39.43 %) + cleaned-up arrays in 7.868e-06 s (0.00 %) + deduplicated arrays in 1.216e-05 s (0.00 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.896e-02 s (28.63 %) + memory allocations took 1.192e-05 s (0.00 %) + leafs setup took 1.693e-05 s (0.01 %) + halfword conversion took 9.919e-02 s (31.92 %) +Built (100 x 100)[0x563294303400]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 48, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7222,11 +7287,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7237,11 +7302,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7251,16 +7316,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.044s; avg 0.01467s ( +/- 20.09/ 11.11 %); best 0.01172s; worst 0.01629s; std dev. 0.002087 (taking best). -Reference operation time is 0.011719 s (6.895 Mflops) with 1 threads. -Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 2, 58 leaves, 2.47 bytes/nz, 0.011719 s/0 threads (speedup 0.00256342 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 79 subms, 58 lsubms, 2.4705 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +3 iterations (1 th.) took 0.1436s; avg 0.04785s ( +/- 38.75/ 30.95 %); best 0.02931s; worst 0.06266s; std dev. 0.01387 (taking best). +Reference operation time is 0.029309 s (2.757 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 2, 48 leaves, 2.434 bytes/nz, 0.029309 s/0 threads (speedup 0.00126087 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 66 subms, 48 lsubms, 2.4341 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7271,12 +7336,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7287,22 +7352,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.041e-01 s (100.00 %) - analyzed arrays in 3.975e-02 s (38.19 %) - cleaned-up arrays in 1.597e-05 s (0.02 %) - deduplicated arrays in 1.287e-05 s (0.01 %) + converted COO to RSB in 3.958e-01 s (100.00 %) + analyzed arrays in 1.539e-01 s (38.89 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.00 %) sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 3.175e-02 s (30.51 %) - memory allocations took 2.122e-05 s (0.02 %) - leafs setup took 3.099e-05 s (0.03 %) - halfword conversion took 3.249e-02 s (31.22 %) -Built (100 x 100)[0x565522f150a0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 120, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 1.350e-01 s (34.11 %) + memory allocations took 2.408e-05 s (0.01 %) + leafs setup took 1.597e-05 s (0.00 %) + halfword conversion took 1.068e-01 s (26.98 %) +Built (100 x 100)[0x563294303400]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 102, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7313,11 +7378,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7328,11 +7393,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7342,17 +7407,17 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.05106s; avg 0.01702s ( +/- 9.32/ 15.98 %); best 0.01543s; worst 0.01974s; std dev. 0.001933 (taking best). -Reference operation time is 0.015435 s (5.235 Mflops) with 1 threads. -Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.015435 s/0 threads (speedup 0.00194628 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 162 subms, 120 lsubms, 2.7255 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 2689.68 Mflops. +3 iterations (1 th.) took 0.1486s; avg 0.04953s ( +/- 43.99/ 60.67 %); best 0.02774s; worst 0.07957s; std dev. 0.02195 (taking best). +Reference operation time is 0.0277388 s (2.913 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 4, 102 leaves, 2.653 bytes/nz, 0.0277388 s/0 threads (speedup 0.00133224 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 138 subms, 102 lsubms, 2.6535 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 2186.45 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7362,23 +7427,23 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 1.10371 s (eq. to 4e+04/ 4e+04 old/new op.times), gained local/global speedup 1 x (3.00407e-05 : 3.00407e-05) / 1 x (3.00407e-05 : 3.00407e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 2.23127 s (eq. to 6e+04/ 6e+04 old/new op.times), gained local/global speedup 1 x (3.69549e-05 : 3.69549e-05) / 1 x (3.69549e-05 : 3.69549e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 1.1s, 0.78s for constructor, 0 clones) obtained NO speedup (best stays 2690 Mflops). -Second run of RSB Autotuner took 1.10384 s and estimated a speedup of 1.000000 x (3.004e-05 s -> 3.004e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 2.2s, 1.5s for constructor, 0 clones) obtained NO speedup (best stays 2186 Mflops). +Second run of RSB Autotuner took 2.23136 s and estimated a speedup of 1.000000 x (3.695e-05 s -> 3.695e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:100 0 #norm:10 0 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.031925 0.080106 0.112031 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.112031 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.031925 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.080106 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.069307 0.137363 0.206670 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.206670 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.069307 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.137363 %:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000000 %:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.112031 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.206670 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 @@ -7393,45 +7458,45 @@ %:SM_MINMAXAVGNNZ:lower-100x100-5050nz S N 1 100 100 5050 5050 5050 5050 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[1] -%operation:lower-100x100-5050nz 0.159926 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.271523 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.031925 0 0.080106 -# so far, program took 11.513s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.369s/0.000s . +%constructor:lower-100x100-5050nz 0 0.0693071 0 0.137363 +# so far, program took 21.728s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 8.772s/0.000s . getrusage() stats: -ru_maxrss: 11 (maximum resident set size -- MB) -ru_stime : 0.115s (system CPU time used) -ru_utime : 56.95s (user CPU time used) +ru_maxrss: 20 (maximum resident set size -- MB) +ru_stime : 3.444s (system CPU time used) +ru_utime : 43.17s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was D). -# Cache block size total 524288 bytes, per-thread 524288 bytes -# so far, program took 11.513s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.369s/0.000s . +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# so far, program took 21.728s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 8.772s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.156e-01 s (100.00 %) - analyzed arrays in 2.347e-02 s (20.31 %) - cleaned-up arrays in 1.597e-05 s (0.01 %) - deduplicated arrays in 1.311e-05 s (0.01 %) + converted COO to RSB in 2.921e-01 s (100.00 %) + analyzed arrays in 5.168e-02 s (17.69 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.216e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.002e-02 s (51.94 %) - memory allocations took 1.502e-05 s (0.01 %) - leafs setup took 1.907e-06 s (0.00 %) - halfword conversion took 3.202e-02 s (27.70 %) -Built (100 x 100)[0x565522eee430]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' -# Constructed matrix (took 0.116s): (100 x 100)[0x565522eee430]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + shuffled partitions in 1.580e-01 s (54.10 %) + memory allocations took 1.001e-05 s (0.00 %) + leafs setup took 6.914e-06 s (0.00 %) + halfword conversion took 8.237e-02 s (28.20 %) +Built (100 x 100)[0x5632942dc760]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' +# Constructed matrix (took 0.292s): (100 x 100)[0x5632942dc760]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz. Parameters: verbosity:2 mintimes:3 maxtimes:10 mindt:0 maxdt:3 Saved plot to test-tuning-lower-100x100-5050nz--Z-N-1--base.eps # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7442,11 +7507,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7457,11 +7522,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7471,16 +7536,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.04394s; avg 0.01465s ( +/- 17.93/ 9.23 %); best 0.01202s; worst 0.016s; std dev. 0.001857 (taking best). -Reference operation time is 0.0120192 s (6.723 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.01202 Mflops: 6.723) -Merge (3 -> 1 leaves) took w.c.t. of 0.000109s, ~9.418e-05s of computing time (of which 5.102e-05s sorting, 2.861e-06s analysis) +3 iterations (1 th.) took 0.1312s; avg 0.04373s ( +/- 30.50/ 25.36 %); best 0.03039s; worst 0.05481s; std dev. 0.0101 (taking best). +Reference operation time is 0.0303888 s (2.659 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.03039 Mflops: 2.659) +Merge (3 -> 1 leaves) took w.c.t. of 9.108e-05s, ~6.89e-05s of computing time (of which 3.29e-05s sorting, 5.007e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7491,11 +7556,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7505,14 +7570,14 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001101s; avg 3.672e-05s ( +/- 4.55/ 9.09 %); best 3.505e-05s; worst 4.005e-05s; std dev. 2.36e-06 (taking best). -Reference operation time is 3.50475e-05 s (2305 Mflops) with 1 threads. +3 iterations (1 th.) took 0.000108s; avg 3.6e-05s ( +/- 11.26/ 19.21 %); best 3.195e-05s; worst 4.292e-05s; std dev. 4.913e-06 (taking best). +Reference operation time is 3.19481e-05 s (2529 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7522,25 +7587,25 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -After merge step 1: tpop: 3.505e-05 s ~Mflops: 2305.441 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 342.939x: 0.01202s -> 3.505e-05s, so taking this instance. +After merge step 1: tpop: 3.195e-05 s ~Mflops: 2529.103 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 951.194x: 0.03039s -> 3.195e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.144s (of which 0.000114s partitioning, 0.1s I/O); computing times: 9.418e-05s in par. loops, 5.102e-05s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.144s, equivalent to 4110.1/12.0 new/old ops (0.09051s for 2 clones -- as 2582.4/7.5 ops, or 1291.2/3.8 ops per clone), SPEEDUP of 342.939x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 342.939x (0.01202s -> 3.505e-05s), will amortize in 12.0 ops by saving 0.01198s per op. -In 1 tuning rounds (tot. 0.24s, 0.091s for constructor, 2 clones) obtained a SPEEDUP of 34193.9% (342.9x) (from 6.723 to 2305 Mflops). Employed 0.11s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.7224s (of which 9.608e-05s partitioning, 0.5787s I/O); computing times: 6.89e-05s in par. loops, 3.29e-05s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.7224s, equivalent to 22612.9/23.8 new/old ops (0.3148s for 2 clones -- as 9854.9/10.4 ops, or 4927.4/5.2 ops per clone), SPEEDUP of 951.194x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 951.194x (0.03039s -> 3.195e-05s), will amortize in 23.8 ops by saving 0.03036s per op. +In 1 tuning rounds (tot. 1s, 0.31s for constructor, 2 clones) obtained a SPEEDUP of 95019.4% (951.2x) (from 2.659 to 2529 Mflops). Employed 2.9s for I/O of matrix plots. #pr: updating sample at index 4 (3^th of 4), 0^th touch for (0,0,0,0,0,3,0). -First run of RSB Autotuner took 0.344359 s (1.202e-02 s -> 3.505e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 3.92197 s (3.039e-02 s -> 3.195e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7551,11 +7616,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7566,13 +7631,13 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success Started tuning inner round: will search for an optimal matrix instance. -Starting with requested 0 threads ; current default 1 ; at most 20. +Starting with requested 0 threads ; current default 1 ; at most 42. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7583,11 +7648,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7597,27 +7662,27 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001411s; avg 4.705e-05s ( +/- 25.51/ 51.01 %); best 3.505e-05s; worst 7.105e-05s; std dev. 1.697e-05 (taking best). -Reference operation time is 3.50475e-05 s (2305 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001309s; avg 4.363e-05s ( +/- 10.38/ 19.13 %); best 3.91e-05s; worst 5.198e-05s; std dev. 5.908e-06 (taking best). +Reference operation time is 3.91006e-05 s (2066 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 5.511e-02 s (100.00 %) - analyzed arrays in 1.908e-02 s (34.62 %) - cleaned-up arrays in 1.502e-05 s (0.03 %) - deduplicated arrays in 1.287e-05 s (0.02 %) + converted COO to RSB in 1.846e-01 s (100.00 %) + analyzed arrays in 1.020e-01 s (55.27 %) + cleaned-up arrays in 1.192e-05 s (0.01 %) + deduplicated arrays in 1.287e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.599e-02 s (65.31 %) - memory allocations took 3.338e-06 s (0.01 %) - leafs setup took 2.146e-06 s (0.00 %) - halfword conversion took 5.960e-06 s (0.01 %) -Built (100 x 100)[0x565522eee310]{Z} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' -Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 20). -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 8.251e-02 s (44.69 %) + memory allocations took 3.028e-05 s (0.02 %) + leafs setup took 6.914e-06 s (0.00 %) + halfword conversion took 9.060e-06 s (0.00 %) +Built (100 x 100)[0x5632942dc640]{Z} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' +Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 42). +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7628,12 +7693,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7644,22 +7709,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 8.373e-02 s (100.00 %) - analyzed arrays in 1.977e-02 s (23.62 %) - cleaned-up arrays in 1.597e-05 s (0.02 %) - deduplicated arrays in 1.407e-05 s (0.02 %) + converted COO to RSB in 2.534e-01 s (100.00 %) + analyzed arrays in 7.239e-02 s (28.57 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.192e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.191e-02 s (38.12 %) - memory allocations took 5.007e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 3.201e-02 s (38.23 %) -Built (100 x 100)[0x565522eee430]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 8, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 1.052e-01 s (41.52 %) + memory allocations took 4.768e-06 s (0.00 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 7.576e-02 s (29.90 %) +Built (100 x 100)[0x5632942dc760]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 6, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7670,11 +7735,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7685,11 +7750,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7699,16 +7764,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.04796s; avg 0.01599s ( +/- 0.27/ 0.19 %); best 0.01594s; worst 0.01602s; std dev. 3.148e-05 (taking best). -Reference operation time is 0.015944 s (5.068 Mflops) with 1 threads. -Challenging best inner round reference (3.50475e-05 s/1 threads) with: subdivision 0.25, 8 leaves, 2.185 bytes/nz, 0.015944 s/0 threads (speedup 0.00219816 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 11 subms, 8 lsubms, 2.1846 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +3 iterations (1 th.) took 0.1446s; avg 0.04821s ( +/- 6.89/ 4.86 %); best 0.04489s; worst 0.05055s; std dev. 0.002412 (taking best). +Reference operation time is 0.044888 s (1.8 Mflops) with 1 threads. +Challenging best inner round reference (3.91006e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.044888 s/0 threads (speedup 0.000871071 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 8 subms, 6 lsubms, 2.1632 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7719,12 +7784,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7735,22 +7800,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.119e-01 s (100.00 %) - analyzed arrays in 4.784e-02 s (42.77 %) - cleaned-up arrays in 1.502e-05 s (0.01 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 2.510e-01 s (100.00 %) + analyzed arrays in 6.624e-02 s (26.39 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.097e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.200e-02 s (28.60 %) - memory allocations took 9.060e-06 s (0.01 %) - leafs setup took 9.060e-06 s (0.01 %) - halfword conversion took 3.198e-02 s (28.59 %) -Built (100 x 100)[0x565522eee430]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 19, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 9.199e-02 s (36.66 %) + memory allocations took 1.001e-05 s (0.00 %) + leafs setup took 6.914e-06 s (0.00 %) + halfword conversion took 9.270e-02 s (36.94 %) +Built (100 x 100)[0x5632942dc760]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 16, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7761,11 +7826,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7776,11 +7841,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7790,16 +7855,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.04796s; avg 0.01599s ( +/- 0.22/ 0.12 %); best 0.01595s; worst 0.016s; std dev. 2.437e-05 (taking best). -Reference operation time is 0.0159509 s (5.066 Mflops) with 1 threads. -Challenging best inner round reference (3.50475e-05 s/1 threads) with: subdivision 0.5, 19 leaves, 2.272 bytes/nz, 0.0159509 s/0 threads (speedup 0.00219721 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 26 subms, 19 lsubms, 2.2725 bpnz +3 iterations (1 th.) took 0.1351s; avg 0.04503s ( +/- 17.51/ 15.66 %); best 0.03714s; worst 0.05208s; std dev. 0.006126 (taking best). +Reference operation time is 0.037143 s (2.175 Mflops) with 1 threads. +Challenging best inner round reference (3.91006e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 0.037143 s/0 threads (speedup 0.00105271 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 22 subms, 16 lsubms, 2.2503 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7810,12 +7875,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7826,22 +7891,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.037e-01 s (100.00 %) - analyzed