Diff of the two buildlogs: -- --- b1/build.log 2025-02-23 17:33:16.516938501 +0000 +++ b2/build.log 2025-02-23 17:47:23.114613215 +0000 @@ -1,6 +1,6 @@ I: pbuilder: network access will be disabled during build -I: Current time: Sun Feb 23 04:25:41 -12 2025 -I: pbuilder-time-stamp: 1740327941 +I: Current time: Sun Mar 29 13:56:18 +14 2026 +I: pbuilder-time-stamp: 1774742178 I: Building the build Environment I: extracting base tarball [/var/cache/pbuilder/unstable-reproducible-base.tgz] I: copying local configuration @@ -26,54 +26,86 @@ dpkg-source: info: applying auto-gitignore I: Not using root during the build. I: Installing the build-deps -I: user script /srv/workspace/pbuilder/14633/tmp/hooks/D02_print_environment starting +I: user script /srv/workspace/pbuilder/67525/tmp/hooks/D01_modify_environment starting +debug: Running on ionos16-i386. +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 Mar 28 23:56 /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/67525/tmp/hooks/D01_modify_environment finished +I: user script /srv/workspace/pbuilder/67525/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='i386' - DEBIAN_FRONTEND='noninteractive' - DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=11 ' - DISTRIBUTION='unstable' - HOME='/root' - HOST_ARCH='i386' + 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]="i686-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=i386 + DEBIAN_FRONTEND=noninteractive + DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=21 ' + DIRSTACK=() + DISTRIBUTION=unstable + EUID=0 + FUNCNAME=([0]="Echo" [1]="main") + GROUPS=() + HOME=/root + HOSTNAME=i-capture-the-hostname + HOSTTYPE=i686 + HOST_ARCH=i386 IFS=' ' - INVOCATION_ID='25810a1f38704b878a9c31c70f54ad56' - LANG='C' - LANGUAGE='en_US:en' - LC_ALL='C' - LD_LIBRARY_PATH='/usr/lib/libeatmydata' - LD_PRELOAD='libeatmydata.so' - 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='14633' - PS1='# ' - PS2='> ' + INVOCATION_ID=b1d3a6f502c0414d8a1c4a70f3a39da5 + LANG=C + LANGUAGE=de_CH:de + LC_ALL=C + LD_LIBRARY_PATH=/usr/lib/libeatmydata + LD_PRELOAD=libeatmydata.so + MACHTYPE=i686-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=67525 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.Td73l0z7/pbuilderrc_vAdh --distribution unstable --hookdir /etc/pbuilder/first-build-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/unstable-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.Td73l0z7/b1 --logfile b1/build.log librsb_1.3.0.2+dfsg-7.dsc' - SUDO_GID='112' - SUDO_UID='107' - 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.Td73l0z7/pbuilderrc_xAK2 --distribution unstable --hookdir /etc/pbuilder/rebuild-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/unstable-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.Td73l0z7/b2 --logfile b2/build.log librsb_1.3.0.2+dfsg-7.dsc' + SUDO_GID=112 + SUDO_UID=107 + 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 ionos2-i386 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 6.1.0-31-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.1.128-1 (2025-02-07) 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/14633/tmp/hooks/D02_print_environment finished + lrwxrwxrwx 1 root root 7 Nov 22 2024 /bin -> usr/bin +I: user script /srv/workspace/pbuilder/67525/tmp/hooks/D02_print_environment finished -> Attempting to satisfy build-dependencies -> Creating pbuilder-satisfydepends-dummy package Package: pbuilder-satisfydepends-dummy @@ -299,7 +331,7 @@ Get: 178 http://deb.debian.org/debian unstable/main i386 libltdl-dev i386 2.5.4-3 [169 kB] Get: 179 http://deb.debian.org/debian unstable/main i386 libhwloc-dev i386 2.12.0-1 [273 kB] Get: 180 http://deb.debian.org/debian unstable/main i386 zlib1g-dev i386 1:1.3.dfsg+really1.3.1-1+b1 [916 kB] -Fetched 392 MB in 9s (42.8 MB/s) +Fetched 392 MB in 4s (89.2 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 ... 19761 files and directories currently installed.) @@ -897,8 +929,8 @@ Setting up tzdata (2025a-2) ... Current default time zone: 'Etc/UTC' -Local time is now: Sun Feb 23 16:29:17 UTC 2025. -Universal Time is now: Sun Feb 23 16:29:17 UTC 2025. +Local time is now: Sat Mar 28 23:57:04 UTC 2026. +Universal Time is now: Sat Mar 28 23:57:04 UTC 2026. Run 'dpkg-reconfigure tzdata' if you wish to change it. Setting up libfontenc1:i386 (1:1.1.8-1+b2) ... @@ -1065,7 +1097,11 @@ 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/67525/tmp/hooks/A99_set_merged_usr starting +Not re-configuring usrmerge for unstable +I: user script /srv/workspace/pbuilder/67525/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 @@ -1085,62 +1121,62 @@ 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'. @@ -1182,90 +1218,90 @@ 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' @@ -1451,7 +1487,7 @@ 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 @@ -1568,7 +1604,7 @@ 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 @@ -1590,7 +1626,7 @@ 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=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-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=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-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=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' '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 @@ -1715,7 +1751,7 @@ 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 @@ -1724,7 +1760,7 @@ 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=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-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=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-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=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' '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 @@ -1836,7 +1872,7 @@ 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 @@ -1846,7 +1882,7 @@ 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=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-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=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-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=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' '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 @@ -1960,7 +1996,7 @@ 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 @@ -1992,7 +2028,7 @@ ARFLAGS : cru M4 : m4 MAKE : gmake - BASH : /bin/bash + BASH : /bin/sh OCTAVE : false DOXYGEN : doxygen HELP2MAN : help2man @@ -2011,7 +2047,7 @@ 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" @@ -2041,28 +2077,28 @@ blhc: ignore-line-regexp: ^.*CC.*: gcc blhc: ignore-line-regexp: ^.*LD.*: /usr/bin/ld.* dh_auto_build - make -j11 + make -j21 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbct rsbct.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbpp rsbpp.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 -Wformat -Werror=format-security -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbct rsbct.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp @@ -2083,253 +2119,246 @@ 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_stropts.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_stropts.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_lb.lo `test -f 'rsb_krnl_lb.c' || echo './'`rsb_krnl_lb.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_stropts.c -o librsb_nounroll_la-rsb_stropts.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_bench.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_bench.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mergesort.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_mergesort.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_l.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.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 -Wformat -Werror=format-security -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 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_l.c -o librsb_nounroll_la-rsb_krnl_bcss_l.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 -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 +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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_u.c -o librsb_nounroll_la-rsb_krnl_bcss_u.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 -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss.lo `test -f 'rsb_krnl_bcss.c' || echo './'`rsb_krnl_bcss.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spmv.lo `test -f 'rsb_spmv.c' || echo './'`rsb_spmv.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_merge.c -o librsb_nounroll_la-rsb_merge.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_util.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_util.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spgemm_csr.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spgemm_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 -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spsum_misc.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spsum_misc.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.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 -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_strmif.c -o librsb_nounroll_la-rsb_strmif.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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_is.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_is.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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mio.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spgemm_csr.c -o librsb_nounroll_la-rsb_spgemm_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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_bio.lo `test -f 'rsb_bio.c' || echo './'`rsb_bio.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_bio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_bio.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mio.c -o librsb_base_la-rsb_mio.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_set.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_set.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_coo.lo `test -f 'rsb_coo.c' || echo './'`rsb_coo.c -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:"", - | ^~ ~~~ -In file included from /usr/include/stdio.h:970, - from rsb_common.h:49, - from rsb_test_matops.h:79, - from rsb_test_matops.c:74: -In function 'sprintf', - inlined from 'rsb__impcdstr' at rsb_test_matops.c:214:2, - inlined from 'rsb__main_block_partitioned_spmv_sxsa' at rsb_test_matops.c:1757:4: -/usr/include/i386-linux-gnu/bits/stdio2.h:30:10: note: '__builtin___sprintf_chk' output 19 or more bytes (assuming 2070) into a destination of size 1025 - 30 | return __builtin___sprintf_chk (__s, __USE_FORTIFY_LEVEL - 1, - | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - 31 | __glibc_objsize (__s), __fmt, - | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - 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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_csr.c -o librsb_base_la-rsb_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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_idx.lo `test -f 'rsb_idx.c' || echo './'`rsb_idx.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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo_check.c -o librsb_base_la-rsb_coo_check.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_idx.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_idx.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo_check.c -o librsb_base_la-rsb_coo_check.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_srt.lo `test -f 'rsb_srt.c' || echo './'`rsb_srt.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_set.c -o librsb_base_la-rsb_set.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_srt.lo `test -f 'rsb_srt.c' || echo './'`rsb_srt.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_srt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srt.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_src.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_src.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_test_accuracy.lo `test -f 'rsb_test_accuracy.c' || echo './'`rsb_test_accuracy.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_test_accuracy.c -o librsb_base_la-rsb_test_accuracy.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_srtp.c -o librsb_base_la-rsb_srtp.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_render.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_render.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_clone.c -o librsb_base_la-rsb_clone.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_test_accuracy.c -o librsb_base_la-rsb_test_accuracy.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_eps.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_eps.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_render.c -o librsb_base_la-rsb_render.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_msort_up.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_msort_up.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_sys.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_sys.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_msort_up.c -o librsb_base_la-rsb_msort_up.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_blas_stuff.lo `test -f 'rsb_blas_stuff.c' || echo './'`rsb_blas_stuff.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_clone.c -o librsb_base_la-rsb_clone.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_gen.lo `test -f 'rsb_gen.c' || echo './'`rsb_gen.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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_gen.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_gen.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_perf.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_perf.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_rsb.lo `test -f 'rsb_rsb.c' || echo './'`rsb_rsb.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rsb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_gen.c -o librsb_base_la-rsb_gen.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_perf.c -o librsb_base_la-rsb_perf.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_err.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_err.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rsb.c -o librsb_base_la-rsb_rsb.