arrays in 3.170e-02 s (30.56 %) - cleaned-up arrays in 1.383e-05 s (0.01 %) - deduplicated arrays in 1.216e-05 s (0.01 %) + converted COO to RSB in 3.190e-01 s (100.00 %) + analyzed arrays in 1.073e-01 s (33.64 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.001e-02 s (38.57 %) - memory allocations took 5.007e-06 s (0.00 %) - leafs setup took 3.099e-06 s (0.00 %) - halfword conversion took 3.198e-02 s (30.83 %) -Built (100 x 100)[0x565522f3c7f0]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 39, symflags:'LS' + shuffled partitions in 1.025e-01 s (32.14 %) + memory allocations took 1.192e-05 s (0.00 %) + leafs setup took 1.097e-05 s (0.00 %) + halfword conversion took 1.091e-01 s (34.20 %) +Built (100 x 100)[0x5632942dc760]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7852,11 +7917,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7867,11 +7932,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7881,16 +7946,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.04796s; avg 0.01599s ( +/- 0.15/ 0.08 %); best 0.01596s; worst 0.016s; std dev. 1.654e-05 (taking best). -Reference operation time is 0.015964 s (5.061 Mflops) with 1 threads. -Challenging best inner round reference (3.50475e-05 s/1 threads) with: subdivision 1, 39 leaves, 2.396 bytes/nz, 0.015964 s/0 threads (speedup 0.00219541 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 54 subms, 39 lsubms, 2.3960 bpnz +3 iterations (1 th.) took 0.1398s; avg 0.04659s ( +/- 14.89/ 28.89 %); best 0.03965s; worst 0.06005s; std dev. 0.009519 (taking best). +Reference operation time is 0.0396509 s (2.038 Mflops) with 1 threads. +Challenging best inner round reference (3.91006e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 0.0396509 s/0 threads (speedup 0.000986122 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7901,12 +7966,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7917,22 +7982,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.117e-01 s (100.00 %) - analyzed arrays in 4.762e-02 s (42.65 %) - cleaned-up arrays in 1.383e-05 s (0.01 %) - deduplicated arrays in 1.216e-05 s (0.01 %) + converted COO to RSB in 3.031e-01 s (100.00 %) + analyzed arrays in 1.203e-01 s (39.69 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.201e-02 s (28.67 %) - memory allocations took 1.121e-05 s (0.01 %) - leafs setup took 8.106e-06 s (0.01 %) - halfword conversion took 3.198e-02 s (28.64 %) -Built (100 x 100)[0x565522f3c7f0]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 84, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 9.921e-02 s (32.74 %) + memory allocations took 1.693e-05 s (0.01 %) + leafs setup took 1.407e-05 s (0.00 %) + halfword conversion took 8.351e-02 s (27.55 %) +Built (100 x 100)[0x56329432ab50]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 75, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7943,11 +8008,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7958,11 +8023,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7972,16 +8037,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.04795s; avg 0.01598s ( +/- 0.22/ 0.14 %); best 0.01595s; worst 0.016s; std dev. 2.495e-05 (taking best). -Reference operation time is 0.0159469 s (5.067 Mflops) with 1 threads. -Challenging best inner round reference (3.50475e-05 s/1 threads) with: subdivision 2, 84 leaves, 2.581 bytes/nz, 0.0159469 s/0 threads (speedup 0.00219777 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 114 subms, 84 lsubms, 2.5806 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +3 iterations (1 th.) took 0.1323s; avg 0.04409s ( +/- 27.04/ 30.33 %); best 0.03217s; worst 0.05746s; std dev. 0.01038 (taking best). +Reference operation time is 0.0321679 s (2.512 Mflops) with 1 threads. +Challenging best inner round reference (3.91006e-05 s/1 threads) with: subdivision 2, 75 leaves, 2.544 bytes/nz, 0.0321679 s/0 threads (speedup 0.00121552 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 102 subms, 75 lsubms, 2.5442 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7992,12 +8057,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 26214 bytes +# Cache block size total 4194304 bytes, per-thread 99864 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 -# RSB_IO_WANT_EXECUTING_THREADS: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 +# RSB_IO_WANT_EXECUTING_THREADS: 42 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -8008,22 +8073,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 9.977e-02 s (100.00 %) - analyzed arrays in 3.572e-02 s (35.80 %) - cleaned-up arrays in 1.407e-05 s (0.01 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 2.675e-01 s (100.00 %) + analyzed arrays in 1.026e-01 s (38.33 %) + cleaned-up arrays in 9.060e-06 s (0.00 %) + deduplicated arrays in 1.001e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.334e-02 s (33.42 %) - memory allocations took 1.431e-05 s (0.01 %) - leafs setup took 1.001e-05 s (0.01 %) - halfword conversion took 3.066e-02 s (30.73 %) -Built (100 x 100)[0x565522f3c7f0]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 120, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 + shuffled partitions in 7.675e-02 s (28.69 %) + memory allocations took 1.478e-05 s (0.01 %) + leafs setup took 2.003e-05 s (0.01 %) + halfword conversion took 8.819e-02 s (32.96 %) +Built (100 x 100)[0x56329432ab50]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 134, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8034,11 +8099,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8049,11 +8114,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8063,17 +8128,17 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.04804s; avg 0.01601s ( +/- 0.35/ 0.42 %); best 0.01596s; worst 0.01608s; std dev. 5.095e-05 (taking best). -Reference operation time is 0.0159588 s (5.063 Mflops) with 1 threads. -Challenging best inner round reference (3.50475e-05 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.0159588 s/0 threads (speedup 0.00219613 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 162 subms, 120 lsubms, 2.7255 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 2305.44 Mflops. +3 iterations (1 th.) took 0.1242s; avg 0.04142s ( +/- 20.74/ 24.71 %); best 0.03283s; worst 0.05165s; std dev. 0.007772 (taking best). +Reference operation time is 0.0328262 s (2.461 Mflops) with 1 threads. +Challenging best inner round reference (3.91006e-05 s/1 threads) with: subdivision 4, 134 leaves, 2.77 bytes/nz, 0.0328262 s/0 threads (speedup 0.00119114 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 183 subms, 134 lsubms, 2.7699 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 2066.46 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 524288 bytes, per-thread 524288 bytes +# Cache block size total 4194304 bytes, per-thread 4194304 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 20 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 42 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8083,23 +8148,23 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.811844 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1 x (3.50475e-05 : 3.50475e-05) / 1 x (3.50475e-05 : 3.50475e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 2.25656 s (eq. to 6e+04/ 6e+04 old/new op.times), gained local/global speedup 1 x (3.91006e-05 : 3.91006e-05) / 1 x (3.91006e-05 : 3.91006e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.81s, 0.57s for constructor, 0 clones) obtained NO speedup (best stays 2305 Mflops). -Second run of RSB Autotuner took 0.811968 s and estimated a speedup of 1.000000 x (3.505e-05 s -> 3.505e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 2.3s, 1.6s for constructor, 0 clones) obtained NO speedup (best stays 2066 Mflops). +Second run of RSB Autotuner took 2.25665 s and estimated a speedup of 1.000000 x (3.910e-05 s -> 3.910e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:100 0 #norm:10 0 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.023474 0.060025 0.083499 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.083499 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.023474 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.060025 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.051681 0.158033 0.209714 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.209714 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.051681 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.158033 %:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000000 %:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.083499 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.209714 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 @@ -8114,68 +8179,68 @@ %:SM_MINMAXAVGNNZ:lower-100x100-5050nz S N 1 100 100 5050 5050 5050 5050 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[1] -%operation:lower-100x100-5050nz 0.115563 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.292126 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.023474 0 0.060025 -# so far, program took 12.873s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 6.525s/0.000s . +%constructor:lower-100x100-5050nz 0 0.051681 0 0.158033 +# so far, program took 28.411s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 14.950s/0.000s . getrusage() stats: -ru_maxrss: 11 (maximum resident set size -- MB) -ru_stime : 0.1153s (system CPU time used) -ru_utime : 71.05s (user CPU time used) +ru_maxrss: 20 (maximum resident set size -- MB) +ru_stime : 3.506s (system CPU time used) +ru_utime : 55.67s (user CPU time used) # benchmarking terminated --- finalizing run. # ====== BEGIN Total summary record. #pr: ======== All results (not limiting) #pr: Dump from a base of 4 samples (of max 4) ordered by (1,1,1,1,1,4,1) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R lower-100x100-5050nz 100 100 5050 1 D S N 1 1 0 2.1212 2.0800 3 1 2017.26 1.594e-02 0.000e+00 1.001e-05 0.000e+00 3.882e-01 5.32e+00 2.60e+00 1 2.02e-02 -pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 1568.98 8.012e-03 0.000e+00 1.287e-05 0.000e+00 9.567e-01 2.48e+00 1.56e+00 1 2.02e-02 -pr: 3:R_R lower-100x100-5050nz 100 100 5050 1 C S N 1 1 0 2.1212 2.0800 3 1 2321.23 1.205e-02 0.000e+00 3.481e-05 0.000e+00 6.482e-01 1.53e+00 6.50e-01 1 8.08e-02 -pr: 4:R_R lower-100x100-5050nz 100 100 5050 1 Z S N 1 1 0 2.1212 2.0800 3 1 2305.44 1.202e-02 0.000e+00 3.505e-05 0.000e+00 3.444e-01 2.74e+00 1.17e+00 1 8.08e-02 +pr: 1:R_R lower-100x100-5050nz 100 100 5050 1 D S N 1 1 0 2.1212 2.0800 3 1 1694.50 4.181e-02 0.000e+00 1.192e-05 0.000e+00 1.084e+00 4.47e+00 2.60e+00 1 2.02e-02 +pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 2017.26 4.835e-02 0.000e+00 1.001e-05 0.000e+00 8.688e-01 3.19e+00 1.56e+00 1 2.02e-02 +pr: 3:R_R lower-100x100-5050nz 100 100 5050 1 C S N 1 1 0 2.1212 2.0800 3 1 2029.34 2.548e-02 0.000e+00 3.982e-05 0.000e+00 8.374e-01 1.34e+00 6.50e-01 1 8.08e-02 +pr: 4:R_R lower-100x100-5050nz 100 100 5050 1 Z S N 1 1 0 2.1212 2.0800 3 1 2529.10 3.039e-02 0.000e+00 3.195e-05 0.000e+00 3.922e+00 3.01e+00 1.17e+00 1 8.08e-02 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 72479.3 % faster, avg. sp. ratio 725.793x, max sp. ratio 1591.738x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 35380.5/9825.5/74309.2/141522.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 56.6/ 24.4/119.4/226.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 56.7, min. 24.4, max. 119.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 248058.0 % faster, avg. sp. ratio 2481.580x, max sp. ratio 4828.238x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 80365.2/21031.4/122760.9/321460.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 51.5/ 18.0/129.1/205.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 51.5, min. 18.0, max. 129.2 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 1683/ 1683/ 1683) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 5050/ 5050/ 5050) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 15150/ 6733/ 26933) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 45450/ 20200/ 80800) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 2.121/ 2.121/ 2.121) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.974/ 1.508/ 5.243,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.075/ 1.531/ 5.323,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.957/ 1.319/ 4.404,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.004/ 1.339/ 4.471,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.495/ 0.650/ 2.599) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 2.080/ 2.080/ 2.080) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.58 s, min 0.34 s, max 0.96 s, tot 2.34 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.58 s, min 0.34 s, max 0.96 s, tot 2.34 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.053e+03, min 1.569e+03, max 2.321e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.304e+00, min 1.267e+00, max 6.723e+00 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.319e-05s, min 1.001e-05s, max 3.505e-05s, tot 9.274e-05s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.201e-02s, min 8.012e-03s, max 1.594e-02s, tot 4.802e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.993e+00 6.930e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.657e+00 -#pr: Record collection took 6.62 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 1.68 s, min 0.84 s, max 3.92 s, tot 6.71 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 1.68 s, min 0.84 s, max 3.92 s, tot 6.71 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.068e+03, min 1.694e+03, max 2.529e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.683e+00, min 4.178e-01, max 3.171e+00 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.342e-05s, min 1.001e-05s, max 3.982e-05s, tot 9.370e-05s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.651e-02s, min 2.548e-02s, max 4.835e-02s, tot 1.460e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.145e+00 7.163e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.698e+00 +#pr: Record collection took 16.96 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 99 environment variables in 5307 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 99 environment variables in 5360 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. #pr: ======== Saved a performance record of 4 samples to test.rpr # Removing the temporary record file test.rpr.tmp. -# terminating run at 1740605525 (after 12.9s of w.c.t.) +# terminating run at 1775018938 (after 28.4s of w.c.t.) + ls -ltr test-tuning-lower-100x100-5050nz--C-N-1--base.eps test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps test-tuning-lower-100x100-5050nz--D-N-1--base.eps test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps test-tuning-lower-100x100-5050nz--S-N-1--base.eps test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps test-tuning-lower-100x100-5050nz--Z-N-1--base.eps test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85633 Feb 26 09:31 test-tuning-lower-100x100-5050nz--D-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84554 Feb 26 09:31 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85632 Feb 26 09:31 test-tuning-lower-100x100-5050nz--S-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84554 Feb 26 09:31 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85632 Feb 26 09:32 test-tuning-lower-100x100-5050nz--C-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84554 Feb 26 09:32 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85632 Feb 26 09:32 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84555 Feb 26 09:32 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Apr 1 18:48 test-tuning-lower-100x100-5050nz--D-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Apr 1 18:48 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Apr 1 18:48 test-tuning-lower-100x100-5050nz--S-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Apr 1 18:48 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Apr 1 18:48 test-tuning-lower-100x100-5050nz--C-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Apr 1 18:48 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85641 Apr 1 18:48 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Apr 1 18:48 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps + rsbench --read-performance-record test.rpr + ls -ltr test.txt --rw-r--r-- 1 pbuilder1 pbuilder1 4100 Feb 26 09:32 test.txt +-rw-r--r-- 1 pbuilder2 pbuilder2 4104 Apr 1 18:48 test.txt + RSB_PR_WLTC=2 + RSB_PR_SR=0 + rsbench --read-performance-record test.rpr @@ -8185,29 +8250,29 @@ /usr/bin/kpsepath ++ kpsepath tex ++ sed 's/!!//g;s/:/\n/g;' -+ find . /nonexistent/first-build/.texlive2024/texmf-config/tex/kpsewhich// /nonexistent/first-build/.texlive2024/texmf-var/tex/kpsewhich// /nonexistent/first-build/texmf/tex/kpsewhich// /usr/local/share/texmf/tex/kpsewhich// /etc/texmf/tex/kpsewhich// /var/lib/texmf/tex/kpsewhich// /usr/share/texmf/tex/kpsewhich// /usr/share/texlive/texmf-dist/tex/kpsewhich// /nonexistent/first-build/.texlive2024/texmf-config/tex/generic// /nonexistent/first-build/.texlive2024/texmf-var/tex/generic// /nonexistent/first-build/texmf/tex/generic// /usr/local/share/texmf/tex/generic// /etc/texmf/tex/generic// /var/lib/texmf/tex/generic// /usr/share/texmf/tex/generic// /usr/share/texlive/texmf-dist/tex/generic// /nonexistent/first-build/.texlive2024/texmf-config/tex/latex// /nonexistent/first-build/.texlive2024/texmf-var/tex/latex// /nonexistent/first-build/texmf/tex/latex// /usr/local/share/texmf/tex/latex// /etc/texmf/tex/latex// /var/lib/texmf/tex/latex// /usr/share/texmf/tex/latex// /usr/share/texlive/texmf-dist/tex/latex// /nonexistent/first-build/.texlive2024/texmf-config/tex/// /nonexistent/first-build/.texlive2024/texmf-var/tex/// /nonexistent/first-build/texmf/tex/// /usr/local/share/texmf/tex/// /etc/texmf/tex/// /var/lib/texmf/tex/// /usr/share/texmf/tex/// /usr/share/texlive/texmf-dist/tex/// -name sciposter.cls -find: '/nonexistent/first-build/.texlive2024/texmf-config/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/.texlive2024/texmf-var/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/texmf/tex/kpsewhich//': No such file or directory ++ find . /nonexistent/second-build/.texlive2024/texmf-config/tex/kpsewhich// /nonexistent/second-build/.texlive2024/texmf-var/tex/kpsewhich// /nonexistent/second-build/texmf/tex/kpsewhich// /usr/local/share/texmf/tex/kpsewhich// /etc/texmf/tex/kpsewhich// /var/lib/texmf/tex/kpsewhich// /usr/share/texmf/tex/kpsewhich// /usr/share/texlive/texmf-dist/tex/kpsewhich// /nonexistent/second-build/.texlive2024/texmf-config/tex/generic// /nonexistent/second-build/.texlive2024/texmf-var/tex/generic// /nonexistent/second-build/texmf/tex/generic// /usr/local/share/texmf/tex/generic// /etc/texmf/tex/generic// /var/lib/texmf/tex/generic// /usr/share/texmf/tex/generic// /usr/share/texlive/texmf-dist/tex/generic// /nonexistent/second-build/.texlive2024/texmf-config/tex/latex// /nonexistent/second-build/.texlive2024/texmf-var/tex/latex// /nonexistent/second-build/texmf/tex/latex// /usr/local/share/texmf/tex/latex// /etc/texmf/tex/latex// /var/lib/texmf/tex/latex// /usr/share/texmf/tex/latex// /usr/share/texlive/texmf-dist/tex/latex// /nonexistent/second-build/.texlive2024/texmf-config/tex/// /nonexistent/second-build/.texlive2024/texmf-var/tex/// /nonexistent/second-build/texmf/tex/// /usr/local/share/texmf/tex/// /etc/texmf/tex/// /var/lib/texmf/tex/// /usr/share/texmf/tex/// /usr/share/texlive/texmf-dist/tex/// -name sciposter.cls +find: '/nonexistent/second-build/.texlive2024/texmf-config/tex/kpsewhich//': No such file or directory +find: '/nonexistent/second-build/.texlive2024/texmf-var/tex/kpsewhich//': No such file or directory +find: '/nonexistent/second-build/texmf/tex/kpsewhich//': No such file or directory find: '/usr/local/share/texmf/tex/kpsewhich//': No such file or directory find: '/etc/texmf/tex/kpsewhich//': No such file or directory find: '/var/lib/texmf/tex/kpsewhich//': No such file or directory find: '/usr/share/texmf/tex/kpsewhich//': No such file or directory find: '/usr/share/texlive/texmf-dist/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/.texlive2024/texmf-config/tex/generic//': No such file or directory -find: '/nonexistent/first-build/.texlive2024/texmf-var/tex/generic//': No such file or directory -find: '/nonexistent/first-build/texmf/tex/generic//': No such file or directory +find: '/nonexistent/second-build/.texlive2024/texmf-config/tex/generic//': No such file or directory +find: '/nonexistent/second-build/.texlive2024/texmf-var/tex/generic//': No such file or directory +find: '/nonexistent/second-build/texmf/tex/generic//': No such file or directory find: '/usr/local/share/texmf/tex/generic//': No such file or directory find: '/usr/share/texmf/tex/generic//': No such file or directory -find: '/nonexistent/first-build/.texlive2024/texmf-config/tex/latex//': No such file or directory -find: '/nonexistent/first-build/.texlive2024/texmf-var/tex/latex//': No such file or directory -find: '/nonexistent/first-build/texmf/tex/latex//': No such file or directory +find: '/nonexistent/second-build/.texlive2024/texmf-config/tex/latex//': No such file or directory +find: '/nonexistent/second-build/.texlive2024/texmf-var/tex/latex//': No such file or directory +find: '/nonexistent/second-build/texmf/tex/latex//': No such file or directory find: '/usr/local/share/texmf/tex/latex//': No such file or directory find: '/etc/texmf/tex/latex//': No such file or directory find: '/var/lib/texmf/tex/latex//': No such file or directory -find: '/nonexistent/first-build/.texlive2024/texmf-config/tex///': No such file or directory -find: '/nonexistent/first-build/.texlive2024/texmf-var/tex///': No such file or directory -find: '/nonexistent/first-build/texmf/tex///': No such file or directory +find: '/nonexistent/second-build/.texlive2024/texmf-config/tex///': No such file or directory +find: '/nonexistent/second-build/.texlive2024/texmf-var/tex///': No such file or directory +find: '/nonexistent/second-build/texmf/tex///': No such file or directory find: '/usr/local/share/texmf/tex///': No such file or directory + exit 0 for mf in pd.mtx vf.mtx ; do if test -f /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/$mf ; then true; else cp -p /build/reproducible-path/librsb-1.3.0.2+dfsg/$mf /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/$mf ; fi; done @@ -8222,7 +8287,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x563748a484a0]{D} @ (0(0..3),0(0..3)) (3 nnz, 1 nnz/r) flags 0x2040384 (coo:1, csr:0, hw:0, ic:1, fi:0), storage: 40, subm: 1, symflags:'' +(3 x 3)[0x559dad1924a0]{D} @ (0(0..3),0(0..3)) (3 nnz, 1 nnz/r) flags 0x2040384 (coo:1, csr:0, hw:0, ic:1, fi:0), storage: 40, subm: 1, symflags:'' Correctly performed a SPMV. Correctly freed the matrix. Correctly finalized the library. @@ -8237,7 +8302,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x557202ba54a0]{D} @ (0(0..3),0(0..3)) (3 nnz, 1 nnz/r) flags 0x2040384 (coo:1, csr:0, hw:0, ic:1, fi:0), storage: 40, subm: 1, symflags:'' +(3 x 3)[0x55bff86534a0]{D} @ (0(0..3),0(0..3)) (3 nnz, 1 nnz/r) flags 0x2040384 (coo:1, csr:0, hw:0, ic:1, fi:0), storage: 40, subm: 1, symflags:'' Correctly performed a SPMV. Correctly freed the matrix. Correctly finalized the library. @@ -8301,51 +8366,51 @@ Done. Building a matrix with 5 nnz, 5 x 5 Duplicates check: 5 - 0 = 5 - converted COO to RSB in 1.463e-01 s (100.00 %) - analyzed arrays in 4.802e-02 s (32.83 %) - cleaned-up arrays in 1.907e-06 s (0.00 %) - deduplicated arrays in 2.146e-06 s (0.00 %) - sorted arrays in 1.427e-02 s (9.76 %) - shuffled partitions in 3.994e-02 s (27.30 %) - memory allocations took 2.193e-05 s (0.01 %) + converted COO to RSB in 3.175e-01 s (100.00 %) + analyzed arrays in 1.078e-01 s (33.95 %) + cleaned-up arrays in 9.537e-07 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) + sorted arrays in 2.472e-02 s (7.79 %) + shuffled partitions in 8.053e-02 s (25.36 %) + memory allocations took 1.693e-05 s (0.01 %) leafs setup took 5.960e-06 s (0.00 %) - halfword conversion took 4.400e-02 s (30.08 %) -Built (5 x 5)[0x557202ba8b20]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' + halfword conversion took 1.044e-01 s (32.89 %) +Built (5 x 5)[0x55bff8659f60]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' Allocated matrix of 5 nonzeroes: -(5 x 5)[0x557202ba8b20]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +(5 x 5)[0x55bff8659f60]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' -Before auto-tuning, 100 multiplications took 1.799927s. +Before auto-tuning, 100 multiplications took 4.600626s. Threads autotuning (may take more than 1.500000s)... Will use autotuning routine to sample matrix: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.94497e-08), 20 suggested as starting thread count(default). -3 iterations (20 th.) took 0.04788s; avg 0.01596s ( +/- 0.59/ 0.61 %); best 0.01587s; worst 0.01606s; std dev. 7.838e-05 (taking best). -Reference operation time is 0.0158651 s (0.001261 Mflops) with 20 threads. -3 iterations (20 th.) took 0.04794s; avg 0.01598s ( +/- 0.35/ 0.19 %); best 0.01593s; worst 0.01601s; std dev. 3.931e-05 (taking best). -Reference operation time is 0.0159259 s (0.001256 Mflops) with 20 threads. -After 0.096007s, autotuning routine did not find a better threads count configuration. -(5 x 5)[0x557202ba8b20]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' -After threads auto-tuning, 100 multiplications took 1.903918s -- effective speedup of 0.945381 x -Matrix autotuning (may take more than 1.500000s; using 20 threads )... +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.77536e-08), 42 suggested as starting thread count(default). +3 iterations (42 th.) took 0.155s; avg 0.05166s ( +/- 58.09/ 43.76 %); best 0.02165s; worst 0.07427s; std dev. 0.02211 (taking best). +Reference operation time is 0.0216501 s (0.0009238 Mflops) with 42 threads. +3 iterations (42 th.) took 0.1624s; avg 0.05413s ( +/- 16.83/ 13.99 %); best 0.04502s; worst 0.0617s; std dev. 0.006895 (taking best). +Reference operation time is 0.0450211 s (0.0004442 Mflops) with 42 threads. +After 0.317525s, autotuning routine did not find a better threads count configuration. +(5 x 5)[0x55bff8659f60]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +After threads auto-tuning, 100 multiplications took 5.996241s -- effective speedup of 0.767252 x +Matrix autotuning (may take more than 1.500000s; using 42 threads )... Will autotune matrix: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.94497e-08), 20 suggested as starting thread count. -3 iterations (20 th.) took 0.0499s; avg 0.01663s ( +/- 3.83/ 7.64 %); best 0.016s; worst 0.0179s; std dev. 0.0008985 (taking best). -Reference operation time is 0.0159969 s (0.00125 Mflops) with 20 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz (tpop: 0.016 Mflops: 0.001) -Merge (2 -> 1 leaves) took w.c.t. of 3.386e-05s, ~5.96e-06s of computing time (of which 0s sorting, 8.106e-06s analysis) -3 iterations (20 th.) took 9.06e-06s; avg 3.02e-06s ( +/- 98.03/168.42 %); best 5.945e-08s; worst 8.106e-06s; std dev. 3.618e-06 (taking best). -Reference operation time is 5.94497e-08 s (336.4 Mflops) with 20 threads. -After merge step 1: tpop: 5.945e-08 s ~Mflops: 336.419 nsubm:1 otn:20 -Applying merge (2 -> 1 leaves, 20 th.) yielded SPEEDUP of 269083.617x: 0.016s -> 5.945e-08s, so taking this instance. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.77536e-08), 42 suggested as starting thread count. +3 iterations (42 th.) took 0.2399s; avg 0.07996s ( +/- 28.32/ 20.66 %); best 0.05731s; worst 0.09648s; std dev. 0.01657 (taking best). +Reference operation time is 0.057312 s (0.000349 Mflops) with 42 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz (tpop: 0.05731 Mflops: 0.000) +Merge (2 -> 1 leaves) took w.c.t. of 3.29e-05s, ~5.96e-06s of computing time (of which 0s sorting, 5.96e-06s analysis) +3 iterations (42 th.) took 9.06e-06s; avg 3.02e-06s ( +/- 98.75/200.00 %); best 3.775e-08s; worst 9.06e-06s; std dev. 4.271e-06 (taking best). +Reference operation time is 3.77536e-08 s (529.8 Mflops) with 42 threads. +After merge step 1: tpop: 3.775e-08 s ~Mflops: 529.751 nsubm:1 otn:42 +Applying merge (2 -> 1 leaves, 42 th.) yielded SPEEDUP of 1518054.942x: 0.05731s -> 3.775e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.05009s (of which 0.0003879s partitioning, 0s I/O); computing times: 5.96e-06s in par. loops, 0s sorting, 8.106e-06s analyzing) -Total merge + benchmarking process took 0.05009s, equivalent to 842626.8/3.1 new/old ops (0.09759s for 2 clones -- as 1641592.1/6.1 ops, or 820796.1/3.1 ops per clone), SPEEDUP of 269083.617x -Applying multi-merge (2 -> 1 leaves, 1 steps, 20 -> 20 th.sp.) yielded SPEEDUP of 269083.617x (0.016s -> 5.945e-08s), will amortize in 3.1 ops by saving 0.016s per op. -In 1 tuning rounds (tot. 0.15s, 0.098s for constructor, 2 clones) obtained a SPEEDUP of 26908261.7% (2.691e+05x) (from 0.00125 to 336.4 Mflops). -After 0.148031s, autotuning routine declared speedup of 269084 x, when using threads count of 20. -(5 x 5)[0x557202bac1e0]{D} @ (0(0..5),0(0..5)) (5 nnz, 1 nnz/r) flags 0x2040186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'' -After threads auto-tuning, 100 multiplications took 0.000042s -- further speedup of 45372.8 x +A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.1657s (of which 7.105e-05s partitioning, 0s I/O); computing times: 5.96e-06s in par. loops, 0s sorting, 5.96e-06s analyzing) +Total merge + benchmarking process took 0.1657s, equivalent to 4388594.9/2.9 new/old ops (0.3116s for 2 clones -- as 8252358.7/5.4 ops, or 4126179.3/2.7 ops per clone), SPEEDUP of 1518054.942x +Applying multi-merge (2 -> 1 leaves, 1 steps, 42 -> 42 th.sp.) yielded SPEEDUP of 1518054.942x (0.05731s -> 3.775e-08s), will amortize in 2.9 ops by saving 0.05731s per op. +In 1 tuning rounds (tot. 0.55s, 0.31s for constructor, 2 clones) obtained a SPEEDUP of 151805394.2% (1.518e+06x) (from 0.000349 to 529.8 Mflops). +After 0.551652s, autotuning routine declared speedup of 1.51805e+06 x, when using threads count of 42. +(5 x 5)[0x55bff865d590]{D} @ (0(0..5),0(0..5)) (5 nnz, 1 nnz/r) flags 0x2040186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'' +After threads auto-tuning, 100 multiplications took 0.000036s -- further speedup of 166557 x 0/2 0 0 -> 0 1/2 1 0 -> 5 0/2 0 3 -> 0 @@ -8356,7 +8421,7 @@ Correctly initialized the library. Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0x557202ba8b20]{D} @ (0(1..2),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' +(6 x 6)[0x55bff8659f60]{D} @ (0(1..2),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' Matrix printout: %%MatrixMarket matrix coordinate real general 6 6 1 @@ -8507,68 +8572,68 @@ Creating 500 x 500 matrix with 62500 nonzeroes. Building a matrix with 62500 nnz, 500 x 500 Duplicates check: 62500 - 0 = 62500 - converted COO to RSB in 3.161e-01 s (100.00 %) - analyzed arrays in 5.946e-02 s (18.81 %) - cleaned-up arrays in 2.160e-04 s (0.07 %) - deduplicated arrays in 2.220e-04 s (0.07 %) - sorted arrays in 1.361e-01 s (43.07 %) - shuffled partitions in 8.799e-02 s (27.83 %) - memory allocations took 1.040e-04 s (0.03 %) - leafs setup took 2.098e-05 s (0.01 %) - halfword conversion took 3.196e-02 s (10.11 %) -Built (500 x 500)[0x56147a9382d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 64, symflags:'' + converted COO to RSB in 4.295e-01 s (100.00 %) + analyzed arrays in 8.731e-02 s (20.33 %) + cleaned-up arrays in 6.604e-05 s (0.02 %) + deduplicated arrays in 1.211e-04 s (0.03 %) + sorted arrays in 1.509e-01 s (35.13 %) + shuffled partitions in 1.217e-01 s (28.34 %) + memory allocations took 7.510e-05 s (0.02 %) + leafs setup took 1.407e-05 s (0.00 %) + halfword conversion took 6.933e-02 s (16.14 %) +Built (500 x 500)[0x55cda11242d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 37, symflags:'' Allocated matrix of 62500 nonzeroes: -(500 x 500)[0x56147a9382d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 64, symflags:'' +(500 x 500)[0x55cda11242d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 37, symflags:'' -Before auto-tuning, 100 multiplications took 1.647625s. +Before auto-tuning, 100 multiplications took 5.365765s. Threads autotuning (may take more than 1.500000s)... -Will use autotuning routine to sample matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 87 subms, 64 lsubms, 2.1321 bpnz. +Will use autotuning routine to sample matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 51 subms, 37 lsubms, 2.0945 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=6.10471e-08), 20 suggested as starting thread count(default). -3 iterations (20 th.) took 0.05986s; avg 0.01995s ( +/- 20.19/ 40.34 %); best 0.01592s; worst 0.028s; std dev. 0.005691 (taking best). -Reference operation time is 0.015924 s (15.7 Mflops) with 20 threads. -3 iterations (20 th.) took 0.05594s; avg 0.01865s ( +/- 35.52/ 49.98 %); best 0.01202s; worst 0.02796s; std dev. 0.006781 (taking best). -Reference operation time is 0.012023 s (20.79 Mflops) with 20 threads. -After 0.116002s, autotuning routine did not find a better threads count configuration. -(500 x 500)[0x56147a9382d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 64, symflags:'' -After threads auto-tuning, 100 multiplications took 1.839923s -- effective speedup of 0.895486 x -Matrix autotuning (may take more than 1.500000s; using 20 threads )... -Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 87 subms, 64 lsubms, 2.1321 bpnz. +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.35574e-08), 42 suggested as starting thread count(default). +3 iterations (42 th.) took 0.112s; avg 0.03734s ( +/- 33.18/ 33.79 %); best 0.02495s; worst 0.04996s; std dev. 0.01021 (taking best). +Reference operation time is 0.0249481 s (10.02 Mflops) with 42 threads. +3 iterations (42 th.) took 0.1268s; avg 0.04227s ( +/- 28.05/ 28.48 %); best 0.03041s; worst 0.05431s; std dev. 0.009757 (taking best). +Reference operation time is 0.0304101 s (8.221 Mflops) with 42 threads. +After 0.238979s, autotuning routine did not find a better threads count configuration. +(500 x 500)[0x55cda11242d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 37, symflags:'' +After threads auto-tuning, 100 multiplications took 4.879605s -- effective speedup of 1.09963 x +Matrix autotuning (may take more than 1.500000s; using 42 threads )... +Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 51 subms, 37 lsubms, 2.0945 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=6.10471e-08), 20 suggested as starting thread count. -3 iterations (20 th.) took 0.05604s; avg 0.01868s ( +/- 14.04/ 27.65 %); best 0.01606s; worst 0.02385s; std dev. 0.003652 (taking best). -Reference operation time is 0.016058 s (15.57 Mflops) with 20 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 87 subms, 64 lsubms, 2.1321 bpnz (tpop: 0.01606 Mflops: 15.569) -Merge (64 -> 40 leaves) took w.c.t. of 0.0758s, ~0.3485s of computing time (of which 0.05568s sorting, 1.907e-05s analysis) -3 iterations (20 th.) took 0.09992s; avg 0.03331s ( +/- 28.09/ 19.88 %); best 0.02395s; worst 0.03993s; std dev. 0.006802 (taking best). -Reference operation time is 0.0239511 s (10.44 Mflops) with 20 threads. -After merge step 1: tpop: 0.02395 s ~Mflops: 10.438 nsubm:40 otn:20 -Applying merge (64 -> 40 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.492x: 0.01606s -> 0.02395s. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.35574e-08), 42 suggested as starting thread count. +3 iterations (42 th.) took 0.1432s; avg 0.04773s ( +/- 26.60/ 31.90 %); best 0.03503s; worst 0.06295s; std dev. 0.01154 (taking best). +Reference operation time is 0.0350292 s (7.137 Mflops) with 42 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 51 subms, 37 lsubms, 2.0945 bpnz (tpop: 0.03503 Mflops: 7.137) +Merge (37 -> 28 leaves) took w.c.t. of 0.02289s, ~0.01138s of computing time (of which 0.0001199s sorting, 1.311e-05s analysis) +3 iterations (42 th.) took 0.1569s; avg 0.05229s ( +/- 16.49/ 23.92 %); best 0.04367s; worst 0.0648s; std dev. 0.009053 (taking best). +Reference operation time is 0.043668 s (5.725 Mflops) with 42 threads. +After merge step 1: tpop: 0.04367 s ~Mflops: 5.725 nsubm:28 otn:42 +Applying merge (37 -> 28 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.247x: 0.03503s -> 0.04367s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (64 -> 40 subms) took 0.1758s (of which 0.07583s partitioning, 0s I/O); computing times: 0.3485s in par. loops, 0.05568s sorting, 1.907e-05s analyzing) -Total merge + benchmarking process took 0.1758s, equivalent to 10.9/10.9 new/old ops (0.04807s for 1 clones -- as 3.0/3.0 ops, or 3.0/3.