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c -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:"", - | ^~ ~~~ -In function 'sprintf', - inlined from 'rsb__impcdstr' at rsb_test_matops.c:214:2, - inlined from 'rsb__main_block_partitioned_spsv_sxsx' at rsb_test_matops.c:6327:4: -/usr/include/i386-linux-gnu/bits/stdio2.h:30:10: note: '__builtin___sprintf_chk' output 19 or more bytes (assuming 2070) into a destination of size 1025 - 30 | return __builtin___sprintf_chk (__s, __USE_FORTIFY_LEVEL - 1, - | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - 31 | __glibc_objsize (__s), __fmt, - | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - 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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_perf.c -o librsb_base_la-rsb_perf.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_err.c -o librsb_base_la-rsb_err.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_do.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_do.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_garbage.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_garbage.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mmio.c -o librsb_base_la-rsb_mmio.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -o librsb_nounroll_la-rsb_krnl_bcss_misc_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_limiter.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_limiter.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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mbw.c -o librsb_base_la-rsb_mbw.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_do.c -o librsb_base_la-rsb_do.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spgemm.c -o librsb_base_la-rsb_spgemm.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spsv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsv.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_lock.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_lock.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_init.lo `test -f 'rsb_init.c' || echo './'`rsb_init.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_init.lo `test -f 'rsb_init.c' || echo './'`rsb_init.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spgemm.c -o librsb_base_la-rsb_spgemm.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_user.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_user.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo2rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo2rec.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_dump.c -o librsb_base_la-rsb_dump.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_rec2coo.lo `test -f 'rsb_rec2coo.c' || echo './'`rsb_rec2coo.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_coo2rec.lo `test -f 'rsb_coo2rec.c' || echo './'`rsb_coo2rec.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_rec2coo.lo `test -f 'rsb_rec2coo.c' || echo './'`rsb_rec2coo.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo2rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo2rec.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_dump.c -o librsb_base_la-rsb_dump.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c +/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 -pipe -fopenmp -c -o rsb_blas_sparse.lo 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_user.c -o librsb_base_la-rsb_user.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_rec2csr.lo `test -f 'rsb_rec2csr.c' || echo './'`rsb_rec2csr.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2coo.o -rsb_test_matops.c: In function 'rsb__main_block_partitioned_mat_stats': +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 -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec2csr.c -o librsb_base_la-rsb_rec2csr.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 -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec2coo.c -o librsb_base_la-rsb_rec2coo.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 -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_libspblas.c -fPIC -DPIC -o .libs/rsb_libspblas.o +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 -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.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 +/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 -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 -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 -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 -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 +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:"", | ^~ ~~~ +In file included from /usr/include/stdio.h:970, + from rsb_common.h:49, + from rsb_test_matops.h:79, + from rsb_test_matops.c:74: In function 'sprintf', inlined from 'rsb__impcdstr' at rsb_test_matops.c:214:2, - inlined from 'rsb__main_block_partitioned_mat_stats' at rsb_test_matops.c:10768:4: + inlined from 'rsb__main_block_partitioned_spmv_sxsa' at rsb_test_matops.c:1757:4: /usr/include/i386-linux-gnu/bits/stdio2.h:30:10: note: '__builtin___sprintf_chk' output 19 or more bytes (assuming 2070) into a destination of size 1025 30 | return __builtin___sprintf_chk (__s, __USE_FORTIFY_LEVEL - 1, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -2337,49 +2366,56 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_csr2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr2coo.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 -pipe -fopenmp -c -o rsb_blas_sparse.lo 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec2csr.c -o librsb_base_la-rsb_rec2csr.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 -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -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 -Wformat -Werror=format-security -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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.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 -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -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 -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -/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 -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 -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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -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 -pipe -fopenmp -c rsb.F90 -o rsb.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 -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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" ) -/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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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_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:"", + | ^~ ~~~ +In function 'sprintf', + inlined from 'rsb__impcdstr' at rsb_test_matops.c:214:2, + inlined from 'rsb__main_block_partitioned_spsv_sxsx' at rsb_test_matops.c:6327:4: +/usr/include/i386-linux-gnu/bits/stdio2.h:30:10: note: '__builtin___sprintf_chk' output 19 or more bytes (assuming 2070) into a destination of size 1025 + 30 | return __builtin___sprintf_chk (__s, __USE_FORTIFY_LEVEL - 1, + | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 31 | __glibc_objsize (__s), __fmt, + | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -o librsb_nounroll_la-rsb_krnl_bcss_misc_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 -Wformat -Werror=format-security -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_mat_stats': +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:"", + | ^~ ~~~ +In function 'sprintf', + inlined from 'rsb__impcdstr' at rsb_test_matops.c:214:2, + inlined from 'rsb__main_block_partitioned_mat_stats' at rsb_test_matops.c:10768:4: +/usr/include/i386-linux-gnu/bits/stdio2.h:30:10: note: '__builtin___sprintf_chk' output 19 or more bytes (assuming 2070) into a destination of size 1025 + 30 | return __builtin___sprintf_chk (__s, __USE_FORTIFY_LEVEL - 1, + | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 31 | __glibc_objsize (__s), __fmt, + | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/i386-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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/i386-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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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") @@ -2391,7 +2427,7 @@ 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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' @@ -2408,27 +2444,27 @@ 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 -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 -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-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 @@ -2447,11 +2483,11 @@ 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. @@ -3162,13 +3198,13 @@ 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -c -o rgt_rv-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp -/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 -Wformat -Werror=format-security -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++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z,relro -o rgt_rv rgt_rv-rgt.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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z,relro -o rgt_ne rgt_ne-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 -Wformat -Werror=format-security -Wl,-z,relro -o rgt_rv rgt_rv-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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 @@ -3183,25 +3219,25 @@ 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z,relro -o span span.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 -Wformat -Werror=format-security -Wl,-z,relro -o assemble assemble.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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/span span.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 -Wformat -Werror=format-security -Wl,-z,relro -o render render.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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/assemble assemble.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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/render render.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z,relro -o misc misc.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 -Wformat -Werror=format-security -Wl,-z,relro -o example example.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/example example.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/misc misc.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -/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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/twonnz twonnz.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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' @@ -3211,7 +3247,7 @@ 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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' @@ -3287,7 +3323,7 @@ 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 @@ -3297,15 +3333,15 @@ 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 1740330260 +# beginning run at 1774742836 # /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 -Wformat -Werror=format-security -O3 -std=c99 -# average timer granularity: 7.75e-07 s -# Will write a final performance record to file rsbench_pr__1740330260_gcc-14.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1740330260_gcc-14.2-1,4th.rpr.tmp +# average timer granularity: 5.18e-08 s +# Will write a final performance record to file rsbench_pr__1774742836_gcc-14.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1774742836_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:/usr/lib/libeatmydata # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -3344,67 +3380,67 @@ # 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: ionos2-i386 +# 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 6.867s +# Memory benchmark took 4.826s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 8 samples (2016 bytes). -# Cache block size total 524288 bytes, per-thread 40329 bytes -# so far, program took 6.927s 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 . +# Cache block size total 4194304 bytes, per-thread 174762 bytes +# so far, program took 4.831s 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, 33510 nnz/s ) (1.03 MB/s ) -#pre-sorting (6 elements) took 0.0319738 s -#weeding duplicates (to 6 elements) took 6.19888e-06 s (and check, 2.86102e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 34474 nnz/s ) (1.06 MB/s ) +#pre-sorting (6 elements) took 0.00438094 s +#weeding duplicates (to 6 elements) took 9.53674e-07 s (and check, 2.14577e-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 0.135s): (3 x 3)[0x56f51470]{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 0.023s): (3 x 3)[0x56d7e390]{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 0.09201s; avg 0.03067s ( +/- 8.77/ 17.50 %); best 0.02798s; worst 0.03604s; std dev. 0.003795 (taking best). -Reference operation time is 0.0279801 s (0.003431 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: 0.02798 Mflops: 0.003) -Merge (3 -> 1 leaves) took w.c.t. of 4.792e-05s, ~1.597e-05s of computing time (of which 3.099e-06s sorting, 1.001e-05s analysis) -3 iterations (1 th.) took 0.01194s; avg 0.003981s ( +/- 99.92/199.54 %); best 3.099e-06s; worst 0.01192s; std dev. 0.005617 (taking best). -Reference operation time is 3.09944e-06 s (30.97 Mflops) with 1 threads. -After merge step 1: tpop: 3.099e-06 s ~Mflops: 30.973 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 9027.462x: 0.02798s -> 3.099e-06s, so taking this instance. +3 iterations (1 th.) took 0.01314s; avg 0.004381s ( +/- 1.62/ 1.16 %); best 0.00431s; worst 0.004432s; std dev. 5.17e-05 (taking best). +Reference operation time is 0.00431013 s (0.02227 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: 0.00431 Mflops: 0.022) +Merge (3 -> 1 leaves) took w.c.t. of 1.884e-05s, ~7.868e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) +3 iterations (1 th.) took 0.002058s; avg 0.000686s ( +/- 99.86/199.72 %); best 9.537e-07s; worst 0.002056s; std dev. 0.0009688 (taking best). +Reference operation time is 9.53674e-07 s (100.7 Mflops) with 1 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 4519.500x: 0.00431s -> 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 0.07197s (of which 5.507e-05s partitioning, 0s I/O); computing times: 1.597e-05s in par. loops, 3.099e-06s sorting, 1.001e-05s analyzing) -Total merge + benchmarking process took 0.07197s, equivalent to 23219.0/2.6 new/old ops (0.1239s for 2 clones -- as 39970.0/4.4 ops, or 19985.0/2.2 ops per clone), SPEEDUP of 9027.462x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 9027.462x (0.02798s -> 3.099e-06s), will amortize in 2.6 ops by saving 0.02798s per op. -In 1 tuning rounds (tot. 0.23s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 902646.2% (9027x) (from 