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (37 -> 28 subms) took 0.1798s (of which 0.02291s partitioning, 0s I/O); computing times: 0.01138s in par. loops, 0.0001199s sorting, 1.311e-05s analyzing) +Total merge + benchmarking process took 0.1798s, equivalent to 5.1/5.1 new/old ops (0.1726s for 1 clones -- as 4.9/4.9 ops, or 4.9/4.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (20 th.) took 0.06006s; avg 0.02002s ( +/- 20.09/ 39.78 %); best 0.016s; worst 0.02798s; std dev. 0.005631 (taking best). -Reference operation time is 0.0159979 s (15.63 Mflops) with 20 threads. -Starting split (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 87 subms, 64 lsubms, 2.1321 bpnz (tpop: 0.016 Mflops: 15.627) -Split (64 -> 160 leaves, 87 -> 215 subms) took 0.02384s (of which: 1.502e-05s analysis, -5.57e+10s mem.mgmt); compute time: 0.005188s overall, 0.0003495s searches, 0.004839s shuffle, 0.002371s switch, 0.0005376s quadrants. -3 iterations (20 th.) took 0.0477s; avg 0.0159s ( +/- 24.60/ 48.99 %); best 0.01199s; worst 0.02369s; std dev. 0.005509 (taking best). -Reference operation time is 0.0119889 s (20.85 Mflops) with 20 threads. -After split step 1: tpop: 0.01199 s ~Mflops: 20.853 nsubm:160 otn:20 -Applying split (64 -> 160 leaves, 20 th.) yielded SPEEDUP of 1.334x: 0.016s -> 0.01199s, so taking this instance. -Split (160 -> 400 leaves, 215 -> 535 subms) took 0.05169s (of which: 3.29e-05s analysis, -1.392e+11s mem.mgmt); compute time: 0.009854s overall, 0.0004878s searches, 0.009366s shuffle, 0.003468s switch, 0.001592s quadrants. -3 iterations (20 th.) took 0.07957s; avg 0.02652s ( +/- 9.58/ 19.13 %); best 0.02398s; worst 0.0316s; std dev. 0.003587 (taking best). -Reference operation time is 0.0239811 s (10.42 Mflops) with 20 threads. -After split step 2: tpop: 0.02398 s ~Mflops: 10.425 nsubm:400 otn:20 -Applying split (160 -> 400 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.000x: 0.01199s -> 0.02398s. +3 iterations (42 th.) took 0.1839s; avg 0.06129s ( +/- 19.03/ 20.63 %); best 0.04963s; worst 0.07394s; std dev. 0.009949 (taking best). +Reference operation time is 0.0496309 s (5.037 Mflops) with 42 threads. +Starting split (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 51 subms, 37 lsubms, 2.0945 bpnz (tpop: 0.04963 Mflops: 5.037) +Split (37 -> 91 leaves, 51 -> 123 subms) took 0.02947s (of which: 1.001e-05s analysis, -3.195e+10s mem.mgmt); compute time: 0.001414s overall, 0.0003605s searches, 0.001054s shuffle, 0.0005782s switch, 2.313e-05s quadrants. +3 iterations (42 th.) took 0.09925s; avg 0.03308s ( +/- 23.55/ 29.66 %); best 0.02529s; worst 0.0429s; std dev. 0.007327 (taking best). +Reference operation time is 0.0252919 s (9.885 Mflops) with 42 threads. +After split step 1: tpop: 0.02529 s ~Mflops: 9.885 nsubm:91 otn:42 +Applying split (37 -> 91 leaves, 42 th.) yielded SPEEDUP of 1.962x: 0.04963s -> 0.02529s, so taking this instance. +Split (91 -> 226 leaves, 123 -> 303 subms) took 0.083s (of which: 1.812e-05s analysis, -7.988e+10s mem.mgmt); compute time: 0.003034s overall, 0.0002272s searches, 0.002807s shuffle, 0.001532s switch, 0.0002475s quadrants. +3 iterations (42 th.) took 0.1331s; avg 0.04437s ( +/- 10.20/ 19.33 %); best 0.03985s; worst 0.05295s; std dev. 0.006067 (taking best). +Reference operation time is 0.0398469 s (6.274 Mflops) with 42 threads. +After split step 2: tpop: 0.03985 s ~Mflops: 6.274 nsubm:226 otn:42 +Applying split (91 -> 226 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.575x: 0.02529s -> 0.03985s. Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 2 split steps (of max 6) (64 -> 400 subms) took 0.2519s (of which 0.07657s partitioning, 0s I/O); computing times: 0.01504s in par. loops, 0.0008373s sorting, 4.792e-05s analyzing) -Total split + benchmarking process took 0.2519s, equivalent to 21.0/15.7 new/old ops (0.1278s for 2 clones -- as 10.7/8.0 ops, or 5.3/4.0 ops per clone), SPEEDUP of 1.334x -Applying multi-split (64 -> 160 leaves, 1 steps, 20 -> 20 th.sp.) yielded SPEEDUP of 1.334x (0.016s -> 0.01199s), will amortize in 62.8 ops by saving 0.004009s per op. -In 1 tuning rounds (tot. 0.67s, 0.18s for constructor, 3 clones) obtained a SPEEDUP of 33.4% (1.334x) (from 15.63 to 20.85 Mflops). -After 0.672408s, autotuning routine declared speedup of 1.33439 x, when using threads count of 20. -(500 x 500)[0x56147aa40bf0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 160, symflags:'' -After threads auto-tuning, 100 multiplications took 2.011583s -- further speedup of 0.914664 x +A total of 2 split steps (of max 6) (37 -> 226 subms) took 0.4316s (of which 0.1131s partitioning, 0s I/O); computing times: 0.004449s in par. loops, 0.0005877s sorting, 2.813e-05s analyzing) +Total split + benchmarking process took 0.4316s, equivalent to 17.1/8.7 new/old ops (3.441s for 2 clones -- as 136.1/69.3 ops, or 68.0/34.7 ops per clone), SPEEDUP of 1.962x +Applying multi-split (37 -> 91 leaves, 1 steps, 42 -> 42 th.sp.) yielded SPEEDUP of 1.962x (0.04963s -> 0.02529s), will amortize in 17.7 ops by saving 0.02434s per op. +In 1 tuning rounds (tot. 4.5s, 3.6s for constructor, 3 clones) obtained a SPEEDUP of 96.2% (1.962x) (from 5.037 to 9.885 Mflops). +After 4.467205s, autotuning routine declared speedup of 1.96232 x, when using threads count of 42. +(500 x 500)[0x55cda122a0a0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 91, symflags:'' +After threads auto-tuning, 100 multiplications took 4.239009s -- further speedup of 1.15112 x librsb timer-based profiling is not supported in this build. If you wish to have it, re-configure librsb with its support. So you can safely ignore the error you might just have seen printed out on screen. /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/backsolve Hello, RSB! @@ -8576,19 +8641,19 @@ Correctly initialized the library. Building a matrix with 7 nnz, 6 x 6 Duplicates check: 1 - 0 = 1 - converted COO to RSB in 1.022e-01 s (100.00 %) - analyzed arrays in 6.947e-02 s (67.96 %) - cleaned-up arrays in 7.868e-06 s (0.01 %) - deduplicated arrays in 1.907e-06 s (0.00 %) - sorted arrays in 2.146e-06 s (0.00 %) - shuffled partitions in 3.267e-02 s (31.96 %) - memory allocations took 3.099e-05 s (0.03 %) - leafs setup took 1.216e-05 s (0.01 %) - halfword conversion took 1.597e-05 s (0.02 %) -Built (6 x 6)[0x565088ca64d0]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' + converted COO to RSB in 1.446e-01 s (100.00 %) + analyzed arrays in 8.823e-02 s (61.00 %) + cleaned-up arrays in 8.106e-06 s (0.01 %) + deduplicated arrays in 9.537e-07 s (0.00 %) + sorted arrays in 3.099e-06 s (0.00 %) + shuffled partitions in 5.634e-02 s (38.95 %) + memory allocations took 3.076e-05 s (0.02 %) + leafs setup took 9.060e-06 s (0.01 %) + halfword conversion took 1.192e-05 s (0.01 %) +Built (6 x 6)[0x55dd365474d0]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0x565088ca64d0]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' +(6 x 6)[0x55dd365474d0]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' Matrix printout: %%MatrixMarket matrix coordinate real general 6 6 1 @@ -8614,55 +8679,55 @@ 1 1 Will autotune matrix: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:5.85e-08 -3 iterations (20 th.) took 4.101e-05s; avg 1.367e-05s ( +/- 99.57/193.02 %); best 5.85e-08s; worst 4.005e-05s; std dev. 1.866e-05 (taking best). -Reference operation time is 5.8496e-08 s (34.19 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 5.85e-08 Mflops: 34.190) +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:4.481e-08 +3 iterations (42 th.) took 4.196e-05s; avg 1.399e-05s ( +/- 99.68/193.18 %); best 4.481e-08s; worst 4.101e-05s; std dev. 1.911e-05 (taking best). +Reference operation time is 4.48108e-08 s (44.63 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 4.481e-08 Mflops: 44.632) Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) -3 iterations (20 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 90.80/ 50.00 %); best 5.85e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.8496e-08 s (34.19 Mflops) with 20 threads. -After merge step 1: tpop: 5.85e-08 s ~Mflops: 34.190 nsubm:1 otn:20 -Applying merge (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 5.85e-08s -> 5.85e-08s, so IGNORING this instance. +3 iterations (42 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 85.90/200.00 %); best 4.481e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 4.48108e-08 s (44.63 Mflops) with 42 threads. +After merge step 1: tpop: 4.481e-08 s ~Mflops: 44.632 nsubm:1 otn:42 +Applying merge (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 4.481e-08s -> 4.481e-08s, so IGNORING this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (1 -> 1 subms) took 1.788e-05s (of which 5.007e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 1.788e-05s, equivalent to 305.7/305.7 new/old ops (0.07108s for 1 clones -- as 1215076.4/1215076.4 ops, or 1215076.4/1215076.4 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (1 -> 1 subms) took 1.788e-05s (of which 4.053e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 1.788e-05s, equivalent to 399.0/399.0 new/old ops (0.1245s for 1 clones -- as 2777903.7/2777903.7 ops, or 2777903.7/2777903.7 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (20 th.) took 1.788e-05s; avg 5.96e-06s ( +/- 99.02/184.00 %); best 5.85e-08s; worst 1.693e-05s; std dev. 7.765e-06 (taking best). -Reference operation time is 5.8496e-08 s (34.19 Mflops) with 20 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 5.85e-08 Mflops: 34.190) -Split (1 -> 1 leaves, 1 -> 1 subms) took 3.695e-05s (of which: 6.914e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (20 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 90.80/ 50.00 %); best 5.85e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.8496e-08 s (34.19 Mflops) with 20 threads. -After split step 1: tpop: 5.85e-08 s ~Mflops: 34.190 nsubm:1 otn:20 -Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 5.85e-08s -> 5.85e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 3.815e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (20 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 91.82/ 66.67 %); best 5.85e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). -Reference operation time is 5.8496e-08 s (34.19 Mflops) with 20 threads. -After split step 2: tpop: 5.85e-08 s ~Mflops: 34.190 nsubm:1 otn:20 -Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 5.85e-08s -> 5.85e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 3.815e-06s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (20 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 90.80/ 50.00 %); best 5.85e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.8496e-08 s (34.19 Mflops) with 20 threads. -After split step 3: tpop: 5.85e-08 s ~Mflops: 34.190 nsubm:1 otn:20 -Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 5.85e-08s -> 5.85e-08s, so IGNORING this instance. +3 iterations (42 th.) took 1.407e-05s; avg 4.689e-06s ( +/- 99.04/179.66 %); best 4.481e-08s; worst 1.311e-05s; std dev. 5.969e-06 (taking best). +Reference operation time is 4.48108e-08 s (44.63 Mflops) with 42 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 4.481e-08 Mflops: 44.632) +Split (1 -> 1 leaves, 1 -> 1 subms) took 3.29e-05s (of which: 6.199e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (42 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.73/200.00 %); best 4.481e-08s; worst 2.146e-06s; std dev. 1.012e-06 (taking best). +Reference operation time is 4.48108e-08 s (44.63 Mflops) with 42 threads. +After split step 1: tpop: 4.481e-08 s ~Mflops: 44.632 nsubm:1 otn:42 +Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 4.481e-08s -> 4.481e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 3.099e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (42 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.68/129.41 %); best 4.481e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 4.48108e-08 s (44.63 Mflops) with 42 threads. +After split step 2: tpop: 4.481e-08 s ~Mflops: 44.632 nsubm:1 otn:42 +Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 4.481e-08s -> 4.481e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 8.106e-06s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (42 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 88.72/200.00 %); best 4.481e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). +Reference operation time is 4.48108e-08 s (44.63 Mflops) with 42 threads. +After split step 3: tpop: 4.481e-08 s ~Mflops: 44.632 nsubm:1 otn:42 +Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 4.481e-08s -> 4.481e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 3.099e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (42 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 85.90/200.00 %); best 4.481e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 4.48108e-08 s (44.63 Mflops) with 42 threads. +After split step 4: tpop: 4.481e-08 s ~Mflops: 44.632 nsubm:1 otn:42 +Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 4.481e-08s -> 4.481e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 1.907e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (42 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 85.90/200.00 %); best 4.481e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 4.48108e-08 s (44.63 Mflops) with 42 threads. +After split step 5: tpop: 4.481e-08 s ~Mflops: 44.632 nsubm:1 otn:42 +Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 4.481e-08s -> 4.481e-08s, so IGNORING this instance. Split (1 -> 1 leaves, 1 -> 1 subms) took 3.099e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (20 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 81.60/200.00 %); best 5.85e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.8496e-08 s (34.19 Mflops) with 20 threads. -After split step 4: tpop: 5.85e-08 s ~Mflops: 34.190 nsubm:1 otn:20 -Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 5.85e-08s -> 5.85e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 4.053e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (20 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 91.82/ 66.67 %); best 5.85e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). -Reference operation time is 5.8496e-08 s (34.19 Mflops) with 20 threads. -After split step 5: tpop: 5.85e-08 s ~Mflops: 34.190 nsubm:1 otn:20 -Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 5.85e-08s -> 5.85e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 2.861e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (20 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 90.80/ 50.00 %); best 5.85e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.8496e-08 s (34.19 Mflops) with 20 threads. -After split step 6: tpop: 5.85e-08 s ~Mflops: 34.190 nsubm:1 otn:20 -Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 5.85e-08s -> 5.85e-08s, so IGNORING this instance. -A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.0005479s (of which 9.561e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 7.868e-06s analyzing) -Total split + benchmarking process took 0.0005479s, equivalent to 9366.2/9366.2 new/old ops (0.04786s for 1 clones -- as 818259.6/818259.6 ops, or 818259.6/818259.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.12s, 0.12s for constructor, 2 clones) obtained NO speedup (best stays 34.19 Mflops). +3 iterations (42 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 85.90/200.00 %); best 4.481e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 4.48108e-08 s (44.63 Mflops) with 42 threads. +After split step 6: tpop: 4.481e-08 s ~Mflops: 44.632 nsubm:1 otn:42 +Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 4.481e-08s -> 4.481e-08s, so IGNORING this instance. +A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.000582s (of which 0.0005074s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 7.153e-06s analyzing) +Total split + benchmarking process took 0.000582s, equivalent to 12987.5/12987.5 new/old ops (0.1124s for 1 clones -- as 2509060.9/2509060.9 ops, or 2509060.9/2509060.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.24s, 0.24s for constructor, 2 clones) obtained NO speedup (best stays 44.63 Mflops). Backsolving we should get a unitary vector: %%MatrixMarket matrix array real general @@ -8697,124 +8762,298 @@ /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran Building a matrix with 210 nnz, 20 x 20 Duplicates check: 210 - 0 = 210 - converted COO to RSB in 1.322e-01 s (100.00 %) - analyzed arrays in 4.794e-02 s (36.25 %) + converted COO to RSB in 2.387e+00 s (100.00 %) + analyzed arrays in 2.108e+00 s (88.33 %) cleaned-up arrays in 3.099e-06 s (0.00 %) deduplicated arrays in 4.053e-06 s (0.00 %) - sorted arrays in 2.022e-02 s (15.29 %) - shuffled partitions in 3.202e-02 s (24.21 %) - memory allocations took 6.390e-05 s (0.05 %) - leafs setup took 1.621e-05 s (0.01 %) - halfword conversion took 3.196e-02 s (24.17 %) -Built (20 x 20)[0x55a92d0379f0]{D} @ (0(0..0),0(0..0)) (210 nnz, 10 nnz/r) flags 0x2446396 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'LS' + sorted arrays in 4.238e-02 s (1.78 %) + shuffled partitions in 1.096e-01 s (4.59 %) + memory allocations took 5.317e-05 s (0.00 %) + leafs setup took 1.383e-05 s (0.00 %) + halfword conversion took 1.264e-01 s (5.30 %) +Built (20 x 20)[0x555aa3d689f0]{D} @ (0(0..0),0(0..0)) (210 nnz, 10 nnz/r) flags 0x2446396 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'LS' Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:6.125e-08 -Starting autotuning (16 x 6.12497e-08 s stages, transA=N, nrhs=1, timer gran.=6.12497e-08), 20 suggested as starting thread count(default). -3 iterations (20 th.) took 0.05996s; avg 0.01999s ( +/- 19.97/ 39.90 %); best 0.016s; worst 0.02796s; std dev. 0.00564 (taking best). -Reference operation time is 0.015995 s (0.05252 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.016 Mflops: 0.053) -Merge (22 -> 16 leaves) took w.c.t. of 0.01869s, ~0.02687s of computing time (of which 5.96e-06s sorting, 1.407e-05s analysis) -3 iterations (20 th.) took 0.1474s; avg 0.04913s ( +/- 31.50/ 49.29 %); best 0.03365s; worst 0.07335s; std dev. 0.01734 (taking best). -Reference operation time is 0.033653 s (0.02496 Mflops) with 20 threads. -After merge step 1: tpop: 0.03365 s ~Mflops: 0.025 nsubm:16 otn:20 -Applying merge (22 -> 16 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.104x: 0.016s -> 0.03365s. -Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.1662s (of which 0.01871s partitioning, 0s I/O); computing times: 0.02687s in par. loops, 5.96e-06s sorting, 1.407e-05s analyzing) -Total merge + benchmarking process took 0.1662s, equivalent to 10.4/10.4 new/old ops (0.04786s for 1 clones -- as 3.0/3.0 ops, or 3.0/3.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (20 th.) took 0.08794s; avg 0.02931s ( +/- 22.00/ 12.87 %); best 0.02286s; worst 0.03309s; std dev. 0.004582 (taking best). -Reference operation time is 0.0228639 s (0.03674 Mflops) with 20 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.02286 Mflops: 0.037) -Split (22 -> 51 leaves, 30 -> 70 subms) took 0.05995s (of which: 8.821e-06s analysis, -1.915e+10s mem.mgmt); compute time: 0.1757s overall, 3.266e-05s searches, 0.1756s shuffle, 0.1748s switch, 4.84e-05s quadrants. -3 iterations (20 th.) took 0.1039s; avg 0.03462s ( +/- 19.20/ 15.50 %); best 0.02798s; worst 0.03999s; std dev. 0.004987 (taking best). -Reference operation time is 0.0279772 s (0.03002 Mflops) with 20 threads. -After split step 1: tpop: 0.02798 s ~Mflops: 0.030 nsubm:51 otn:20 -Applying split (22 -> 51 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.224x: 0.02286s -> 0.02798s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 split steps (of max 6) (22 -> 51 subms) took 0.164s (of which 0.0601s partitioning, 0s I/O); computing times: 0.1757s in par. loops, 3.266e-05s sorting, 8.821e-06s analyzing) -Total split + benchmarking process took 0.164s, equivalent to 7.2/7.2 new/old ops (0.09382s for 1 clones -- as 4.1/4.1 ops, or 4.1/4.1 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.62s, 0.14s for constructor, 2 clones) obtained NO speedup (best stays 0.03674 Mflops). - autotuner chose 20 threads -Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:6.125e-08 -Starting autotuning (16 x 6.12497e-08 s stages, transA=N, nrhs=1, timer gran.=6.12497e-08), 20 suggested as starting thread count(default). -3 iterations (20 th.) took 0.04413s; avg 0.01471s ( +/- 68.96/ 63.94 %); best 0.004566s; worst 0.02411s; std dev. 0.007997 (taking best). -~ 20 threads: 0.004566s (0.18 Mflops) (0/2 degradations so far) - -3 iterations (19 th.) took 0.04783s; avg 0.01594s ( +/- 51.00/ 50.64 %); best 0.007811s; worst 0.02401s; std dev. 0.006615 (taking best). - 19 threads: 0.007811s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (18 th.) took 0.07283s; avg 0.02428s ( +/- 33.81/ 18.89 %); best 0.01607s; worst 0.02886s; std dev. 0.005817 (taking best). - 18 threads: 0.01607s (0.052 Mflops) (2/2 degradations so far) - -Best threads choice is 20; starting threads were 20; max speed gap is 3.5x; search took 0.16s. -Starting merge (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.004566 Mflops: 0.184) -Merge (22 -> 16 leaves) took w.c.t. of 0.01522s, ~5.817e-05s of computing time (of which 5.96e-06s sorting, 9.06e-06s analysis) -3 iterations (20 th.) took 0.1158s; avg 0.03861s ( +/- 58.55/ 75.68 %); best 0.016s; worst 0.06783s; std dev. 0.02167 (taking best). -~ 20 threads: 0.016s (0.052 Mflops) (0/2 degradations so far) - -3 iterations (19 th.) took 0.07997s; avg 0.02666s ( +/- 39.94/ 20.06 %); best 0.01601s; worst 0.032s; std dev. 0.007528 (taking best). - 19 threads: 0.01601s (0.052 Mflops) (1/2 degradations so far) - -3 iterations (18 th.) took 0.07996s; avg 0.02665s ( +/- 40.23/ 20.12 %); best 0.01593s; worst 0.03201s; std dev. 0.007581 (taking best). - 18 threads: 0.01593s (0.053 Mflops) (0/2 degradations so far) - -3 iterations (17 th.) took 0.08395s; avg 0.02798s ( +/- 42.33/ 27.98 %); best 0.01614s; worst 0.03581s; std dev. 0.008519 (taking best). - 17 threads: 0.01614s (0.052 Mflops) (1/2 degradations so far) - -3 iterations (16 th.) took 0.09596s; avg 0.03199s ( +/- 0.07/ 0.09 %); best 0.03197s; worst 0.03202s; std dev. 2.098e-05 (taking best). - 16 threads: 0.03197s (0.026 Mflops) (2/2 degradations so far) - -Best threads choice is 18; starting threads were 20; max speed gap is 2x; search took 0.46s. -After merge step 1: tpop: 0.01593 s ~Mflops: 0.053 nsubm:16 otn:18 -Applying merge (22 -> 16 leaves, 18 th.) yielded SLOWDOWN (1th of 3 tolerable) of 3.489x: 0.004566s -> 0.01593s. -Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.4711s (of which 0.01524s partitioning, 0s I/O); computing times: 5.817e-05s in par. loops, 5.96e-06s sorting, 9.06e-06s analyzing) -Total merge + benchmarking process took 0.4711s, equivalent to 103.2/103.2 new/old ops (0.07593s for 1 clones -- as 16.6/16.6 ops, or 16.6/16.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:4.42e-08 +Starting autotuning (16 x 4.42028e-08 s stages, transA=N, nrhs=1, timer gran.=4.42028e-08), 42 suggested as starting thread count(default). +3 iterations (42 th.) took 0.1845s; avg 0.06149s ( +/- 31.55/ 39.26 %); best 0.04209s; worst 0.08563s; std dev. 0.01809 (taking best). +Reference operation time is 0.0420902 s (0.01996 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.04209 Mflops: 0.020) +Merge (22 -> 16 leaves) took w.c.t. of 0.04352s, ~0.000107s of computing time (of which 5.007e-06s sorting, 1.287e-05s analysis) +3 iterations (42 th.) took 0.1191s; avg 0.03969s ( +/- 9.92/ 8.88 %); best 0.03575s; worst 0.04322s; std dev. 0.003062 (taking best). +Reference operation time is 0.0357528 s (0.02349 Mflops) with 42 threads. +After merge step 1: tpop: 0.03575 s ~Mflops: 0.023 nsubm:16 otn:42 +Applying merge (22 -> 16 leaves, 42 th.) yielded SPEEDUP of 1.177x: 0.04209s -> 0.03575s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.02001s, ~4.125e-05s of computing time (of which 4.053e-06s sorting, 1.287e-05s analysis) +3 iterations (42 th.) took 0.1646s; avg 0.05488s ( +/- 35.28/ 51.13 %); best 0.03552s; worst 0.08294s; std dev. 0.02031 (taking best). +Reference operation time is 0.0355189 s (0.02365 Mflops) with 42 threads. +After merge step 2: tpop: 0.03552 s ~Mflops: 0.024 nsubm:10 otn:42 +Applying merge (16 -> 10 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00658x): 0.03575s -> 0.03552s, so IGNORING this instance. +Merge (10 -> 8 leaves) took w.c.t. of 3.886e-05s, ~1.287e-05s of computing time (of which 3.099e-06s sorting, 1.097e-05s analysis) +3 iterations (42 th.) took 0.1392s; avg 0.0464s ( +/- 17.80/ 16.20 %); best 0.03814s; worst 0.05391s; std dev. 0.006461 (taking best). +Reference operation time is 0.0381401 s (0.02202 Mflops) with 42 threads. +After merge step 3: tpop: 0.03814 s ~Mflops: 0.022 nsubm:8 otn:42 +Applying merge (10 -> 8 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.067x: 0.03575s -> 0.03814s. +Merge (8 -> 6 leaves) took w.c.t. of 4.601e-05s, ~1.311e-05s of computing time (of which 1.907e-06s sorting, 1.001e-05s analysis) +3 iterations (42 th.) took 0.1334s; avg 0.04448s ( +/- 23.23/ 20.50 %); best 0.03415s; worst 0.0536s; std dev. 0.007987 (taking best). +Reference operation time is 0.0341458 s (0.0246 Mflops) with 42 threads. +After merge step 4: tpop: 0.03415 s ~Mflops: 0.025 nsubm:6 otn:42 +Applying merge (8 -> 6 leaves, 42 th.) yielded SPEEDUP of 1.047x: 0.03575s -> 0.03415s, so taking this instance. +Merge (6 -> 3 leaves) took w.c.t. of 3.6e-05s, ~1.407e-05s of computing time (of which 2.861e-06s sorting, 7.153e-06s analysis) +3 iterations (42 th.) took 0.1464s; avg 0.04881s ( +/- 17.10/ 17.76 %); best 0.04047s; worst 0.05748s; std dev. 0.006951 (taking best). +Reference operation time is 0.040467 s (0.02076 Mflops) with 42 threads. +After merge step 5: tpop: 0.04047 s ~Mflops: 0.021 nsubm:3 otn:42 +Applying merge (6 -> 3 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.185x: 0.03415s -> 0.04047s. +Merge (3 -> 1 leaves) took w.c.t. of 3.719e-05s, ~1.597e-05s of computing time (of which 4.053e-06s sorting, 6.914e-06s analysis) +3 iterations (42 th.) took 1.097e-05s; avg 3.656e-06s ( +/- 98.79/173.91 %); best 4.42e-08s; worst 1.001e-05s; std dev. 4.512e-06 (taking best). +Reference operation time is 4.42028e-08 s (1.9e+04 Mflops) with 42 threads. +After merge step 6: tpop: 4.42e-08 s ~Mflops: 19003.319 nsubm:1 otn:42 +Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 772481.122x: 0.03415s -> 4.42e-08s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 6 merge steps (of max 6) (22 -> 1 subms) took 1.302s (of which 0.06377s partitioning, 0s I/O); computing times: 0.0002043s in par. loops, 2.098e-05s sorting, 6.08e-05s analyzing) +Total merge + benchmarking process took 1.302s, equivalent to 29461521.0/30.9 new/old ops (0.6848s for 4 clones -- as 15491936.4/16.3 ops, or 3872984.1/4.1 ops per clone), SPEEDUP of 952206.041x +Applying multi-merge (22 -> 1 leaves, 6 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 952206.041x (0.04209s -> 4.42e-08s), will amortize in 30.9 ops by saving 0.04209s per op. +In 1 tuning rounds (tot. 1.6s, 0.68s for constructor, 4 clones) obtained a SPEEDUP of 95220504.1% (9.522e+05x) (from 0.01996 to 1.9e+04 Mflops). + autotuner chose 42 threads +Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 1 subms, 1 lsubms, 2.4000 bpnz. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:4.42e-08 +Starting autotuning (16 x 4.42028e-08 s stages, transA=N, nrhs=1, timer gran.=4.42028e-08), 42 suggested as starting thread count(default). +3 iterations (42 th.) took 1.502e-05s; avg 5.007e-06s ( +/- 80.95/161.90 %); best 9.537e-07s; worst 1.311e-05s; std dev. 5.732e-06 (taking best). +~ 42 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (41 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 41 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (40 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). + 40 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (39 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 39 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (38 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 38 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (37 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). + 37 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (36 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 36 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (35 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). + 35 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (34 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 34 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (33 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). + 33 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (32 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 32 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (31 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 31 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (30 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 30 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (29 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 29 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (28 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 28 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (27 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 27 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (26 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 26 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (25 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 25 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (24 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 29.41/ 41.18 %); best 9.537e-07s; worst 1.907e-06s; std dev. 4.052e-07 (taking best). + 24 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (23 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 23 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (22 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 22 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (21 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 21 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (20 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 20 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). + 19 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (18 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). + 18 threads: 9.537e-07s (8.8e+02 Mflops) (2/2 degradations so far) - +Best threads choice is 41; starting threads were 42; max speed gap is 22x; search took 0.00024s. +Starting merge (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 1 subms, 1 lsubms, 2.4000 bpnz (tpop: 4.42e-08 Mflops: 19003.319) +Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) +3 iterations (42 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +~ 42 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (41 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 41 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (40 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 40 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (39 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). + 39 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (38 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 38 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (37 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 37 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (36 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 36 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (35 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 35 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (34 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 34 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (33 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 33 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (32 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 32 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (31 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 31 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (30 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 30 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (29 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 29 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (28 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 28 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (27 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 27 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (26 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 26 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (25 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 25 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (24 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 24 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (23 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). + 23 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (22 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 22 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (21 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 21 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (20 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 20 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 19 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (18 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 18 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (17 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 17 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (16 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 16 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (15 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 15 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (14 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 14 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (13 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 13 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (12 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 12 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 11 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 10 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 9 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (8 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 8 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (7 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 7 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (6 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 6 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (5 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 5 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (4 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 4 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (3 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 3 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (2 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). + 2 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (1 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 1 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +Best threads choice is 42; starting threads were 42; max speed gap is 22x; search took 0.0003s. +After merge step 1: tpop: 4.42e-08 s ~Mflops: 19003.319 nsubm:1 otn:42 +Applying merge (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 4.42e-08s -> 4.42e-08s, so IGNORING this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 1 merge steps (of max 6) (1 -> 1 subms) took 0.0003119s (of which 2.861e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 0.0003119s, equivalent to 7055.0/7055.0 