0.003431 to 30.97 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01302s (of which 2.289e-05s partitioning, 0s I/O); computing times: 7.868e-06s in par. loops, 9.537e-07s sorting, 2.861e-06s analyzing) +Total merge + benchmarking process took 0.01302s, equivalent to 13651.5/3.0 new/old ops (0.02325s for 2 clones -- as 24377.5/5.4 ops, or 12188.8/2.7 ops per clone), SPEEDUP of 4519.500x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 4519.500x (0.00431s -> 9.537e-07s), will amortize in 3.0 ops by saving 0.004309s per op. +In 1 tuning rounds (tot. 0.039s, 0.023s for constructor, 2 clones) obtained a SPEEDUP of 451850.0% (4520x) (from 0.02227 to 100.7 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 0.232009 s (2.798e-02 s -> 3.099e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0391929 s (4.310e-03 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 1.03595 s and estimated a speedup of 1.000000 x (1.059e-06 s -> 1.059e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.218498 s and estimated a speedup of 1.000000 x (5.200e-08 s -> 5.200e-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 0.000001 0.039000 0.047962 0.086962 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.086963 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.039000 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.047962 -%: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 0.086962 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.006342 0.008500 0.014842 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.014842 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.006342 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.008500 +%: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 0.014842 %: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 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 1 3 3 6 -nan 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 @@ -3413,47 +3449,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.155s): (3 x 3)[0x56f54bc0]{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 0.025s): (3 x 3)[0x56d81a80]{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 0.0603s; avg 0.0201s ( +/- 38.81/ 19.55 %); best 0.0123s; worst 0.02403s; std dev. 0.005517 (taking best). -Reference operation time is 0.0122991 s (0.007805 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: 0.0123 Mflops: 0.008) -Merge (3 -> 1 leaves) took w.c.t. of 6.413e-05s, ~1.311e-05s of computing time (of which 4.053e-06s sorting, 6.914e-06s analysis) -3 iterations (4 th.) took 1.287e-05s; avg 4.292e-06s ( +/- 75.32/155.56 %); best 1.059e-06s; worst 1.097e-05s; std dev. 4.72e-06 (taking best). -Reference operation time is 1.0592e-06 s (90.63 Mflops) with 4 threads. -After merge step 1: tpop: 1.059e-06 s ~Mflops: 90.635 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 11611.669x: 0.0123s -> 1.059e-06s, so taking this instance. +3 iterations (4 th.) took 0.01277s; avg 0.004255s ( +/- 0.45/ 0.30 %); best 0.004236s; worst 0.004268s; std dev. 1.387e-05 (taking best). +Reference operation time is 0.00423598 s (0.02266 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: 0.004236 Mflops: 0.023) +Merge (3 -> 1 leaves) took w.c.t. of 1.097e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (4 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.73/ 66.67 %); best 5.2e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). +Reference operation time is 5.19991e-08 s (1846 Mflops) with 4 threads. +After merge step 1: tpop: 5.2e-08 s ~Mflops: 1846.186 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 81462.632x: 0.004236s -> 5.2e-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 0.07165s (of which 7.01e-05s partitioning, 0s I/O); computing times: 1.311e-05s in par. loops, 4.053e-06s sorting, 6.914e-06s analyzing) -Total merge + benchmarking process took 0.07165s, equivalent to 67642.6/5.8 new/old ops (0.1434s for 2 clones -- as 135368.5/11.7 ops, or 67684.2/5.8 ops per clone), SPEEDUP of 11611.669x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 11611.669x (0.0123s -> 1.059e-06s), will amortize in 5.8 ops by saving 0.0123s per op. -In 1 tuning rounds (tot. 0.2s, 0.14s for constructor, 2 clones) obtained a SPEEDUP of 1161066.9% (1.161e+04x) (from 0.007805 to 90.63 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01287s (of which 1.407e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.01287s, equivalent to 247565.3/3.0 new/old ops (0.02566s for 2 clones -- as 493525.9/6.1 ops, or 246763.0/3.0 ops per clone), SPEEDUP of 81462.632x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 81462.632x (0.004236s -> 5.2e-08s), will amortize in 3.0 ops by saving 0.004236s per op. +In 1 tuning rounds (tot. 0.038s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 8146163.2% (8.146e+04x) (from 0.02266 to 1846 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 0.203998 s (1.230e-02 s -> 1.059e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0385101 s (4.236e-03 s -> 5.200e-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 1.07206 s and estimated a speedup of 1.000000 x (1.059e-06 s -> 1.059e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.216771 s and estimated a speedup of 1.000000 x (5.200e-08 s -> 5.200e-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 0.000001 0.050980 0.068023 0.119003 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.119004 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.050980 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.068023 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 4 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.119003 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.007866 0.008408 0.016274 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.016274 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.007866 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.008408 +%: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 0.016274 %: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 0.73 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.73 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.77 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.71 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 1.00 0.77 0.71 0.73 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.91 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.91 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.81 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.01 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.81 1.01 0.91 #%: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 @@ -3462,56 +3498,56 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.134997 1e+09 1e+09 +%operation:A.mtx 0.023391 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 9.53674e-07 0.039 0 0.0479622 +%constructor:A.mtx 0 0.00634193 0 0.0085001 # 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 0.156s): (3 x 3)[0x56f54bc0]{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 0.023s): (3 x 3)[0x56d81a80]{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 0.07178s; avg 0.02393s ( +/- 0.55/ 0.28 %); best 0.02379s; worst 0.02399s; std dev. 9.385e-05 (taking best). -Reference operation time is 0.0237939 s (0.008069 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: 0.02379 Mflops: 0.008) -Merge (3 -> 1 leaves) took w.c.t. of 4.506e-05s, ~1.311e-05s of computing time (of which 4.053e-06s sorting, 6.914e-06s analysis) -3 iterations (1 th.) took 1.502e-05s; avg 5.007e-06s ( +/- 78.84/142.86 %); best 1.059e-06s; worst 1.216e-05s; std dev. 5.073e-06 (taking best). -Reference operation time is 1.0592e-06 s (181.3 Mflops) with 1 threads. -After merge step 1: tpop: 1.059e-06 s ~Mflops: 181.269 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 22464.098x: 0.02379s -> 1.059e-06s, so taking this instance. +3 iterations (1 th.) took 0.01316s; avg 0.004385s ( +/- 0.48/ 0.53 %); best 0.004364s; worst 0.004408s; std dev. 1.806e-05 (taking best). +Reference operation time is 0.00436401 s (0.044 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: 0.004364 Mflops: 0.044) +Merge (3 -> 1 leaves) took w.c.t. of 9.06e-06s, ~2.146e-06s of computing time (of which 1.192e-06s sorting, 9.537e-07s analysis) +3 iterations (1 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.15/129.41 %); best 5.2e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 5.19991e-08 s (3692 Mflops) with 1 threads. +After merge step 1: tpop: 5.2e-08 s ~Mflops: 3692.372 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 83924.805x: 0.004364s -> 5.2e-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 0.072s (of which 5.198e-05s partitioning, 0s I/O); computing times: 1.311e-05s in par. loops, 4.053e-06s sorting, 6.914e-06s analyzing) -Total merge + benchmarking process took 0.072s, equivalent to 67979.8/3.0 new/old ops (0.132s for 2 clones -- as 124624.3/5.5 ops, or 62312.2/2.8 ops per clone), SPEEDUP of 22464.098x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 22464.098x (0.02379s -> 1.059e-06s), will amortize in 3.0 ops by saving 0.02379s per op. -In 1 tuning rounds (tot. 0.2s, 0.13s for constructor, 2 clones) obtained a SPEEDUP of 2246309.8% (2.246e+04x) (from 0.008069 to 181.3 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.0112s (of which 1.311e-05s partitioning, 0s I/O); computing times: 2.146e-06s in par. loops, 1.192e-06s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.0112s, equivalent to 215369.1/2.6 new/old ops (0.02413s for 2 clones -- as 464140.3/5.5 ops, or 232070.2/2.8 ops per clone), SPEEDUP of 83924.805x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 83924.805x (0.004364s -> 5.2e-08s), will amortize in 2.6 ops by saving 0.004364s per op. +In 1 tuning rounds (tot. 0.037s, 0.024s for constructor, 2 clones) obtained a SPEEDUP of 8392380.5% (8.392e+04x) (from 0.044 to 3692 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 0.204042 s (2.379e-02 s -> 1.059e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.037369 s (4.364e-03 s -> 5.200e-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 1.26791 s and estimated a speedup of 1.000000 x (1.059e-06 s -> 1.059e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.21818 s and estimated a speedup of 1.000000 x (5.200e-08 s -> 5.200e-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 0.000001 0.035883 0.036419 0.072302 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.072303 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.035883 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.036419 -%: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 0.072302 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.005896 0.008565 0.014461 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.014461 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.005896 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.008565 +%: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 0.014461 %: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 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 1 3 3 6 -nan 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 @@ -3520,47 +3556,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.155s): (3 x 3)[0x56f54bc0]{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 0.024s): (3 x 3)[0x56d81a80]{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 0.088s; avg 0.02933s ( +/- 34.96/ 25.88 %); best 0.01908s; worst 0.03692s; std dev. 0.007524 (taking best). -Reference operation time is 0.019078 s (0.01006 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: 0.01908 Mflops: 0.010) -Merge (3 -> 1 leaves) took w.c.t. of 4.387e-05s, ~1.311e-05s of computing time (of which 5.007e-06s sorting, 7.153e-06s analysis) -3 iterations (4 th.) took 1.597e-05s; avg 5.325e-06s ( +/- 64.18/123.88 %); best 1.907e-06s; worst 1.192e-05s; std dev. 4.665e-06 (taking best). -Reference operation time is 1.90735e-06 s (100.7 Mflops) with 4 threads. -After merge step 1: tpop: 1.907e-06 s ~Mflops: 100.663 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 10002.375x: 0.01908s -> 1.907e-06s, so taking this instance. +3 iterations (4 th.) took 0.01189s; avg 0.003964s ( +/- 15.78/ 8.34 %); best 0.003338s; worst 0.004294s; std dev. 0.0004426 (taking best). +Reference operation time is 0.0033381 s (0.05752 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: 0.003338 Mflops: 0.058) +Merge (3 -> 1 leaves) took w.c.t. of 9.06e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (4 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 94.97/ 84.62 %); best 5.2e-08s; worst 1.907e-06s; std dev. 7.867e-07 (taking best). +Reference operation time is 5.19991e-08 s (3692 Mflops) with 4 threads. +After merge step 1: tpop: 5.2e-08 s ~Mflops: 3692.372 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 64195.323x: 0.003338s -> 5.2e-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 0.06797s (of which 5.078e-05s partitioning, 0s I/O); computing times: 1.311e-05s in par. loops, 5.007e-06s sorting, 7.153e-06s analyzing) -Total merge + benchmarking process took 0.06797s, equivalent to 35633.8/3.6 new/old ops (0.2197s for 2 clones -- as 115211.6/11.5 ops, or 57605.8/5.8 ops per clone), SPEEDUP of 10002.375x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 10002.375x (0.01908s -> 1.907e-06s), will amortize in 3.6 ops by saving 0.01908s per op. -In 1 tuning rounds (tot. 0.31s, 0.22s for constructor, 2 clones) obtained a SPEEDUP of 1000137.5% (1e+04x) (from 0.01006 to 100.7 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01286s (of which 1.311e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.01286s, equivalent to 247235.2/3.9 new/old ops (0.02565s for 2 clones -- as 493237.0/7.7 ops, or 246618.5/3.8 ops per clone), SPEEDUP of 64195.323x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 64195.323x (0.003338s -> 5.2e-08s), will amortize in 3.9 ops by saving 0.003338s per op. +In 1 tuning rounds (tot. 0.038s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 6419432.3% (6.42e+04x) (from 0.05752 to 3692 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 0.307996 s (1.908e-02 s -> 1.907e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.037622 s (3.338e-03 s -> 5.200e-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 1.33669 s and estimated a speedup of 1.000000 x (1.192e-06 s -> 1.192e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.217727 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:1.7320508075688772 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 0.000001 0.067362 0.055983 0.123345 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.123346 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.067362 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.055983 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 4 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.123345 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.006557 0.008378 0.014935 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.014935 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.006557 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.008378 +%: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 0.014935 %: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 0.59 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.59 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.53 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.65 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 1.00 0.53 0.65 0.59 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.97 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.97 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.90 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.02 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.90 1.02 0.97 #%: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 @@ -3569,185 +3605,185 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.155858 1e+09 1e+09 +%operation:A.mtx 0.0231719 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 9.53674e-07 0.0358832 0 0.0364192 +%constructor:A.mtx 0 0.00589585 0 0.00856495 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 13.724s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.661s/0.000s . +# so far, program took 6.122s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.024s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.09342s (system CPU time used) -ru_utime : 34.46s (user CPU time used) +ru_maxrss: 21 (maximum resident set size -- MB) +ru_stime : 1.676s (system CPU time used) +ru_utime : 31.07s (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 30.97 2.798e-02 0.000e+00 3.099e-06 0.000e+00 2.320e-01 8.65e-02 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 90.63 1.230e-02 0.000e+00 1.059e-06 0.000e+00 2.040e-01 2.53e-01 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 1 100.66 4.310e-03 0.000e+00 9.537e-07 0.000e+00 3.919e-02 2.81e-01 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 1846.19 4.236e-03 0.000e+00 5.200e-08 0.000e+00 3.851e-02 5.15e+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. 1031856.5 % faster, avg. sp. ratio 10319.565x, max sp. ratio 11611.669x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 133725.8/74855.1/192596.5/267451.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.4/ 8.3/ 16.6/ 24.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.4, min. 8.3, max. 16.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4299006.6 % faster, avg. sp. ratio 42991.066x, max sp. ratio 81462.632x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 390844.1/41096.8/740591.5/781688.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 9.1/ 9.1/ 18.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.1, min. 9.1, 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 0.139/ 0.071/ 0.208,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.339/ 0.086/ 0.253,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.231/ 0.231/ 4.231,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.435/ 0.281/ 5.154,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.: 0.22 s, min 0.20 s, max 0.23 s, tot 0.44 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.22 s, min 0.20 s, max 0.23 s, tot 0.44 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.080e+01, min 3.097e+01, max 9.063e+01 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 5.618e-03, min 3.431e-03, max 7.805e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.079e-06s, min 1.059e-06s, max 3.099e-06s, tot 4.159e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.014e-02s, min 1.230e-02s, max 2.798e-02s, tot 4.028e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.037e+01 3.033e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.309e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 9.734e+02, min 1.007e+02, max 1.846e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.247e-02, min 2.227e-02, max 2.266e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.028e-07s, min 5.200e-08s, max 9.537e-07s, tot 1.006e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.273e-03s, min 4.236e-03s, max 4.310e-03s, tot 8.546e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.513e+00 1.011e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.748e+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 1 181.27 2.379e-02 0.000e+00 1.059e-06 0.000e+00 2.040e-01 3.89e-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 1 100.66 1.908e-02 0.000e+00 1.907e-06 0.000e+00 3.080e-01 2.16e-01 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 3692.37 4.364e-03 0.000e+00 5.200e-08 0.000e+00 3.737e-02 7.92e+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 3692.37 3.338e-03 0.000e+00 5.200e-08 0.000e+00 3.762e-02 7.92e+00 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. 1623223.6 % faster, avg. sp. ratio 16233.236x, max sp. ratio 22464.098x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 177058.4/161478.6/192638.1/354116.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.4/ 8.6/ 16.1/ 24.7 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.4, min. 8.6, max. 16.1 ops) +#pr: (in succ. cases rsb autotuning gave avg. 7405906.4 % faster, avg. sp. ratio 74060.064x, max sp. ratio 83924.805x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 721079.8/718647.4/723512.2/1442159.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.9/ 8.6/ 11.3/ 19.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.9, min. 8.6, max. 11.3 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 0.232/ 0.166/ 0.298,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.605/ 0.216/ 0.389,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.077/ 6.077/ 6.077,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 15.846/ 7.923/ 7.923,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.: 0.26 s, min 0.20 s, max 0.31 s, tot 0.51 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.26 s, min 0.20 s, max 0.31 s, tot 0.51 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.410e+02, min 1.007e+02, max 1.813e+02 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 9.067e-03, min 8.069e-03, max 1.006e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 1.483e-06s, min 1.059e-06s, max 1.907e-06s, tot 2.967e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.144e-02s, min 1.908e-02s, max 2.379e-02s, tot 4.287e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.217e+00 1.300e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.309e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.482e+00 x, min 1.111e+00 x, max 5.852e+00 x (2 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.07 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.07 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.692e+03, min 3.692e+03, max 3.692e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.076e-02, min 4.400e-02, max 5.752e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.200e-08s, min 5.200e-08s, max 5.200e-08s, tot 1.040e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.851e-03s, min 3.338e-03s, max 4.364e-03s, tot 7.702e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.838e+00 3.838e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.748e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.934e+01 x, min 2.000e+00 x, max 3.668e+01 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 30.97 2.798e-02 0.000e+00 3.099e-06 0.000e+00 2.320e-01 8.65e-02 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 1 181.27 2.379e-02 0.000e+00 1.059e-06 0.000e+00 2.040e-01 3.89e-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 90.63 1.230e-02 0.000e+00 1.059e-06 0.000e+00 2.040e-01 2.53e-01 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 1 100.66 1.908e-02 0.000e+00 1.907e-06 0.000e+00 3.080e-01 2.16e-01 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 1 100.66 4.310e-03 0.000e+00 9.537e-07 0.000e+00 3.919e-02 2.81e-01 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 3692.37 4.364e-03 0.000e+00 5.200e-08 0.000e+00 3.737e-02 7.92e+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 1846.19 4.236e-03 0.000e+00 5.200e-08 0.000e+00 3.851e-02 5.15e+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 3692.37 3.338e-03 0.000e+00 5.200e-08 0.000e+00 3.762e-02 7.92e+00 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. 1327540.1 % faster, avg. sp. ratio 13276.401x, max sp. ratio 22464.098x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 155392.1/74855.1/192638.1/621568.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.4/ 8.3/ 16.6/ 49.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.4, min. 8.3, max. 16.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 5852456.5 % faster, avg. sp. ratio 58525.565x, max sp. ratio 83924.805x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 555961.9/41096.8/740591.5/2223847.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.5/ 8.6/ 11.3/ 38.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.5, min. 8.6, max. 11.3 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 0.186/ 0.071/ 0.298,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.944/ 0.086/ 0.389,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.154/ 0.231/ 6.077,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 21.281/ 0.281/ 7.923,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.: 0.24 s, min 0.20 s, max 0.31 s, tot 0.95 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.24 s, min 0.20 s, max 0.31 s, tot 0.95 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.009e+02, min 3.097e+01, max 1.813e+02 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 7.342e-03, min 3.431e-03, max 1.006e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.781e-06s, min 1.059e-06s, max 3.099e-06s, tot 7.125e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.079e-02s, min 1.230e-02s, max 2.798e-02s, tot 8.315e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.217e+00 3.033e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.309e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.482e+00 x, min 1.111e+00 x, max 5.852e+00 x (2 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.15 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.15 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.333e+03, min 1.007e+02, max 3.692e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.661e-02, min 2.227e-02, max 5.752e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.774e-07s, min 5.200e-08s, max 9.537e-07s, tot 1.110e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.062e-03s, min 3.338e-03s, max 4.364e-03s, tot 1.625e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.838e+00 1.011e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.748e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.934e+01 x, min 2.000e+00 x, max 3.668e+01 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 30.97 2.798e-02 0.000e+00 3.099e-06 0.000e+00 2.320e-01 8.65e-02 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 90.63 1.230e-02 0.000e+00 1.059e-06 0.000e+00 2.040e-01 2.53e-01 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 1 100.66 4.310e-03 0.000e+00 9.537e-07 0.000e+00 3.919e-02 2.81e-01 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 1846.19 4.236e-03 0.000e+00 5.200e-08 0.000e+00 3.851e-02 5.15e+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. 1031856.5 % faster, avg. sp. ratio 10319.565x, max sp. ratio 11611.669x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 133725.8/74855.1/192596.5/267451.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.4/ 8.3/ 16.6/ 24.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.4, min. 8.3, max. 16.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4299006.6 % faster, avg. sp. ratio 42991.066x, max sp. ratio 81462.632x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 390844.1/41096.8/740591.5/781688.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 9.1/ 9.1/ 18.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.1, min. 9.1, 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 0.139/ 0.071/ 0.208,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.339/ 0.086/ 0.253,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.231/ 0.231/ 4.231,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.435/ 0.281/ 5.154,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.: 0.22 s, min 0.20 s, max 0.23 s, tot 0.44 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.22 s, min 0.20 s, max 0.23 s, tot 0.44 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.080e+01, min 3.097e+01, max 9.063e+01 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 5.618e-03, min 3.431e-03, max 7.805e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.079e-06s, min 1.059e-06s, max 3.099e-06s, tot 4.159e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.014e-02s, min 1.230e-02s, max 2.798e-02s, tot 4.028e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.037e+01 3.033e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.309e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 9.734e+02, min 1.007e+02, max 1.846e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.247e-02, min 2.227e-02, max 2.266e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.028e-07s, min 5.200e-08s, max 9.537e-07s, tot 1.006e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.273e-03s, min 4.236e-03s, max 4.310e-03s, tot 8.546e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.513e+00 1.011e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.748e+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 1 181.27 2.379e-02 0.000e+00 1.059e-06 0.000e+00 2.040e-01 3.89e-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 1 100.66 1.908e-02 0.000e+00 1.907e-06 0.000e+00 3.080e-01 2.16e-01 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 3692.37 4.364e-03 0.000e+00 5.200e-08 0.000e+00 3.737e-02 7.92e+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 3692.37 3.338e-03 0.000e+00 5.200e-08 0.000e+00 3.762e-02 7.92e+00 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. 1623223.6 % faster, avg. sp. ratio 16233.236x, max sp. ratio 22464.098x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 177058.4/161478.6/192638.1/354116.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.4/ 8.6/ 16.1/ 24.7 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.4, min. 8.6, max. 16.1 ops) +#pr: (in succ. cases rsb autotuning gave avg. 7405906.4 % faster, avg. sp. ratio 74060.064x, max sp. ratio 83924.805x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 721079.8/718647.4/723512.2/1442159.