new/old ops (0.1615s for 1 clones -- as 3653047.5/3653047.5 ops, or 3653047.5/3653047.5 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (20 th.) took 0.07591s; avg 0.0253s ( +/- 36.69/ 26.36 %); best 0.01602s; worst 0.03197s; std dev. 0.00677 (taking best). -~ 20 threads: 0.01602s (0.052 Mflops) (0/2 degradations so far) - -3 iterations (19 th.) took 0.064s; avg 0.02133s ( +/- 25.00/ 49.76 %); best 0.016s; worst 0.03195s; std dev. 0.007506 (taking best). - 19 threads: 0.016s (0.052 Mflops) (0/2 degradations so far) - -3 iterations (18 th.) took 0.07992s; avg 0.02664s ( +/- 39.89/ 20.10 %); best 0.01601s; worst 0.03199s; std dev. 0.007515 (taking best). - 18 threads: 0.01601s (0.052 Mflops) (1/2 degradations so far) - -3 iterations (17 th.) took 0.06397s; avg 0.02132s ( +/- 25.03/ 49.82 %); best 0.01599s; worst 0.03195s; std dev. 0.007513 (taking best). - 17 threads: 0.01599s (0.053 Mflops) (0/2 degradations so far) - -3 iterations (16 th.) took 0.07444s; avg 0.02481s ( +/- 35.35/ 28.63 %); best 0.01604s; worst 0.03192s; std dev. 0.006588 (taking best). - 16 threads: 0.01604s (0.052 Mflops) (1/2 degradations so far) - -3 iterations (15 th.) took 0.08915s; avg 0.02972s ( +/- 42.19/ 34.97 %); best 0.01718s; worst 0.04011s; std dev. 0.009483 (taking best). - 15 threads: 0.01718s (0.049 Mflops) (2/2 degradations so far) - -Best threads choice is 17; starting threads were 20; max speed gap is 1.1x; search took 0.45s. -Starting split (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.01599 Mflops: 0.053) -Split (22 -> 51 leaves, 30 -> 70 subms) took 0.02392s (of which: 9.775e-06s analysis, -1.915e+10s mem.mgmt); compute time: 0.0004642s overall, 3.29e-05s searches, 0.0004313s shuffle, 0.0001502s switch, 4.816e-05s quadrants. -3 iterations (20 th.) took 0.09594s; avg 0.03198s ( +/- 37.67/ 37.52 %); best 0.01993s; worst 0.04398s; std dev. 0.009817 (taking best). -~ 20 threads: 0.01993s (0.042 Mflops) (0/2 degradations so far) - -3 iterations (19 th.) took 0.07198s; avg 0.02399s ( +/- 0.25/ 0.24 %); best 0.02393s; worst 0.02405s; std dev. 4.782e-05 (taking best). - 19 threads: 0.02393s (0.035 Mflops) (1/2 degradations so far) - -3 iterations (18 th.) took 0.1039s; avg 0.03463s ( +/- 7.86/ 3.97 %); best 0.0319s; worst 0.036s; std dev. 0.001925 (taking best). - 18 threads: 0.0319s (0.026 Mflops) (2/2 degradations so far) - -Best threads choice is 20; starting threads were 20; max speed gap is 1.6x; search took 0.27s. -After split step 1: tpop: 0.01993 s ~Mflops: 0.042 nsubm:51 otn:20 -Applying split (22 -> 51 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.247x: 0.01599s -> 0.01993s. +3 iterations (42 th.) took 1.407e-05s; avg 4.689e-06s ( +/- 79.66/154.24 %); best 9.537e-07s; worst 1.192e-05s; std dev. 5.115e-06 (taking best). +~ 42 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (41 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 41 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (40 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 40 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (39 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). + 39 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (38 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 38 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (37 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 37 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (36 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 36 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (35 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 35 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (34 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 34 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (33 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 33 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (32 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 32 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (31 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 31 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (30 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 30 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (29 th.) took 2.003e-05s; avg 6.676e-06s ( +/- 85.71/167.86 %); best 9.537e-07s; worst 1.788e-05s; std dev. 7.924e-06 (taking best). + 29 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (28 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 95.72/ 84.62 %); best 4.42e-08s; worst 1.907e-06s; std dev. 7.867e-07 (taking best). + 28 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (27 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 27 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (26 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 26 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (25 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 93.82/ 66.67 %); best 4.42e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 25 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (24 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 24 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (23 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 93.05/ 50.00 %); best 4.42e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 23 threads: 4.42e-08s (1.9e+04 Mflops) (0/2 degradations so far) - +3 iterations (22 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). + 22 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (21 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). + 21 threads: 9.537e-07s (8.8e+02 Mflops) (2/2 degradations so far) - +Best threads choice is 41; starting threads were 42; max speed gap is 22x; search took 0.00024s. +Starting split (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 1 subms, 1 lsubms, 2.4000 bpnz (tpop: 4.42e-08 Mflops: 19003.319) +Split (1 -> 3 leaves, 1 -> 4 subms) took 5.388e-05s (of which: 5.007e-06s analysis, -1.775e+09s mem.mgmt); compute time: 2.313e-05s overall, 4.053e-06s searches, 1.907e-05s shuffle, 8.106e-06s switch, 9.537e-07s quadrants. +3 iterations (42 th.) took 0.1892s; avg 0.06308s ( +/- 3.00/ 2.34 %); best 0.06119s; worst 0.06456s; std dev. 0.001406 (taking best). +~ 42 threads: 0.06119s (0.014 Mflops) (0/2 degradations so far) - +3 iterations (41 th.) took 0.1786s; avg 0.05955s ( +/- 13.41/ 22.20 %); best 0.05156s; worst 0.07277s; std dev. 0.009416 (taking best). + 41 threads: 0.05156s (0.016 Mflops) (0/2 degradations so far) - +3 iterations (40 th.) took 0.198s; avg 0.06601s ( +/- 24.03/ 18.54 %); best 0.05015s; worst 0.07825s; std dev. 0.01175 (taking best). + 40 threads: 0.05015s (0.017 Mflops) (0/2 degradations so far) - +3 iterations (39 th.) took 0.1451s; avg 0.04836s ( +/- 5.96/ 11.11 %); best 0.04548s; worst 0.05373s; std dev. 0.003801 (taking best). + 39 threads: 0.04548s (0.018 Mflops) (0/2 degradations so far) - +3 iterations (38 th.) took 0.1843s; avg 0.06143s ( +/- 22.05/ 15.66 %); best 0.04788s; worst 0.07105s; std dev. 0.009857 (taking best). + 38 threads: 0.04788s (0.018 Mflops) (1/2 degradations so far) - +3 iterations (37 th.) took 0.1683s; avg 0.0561s ( +/- 27.92/ 14.10 %); best 0.04044s; worst 0.06401s; std dev. 0.01107 (taking best). + 37 threads: 0.04044s (0.021 Mflops) (0/2 degradations so far) - +3 iterations (36 th.) took 0.2201s; avg 0.07338s ( +/- 18.23/ 25.38 %); best 0.06s; worst 0.092s; std dev. 0.01358 (taking best). + 36 threads: 0.06s (0.014 Mflops) (1/2 degradations so far) - +3 iterations (35 th.) took 0.1771s; avg 0.05903s ( +/- 23.44/ 21.59 %); best 0.04519s; worst 0.07178s; std dev. 0.01088 (taking best). + 35 threads: 0.04519s (0.019 Mflops) (2/2 degradations so far) - +Best threads choice is 37; starting threads were 42; max speed gap is 1.5x; search took 1.5s. +After split step 1: tpop: 0.04044 s ~Mflops: 0.021 nsubm:3 otn:37 +Applying split (1 -> 3 leaves, 37 th.) yielded SLOWDOWN (1th of 3 tolerable) of 914778.857x: 4.42e-08s -> 0.04044s. Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 split steps (of max 6) (22 -> 51 subms) took 0.296s (of which 0.02401s partitioning, 0s I/O); computing times: 0.0004642s in par. loops, 3.29e-05s sorting, 9.775e-06s analyzing) -Total split + benchmarking process took 0.296s, equivalent to 18.5/18.5 new/old ops (0.08s for 1 clones -- as 5.0/5.0 ops, or 5.0/5.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 1.5s, 0.16s for constructor, 2 clones) obtained NO speedup (best stays 0.05254 Mflops). +A total of 1 split steps (of max 6) (1 -> 3 subms) took 1.461s (of which 7.296e-05s partitioning, 0s I/O); computing times: 2.313e-05s in par. loops, 4.053e-06s sorting, 5.007e-06s analyzing) +Total split + benchmarking process took 1.461s, equivalent to 33054919.1/33054919.1 new/old ops (0.186s for 1 clones -- as 4208123.0/4208123.0 ops, or 4208123.0/4208123.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 1.8s, 0.35s for constructor, 2 clones) obtained NO speedup (best stays 1.9e+04 Mflops). check results are ok Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.033e-01 s (100.00 %) - analyzed arrays in 4.136e-02 s (40.05 %) + converted COO to RSB in 1.930e-01 s (100.00 %) + analyzed arrays in 8.493e-02 s (44.00 %) cleaned-up arrays in 9.537e-07 s (0.00 %) deduplicated arrays in 1.907e-06 s (0.00 %) - sorted arrays in 3.124e-02 s (30.26 %) - shuffled partitions in 3.060e-02 s (29.63 %) - memory allocations took 3.219e-05 s (0.03 %) - leafs setup took 1.097e-05 s (0.01 %) - halfword conversion took 5.007e-06 s (0.00 %) -Built (6 x 6)[0x55a92d036590]{Z} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x20440b4 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'UL' + sorted arrays in 4.760e-02 s (24.66 %) + shuffled partitions in 6.046e-02 s (31.32 %) + memory allocations took 1.907e-05 s (0.01 %) + leafs setup took 6.914e-06 s (0.00 %) + halfword conversion took 3.099e-06 s (0.00 %) +Built (6 x 6)[0x555aa3d6ce40]{Z} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x20440b4 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'UL' Read matrix pd.mtx 6 x 6 : 36 Matrix has no symmetry Using NRHS=4 -Repeated USMV took 0.4292E-04 s -A single USMM took 0.2813E-04 s -USMM-to-USMV speed ratio is is 1.525 x +Repeated USMV took 0.5484E-04 s +A single USMM took 0.2718E-04 s +USMM-to-USMV speed ratio is is 2.018 x Call auto-tuning routine.. Repeat measurement. Tuned USMM took 0.5007E-05 s -Tuned-to-untuned speed ratio is is 5.619 x +Tuned-to-untuned speed ratio is is 5.429 x FAILED: 0 PASSED: 2 /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran_rsb_fi @@ -8863,218 +9102,218 @@ Loading matrix from file "/build/reproducible-path/librsb-1.3.0.2+dfsg/pd.mtx". Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 2.184e-01 s (100.00 %) - analyzed arrays in 7.997e-02 s (36.62 %) - cleaned-up arrays in 1.907e-06 s (0.00 %) - deduplicated arrays in 3.815e-06 s (0.00 %) - sorted arrays in 3.032e-02 s (13.88 %) - shuffled partitions in 7.200e-02 s (32.97 %) - memory allocations took 3.195e-05 s (0.01 %) - leafs setup took 2.289e-05 s (0.01 %) - halfword conversion took 3.600e-02 s (16.49 %) -Built (6 x 6)[0x55ed5e78fa20]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' + converted COO to RSB in 3.513e+00 s (100.00 %) + analyzed arrays in 8.788e-02 s (2.50 %) + cleaned-up arrays in 2.146e-06 s (0.00 %) + deduplicated arrays in 2.146e-06 s (0.00 %) + sorted arrays in 3.452e-02 s (0.98 %) + shuffled partitions in 8.503e-02 s (2.42 %) + memory allocations took 2.789e-05 s (0.00 %) + leafs setup took 1.788e-05 s (0.00 %) + halfword conversion took 3.306e+00 s (94.09 %) +Built (6 x 6)[0x55ea3b156a20]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Considering D clone. Base matrix: -(6 x 6)[0x55ed5e794e10]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' +(6 x 6)[0x55ea3b15f060]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (20 th.) took 0.05989s; avg 0.01996s ( +/- 39.18/ 20.22 %); best 0.01214s; worst 0.024s; std dev. 0.005532 (taking best). -Reference operation time is 0.01214 s (0.01186 Mflops) with 20 threads. -After 0.059991s, autotuning routine did not find a better threads count configuration. +3 iterations (42 th.) took 0.1691s; avg 0.05636s ( +/- 15.13/ 15.23 %); best 0.04783s; worst 0.06494s; std dev. 0.006985 (taking best). +Reference operation time is 0.0478311 s (0.003011 Mflops) with 42 threads. +After 0.169179s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (20 th.) took 0.07202s; avg 0.02401s ( +/- 0.09/ 0.11 %); best 0.02398s; worst 0.02403s; std dev. 1.948e-05 (taking best). -Reference operation time is 0.0239849 s (0.006004 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.02398 Mflops: 0.006) -Merge (22 -> 16 leaves) took w.c.t. of 0.00819s, ~0.0002291s of computing time (of which 8.821e-06s sorting, 1.192e-05s analysis) -3 iterations (20 th.) took 0.1228s; avg 0.04093s ( +/- 63.11/ 75.25 %); best 0.0151s; worst 0.07173s; std dev. 0.02339 (taking best). -Reference operation time is 0.015099 s (0.009537 Mflops) with 20 threads. -After merge step 1: tpop: 0.0151 s ~Mflops: 0.010 nsubm:16 otn:20 -Applying merge (22 -> 16 leaves, 20 th.) yielded SPEEDUP of 1.589x: 0.02398s -> 0.0151s, so taking this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.01057s, ~5.198e-05s of computing time (of which 5.007e-06s sorting, 1.383e-05s analysis) -3 iterations (20 th.) took 0.1094s; avg 0.03645s ( +/- 67.62/101.74 %); best 0.0118s; worst 0.07354s; std dev. 0.02669 (taking best). -Reference operation time is 0.0118048 s (0.0122 Mflops) with 20 threads. -After merge step 2: tpop: 0.0118 s ~Mflops: 0.012 nsubm:10 otn:20 -Applying merge (16 -> 10 leaves, 20 th.) yielded SPEEDUP of 1.279x: 0.0151s -> 0.0118s, so taking this instance. -Merge (10 -> 7 leaves) took w.c.t. of 4.697e-05s, ~1.502e-05s of computing time (of which 1.907e-06s sorting, 1.311e-05s analysis) -3 iterations (20 th.) took 0.04791s; avg 0.01597s ( +/- 24.84/ 49.55 %); best 0.012s; worst 0.02388s; std dev. 0.005595 (taking best). -Reference operation time is 0.0120029 s (0.012 Mflops) with 20 threads. -After merge step 3: tpop: 0.012 s ~Mflops: 0.012 nsubm:7 otn:20 -Applying merge (10 -> 7 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98349x): 0.0118s -> 0.012s, so IGNORING this instance. -Merge (7 -> 4 leaves) took w.c.t. of 4.506e-05s, ~1.597e-05s of computing time (of which 1.907e-06s sorting, 1.097e-05s analysis) -3 iterations (20 th.) took 0.06002s; avg 0.02001s ( +/- 39.52/ 19.99 %); best 0.0121s; worst 0.02401s; std dev. 0.005592 (taking best). -Reference operation time is 0.0121 s (0.0119 Mflops) with 20 threads. -After merge step 4: tpop: 0.0121 s ~Mflops: 0.012 nsubm:4 otn:20 -Applying merge (7 -> 4 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.025x: 0.0118s -> 0.0121s. -Merge (4 -> 1 leaves) took w.c.t. of 4.196e-05s, ~1.478e-05s of computing time (of which 3.099e-06s sorting, 8.106e-06s analysis) -3 iterations (20 th.) took 1.311e-05s; avg 4.371e-06s ( +/- 78.18/150.91 %); best 9.537e-07s; worst 1.097e-05s; std dev. 4.665e-06 (taking best). -Reference operation time is 9.53674e-07 s (151 Mflops) with 20 threads. -After merge step 5: tpop: 9.537e-07 s ~Mflops: 150.995 nsubm:1 otn:20 -Applying merge (4 -> 1 leaves, 20 th.) yielded SPEEDUP of 12378.250x: 0.0118s -> 9.537e-07s, so taking this instance. +3 iterations (42 th.) took 0.1975s; avg 0.06584s ( +/- 5.50/ 5.60 %); best 0.06222s; worst 0.06953s; std dev. 0.002982 (taking best). +Reference operation time is 0.0622239 s (0.002314 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.06222 Mflops: 0.002) +Merge (22 -> 16 leaves) took w.c.t. of 0.05092s, ~0.0001059s of computing time (of which 5.007e-06s sorting, 1.001e-05s analysis) +3 iterations (42 th.) took 0.1424s; avg 0.04747s ( +/- 15.38/ 12.52 %); best 0.04017s; worst 0.05341s; std dev. 0.005493 (taking best). +Reference operation time is 0.0401659 s (0.003585 Mflops) with 42 threads. +After merge step 1: tpop: 0.04017 s ~Mflops: 0.004 nsubm:16 otn:42 +Applying merge (22 -> 16 leaves, 42 th.) yielded SPEEDUP of 1.549x: 0.06222s -> 0.04017s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.02298s, ~3.886e-05s of computing time (of which 2.861e-06s sorting, 1.097e-05s analysis) +3 iterations (42 th.) took 0.1694s; avg 0.05646s ( +/- 19.96/ 23.91 %); best 0.04519s; worst 0.06996s; std dev. 0.01023 (taking best). +Reference operation time is 0.0451889 s (0.003187 Mflops) with 42 threads. +After merge step 2: tpop: 0.04519 s ~Mflops: 0.003 nsubm:10 otn:42 +Applying merge (16 -> 10 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.125x: 0.04017s -> 0.04519s. +Merge (10 -> 7 leaves) took w.c.t. of 4.601e-05s, ~1.907e-05s of computing time (of which 2.146e-06s sorting, 1.192e-05s analysis) +3 iterations (42 th.) took 0.1329s; avg 0.04428s ( +/- 3.36/ 1.86 %); best 0.0428s; worst 0.04511s; std dev. 0.001054 (taking best). +Reference operation time is 0.0427971 s (0.003365 Mflops) with 42 threads. +After merge step 3: tpop: 0.0428 s ~Mflops: 0.003 nsubm:7 otn:42 +Applying merge (10 -> 7 leaves, 42 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.066x: 0.04017s -> 0.0428s. +Merge (7 -> 4 leaves) took w.c.t. of 3.6e-05s, ~1.097e-05s of computing time (of which 1.907e-06s sorting, 8.821e-06s analysis) +3 iterations (42 th.) took 0.1745s; avg 0.05818s ( +/- 18.05/ 19.81 %); best 0.04768s; worst 0.0697s; std dev. 0.009021 (taking best). +Reference operation time is 0.047678 s (0.00302 Mflops) with 42 threads. +After merge step 4: tpop: 0.04768 s ~Mflops: 0.003 nsubm:4 otn:42 +Applying merge (7 -> 4 leaves, 42 th.) yielded SLOWDOWN (3th of 3 tolerable) of 1.187x: 0.04017s -> 0.04768s. +Merge (4 -> 1 leaves) took w.c.t. of 3.409e-05s, ~1.192e-05s of computing time (of which 1.907e-06s sorting, 6.914e-06s analysis) +3 iterations (42 th.) took 9.06e-06s; avg 3.02e-06s ( +/- 98.68/168.42 %); best 4.001e-08s; worst 8.106e-06s; std dev. 3.618e-06 (taking best). +Reference operation time is 4.00066e-08 s (3599 Mflops) with 42 threads. +After merge step 5: tpop: 4.001e-08 s ~Mflops: 3599.403 nsubm:1 otn:42 +Applying merge (4 -> 1 leaves, 42 th.) yielded SPEEDUP of 1003980.930x: 0.04017s -> 4.001e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 