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.9/ 8.6/ 11.3/ 19.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.9, min. 8.6, max. 11.3 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 0.232/ 0.166/ 0.298,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.605/ 0.216/ 0.389,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.077/ 6.077/ 6.077,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 15.846/ 7.923/ 7.923,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.: 0.26 s, min 0.20 s, max 0.31 s, tot 0.51 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.26 s, min 0.20 s, max 0.31 s, tot 0.51 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.410e+02, min 1.007e+02, max 1.813e+02 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 9.067e-03, min 8.069e-03, max 1.006e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 1.483e-06s, min 1.059e-06s, max 1.907e-06s, tot 2.967e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.144e-02s, min 1.908e-02s, max 2.379e-02s, tot 4.287e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.217e+00 1.300e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.309e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.482e+00 x, min 1.111e+00 x, max 5.852e+00 x (2 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.07 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.07 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.692e+03, min 3.692e+03, max 3.692e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.076e-02, min 4.400e-02, max 5.752e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.200e-08s, min 5.200e-08s, max 5.200e-08s, tot 1.040e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.851e-03s, min 3.338e-03s, max 4.364e-03s, tot 7.702e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.838e+00 3.838e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.748e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.934e+01 x, min 2.000e+00 x, max 3.668e+01 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. #pr: ======== Limiting to both transA=T and nrhs=1: @@ -3757,44 +3793,44 @@ #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 30.97 2.798e-02 0.000e+00 3.099e-06 0.000e+00 2.320e-01 8.65e-02 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 1 181.27 2.379e-02 0.000e+00 1.059e-06 0.000e+00 2.040e-01 3.89e-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 90.63 1.230e-02 0.000e+00 1.059e-06 0.000e+00 2.040e-01 2.53e-01 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 1 100.66 1.908e-02 0.000e+00 1.907e-06 0.000e+00 3.080e-01 2.16e-01 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 1 100.66 4.310e-03 0.000e+00 9.537e-07 0.000e+00 3.919e-02 2.81e-01 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 3692.37 4.364e-03 0.000e+00 5.200e-08 0.000e+00 3.737e-02 7.92e+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 1846.19 4.236e-03 0.000e+00 5.200e-08 0.000e+00 3.851e-02 5.15e+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 3692.37 3.338e-03 0.000e+00 5.200e-08 0.000e+00 3.762e-02 7.92e+00 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. 1327540.1 % faster, avg. sp. ratio 13276.401x, max sp. ratio 22464.098x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 155392.1/74855.1/192638.1/621568.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.4/ 8.3/ 16.6/ 49.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.4, min. 8.3, max. 16.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 5852456.5 % faster, avg. sp. ratio 58525.565x, max sp. ratio 83924.805x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 555961.9/41096.8/740591.5/2223847.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.5/ 8.6/ 11.3/ 38.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.5, min. 8.6, max. 11.3 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 0.186/ 0.071/ 0.298,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.944/ 0.086/ 0.389,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.154/ 0.231/ 6.077,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 21.281/ 0.281/ 7.923,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.: 0.24 s, min 0.20 s, max 0.31 s, tot 0.95 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.24 s, min 0.20 s, max 0.31 s, tot 0.95 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.009e+02, min 3.097e+01, max 1.813e+02 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 7.342e-03, min 3.431e-03, max 1.006e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.781e-06s, min 1.059e-06s, max 3.099e-06s, tot 7.125e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.079e-02s, min 1.230e-02s, max 2.798e-02s, tot 8.315e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.217e+00 3.033e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.309e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.482e+00 x, min 1.111e+00 x, max 5.852e+00 x (2 samples, the non-min-nrhs ones) -#pr: Record collection took 5.35 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.15 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.15 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.333e+03, min 1.007e+02, max 3.692e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.661e-02, min 2.227e-02, max 5.752e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.774e-07s, min 5.200e-08s, max 9.537e-07s, tot 1.110e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.062e-03s, min 3.338e-03s, max 4.364e-03s, tot 1.625e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.838e+00 1.011e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.748e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.934e+01 x, min 2.000e+00 x, max 3.668e+01 x (2 samples, the non-min-nrhs ones) +#pr: Record collection took 1.03 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4730 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4783 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1740330260_gcc-14.2-1,4th.rpr -# Removing the temporary record file rsbench_pr__1740330260_gcc-14.2-1,4th.rpr.tmp. -# terminating run at 1740330273 (after 13.7s of w.c.t.) +#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1774742836_gcc-14.2-1,4th.rpr +# Removing the temporary record file rsbench_pr__1774742836_gcc-14.2-1,4th.rpr.tmp. +# terminating run at 1774742842 (after 6.1s 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. @@ -4048,38 +4084,49 @@ Written by michelemartone_AT_users_DOT_sourceforge_DOT_net. + ./rsbench -I -cache block size : 40329 -hwloc size of cache level 1: 65536 -hwloc size of cache level 2: 524288 -detected max available cores/threads : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 -detected max OpenMP procs : 13 +cache block size : 174762 +hwloc size of cache level 1: 32768 +hwloc size of cache level 2: 4194304 +detected max available cores/threads : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 +detected max OpenMP procs : 24 detected 2 levels of cache -L1 size: 65536 -L2 size: 524288 +L1 size: 32768 +L2 size: 4194304 sysconf() : 4096 bytes per pagesize -sysconf() : 2028579 physical pages -sysconf() : 4014092288 bytes (3828 MB) of physical memory -sysconf() : 51172 available (free) physical pages -sysconf() : 209600512 available (free) physical memory -sysconf() , processors : 64 -sysconf() , processors online : 13 -sysconf() : level 1 cache size 65536 -sysconf() : level 1 cache associativity 2 +sysconf() : 2024092 physical pages +sysconf() : 3995713536 bytes (3810 MB) of physical memory +sysconf() : 710196 available (free) physical pages +sysconf() : 2908962816 available (free) physical memory +sysconf() , processors : 128 +sysconf() , processors online : 24 +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 @@ -4101,30 +4148,33 @@ RSB_SUBM_IDX_MARKER : 2147483647 RSB_MAX_ALLOCATABLE_MEMORY_CHUNK: 4294967295 timing min delta (if negative, don't complain with us) : 0 s -timing granularity : 9.57549e-07 s +timing granularity : 5.32508e-08 s CFLAGS : -g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 CXXFLAGS : -g -O2 -fstack-protector-strong -Wformat -Werror=format-security -fopenmp CC : gcc -memhinfo : L2:16/64/512K,L1:2/64/64K -detected free memory : 209084416 -detected total memory : -280875008 -for array sized 524288 elems, took 0.000563145 s for linear search and 0 s for binary search for element 524287, in 36 tries, for a total of 0.100311 s (ignore this:37748664) -for array sized 524288 elems, took 0.000274181 s for linear search and 0 s for binary search for element 262143, in 104 tries, for a total of 0.108490 s (ignore this:92274408) -for array sized 524288 elems, took 0.000137091 s for linear search and 0 s for binary search for element 131071, in 291 tries, for a total of 0.103361 s (ignore this:168557730) -for array sized 524288 elems, took 6.60419e-05 s for linear search and 0 s for binary search for element 65535, in 489 tries, for a total of 0.107305 s (ignore this:232650960) -for array sized 524288 elems, took 3.29018e-05 s for linear search and 0 s for binary search for element 32767, in 760 tries, for a total of 0.100012 s (ignore this:282456800) -for array sized 524288 elems, took 1.69277e-05 s for linear search and 0 s for binary search for element 16383, in 1174 tries, for a total of 0.101496 s (ignore this:320924084) -for array sized 524288 elems, took 8.82149e-06 s for linear search and 0 s for binary search for element 8191, in 2441 tries, for a total of 0.100007 s (ignore this:360912546) -for array sized 524288 elems, took 3.8147e-06 s for linear search and 0 s for binary search for element 4095, in 4458 tries, for a total of 0.103769 s (ignore this:397423566) -for array sized 524288 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 2047, in 8281 tries, for a total of 0.100001 s (ignore this:431325980) -for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 1023, in 21289 tries, for a total of 0.100000 s (ignore this:474883274) -for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 511, in 28073 tries, for a total of 0.102460 s (ignore this:503573880) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 40634 tries, for a total of 0.100001 s (ignore this:524297220) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 43898 tries, for a total of 0.100001 s (ignore this:535447312) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 48988 tries, for a total of 0.101661 s (ignore this:541619800) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 34363 tries, for a total of 0.106456 s (ignore this:543750306) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 29444 tries, for a total of 0.100012 s (ignore this:544633626) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 37767 tries, for a total of 0.106127 s (ignore this:545162364) +memhinfo : L2:16/64/4M,L1:8/64/32K +detected free memory : -1386004480 +detected total memory : -299253760 +for array sized 4194304 elems, took 0.00145698 s for linear search and 0 s for binary search for element 4194303, in 67 tries, for a total of 0.100970 s (ignore this:562036602) +for array sized 4194304 elems, took 0.000727892 s for linear search and 0 s for binary search for element 2097151, in 136 tries, for a total of 0.100335 s (ignore this:1132461674) +for array sized 4194304 elems, took 0.000362873 s for linear search and 0 s for binary search for element 1048575, in 274 tries, for a total of 0.100290 s (ignore this:1707080774) +for array sized 4194304 elems, took 0.00018096 s for linear search and 0 s for binary search for element 524287, in 547 tries, for a total of 0.100080 s (ignore this:-2014316544) +for array sized 4194304 elems, took 9.08375e-05 s for linear search and 0 s for binary search for element 262143, in 1093 tries, for a total of 0.100042 s (ignore this:-1441271946) +for array sized 4194304 elems, took 4.48227e-05 s for linear search and 0 s for binary search for element 131071, in 2179 tries, for a total of 0.100044 s (ignore this:-870064528) +for array sized 4194304 elems, took 2.19345e-05 s for linear search and 0 s for binary search for element 65535, in 4330 tries, for a total of 0.100021 s (ignore this:-302531428) +for array sized 4194304 elems, took 1.09673e-05 s for linear search and 0 s for binary search for element 32767, in 8652 tries, for a total of 0.100004 s (ignore this:264468740) +for array sized 4194304 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 16383, in 17072 tries, for a total of 0.100002 s (ignore this:823849892) +for array sized 4194304 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 8191, in 33157 tries, for a total of 0.100001 s (ignore this:1367027866) +for array sized 4194304 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 4095, in 63198 tries, for a total of 0.100000 s (ignore this:1884619486) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 2047, in 115454 tries, for a total of 0.100001 s (ignore this:-1937679134) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 197753 tries, for a total of 0.100000 s (ignore this:-1533076496) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 511, in 304983 tries, for a total of 0.100001 s (ignore this:-1221383870) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 255, in 418450 tries, for a total of 0.100001 s (ignore this:-1007974370) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 127, in 515689 tries, for a total of 0.100001 s (ignore this:-876989364) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 63, in 588991 tries, for a total of 0.100000 s (ignore this:-802776498) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 31, in 686684 tries, for a total of 0.100000 s (ignore this:-760202090) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 15, in 737119 tries, for a total of 0.100001 s (ignore this:-738088520) +for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 7, in 755139 tries, for a total of 0.100001 s (ignore this:-727516574) + ./rsbench -C /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench version: 1.3.0 format switches:br @@ -4151,7 +4201,7 @@ 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. @@ -4171,17 +4221,17 @@ 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 1740330277 +# beginning run at 1774742845 # /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 -Wformat -Werror=format-security -O3 -std=c99 -# User did not specify threads; assuming 1. Environment provides max 13 threads; this build supports max 128. -# User did not specify threads; assuming 1. Environment provides max 13 threads; this build supports max 128. -# average timer granularity: 9.13e-07 s -# Will write a final performance record to file rsbench_pr__1740330277_gcc-14.2.rpr and periodic checkpoints to rsbench_pr__1740330277_gcc-14.2.rpr.tmp +# User did not specify threads; assuming 1. Environment provides max 24 threads; this build supports max 128. +# User did not specify threads; assuming 1. Environment provides max 24 threads; this build supports max 128. +# average timer granularity: 5.08e-08 s +# Will write a final performance record to file rsbench_pr__1774742845_gcc-14.2.rpr and periodic checkpoints to rsbench_pr__1774742845_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:/usr/lib/libeatmydata # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -4220,835 +4270,835 @@ # 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: ionos2-i386 +# 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 5.349s +# Memory benchmark took 4.367s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 16 samples (4032 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). -# Cache block size total 524288 bytes, per-thread 40329 bytes -# so far, program took 5.396s 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 174762 bytes +# so far, program took 4.369s 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, 33157 nnz/s ) (1.02 MB/s ) -#pre-sorting (6 elements) took 0.042985 s -#weeding duplicates (to 6 elements) took 4.05312e-06 s (and check, 3.09944e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 54947 nnz/s ) (1.69 MB/s ) +#pre-sorting (6 elements) took 0.00425696 s +#weeding duplicates (to 6 elements) took 1.90735e-06 s (and check, 9.53674e-07 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 13 threads -# Constructed matrix (took 0.152s): (3 x 3)[0x566c1c80]{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 24 threads +# Constructed matrix (took 0.028s): (3 x 3)[0x5818bb10]{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 (13 th.) took 0.05065s; avg 0.01688s ( +/- 28.53/ 41.74 %); best 0.01207s; worst 0.02393s; std dev. 0.005094 (taking best). -Reference operation time is 0.012068 s (0.001989 Mflops) with 13 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: 0.01207 Mflops: 0.002) -Merge (3 -> 1 leaves) took w.c.t. of 6.723e-05s, ~2.003e-05s of computing time (of which 4.053e-06s sorting, 1.097e-05s analysis) -3 iterations (13 th.) took 3.195e-05s; avg 1.065e-05s ( +/- 89.38/182.09 %); best 1.131e-06s; worst 3.004e-05s; std dev. 1.371e-05 (taking best). -Reference operation time is 1.1313e-06 s (21.21 Mflops) with 13 threads. -After merge step 1: tpop: 1.131e-06 s ~Mflops: 21.215 nsubm:1 otn:13 -Applying merge (3 -> 1 leaves, 13 th.) yielded SPEEDUP of 10667.439x: 0.01207s -> 1.131e-06s, so taking this instance. +3 iterations (24 th.) took 0.01342s; avg 0.004474s ( +/- 0.43/ 0.75 %); best 0.004455s; worst 0.004508s; std dev. 2.375e-05 (taking best). +Reference operation time is 0.00445509 s (0.005387 Mflops) with 24 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: 0.004455 Mflops: 0.005) +Merge (3 -> 1 leaves) took w.c.t. of 1.693e-05s, ~6.914e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (24 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 99.27/186.36 %); best 5.106e-08s; worst 2.003e-05s; std dev. 9.224e-06 (taking best). +Reference operation time is 5.10573e-08 s (470.1 Mflops) with 24 threads. +After merge step 1: tpop: 5.106e-08 s ~Mflops: 470.060 nsubm:1 otn:24 +Applying merge (3 -> 1 leaves, 24 th.) yielded SPEEDUP of 87256.596x: 0.004455s -> 5.106e-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 0.05989s (of which 7.486e-05s partitioning, 0s I/O); computing times: 2.003e-05s in par. loops, 4.053e-06s sorting, 1.097e-05s analyzing) -Total merge + benchmarking process took 0.05989s, equivalent to 52941.0/5.0 new/old ops (0.1206s for 2 clones -- as 106627.2/10.0 ops, or 53313.6/5.0 ops per clone), SPEEDUP of 10667.439x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 10667.439x (0.01207s -> 1.131e-06s), will amortize in 5.0 ops by saving 0.01207s per op. -In 1 tuning rounds (tot. 0.17s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 1066643.9% (1.067e+04x) (from 0.001989 to 21.21 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01305s (of which 2.003e-05s partitioning, 0s I/O); computing times: 6.914e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.01305s, equivalent to 255591.9/2.9 new/old ops (0.02606s for 2 clones -- as 510422.6/5.8 ops, or 255211.3/2.9 ops per clone), SPEEDUP of 87256.596x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 87256.596x (0.004455s -> 5.106e-08s), will amortize in 2.9 ops by saving 0.004455s per op. +In 1 tuning rounds (tot. 0.04s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 8725559.6% (8.726e+04x) (from 0.005387 to 470.1 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 0.171594 s (1.207e-02 s -> 1.131e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.039624 s (4.455e-03 s -> 5.106e-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 1.06009 s and estimated a speedup of 1.000000 x (1.131e-06 s -> 1.131e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.218334 s and estimated a speedup of 1.000000 x (5.106e-08 s -> 5.106e-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 13 3 3 6 0.000000 0.071570 0.035984 0.107554 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.107554 -%:RSB_SUBDIVISION_TIME:A.mtx S N 13 3 3 6 0.071570 -%:RSB_SHUFFLE_TIME:A.mtx S N 13 3 3 6 0.035984 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 13 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 13 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.107554 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 13 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 13 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 13 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 24 3 3 6 0.000000 0.010444 0.008526 0.018970 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018970 +%:RSB_SUBDIVISION_TIME:A.mtx S N 24 3 3 6 0.010444 +%:RSB_SHUFFLE_TIME:A.mtx S N 24 3 3 6 0.008526 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 24 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 24 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018970 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 24 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 24 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 24 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 13 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 13 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 13 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 13 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 13 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 24 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 24 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 24 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 24 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 24 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[13] SPMV[13] SPMV[13] -%operation:A.mtx 0.151937 1e+09 1e+09 -%constructor:matrix SORT[13] SCAN[13] SHUFFLE[13] INSERT[13] -%constructor:A.mtx 0 0.0715699 0 0.035984 +%operation:matrix CONSTRUCTOR[24] SPMV[24] SPMV[24] +%operation:A.mtx 0.0275278 1e+09 1e+09 +%constructor:matrix SORT[24] SCAN[24] SHUFFLE[24] INSERT[24] +%constructor:A.mtx 0 0.0104439 0 0.00852609 # 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 13 threads -# Constructed matrix (took 0.144s): (3 x 3)[0x566c1c80]{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 24 threads +# Constructed matrix (took 0.027s): (3 x 3)[0x5818bb10]{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 (13 th.) took 0.09617s; avg 0.03206s ( +/- 24.79/ 33.99 %); best 0.02411s; worst 0.04295s; std dev. 0.00797 (taking best). -Reference operation time is 0.0241098 s (0.003982 Mflops) with 13 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: 0.02411 Mflops: 0.004) -Merge (3 -> 1 leaves) took w.c.t. of 4.005e-05s, ~1.216e-05s of computing time (of which 3.099e-06s sorting, 6.914e-06s analysis) -3 iterations (13 th.) took 9.06e-06s; avg 3.02e-06s ( +/- 62.54/ 97.37 %); best 1.131e-06s; worst 5.96e-06s; std dev. 2.135e-06 (taking best). -Reference operation time is 1.1313e-06 s (84.86 Mflops) with 13 threads. -After merge step 1: tpop: 1.131e-06 s ~Mflops: 84.858 nsubm:1 otn:13 -Applying merge (3 -> 1 leaves, 13 th.) yielded SPEEDUP of 21311.697x: 0.02411s -> 1.131e-06s, so taking this instance. +3 iterations (24 th.) took 0.01305s; avg 0.004351s ( +/- 0.72/ 0.49 %); best 0.004319s; worst 0.004372s; std dev. 2.27e-05 (taking best). +Reference operation time is 0.00431919 s (0.02223 Mflops) with 24 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: 0.004319 Mflops: 0.022) +Merge (3 -> 1 leaves) took w.c.t. of 9.06e-06s, ~1.907e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (24 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.22/129.41 %); best 5.106e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 5.10573e-08 s (1880 Mflops) with 24 threads. +After merge step 1: tpop: 5.106e-08 s ~Mflops: 1880.239 nsubm:1 otn:24 +Applying merge (3 -> 1 leaves, 24 th.) yielded SPEEDUP of 84594.910x: 0.004319s -> 5.106e-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 0.09586s (of which 4.697e-05s partitioning, 0s I/O); computing times: 1.216e-05s in par. loops, 3.099e-06s sorting, 6.914e-06s analyzing) -Total merge + benchmarking process took 0.09586s, equivalent to 84732.8/4.0 new/old ops (0.1756s for 2 clones -- as 155211.4/7.3 ops, or 77605.7/3.6 ops per clone), SPEEDUP of 21311.697x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 21311.697x (0.02411s -> 1.131e-06s), will amortize in 4.0 ops by saving 0.02411s per op. -In 1 tuning rounds (tot. 0.27s, 0.18s for constructor, 2 clones) obtained a SPEEDUP of 2131069.7% (2.131e+04x) (from 0.003982 to 84.86 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01306s (of which 1.192e-05s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.01306s, equivalent to 255750.6/3.0 new/old ops (0.02601s for 2 clones -- as 509428.0/6.0 ops, or 254714.0/3.0 ops per clone), SPEEDUP of 84594.910x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 84594.910x (0.004319s -> 5.106e-08s), will amortize in 3.0 ops by saving 0.004319s per op. +In 1 tuning rounds (tot. 0.039s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 8459391.0% (8.459e+04x) (from 0.02223 to 1880 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 0.271973 s (2.411e-02 s -> 1.131e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0391421 s (4.319e-03 s -> 5.106e-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 1.14787 s and estimated a speedup of 1.000000 x (1.131e-06 s -> 1.131e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.217464 s and estimated a speedup of 1.000000 x (5.106e-08 s -> 5.106e-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 13 3 3 6 0.000001 0.056943 0.046509 0.103452 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.103453 -%:RSB_SUBDIVISION_TIME:A.mtx S N 13 3 3 6 0.056943 -%:RSB_SHUFFLE_TIME:A.mtx S N 13 3 3 6 0.046509 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 13 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 13 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.103452 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 13 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 13 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 13 3 3 6 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 24 3 3 6 0.000000 0.010014 0.008601 0.018615 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018615 +%:RSB_SUBDIVISION_TIME:A.mtx S N 24 3 3 6 0.010014 +%:RSB_SHUFFLE_TIME:A.mtx S N 24 3 3 6 0.008601 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 24 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 24 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018615 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 24 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 24 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 24 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 13 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 13 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 13 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 13 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 13 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 24 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 24 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 24 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 24 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 24 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[13] SPMV[13] SPMV[13] -%operation:A.mtx 0.14417 1e+09 1e+09 -%constructor:matrix SORT[13] SCAN[13] SHUFFLE[13] INSERT[13] -%constructor:A.mtx 9.53674e-07 0.0569429 0 0.046509 +%operation:matrix CONSTRUCTOR[24] SPMV[24] SPMV[24] +%operation:A.mtx 0.027324 1e+09 1e+09 +%constructor:matrix SORT[24] SCAN[24] SHUFFLE[24] INSERT[24] +%constructor:A.mtx 0 0.0100138 0 0.00860095 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 8.623s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.652s/0.000s . +# so far, program took 5.024s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.515s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.07412s (system CPU time used) -ru_utime : 16.69s (user CPU time used) +ru_maxrss: 21 (maximum resident set size -- MB) +ru_stime : 0.9824s (system CPU time used) +ru_utime : 17.6s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). -# Cache block size total 524288 bytes, per-thread 40329 bytes -# so far, program took 8.623s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.652s/0.000s . +# Cache block size total 4194304 bytes, per-thread 174762 bytes +# so far, program took 5.024s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.515s/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 13 threads -# Constructed matrix (took 0.132s): (3 x 3)[0x566c1c80]{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 24 threads +# Constructed matrix (took 0.027s): (3 x 3)[0x5818bb10]{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 (13 th.) took 0.09211s; avg 0.0307s ( +/- 48.18/ 56.69 %); best 0.01591s; worst 0.04811s; std dev. 0.01327 (taking best). -Reference operation time is 0.0159111 s (0.001508 Mflops) with 13 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: 0.01591 Mflops: 0.002) -Merge (3 -> 1 leaves) took w.c.t. of 4.005e-05s, ~1.097e-05s of computing time (of which 1.907e-06s sorting, 8.106e-06s analysis) -3 iterations (13 th.) took 0.003767s; avg 0.001256s ( +/- 99.91/199.70 %); best 1.131e-06s; worst 0.003763s; std dev. 0.001773 (taking best). -Reference operation time is 1.1313e-06 s (21.21 Mflops) with 13 threads. -After merge step 1: tpop: 1.131e-06 s ~Mflops: 21.215 nsubm:1 otn:13 -Applying merge (3 -> 1 