5 merge steps (of max 6) (22 -> 1 subms) took 0.552s (of which 0.01956s partitioning, 0s I/O); computing times: 0.0003269s in par. loops, 2.074e-05s sorting, 5.794e-05s analyzing) -Total merge + benchmarking process took 0.552s, equivalent to 578798.2/23.0 new/old ops (0.2639s for 4 clones -- as 276755.8/11.0 ops, or 69188.9/2.8 ops per clone), SPEEDUP of 25150.000x -Applying multi-merge (22 -> 1 leaves, 5 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 25150.000x (0.02398s -> 9.537e-07s), will amortize in 23.0 ops by saving 0.02398s per op. -In 1 tuning rounds (tot. 0.7s, 0.26s for constructor, 4 clones) obtained a SPEEDUP of 2514900.0% (2.515e+04x) (from 0.006004 to 151 Mflops). -After 0.696088s, global autotuning declared speedup of 25150 x, when using threads count of 20 and a new matrix: -(6 x 6)[0x55ed5e7971e0]{D} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' +A total of 5 merge steps (of max 6) (22 -> 1 subms) took 0.9882s (of which 0.0741s partitioning, 0s I/O); computing times: 0.0001867s in par. loops, 1.383e-05s sorting, 4.864e-05s analyzing) +Total merge + benchmarking process took 0.9882s, equivalent to 24700327.8/15.9 new/old ops (0.4072s for 3 clones -- as 10177187.1/6.5 ops, or 3392395.7/2.2 ops per clone), SPEEDUP of 1555339.690x +Applying multi-merge (22 -> 1 leaves, 5 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 1555339.690x (0.06222s -> 4.001e-08s), will amortize in 15.9 ops by saving 0.06222s per op. +In 1 tuning rounds (tot. 1.3s, 0.41s for constructor, 3 clones) obtained a SPEEDUP of 155533869.0% (1.555e+06x) (from 0.002314 to 3599 Mflops). +After 1.298277s, global autotuning declared speedup of 1.55534e+06 x, when using threads count of 42 and a new matrix: +(6 x 6)[0x55ea3b164420]{D} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' Considering S clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.198e-01 s (100.00 %) - analyzed arrays in 4.794e-02 s (40.01 %) + converted COO to RSB in 3.674e-01 s (100.00 %) + analyzed arrays in 1.025e-01 s (27.90 %) cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 1.907e-06 s (0.00 %) + deduplicated arrays in 1.192e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.586e-02 s (29.93 %) - memory allocations took 1.812e-05 s (0.02 %) - leafs setup took 1.192e-05 s (0.01 %) - halfword conversion took 3.597e-02 s (30.03 %) -Built (6 x 6)[0x55ed5e794e10]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' + shuffled partitions in 1.259e-01 s (34.27 %) + memory allocations took 1.001e-05 s (0.00 %) + leafs setup took 6.914e-06 s (0.00 %) + halfword conversion took 1.390e-01 s (37.82 %) +Built (6 x 6)[0x55ea3b15f060]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' Base matrix: -(6 x 6)[0x55ed5e794e10]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' +(6 x 6)[0x55ea3b15f060]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (20 th.) took 0.05989s; avg 0.01996s ( +/- 27.06/ 19.75 %); best 0.01456s; worst 0.02391s; std dev. 0.003953 (taking best). -Reference operation time is 0.0145609 s (0.009889 Mflops) with 20 threads. -After 0.059995s, autotuning routine did not find a better threads count configuration. +3 iterations (42 th.) took 0.1551s; avg 0.05168s ( +/- 21.73/ 25.47 %); best 0.04045s; worst 0.06485s; std dev. 0.01005 (taking best). +Reference operation time is 0.0404532 s (0.00356 Mflops) with 42 threads. +After 0.155110s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (20 th.) took 0.07192s; avg 0.02397s ( +/- 0.19/ 0.12 %); best 0.02393s; worst 0.024s; std dev. 3.282e-05 (taking best). -Reference operation time is 0.0239289 s (0.006018 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz (tpop: 0.02393 Mflops: 0.006) -Merge (16 -> 10 leaves) took w.c.t. of 0.01995s, ~6.604e-05s of computing time (of which 5.96e-06s sorting, 1.311e-05s analysis) -3 iterations (20 th.) took 0.0999s; avg 0.0333s ( +/- 52.31/ 56.29 %); best 0.01588s; worst 0.05205s; std dev. 0.01479 (taking best). -Reference operation time is 0.015883 s (0.009066 Mflops) with 20 threads. -After merge step 1: tpop: 0.01588 s ~Mflops: 0.009 nsubm:10 otn:20 -Applying merge (16 -> 10 leaves, 20 th.) yielded SPEEDUP of 1.507x: 0.02393s -> 0.01588s, so taking this instance. -Merge (10 -> 7 leaves) took w.c.t. of 5.007e-05s, ~1.812e-05s of computing time (of which 9.537e-07s sorting, 1.001e-05s analysis) -3 iterations (20 th.) took 0.04846s; avg 0.01615s ( +/- 21.49/ 42.85 %); best 0.01268s; worst 0.02307s; std dev. 0.004894 (taking best). -Reference operation time is 0.012682 s (0.01135 Mflops) with 20 threads. -After merge step 2: tpop: 0.01268 s ~Mflops: 0.011 nsubm:7 otn:20 -Applying merge (10 -> 7 leaves, 20 th.) yielded SPEEDUP of 1.252x: 0.01588s -> 0.01268s, so taking this instance. -Merge (7 -> 4 leaves) took w.c.t. of 5.794e-05s, ~1.884e-05s of computing time (of which 2.861e-06s sorting, 1.311e-05s analysis) -3 iterations (20 th.) took 0.06764s; avg 0.02255s ( +/- 46.66/ 40.18 %); best 0.01203s; worst 0.03161s; std dev. 0.008061 (taking best). -Reference operation time is 0.0120258 s (0.01197 Mflops) with 20 threads. -After merge step 3: tpop: 0.01203 s ~Mflops: 0.012 nsubm:4 otn:20 -Applying merge (7 -> 4 leaves, 20 th.) yielded SPEEDUP of 1.055x: 0.01268s -> 0.01203s, so taking this instance. -Merge (4 -> 1 leaves) took w.c.t. of 4.697e-05s, ~1.979e-05s of computing time (of which 3.099e-06s sorting, 8.106e-06s analysis) -3 iterations (20 th.) took 1.907e-05s; avg 6.358e-06s ( +/- 85.00/170.00 %); best 9.537e-07s; worst 1.717e-05s; std dev. 7.643e-06 (taking best). -Reference operation time is 9.53674e-07 s (151 Mflops) with 20 threads. -After merge step 4: tpop: 9.537e-07 s ~Mflops: 150.995 nsubm:1 otn:20 -Applying merge (4 -> 1 leaves, 20 th.) yielded SPEEDUP of 12610.000x: 0.01203s -> 9.537e-07s, so taking this instance. +3 iterations (42 th.) took 0.1891s; avg 0.06305s ( +/- 3.96/ 4.15 %); best 0.06055s; worst 0.06567s; std dev. 0.00209 (taking best). +Reference operation time is 0.06055 s (0.002378 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz (tpop: 0.06055 Mflops: 0.002) +Merge (16 -> 10 leaves) took w.c.t. of 0.03185s, ~3.29e-05s of computing time (of which 4.053e-06s sorting, 6.914e-06s analysis) +3 iterations (42 th.) took 0.1593s; avg 0.05311s ( +/- 12.18/ 22.90 %); best 0.04664s; worst 0.06527s; std dev. 0.008606 (taking best). +Reference operation time is 0.0466399 s (0.003087 Mflops) with 42 threads. +After merge step 1: tpop: 0.04664 s ~Mflops: 0.003 nsubm:10 otn:42 +Applying merge (16 -> 10 leaves, 42 th.) yielded SPEEDUP of 1.298x: 0.06055s -> 0.04664s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 3.791e-05s, ~1.097e-05s of computing time (of which 9.537e-07s sorting, 9.06e-06s analysis) +3 iterations (42 th.) took 0.2064s; avg 0.06879s ( +/- 20.63/ 37.51 %); best 0.0546s; worst 0.0946s; std dev. 0.01828 (taking best). +Reference operation time is 0.0546019 s (0.002637 Mflops) with 42 threads. +After merge step 2: tpop: 0.0546 s ~Mflops: 0.003 nsubm:7 otn:42 +Applying merge (10 -> 7 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.171x: 0.04664s -> 0.0546s. +Merge (7 -> 4 leaves) took w.c.t. of 3.505e-05s, ~1.192e-05s of computing time (of which 2.146e-06s sorting, 7.868e-06s analysis) +3 iterations (42 th.) took 0.1763s; avg 0.05877s ( +/- 23.66/ 14.22 %); best 0.04486s; worst 0.06713s; std dev. 0.009899 (taking best). +Reference operation time is 0.0448649 s (0.00321 Mflops) with 42 threads. +After merge step 3: tpop: 0.04486 s ~Mflops: 0.003 nsubm:4 otn:42 +Applying merge (7 -> 4 leaves, 42 th.) yielded SPEEDUP of 1.040x: 0.04664s -> 0.04486s, so taking this instance. +Merge (4 -> 1 leaves) took w.c.t. of 3.195e-05s, ~1.192e-05s of computing time (of which 2.146e-06s sorting, 5.96e-06s analysis) +3 iterations (42 th.) took 1.192e-05s; avg 3.974e-06s ( +/- 98.99/176.00 %); best 4.001e-08s; worst 1.097e-05s; std dev. 4.961e-06 (taking best). +Reference operation time is 4.00066e-08 s (3599 Mflops) with 42 threads. +After merge step 4: tpop: 4.001e-08 s ~Mflops: 3599.403 nsubm:1 otn:42 +Applying merge (4 -> 1 leaves, 42 th.) yielded SPEEDUP of 1121436.234x: 0.04486s -> 4.001e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 4 merge steps (of max 6) (16 -> 1 subms) took 0.5081s (of which 0.02015s partitioning, 0s I/O); computing times: 0.0001228s in par. loops, 1.287e-05s sorting, 4.435e-05s analyzing) -Total merge + benchmarking process took 0.5081s, equivalent to 532749.0/21.2 new/old ops (0.3315s for 5 clones -- as 347554.0/13.9 ops, or 69510.8/2.8 ops per clone), SPEEDUP of 25091.250x -Applying multi-merge (16 -> 1 leaves, 4 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 25091.250x (0.02393s -> 9.537e-07s), will amortize in 21.2 ops by saving 0.02393s per op. -In 1 tuning rounds (tot. 0.64s, 0.33s for constructor, 5 clones) obtained a SPEEDUP of 2509025.0% (2.509e+04x) (from 0.006018 to 151 Mflops). -After 0.640120s, global autotuning declared speedup of 25091.2 x, when using threads count of 20 and a new matrix: -(6 x 6)[0x55ed5e792a80]{S} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' +A total of 4 merge steps (of max 6) (16 -> 1 subms) took 1.139s (of which 0.03199s partitioning, 0s I/O); computing times: 6.771e-05s in par. loops, 9.298e-06s sorting, 2.98e-05s analyzing) +Total merge + benchmarking process took 1.139s, equivalent to 28473450.5/18.8 new/old ops (0.712s for 4 clones -- as 17796448.2/11.8 ops, or 4449112.0/2.9 ops per clone), SPEEDUP of 1513498.212x +Applying multi-merge (16 -> 1 leaves, 4 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 1513498.212x (0.06055s -> 4.001e-08s), will amortize in 18.8 ops by saving 0.06055s per op. +In 1 tuning rounds (tot. 1.5s, 0.71s for constructor, 4 clones) obtained a SPEEDUP of 151349721.2% (1.513e+06x) (from 0.002378 to 3599 Mflops). +After 1.475732s, global autotuning declared speedup of 1.5135e+06 x, when using threads count of 42 and a new matrix: +(6 x 6)[0x55ea3b15c880]{S} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' Considering C clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.758e-01 s (100.00 %) - analyzed arrays in 7.576e-02 s (43.10 %) - cleaned-up arrays in 3.099e-06 s (0.00 %) - deduplicated arrays in 1.907e-06 s (0.00 %) + converted COO to RSB in 3.261e-01 s (100.00 %) + analyzed arrays in 8.200e-02 s (25.15 %) + cleaned-up arrays in 2.146e-06 s (0.00 %) + deduplicated arrays in 0.000e+00 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.515e-02 s (37.06 %) - memory allocations took 3.791e-05 s (0.02 %) - leafs setup took 8.821e-06 s (0.01 %) - halfword conversion took 3.483e-02 s (19.81 %) -Built (6 x 6)[0x55ed5e79cd30]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' + shuffled partitions in 1.441e-01 s (44.19 %) + memory allocations took 2.599e-05 s (0.01 %) + leafs setup took 1.502e-05 s (0.00 %) + halfword conversion took 9.992e-02 s (30.65 %) +Built (6 x 6)[0x55ea3b168960]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Base matrix: -(6 x 6)[0x55ed5e79cd30]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' +(6 x 6)[0x55ea3b168960]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (20 th.) took 0.07191s; avg 0.02397s ( +/- 33.60/ 28.41 %); best 0.01592s; worst 0.03078s; std dev. 0.006132 (taking best). -Reference operation time is 0.0159168 s (0.03619 Mflops) with 20 threads. -After 0.071978s, autotuning routine did not find a better threads count configuration. +3 iterations (42 th.) took 0.1531s; avg 0.05102s ( +/- 14.60/ 20.55 %); best 0.04358s; worst 0.06151s; std dev. 0.00763 (taking best). +Reference operation time is 0.043576 s (0.01322 Mflops) with 42 threads. +After 0.153125s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (20 th.) took 0.04737s; avg 0.01579s ( +/- 27.95/ 25.88 %); best 0.01138s; worst 0.01988s; std dev. 0.003478 (taking best). -Reference operation time is 0.0113759 s (0.05063 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.01138 Mflops: 0.051) -Merge (22 -> 16 leaves) took w.c.t. of 0.02279s, ~4.721e-05s of computing time (of which 6.199e-06s sorting, 7.153e-06s analysis) -3 iterations (20 th.) took 0.1333s; avg 0.04444s ( +/- 64.10/ 90.70 %); best 0.01595s; worst 0.08474s; std dev. 0.0293 (taking best). -Reference operation time is 0.0159519 s (0.03611 Mflops) with 20 threads. -After merge step 1: tpop: 0.01595 s ~Mflops: 0.036 nsubm:16 otn:20 -Applying merge (22 -> 16 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.402x: 0.01138s -> 0.01595s. +3 iterations (42 th.) took 0.1922s; avg 0.06405s ( +/- 21.05/ 22.91 %); best 0.05057s; worst 0.07872s; std dev. 0.01153 (taking best). +Reference operation time is 0.050566 s (0.01139 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.05057 Mflops: 0.011) +Merge (22 -> 16 leaves) took w.c.t. of 0.01921s, ~2.885e-05s of computing time (of which 5.96e-06s sorting, 6.914e-06s analysis) +3 iterations (42 th.) took 0.1209s; avg 0.0403s ( +/- 8.09/ 4.42 %); best 0.03704s; worst 0.04208s; std dev. 0.002309 (taking best). +Reference operation time is 0.0370369 s (0.01555 Mflops) with 42 threads. +After merge step 1: tpop: 0.03704 s ~Mflops: 0.016 nsubm:16 otn:42 +Applying merge (22 -> 16 leaves, 42 th.) yielded SPEEDUP of 1.365x: 0.05057s -> 0.03704s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.01531s, ~3.195e-05s of computing time (of which 2.861e-06s sorting, 8.106e-06s analysis) +3 iterations (42 th.) took 0.1396s; avg 0.04654s ( +/- 14.17/ 27.98 %); best 0.03995s; worst 0.05956s; std dev. 0.009208 (taking best). +Reference operation time is 0.039947 s (0.01442 Mflops) with 42 threads. +After merge step 2: tpop: 0.03995 s ~Mflops: 0.014 nsubm:10 otn:42 +Applying merge (16 -> 10 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.079x: 0.03704s -> 0.03995s. +Merge (10 -> 7 leaves) took w.c.t. of 3.815e-05s, ~1.097e-05s of computing time (of which 2.146e-06s sorting, 9.06e-06s analysis) +3 iterations (42 th.) took 0.114s; avg 0.03799s ( +/- 25.30/ 24.83 %); best 0.02838s; worst 0.04743s; std dev. 0.007776 (taking best). +Reference operation time is 0.0283821 s (0.02029 Mflops) with 42 threads. +After merge step 3: tpop: 0.02838 s ~Mflops: 0.020 nsubm:7 otn:42 +Applying merge (10 -> 7 leaves, 42 th.) yielded SPEEDUP of 1.305x: 0.03704s -> 0.02838s, so taking this instance. +Merge (7 -> 4 leaves) took w.c.t. of 3.314e-05s, ~1.192e-05s of computing time (of which 9.537e-07s sorting, 6.914e-06s analysis) +3 iterations (42 th.) took 0.2501s; avg 0.08338s ( +/- 25.61/ 21.65 %); best 0.06203s; worst 0.1014s; std dev. 0.01626 (taking best). +Reference operation time is 0.0620251 s (0.009287 Mflops) with 42 threads. +After merge step 4: tpop: 0.06203 s ~Mflops: 0.009 nsubm:4 otn:42 +Applying merge (7 -> 4 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.185x: 0.02838s -> 0.06203s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.1562s (of which 0.02282s partitioning, 0s I/O); computing times: 4.721e-05s in par. loops, 6.199e-06s sorting, 7.153e-06s analyzing) -Total merge + benchmarking process took 0.1562s, equivalent to 13.7/13.7 new/old ops (0.08056s for 1 clones -- as 7.1/7.1 ops, or 7.1/7.1 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (20 th.) took 0.0701s; avg 0.02337s ( +/- 31.26/ 36.94 %); best 0.01606s; worst 0.032s; std dev. 0.006573 (taking best). -Reference operation time is 0.016063 s (0.03586 Mflops) with 20 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.01606 Mflops: 0.036) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.04988s (of which: 1.097e-05s analysis, -3.481e+09s mem.mgmt); compute time: 0.074s overall, 2.813e-05s searches, 0.07397s shuffle, 0.03519s switch, 7.153e-06s quadrants. -3 iterations (20 th.) took 0.08794s; avg 0.02931s ( +/- 33.43/ 36.28 %); best 0.01952s; worst 0.03995s; std dev. 0.008363 (taking best). -Reference operation time is 0.019515 s (0.02952 Mflops) with 20 threads. -After split step 1: tpop: 0.01952 s ~Mflops: 0.030 nsubm:28 otn:20 -Applying split (22 -> 28 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.215x: 0.01606s -> 0.01952s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 split steps (of max 6) (22 -> 28 subms) took 0.138s (of which 0.04998s partitioning, 0s I/O); computing times: 0.074s in par. loops, 2.813e-05s sorting, 1.097e-05s analyzing) -Total split + benchmarking process took 0.138s, equivalent to 8.6/8.6 new/old ops (0.07532s for 1 clones -- as 4.7/4.7 ops, or 4.7/4.7 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.57s, 0.16s for constructor, 2 clones) obtained NO speedup (best stays 0.03586 Mflops). -After 0.568142s, global autotuning found old matrix optimal, with declared speedup 1 x when using 20 threads +A total of 4 merge steps (of max 6) (22 -> 4 subms) took 0.9469s (of which 0.03465s partitioning, 0s I/O); computing times: 8.368e-05s in par. loops, 1.192e-05s sorting, 3.099e-05s analyzing) +Total merge + benchmarking process took 0.9469s, equivalent to 33.4/18.7 new/old ops (0.432s for 3 clones -- as 15.2/8.5 ops, or 5.1/2.8 ops per clone), SPEEDUP of 1.782x +Applying multi-merge (22 -> 7 leaves, 3 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 1.782x (0.05057s -> 0.02838s), will amortize in 42.7 ops by saving 0.02218s per op. +In 1 tuning rounds (tot. 1.3s, 0.43s for constructor, 3 clones) obtained a SPEEDUP of 78.2% (1.782x) (from 0.01139 to 0.02029 Mflops). +After 1.283718s, global autotuning declared speedup of 1.78162 x, when using threads count of 42 and a new matrix: +(6 x 6)[0x55ea3b164400]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 7, symflags:'' Considering Z clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.599e-01 s (100.00 %) - analyzed arrays in 6.632e-02 s (41.49 %) - cleaned-up arrays in 2.146e-06 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) + converted COO to RSB in 3.133e+00 s (100.00 %) + analyzed arrays in 2.866e+00 s (91.46 %) + cleaned-up arrays in 2.861e-06 s (0.00 %) + deduplicated arrays in 0.000e+00 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.942e-02 s (30.92 %) - memory allocations took 2.599e-05 s (0.02 %) - leafs setup took 1.502e-05 s (0.01 %) - halfword conversion took 4.408e-02 s (27.57 %) -Built (6 x 6)[0x55ed5e79b590]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' + shuffled partitions in 1.713e-01 s (5.47 %) + memory allocations took 1.717e-05 s (0.00 %) + leafs setup took 1.001e-05 s (0.00 %) + halfword conversion took 9.628e-02 s (3.07 %) +Built (6 x 6)[0x55ea3b165de0]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' Base matrix: -(6 x 6)[0x55ed5e79b590]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' +(6 x 6)[0x55ea3b165de0]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (20 th.) took 0.09179s; avg 0.0306s ( +/- 9.13/ 17.73 %); best 0.0278s; worst 0.03602s; std dev. 0.003837 (taking best). -Reference operation time is 0.027802 s (0.02072 Mflops) with 20 threads. -After 0.092019s, autotuning routine did not find a better threads count configuration. +3 iterations (42 th.) took 0.1688s; avg 0.05626s ( +/- 22.57/ 15.96 %); best 0.04356s; worst 0.06524s; std dev. 0.009233 (taking best). +Reference operation time is 0.0435641 s (0.01322 Mflops) with 42 threads. +After 0.168856s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (20 th.) took 0.06806s; avg 0.02269s ( +/- 29.26/ 41.79 %); best 0.01605s; worst 0.03217s; std dev. 0.006881 (taking best). -Reference operation time is 0.016047 s (0.03589 Mflops) with 20 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.01605 Mflops: 0.036) -Merge (28 -> 22 leaves) took w.c.t. of 0.01588s, ~5.889e-05s of computing time (of which 8.106e-06s sorting, 2.003e-05s analysis) -3 iterations (20 th.) took 0.1239s; avg 0.0413s ( +/- 32.41/ 64.46 %); best 0.02791s; worst 0.06792s; std dev. 0.01882 (taking best). -Reference operation time is 0.0279138 s (0.02063 Mflops) with 20 threads. -After merge step 1: tpop: 0.02791 s ~Mflops: 0.021 nsubm:22 otn:20 -Applying merge (28 -> 22 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.740x: 0.01605s -> 0.02791s. +3 iterations (42 th.) took 0.1541s; avg 0.05137s ( +/- 11.97/ 10.10 %); best 0.04522s; worst 0.05656s; std dev. 0.004677 (taking best). +Reference operation time is 0.0452209 s (0.01274 Mflops) with 42 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.04522 Mflops: 0.013) +Merge (28 -> 22 leaves) took w.c.t. of 0.0356s, ~2.694e-05s of computing time (of which 5.007e-06s sorting, 7.868e-06s analysis) +3 iterations (42 th.) took 0.1541s; avg 0.05137s ( +/- 34.53/ 43.21 %); best 0.03363s; worst 0.07356s; std dev. 0.0166 (taking best). +Reference operation time is 0.0336268 s (0.01713 Mflops) with 42 threads. +After merge step 1: tpop: 0.03363 s ~Mflops: 0.017 nsubm:22 otn:42 +Applying merge (28 -> 22 leaves, 42 th.) yielded SPEEDUP of 1.345x: 0.04522s -> 0.03363s, so taking this instance. +Merge (22 -> 16 leaves) took w.c.t. of 0.01556s, ~2.909e-05s of computing time (of which 6.676e-06s sorting, 1.001e-05s analysis) +3 iterations (42 th.) took 0.1684s; avg 0.05614s ( +/- 24.55/ 21.18 %); best 0.04235s; worst 0.06803s; std dev. 0.01057 (taking best). +Reference operation time is 0.0423541 s (0.0136 Mflops) with 42 threads. +After merge step 2: tpop: 0.04235 s ~Mflops: 0.014 nsubm:16 otn:42 +Applying merge (22 -> 16 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.260x: 0.03363s -> 0.04235s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (28 -> 22 subms) took 0.1399s (of which 0.01593s partitioning, 0s I/O); computing times: 5.889e-05s in par. loops, 8.106e-06s sorting, 2.003e-05s analyzing) -Total merge + benchmarking process took 0.1399s, equivalent to 8.7/8.7 new/old ops (0.09978s for 1 clones -- as 6.2/6.2 ops, or 6.2/6.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (20 th.) took 0.07218s; avg 0.02406s ( +/- 34.57/ 32.92 %); best 0.01574s; worst 0.03198s; std dev. 0.006635 (taking best). -Reference operation time is 0.0157411 s (0.03659 Mflops) with 20 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.01574 Mflops: 0.037) -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.0324s (of which: 9.06e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (20 th.) took 0.06934s; avg 0.02311s ( +/- 10.98/ 18.06 %); best 0.02058s; worst 0.02729s; std dev. 0.002974 (taking best). -Reference operation time is 0.020576 s (0.02799 Mflops) with 20 threads. -After split step 1: tpop: 0.02058 s ~Mflops: 0.028 nsubm:28 otn:20 -Applying split (28 -> 28 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.307x: 0.01574s -> 0.02058s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 split steps (of max 6) (28 -> 28 subms) took 0.1019s (of which 0.03246s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 9.06e-06s analyzing) -Total split + benchmarking process took 0.1019s, equivalent to 6.5/6.5 new/old ops (0.07193s for 1 clones -- as 4.6/4.6 ops, or 4.6/4.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.55s, 0.17s for constructor, 2 clones) obtained NO speedup (best stays 0.03659 Mflops). -After 0.553961s, global autotuning found old matrix optimal, with declared speedup 1 x when using 20 threads +A total of 2 merge steps (of max 6) (28 -> 16 subms) took 0.5159s (of which 0.0512s partitioning, 0s I/O); computing times: 5.603e-05s in par. loops, 1.168e-05s sorting, 1.788e-05s analyzing) +Total merge + benchmarking process took 0.5159s, equivalent to 15.3/11.4 new/old ops (0.3106s for 2 clones -- as 9.2/6.9 ops, or 4.6/3.4 ops per clone), SPEEDUP of 1.345x +Applying multi-merge (28 -> 22 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 1.345x (0.04522s -> 0.03363s), will amortize in 44.5 ops by saving 0.01159s per op. +In 1 tuning rounds (tot. 0.84s, 0.31s for constructor, 2 clones) obtained a SPEEDUP of 34.5% (1.345x) (from 0.01274 to 0.01713 Mflops). +After 0.838577s, global autotuning declared speedup of 1.34479 x, when using threads count of 42 and a new matrix: +(6 x 6)[0x55ea3b159380]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' gmake[3]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' @@ -9205,18 +9444,19 @@ 4 0 DIFF PRINT TEST END Beginning large binary search test. -Detected 84322365440 bytes of memory, comprehensive of 21483253760 of free memory. +Detected 84307591168 bytes of memory, comprehensive of 23526883328 of free memory. On this system, maximal array of coordinates can have 2147483137 elements and occupy 8589932548 bytes. -Will perform the test using less memory (17592186043398 MB) than on the maximal coordinate indices array (18446744072642122752) allows. -Skipping test: too little memory. -Skipping large binary search test. +Will perform the test using less memory (443 MB) than on the maximal coordinate indices array (465293312) allows. +(c)allocated 116323328 nnz (465293312 bytes) +Succeeded retrieving array last element. +Successfully performed large binary search test. BASIC SPARSE BLAS TEST: BEGIN INIT INTERFACE TEST: BEGIN got RSB_IO_WANT_EXTRA_VERBOSE_INTERFACE: -1 got RSB_IO_WANT_IS_INITIALIZED_MARKER: 1 INIT INTERFACE TEST: END (SUCCESS) DEVEL PRINT TEST: BEGIN -(4 x 4)[0x55dec1a45740]{S} @ (0(0..0),0(0..0)) (4 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +(4 x 4)[0x55fbbf193e70]{S} @ (0(0..0),0(0..0)) (4 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' RSB_FLAG_USE_HALFWORD_INDICES | RSB_FLAG_SORTED_INPUT | RSB_FLAG_WANT_COO_STORAGE | @@ -9225,8 +9465,8 @@ RSB_FLAG_ASSEMBLED_IN_COO_ARRAYS | RSB_FLAG_OWN_PARTITIONING_ARRAYS | RSB_FLAG_SORT_INPUT -(2 x 2)[0x55dec1a45850]{S} @ (0(0..2),0(0..2)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' -(2 x 2)[0x55dec1a45960]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' +(2 x 2)[0x55fbbf193f80]{S} @ (0(0..2),0(0..2)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' +(2 x 2)[0x55fbbf194090]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' #R 4 x 4, 4 nnz (16 bytes), 16 index space for bytes, 544 bytes for 2 structs (2 of which are on the diagonal) (1e+02% of nnz are on the diagonal) #N at 0 0, 4 x 4, 4 nnz ( 25%) #T at 0 0, 2 x 2, 2 nnz ( 50%) @@ -9234,9 +9474,9 @@ ( 0x2046186 = { rec:1 coo:1 css:1 hw:1 ic:1 fi:0 symflags: } ) DEVEL PRINT TEST: END PRINT TEST: BEGIN [QUIET] -(2 x 2)[0x55dec1a45850]{S} @ (0(0..2),0(0..2)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' -(2 x 2)[0x55dec1a45960]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' -(4 x 4)[0x55dec1a45740]{S} @ (0(0..0),0(0..0)) (4 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +(2 x 2)[0x55fbbf193f80]{S} @ (0(0..2),0(0..2)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' +(2 x 2)[0x55fbbf194090]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' +(4 x 4)[0x55fbbf193e70]{S} @ (0(0..0),0(0..0)) (4 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' RSB_FLAG_USE_HALFWORD_INDICES | RSB_FLAG_SORTED_INPUT | RSB_FLAG_WANT_COO_STORAGE | @@ -9254,8 +9494,8 @@ BASIC PRIMITIVES TEST: BEGIN BASIC PRIMITIVES TEST: END (SUCCESS) ADVANCED SPARSE BLAS TEST: BEGIN [limit 30.000000s] [QUIET] -Terminating testing earlier due to user timeout request: test took 30.023981 s, max allowed was 30.000000. - PASSED:625 +Terminating testing earlier due to user timeout request: test took 30.175508 s, max allowed was 30.000000. + PASSED:616 FAILED:0 ADVANCED SPARSE BLAS TEST: END (SUCCESS) gmake qtests -C librsbpp @@ -9264,59 +9504,59 @@ gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' ./rsbtt -if ! test -f G.mtx ; then cp -p /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/G.mtx . ; fi ; /bin/bash /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/test.sh +if ! test -f G.mtx ; then cp -p /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/G.mtx . ; fi ; /bin/sh /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/test.sh ++ ./rsbpp Td,s G.mtx ++ grep Z-sort ++ wc -l + test 54 = 54 -++ ./rsbpp Td G.mtx -++ wc -l ++ grep Z-sort -+ test 27 = 27 ++ wc -l -++ grep Z-sort +++ ./rsbpp Td G.mtx ++ test 27 = 27 ++ ./rsbpp Td,z G.mtx -+ test 54 = 54 +++ grep Z-sort ++ wc -l ++ test 54 = 54 ++ ./rsbpp vTd,z G.mtx ++ grep Z-sort +++ wc -l + test 54 = 54 ++ grep Z-sort -++ ./rsbpp vTd,z G.mtx ++ wc -l +++ ./rsbpp vTd,z G.mtx + test 54 = 54 -++ grep Zorted -++ wc -l ++ ./rsbpp vvvTd,z G.mtx +++ wc -l +++ grep Zorted + test 8 = 8 -++ grep Z-sort ++ ./rsbpp vvTd,z G.mtx +++ grep Z-sort ++ wc -l + test 54 = 54 ++ ./rsbpp vvTd,z G.mtx -++ grep Range ++ wc -l +++ grep Range + test 0 = 0 -++ ./rsbpp vvvTd,z G.mtx -++ wc -l ++ grep Range +++ wc -l +++ ./rsbpp vvvTd,z G.mtx + test 258 -gt 0 ++ ./rsbpp vvvTd,z S.mtx -++ wc -l ++ grep Range -+ test 0 -eq 0 ++ wc -l -++ grep Range ++ test 0 -eq 0 ++ ./rsbpp vvvTd,z G.mtx +++ grep Range +++ wc -l + test 258 = 258 -++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp m10M10I1r1,4,8sFv +++ grep spmm- ++ wc -l + test 9 = 9 -++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1,4,8sFv +++ grep spmm- ++ wc -l + test 9 = 9 ++ OMP_NUM_THREADS=1 @@ -9325,32 +9565,32 @@ ++ grep spmm- + test 3 = 3 ++ OMP_NUM_THREADS=1 +++ grep spmm- ++ ./rsbpp C1000m100M100I1r1vtN,TsF ++ wc -l -++ grep spmm- + test 2 = 2 -++ wc -l ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r0vtN,TsF +++ wc -l ++ grep spmm- + test 0 = 0 -++ grep Recursing ++ wc -l ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF +++ grep Recursing + test 4 = 4 ++ OMP_NUM_THREADS=2 -++ grep Recursing -++ wc -l ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF -+ test 4 = 4 ++ grep Recursing ++ wc -l ++ test 4 = 4 ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF +++ grep Recursing +++ wc -l + test 208 = 208 ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 @@ -9403,7 +9643,7 @@ 0 0 0 0 before tuning for SPMV: -(3 x 3)[0x55abd04b0390]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'' +(3 x 3)[0x5632793d5c40]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'' ** x: 1.1 @@ -9492,18 +9732,18 @@ BEGIN Rsb_Matrix_test_multimatrix_ms_mnrhs BEGIN -(3 x 3)[0x55abd04dfee0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -Tuned with speedup factor of 1.28303: -(3 x 3)[0x55abd04e6840]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -(3 x 3)[0x55abd04dfee0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x563279401920]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' Tuned with speedup factor of 1: -(3 x 3)[0x55abd04dfee0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -(3 x 3)[0x55abd04c00e0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -Tuned with speedup factor of 1.42342: -(3 x 3)[0x55abd04e71e0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -(3 x 3)[0x55abd04c00e0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x563279401920]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x5632793ff440]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' Tuned with speedup factor of 1: -(3 x 3)[0x55abd04c00e0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x5632793ff440]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x563279401920]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +Tuned with speedup factor of 2.82431: +(3 x 3)[0x563279409b60]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x563279401920]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +Tuned with speedup factor of 1.29254: +(3 x 3)[0x5632794005b0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' END OK: terminating with no allocations registered in librsb [*] tests terminated successfully ! @@ -9520,10 +9760,10 @@ ./rsbtest --no-tune --max_t 0.01 --serial | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q Building ./rsbtest --no-tune --max_t 0.01 --max 1 --nrhs 1 --beta 1 --incy 1 --incx 1 --no-trans --alpha 1 --type d --rand --serial . | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q adding ! ./rsbtest --mkl A.mkl -running on ionos1-amd64 +running on i-capture-the-hostname Built without the MKL. ( ! ./rsbtest --unrecognized-option-triggers-abort ) -running on ionos1-amd64 +running on i-capture-the-hostname /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest/.libs/rsbtest: unrecognized option '--unrecognized-option-triggers-abort' unrecognized option, aborting. ( ./rsbtest --no-tune --max_t 0.01 --skip-loading-hermitian-matrices --skip-loading-unsymmetric-matrices --tune-maxt 10 --tune-maxr 10 --verbose-tuning --extra-verbose-interface --min_t 0.01 --max_t 0.01 --mintimes 1 --maxtimes 1 --verbose --skip-loading-symmetric-matrices A.mtx | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q skip ) @@ -9532,7 +9772,7 @@ ( ! ./rsbtest --no-tune --max_t 0.01 --quiet --types all --nthreads 1,2 --maxtimes 1 -+ A.mtx | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q 2.threads ) ( ! ./rsbtest --no-tune --max_t 0.01 --quiet --render-only A.mtx > /dev/null ) ! ./rsbtest --no-tune --max_t 0.01 --quiet --max 1 --nrhs 1 --beta 1 --incy 1 --incx 1 --render --no-trans --alpha 1 --type all A.mtx -running on ionos1-amd64 +running on i-capture-the-hostname Will not invoke autotuning routine. Benchmark will sample for at most 0.01 s Built without render support! @@ -9584,7 +9824,7 @@ gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' /usr/bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu' - /bin/bash ./libtool --mode=install /usr/bin/install -c librsb.la '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu' + /bin/sh ./libtool --mode=install /usr/bin/install -c librsb.la '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu' libtool: install: /usr/bin/install -c .libs/librsb.so.0.0.0 /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu/librsb.so.0.0.0 libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu && { ln -s -f librsb.so.0.0.0 librsb.so.0 || { rm -f librsb.so.0 && ln -s librsb.so.0.0.0 librsb.so.0; }; }) libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu && { ln -s -f librsb.so.0.0.0 librsb.so || { rm -f librsb.so && ln -s librsb.so.0.0.0 librsb.so; }; }) @@ -9594,7 +9834,7 @@ libtool: install: ranlib /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu/librsb.a libtool: warning: remember to run 'libtool --finish /usr/lib/x86_64-linux-gnu' /usr/bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' - /bin/bash ./libtool --mode=install /usr/bin/install -c rsbench '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' + /bin/sh ./libtool --mode=install /usr/bin/install -c rsbench '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' libtool: warning: 'librsb.la' has not been installed in '/usr/lib/x86_64-linux-gnu' libtool: install: /usr/bin/install -c .libs/rsbench /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin/rsbench /usr/bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' @@ -9721,12 +9961,12 @@ dh_gencontrol dh_md5sums dh_builddeb +dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-7_amd64.deb'. dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-7_amd64.deb'. -dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-7_amd64.deb'. +dpkg-deb: building package 'librsb0t64' in '../librsb0t64_1.3.0.2+dfsg-7_amd64.deb'. dpkg-deb: building package 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-7_all.deb'. dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-7_amd64.deb'. -dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-7_amd64.deb'. -dpkg-deb: building package 'librsb0t64' in '../librsb0t64_1.3.0.2+dfsg-7_amd64.deb'. +dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-7_amd64.deb'. dpkg-genbuildinfo --build=binary -O../librsb_1.3.0.2+dfsg-7_amd64.buildinfo dpkg-genchanges --build=binary -O../librsb_1.3.0.2+dfsg-7_amd64.changes dpkg-genchanges: info: binary-only upload (no source code included) @@ -9735,12 +9975,14 @@ dpkg-buildpackage: info: binary-only upload (no source included) dpkg-genchanges: info: not including original source code in upload I: copying local configuration +I: user script /srv/workspace/pbuilder/673649/tmp/hooks/B01_cleanup starting +I: user script /srv/workspace/pbuilder/673649/tmp/hooks/B01_cleanup finished I: unmounting dev/ptmx filesystem I: unmounting dev/pts filesystem I: unmounting dev/shm filesystem I: unmounting proc filesystem I: unmounting sys filesystem I: cleaning the build env -I: removing directory /srv/workspace/pbuilder/1847806 and its subdirectories -I: Current time: Wed Feb 26 09:49:38 -12 2025 -I: pbuilder-time-stamp: 1740606578 +I: removing directory /srv/workspace/pbuilder/673649 and its subdirectories +I: Current time: Wed Apr 1 19:15:18 +14 2026 +I: pbuilder-time-stamp: 1775020518