leaves, 13 th.) yielded SPEEDUP of 14064.489x: 0.01591s -> 1.131e-06s, so taking this instance. +3 iterations (24 th.) took 0.01294s; avg 0.004314s ( +/- 2.32/ 3.20 %); best 0.004214s; worst 0.004452s; std dev. 0.0001008 (taking best). +Reference operation time is 0.00421405 s (0.005695 Mflops) with 24 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: 0.004214 Mflops: 0.006) +Merge (3 -> 1 leaves) took w.c.t. of 7.868e-06s, ~3.099e-06s of computing time (of which 1.192e-06s sorting, 1.907e-06s analysis) +3 iterations (24 th.) took 0.0008421s; avg 0.0002807s ( +/- 99.98/199.24 %); best 5.106e-08s; worst 0.0008399s; std dev. 0.0003955 (taking best). +Reference operation time is 5.10573e-08 s (470.1 Mflops) with 24 threads. +After merge step 1: tpop: 5.106e-08 s ~Mflops: 470.060 nsubm:1 otn:24 +Applying merge (3 -> 1 leaves, 24 th.) yielded SPEEDUP of 82535.606x: 0.004214s -> 5.106e-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 0.07567s (of which 4.601e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 1.907e-06s sorting, 8.106e-06s analyzing) -Total merge + benchmarking process took 0.07567s, equivalent to 66886.2/4.8 new/old ops (0.1397s for 2 clones -- as 123504.3/8.8 ops, or 61752.2/4.4 ops per clone), SPEEDUP of 14064.489x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 14064.489x (0.01591s -> 1.131e-06s), will amortize in 4.8 ops by saving 0.01591s per op. -In 1 tuning rounds (tot. 0.24s, 0.14s for constructor, 2 clones) obtained a SPEEDUP of 1406348.9% (1.406e+04x) (from 0.001508 to 21.21 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01312s (of which 1.311e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 1.192e-06s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.01312s, equivalent to 256908.7/3.1 new/old ops (0.02522s for 2 clones -- as 494013.5/6.0 ops, or 247006.8/3.0 ops per clone), SPEEDUP of 82535.606x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 82535.606x (0.004214s -> 5.106e-08s), will amortize in 3.1 ops by saving 0.004214s per op. +In 1 tuning rounds (tot. 0.039s, 0.025s for constructor, 2 clones) obtained a SPEEDUP of 8253460.6% (8.254e+04x) (from 0.005695 to 470.1 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 0.239869 s (1.591e-02 s -> 1.131e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.039094 s (4.214e-03 s -> 5.106e-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 0.97198 s and estimated a speedup of 1.000000 x (1.131e-06 s -> 1.131e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.191605 s and estimated a speedup of 1.000000 x (5.106e-08 s -> 5.106e-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 13 3 3 6 0.000001 0.047793 0.048204 0.095997 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.095998 -%:RSB_SUBDIVISION_TIME:A.mtx S N 13 3 3 6 0.047793 -%:RSB_SHUFFLE_TIME:A.mtx S N 13 3 3 6 0.048204 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 13 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 13 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.095997 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 13 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 13 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 13 3 3 6 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 24 3 3 6 0.000000 0.010038 0.008661 0.018699 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018699 +%:RSB_SUBDIVISION_TIME:A.mtx S N 24 3 3 6 0.010038 +%:RSB_SHUFFLE_TIME:A.mtx S N 24 3 3 6 0.008661 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 24 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 24 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018699 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 24 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 24 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 24 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 13 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 13 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 13 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 13 3 3 6 96 -%:SM_MINMAXAVGNNZ:A.mtx S N 13 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 24 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 24 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 24 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 24 3 3 6 96 +%:SM_MINMAXAVGNNZ:A.mtx S N 24 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[13] SPMV[13] SPMV[13] -%operation:A.mtx 0.132034 1e+09 1e+09 -%constructor:matrix SORT[13] SCAN[13] SHUFFLE[13] INSERT[13] -%constructor:A.mtx 9.53674e-07 0.0477929 0 0.0482039 +%operation:matrix CONSTRUCTOR[24] SPMV[24] SPMV[24] +%operation:A.mtx 0.027478 1e+09 1e+09 +%constructor:matrix SORT[24] SCAN[24] SHUFFLE[24] INSERT[24] +%constructor:A.mtx 0 0.0100381 0 0.00866103 # 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 13 threads -# Constructed matrix (took 0.123s): (3 x 3)[0x566c1c80]{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 24 threads +# Constructed matrix (took 0.027s): (3 x 3)[0x5818bb10]{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 (13 th.) took 0.05579s; avg 0.0186s ( +/- 34.13/ 27.76 %); best 0.01225s; worst 0.02376s; std dev. 0.004772 (taking best). -Reference operation time is 0.0122509 s (0.007836 Mflops) with 13 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: 0.01225 Mflops: 0.008) -Merge (3 -> 1 leaves) took w.c.t. of 4.387e-05s, ~1.407e-05s of computing time (of which 3.815e-06s sorting, 7.868e-06s analysis) -3 iterations (13 th.) took 1.311e-05s; avg 4.371e-06s ( +/- 74.12/150.91 %); best 1.131e-06s; worst 1.097e-05s; std dev. 4.665e-06 (taking best). -Reference operation time is 1.1313e-06 s (84.86 Mflops) with 13 threads. -After merge step 1: tpop: 1.131e-06 s ~Mflops: 84.858 nsubm:1 otn:13 -Applying merge (3 -> 1 leaves, 13 th.) yielded SPEEDUP of 10829.083x: 0.01225s -> 1.131e-06s, so taking this instance. +3 iterations (24 th.) took 0.01305s; avg 0.00435s ( +/- 1.46/ 1.42 %); best 0.004287s; worst 0.004412s; std dev. 5.111e-05 (taking best). +Reference operation time is 0.004287 s (0.02239 Mflops) with 24 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: 0.004287 Mflops: 0.022) +Merge (3 -> 1 leaves) took w.c.t. of 8.106e-06s, ~1.907e-06s of computing time (of which 9.537e-07s sorting, 1.192e-06s analysis) +3 iterations (24 th.) took 3.815e-06s; avg 1.272e-06s ( +/- 95.98/125.00 %); best 5.106e-08s; worst 2.861e-06s; std dev. 1.189e-06 (taking best). +Reference operation time is 5.10573e-08 s (1880 Mflops) with 24 threads. +After merge step 1: tpop: 5.106e-08 s ~Mflops: 1880.239 nsubm:1 otn:24 +Applying merge (3 -> 1 leaves, 24 th.) yielded SPEEDUP of 83964.511x: 0.004287s -> 5.106e-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 0.06467s (of which 4.911e-05s partitioning, 0s I/O); computing times: 1.407e-05s in par. loops, 3.815e-06s sorting, 7.868e-06s analyzing) -Total merge + benchmarking process took 0.06467s, equivalent to 57164.6/5.3 new/old ops (0.1317s for 2 clones -- as 116434.6/10.8 ops, or 58217.3/5.4 ops per clone), SPEEDUP of 10829.083x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 10829.083x (0.01225s -> 1.131e-06s), will amortize in 5.3 ops by saving 0.01225s per op. -In 1 tuning rounds (tot. 0.19s, 0.13s for constructor, 2 clones) obtained a SPEEDUP of 1082808.3% (1.083e+04x) (from 0.007836 to 84.86 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01303s (of which 1.216e-05s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 9.537e-07s sorting, 1.192e-06s analyzing) +Total merge + benchmarking process took 0.01303s, equivalent to 255241.7/3.0 new/old ops (0.02618s for 2 clones -- as 512776.1/6.1 ops, or 256388.0/3.1 ops per clone), SPEEDUP of 83964.511x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 83964.511x (0.004287s -> 5.106e-08s), will amortize in 3.0 ops by saving 0.004287s per op. +In 1 tuning rounds (tot. 0.039s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 8396351.1% (8.396e+04x) (from 0.02239 to 1880 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 0.188212 s (1.225e-02 s -> 1.131e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0393209 s (4.287e-03 s -> 5.106e-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 0.939333 s and estimated a speedup of 1.000000 x (1.131e-06 s -> 1.131e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.192424 s and estimated a speedup of 1.000000 x (5.106e-08 s -> 5.106e-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 13 3 3 6 0.000000 0.054749 0.044096 0.098845 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.098845 -%:RSB_SUBDIVISION_TIME:A.mtx S N 13 3 3 6 0.054749 -%:RSB_SHUFFLE_TIME:A.mtx S N 13 3 3 6 0.044096 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 13 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 13 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.098845 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 13 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 13 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 13 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 24 3 3 6 0.000000 0.010233 0.008061 0.018294 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018294 +%:RSB_SUBDIVISION_TIME:A.mtx S N 24 3 3 6 0.010233 +%:RSB_SHUFFLE_TIME:A.mtx S N 24 3 3 6 0.008061 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 24 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 24 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018294 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 24 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 24 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 24 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 13 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 13 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 13 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 13 3 3 6 96 -%:SM_MINMAXAVGNNZ:A.mtx S N 13 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 24 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 24 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 24 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 24 3 3 6 96 +%:SM_MINMAXAVGNNZ:A.mtx S N 24 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[13] SPMV[13] SPMV[13] -%operation:A.mtx 0.123238 1e+09 1e+09 -%constructor:matrix SORT[13] SCAN[13] SHUFFLE[13] INSERT[13] -%constructor:A.mtx 0 0.054749 0 0.044096 +%operation:matrix CONSTRUCTOR[24] SPMV[24] SPMV[24] +%operation:A.mtx 0.027071 1e+09 1e+09 +%constructor:matrix SORT[24] SCAN[24] SHUFFLE[24] INSERT[24] +%constructor:A.mtx 0 0.0102332 0 0.00806093 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 11.439s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.991s/0.000s . +# so far, program took 5.625s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.977s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.09988s (system CPU time used) -ru_utime : 29.75s (user CPU time used) +ru_maxrss: 21 (maximum resident set size -- MB) +ru_stime : 1.04s (system CPU time used) +ru_utime : 30.48s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was S). -# Cache block size total 524288 bytes, per-thread 40329 bytes -# so far, program took 11.439s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.991s/0.000s . +# Cache block size total 4194304 bytes, per-thread 174762 bytes +# so far, program took 5.625s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.977s/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 13 threads -# Constructed matrix (took 0.152s): (3 x 3)[0x566c4500]{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 24 threads +# Constructed matrix (took 0.028s): (3 x 3)[0x5818e3a0]{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 (13 th.) took 0.06797s; avg 0.02266s ( +/- 46.96/ 58.84 %); best 0.01202s; worst 0.03599s; std dev. 0.00997 (taking best). -Reference operation time is 0.0120182 s (0.007988 Mflops) with 13 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: 0.01202 Mflops: 0.008) -Merge (3 -> 1 leaves) took w.c.t. of 3.91e-05s, ~1.192e-05s of computing time (of which 2.861e-06s sorting, 6.914e-06s analysis) -3 iterations (13 th.) took 0.02392s; avg 0.007972s ( +/- 99.99/199.85 %); best 1.131e-06s; worst 0.02391s; std dev. 0.01127 (taking best). -Reference operation time is 1.1313e-06 s (84.86 Mflops) with 13 threads. -After merge step 1: tpop: 1.131e-06 s ~Mflops: 84.858 nsubm:1 otn:13 -Applying merge (3 -> 1 leaves, 13 th.) yielded SPEEDUP of 10623.393x: 0.01202s -> 1.131e-06s, so taking this instance. +3 iterations (24 th.) took 0.01315s; avg 0.004382s ( +/- 0.30/ 0.47 %); best 0.004369s; worst 0.004403s; std dev. 1.487e-05 (taking best). +Reference operation time is 0.00436902 s (0.02197 Mflops) with 24 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: 0.004369 Mflops: 0.022) +Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (24 th.) took 0.0007212s; avg 0.0002404s ( +/- 99.98/199.11 %); best 5.106e-08s; worst 0.0007191s; std dev. 0.0003385 (taking best). +Reference operation time is 5.10573e-08 s (1880 Mflops) with 24 threads. +After merge step 1: tpop: 5.106e-08 s ~Mflops: 1880.239 nsubm:1 otn:24 +Applying merge (3 -> 1 leaves, 24 th.) yielded SPEEDUP of 85570.862x: 0.004369s -> 5.106e-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 0.08401s (of which 4.601e-05s partitioning, 0s I/O); computing times: 1.192e-05s in par. loops, 2.861e-06s sorting, 6.914e-06s analyzing) -Total merge + benchmarking process took 0.08401s, equivalent to 74263.4/7.0 new/old ops (0.139s for 2 clones -- as 122901.4/11.6 ops, or 61450.7/5.8 ops per clone), SPEEDUP of 10623.393x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 10623.393x (0.01202s -> 1.131e-06s), will amortize in 7.0 ops by saving 0.01202s per op. -In 1 tuning rounds (tot. 0.23s, 0.14s for constructor, 2 clones) obtained a SPEEDUP of 1062239.3% (1.062e+04x) (from 0.007988 to 84.86 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01291s (of which 1.287e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.01291s, equivalent to 252930.2/3.0 new/old ops (0.02521s for 2 clones -- as 493719.4/5.8 ops, or 246859.7/2.9 ops per clone), SPEEDUP of 85570.862x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 85570.862x (0.004369s -> 5.106e-08s), will amortize in 3.0 ops by saving 0.004369s per op. +In 1 tuning rounds (tot. 0.039s, 0.025s for constructor, 2 clones) obtained a SPEEDUP of 8556986.2% (8.557e+04x) (from 0.02197 to 1880 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 0.231158 s (1.202e-02 s -> 1.131e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0391622 s (4.369e-03 s -> 5.106e-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 1.47993 s and estimated a speedup of 1.000000 x (1.131e-06 s -> 1.131e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.216128 s and estimated a speedup of 1.000000 x (5.106e-08 s -> 5.106e-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 13 3 3 6 0.000001 0.055228 0.044221 0.099449 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.099450 -%:RSB_SUBDIVISION_TIME:A.mtx S N 13 3 3 6 0.055228 -%:RSB_SHUFFLE_TIME:A.mtx S N 13 3 3 6 0.044221 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 13 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 13 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.099449 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 13 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 13 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 13 3 3 6 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 24 3 3 6 0.000000 0.010229 0.008664 0.018893 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018893 +%:RSB_SUBDIVISION_TIME:A.mtx S N 24 3 3 6 0.010229 +%:RSB_SHUFFLE_TIME:A.mtx S N 24 3 3 6 0.008664 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 24 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 24 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018893 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 24 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 24 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 24 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 13 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 13 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 13 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 13 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 13 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 24 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 24 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 24 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 24 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 24 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[13] SPMV[13] SPMV[13] -%operation:A.mtx 0.152129 1e+09 1e+09 -%constructor:matrix SORT[13] SCAN[13] SHUFFLE[13] INSERT[13] -%constructor:A.mtx 9.53674e-07 0.055228 0 0.0442209 +%operation:matrix CONSTRUCTOR[24] SPMV[24] SPMV[24] +%operation:A.mtx 0.0276361 1e+09 1e+09 +%constructor:matrix SORT[24] SCAN[24] SHUFFLE[24] INSERT[24] +%constructor:A.mtx 0 0.0102289 0 0.00866413 # 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 13 threads -# Constructed matrix (took 0.155s): (3 x 3)[0x566c4500]{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 24 threads +# Constructed matrix (took 0.027s): (3 x 3)[0x5818e3a0]{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 (13 th.) took 0.06806s; avg 0.02269s ( +/- 46.94/ 28.79 %); best 0.01204s; worst 0.02922s; std dev. 0.007595 (taking best). -Reference operation time is 0.012037 s (0.0319 Mflops) with 13 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: 0.01204 Mflops: 0.032) -Merge (3 -> 1 leaves) took w.c.t. of 3.505e-05s, ~1.097e-05s of computing time (of which 2.861e-06s sorting, 6.914e-06s analysis) -3 iterations (13 th.) took 0.0002501s; avg 8.337e-05s ( +/- 98.64/195.14 %); best 1.131e-06s; worst 0.000246s; std dev. 0.000115 (taking best). -Reference operation time is 1.1313e-06 s (339.4 Mflops) with 13 threads. -After merge step 1: tpop: 1.131e-06 s ~Mflops: 339.434 nsubm:1 otn:13 -Applying merge (3 -> 1 leaves, 13 th.) yielded SPEEDUP of 10640.042x: 0.01204s -> 1.131e-06s, so taking this instance. +3 iterations (24 th.) took 0.0131s; avg 0.004368s ( +/- 2.07/ 1.24 %); best 0.004277s; worst 0.004422s; std dev. 6.449e-05 (taking best). +Reference operation time is 0.00427699 s (0.08978 Mflops) with 24 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: 0.004277 Mflops: 0.090) +Merge (3 -> 1 leaves) took w.c.t. of 8.106e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 1.192e-06s analysis) +3 iterations (24 th.) took 0.0001199s; avg 3.997e-05s ( +/- 97.61/195.23 %); best 9.537e-07s; worst 0.000118s; std dev. 5.518e-05 (taking best). +Reference operation time is 9.53674e-07 s (402.7 Mflops) with 24 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 402.653 nsubm:1 otn:24 +Applying merge (3 -> 1 leaves, 24 th.) yielded SPEEDUP of 4484.750x: 0.004277s -> 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 0.07195s (of which 3.982e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 2.861e-06s sorting, 6.914e-06s analyzing) -Total merge + benchmarking process took 0.07195s, equivalent to 63602.3/6.0 new/old ops (0.1595s for 2 clones -- as 140977.0/13.2 ops, or 70488.5/6.6 ops per clone), SPEEDUP of 10640.042x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 10640.042x (0.01204s -> 1.131e-06s), will amortize in 6.0 ops by saving 0.01204s per op. -In 1 tuning rounds (tot. 0.23s, 0.16s for constructor, 2 clones) obtained a SPEEDUP of 1063904.2% (1.064e+04x) (from 0.0319 to 339.4 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01316s (of which 1.216e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 9.537e-07s sorting, 1.192e-06s analyzing) +Total merge + benchmarking process took 0.01316s, equivalent to 13797.2/3.1 new/old ops (0.02604s for 2 clones -- as 27307.0/6.1 ops, or 13653.5/3.0 ops per clone), SPEEDUP of 4484.750x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 4484.750x (0.004277s -> 9.537e-07s), will amortize in 3.1 ops by saving 0.004276s per op. +In 1 tuning rounds (tot. 0.039s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 448375.0% (4485x) (from 0.08978 to 402.7 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 0.227982 s (1.204e-02 s -> 1.131e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0393441 s (4.277e-03 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 1.13194 s and estimated a speedup of 1.000000 x (1.131e-06 s -> 1.131e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.217815 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 13 3 3 6 0.000001 0.055129 0.056023 0.111152 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.111153 -%:RSB_SUBDIVISION_TIME:A.mtx S N 13 3 3 6 0.055129 -%:RSB_SHUFFLE_TIME:A.mtx S N 13 3 3 6 0.056023 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 13 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 13 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.111152 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 13 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 13 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 13 3 3 6 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 24 3 3 6 0.000000 0.010099 0.008570 0.018669 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018669 +%:RSB_SUBDIVISION_TIME:A.mtx S N 24 3 3 6 0.010099 +%:RSB_SHUFFLE_TIME:A.mtx S N 24 3 3 6 0.008570 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 24 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 24 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018669 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 24 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 24 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 24 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 13 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 13 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 13 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 13 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 13 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 24 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 24 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 24 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 24 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 24 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[13] SPMV[13] SPMV[13] -%operation:A.mtx 0.155188 1e+09 1e+09 -%constructor:matrix SORT[13] SCAN[13] SHUFFLE[13] INSERT[13] -%constructor:A.mtx 9.53674e-07 0.0551288 0 0.0560231 +%operation:matrix CONSTRUCTOR[24] SPMV[24] SPMV[24] +%operation:A.mtx 0.0273869 1e+09 1e+09 +%constructor:matrix SORT[24] SCAN[24] SHUFFLE[24] INSERT[24] +%constructor:A.mtx 0 0.0100989 0 0.00856996 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 15.071s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 8.062s/0.000s . +# so far, program took 6.273s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.489s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.1229s (system CPU time used) -ru_utime : 45.05s (user CPU time used) +ru_maxrss: 21 (maximum resident set size -- MB) +ru_stime : 1.073s (system CPU time used) +ru_utime : 44.54s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was C). -# Cache block size total 524288 bytes, per-thread 40329 bytes -# so far, program took 15.071s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 8.062s/0.000s . +# Cache block size total 4194304 bytes, per-thread 174762 bytes +# so far, program took 6.273s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.489s/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 13 threads -# Constructed matrix (took 0.167s): (3 x 3)[0x566c4500]{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 24 threads +# Constructed matrix (took 0.028s): (3 x 3)[0x5818e3a0]{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 (13 th.) took 0.084s; avg 0.028s ( +/- 14.31/ 11.05 %); best 0.02399s; worst 0.03109s; std dev. 0.00297 (taking best). -Reference operation time is 0.0239921 s (0.004001 Mflops) with 13 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: 0.02399 Mflops: 0.004) -Merge (3 -> 1 leaves) took w.c.t. of 4.387e-05s, ~1.311e-05s of computing time (of which 4.053e-06s sorting, 8.106e-06s analysis) -3 iterations (13 th.) took 2.909e-05s; avg 9.696e-06s ( +/- 88.33/177.87 %); best 1.131e-06s; worst 2.694e-05s; std dev. 1.219e-05 (taking best). -Reference operation time is 1.1313e-06 s (84.86 Mflops) with 13 threads. -After merge step 1: tpop: 1.131e-06 s ~Mflops: 84.858 nsubm:1 otn:13 -Applying merge (3 -> 1 leaves, 13 th.) yielded SPEEDUP of 21207.587x: 0.02399s -> 1.131e-06s, so taking this instance. +3 iterations (24 th.) took 0.01294s; avg 0.004312s ( +/- 1.57/ 1.42 %); best 0.004244s; worst 0.004373s; std dev. 5.284e-05 (taking best). +Reference operation time is 0.00424409 s (0.02262 Mflops) with 24 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: 0.004244 Mflops: 0.023) +Merge (3 -> 1 leaves) took w.c.t. of 8.821e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (24 th.) took 1.311e-05s; avg 4.371e-06s ( +/- 98.83/178.18 %); best 5.106e-08s; worst 1.216e-05s; std dev. 5.521e-06 (taking best). +Reference operation time is 5.10573e-08 s (1880 Mflops) with 24 threads. +After merge step 1: tpop: 5.106e-08 s ~Mflops: 1880.239 nsubm:1 otn:24 +Applying merge (3 -> 1 leaves, 24 th.) yielded SPEEDUP of 83123.979x: 0.004244s -> 5.106e-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 0.05998s (of which 5.102e-05s partitioning, 0s I/O); computing times: 1.311e-05s in par. loops, 4.053e-06s sorting, 8.106e-06s analyzing) -Total merge + benchmarking process took 0.05998s, equivalent to 53020.7/2.5 new/old ops (0.1238s for 2 clones -- as 109426.8/5.2 ops, or 54713.4/2.6 ops per clone), SPEEDUP of 21207.587x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 21207.587x (0.02399s -> 1.131e-06s), will amortize in 2.5 ops by saving 0.02399s per op. -In 1 tuning rounds (tot. 0.21s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 2120658.7% (2.121e+04x) (from 0.004001 to 84.86 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01296s (of which 1.192e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.01296s, equivalent to 253868.8/3.1 new/old ops (0.02589s for 2 clones -- as 507013.8/6.1 ops, or 253506.9/3.0 ops per clone), SPEEDUP of 83123.979x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 83123.979x (0.004244s -> 5.106e-08s), will amortize in 3.1 ops by saving 0.004244s per op. +In 1 tuning rounds (tot. 0.039s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 8312297.9% (8.312e+04x) (from 0.02262 to 1880 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 0.208026 s (2.399e-02 s -> 1.131e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0389121 s (4.244e-03 s -> 5.106e-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 1.06982 s and estimated a speedup of 1.000000 x (1.131e-06 s -> 1.131e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.216089 s and estimated a speedup of 1.000000 x (5.106e-08 s -> 5.106e-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 13 3 3 6 0.000000 0.055955 0.067389 0.123344 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.123344 -%:RSB_SUBDIVISION_TIME:A.mtx S N 13 3 3 6 0.055955 -%:RSB_SHUFFLE_TIME:A.mtx S N 13 3 3 6 0.067389 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 13 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 13 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.123344 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 13 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 13 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 13 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 24 3 3 6 0.000000 0.010242 0.008618 0.018860 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018860 +%:RSB_SUBDIVISION_TIME:A.mtx S N 24 3 3 6 0.010242 +%:RSB_SHUFFLE_TIME:A.mtx S N 24 3 3 6 0.008618 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 24 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 24 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018860 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 24 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 24 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 24 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 13 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 13 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 13 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 13 3 3 6 276 -%:SM_MINMAXAVGNNZ:A.mtx S N 13 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 24 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 24 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 24 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 24 3 3 6 276 +%:SM_MINMAXAVGNNZ:A.mtx S N 24 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[13] SPMV[13] SPMV[13] -%operation:A.mtx 0.167381 1e+09 1e+09 -%constructor:matrix SORT[13] SCAN[13] SHUFFLE[13] INSERT[13] -%constructor:A.mtx 0 0.0559549 0 0.067389 +%operation:matrix CONSTRUCTOR[24] SPMV[24] SPMV[24] +%operation:A.mtx 0.0276148 1e+09 1e+09 +%constructor:matrix SORT[24] SCAN[24] SHUFFLE[24] INSERT[24] +%constructor:A.mtx 0 0.010242 0 0.00861812 # 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 13 threads -# Constructed matrix (took 0.156s): (3 x 3)[0x566c4500]{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 24 threads +# Constructed matrix (took 0.027s): (3 x 3)[0x5818e3a0]{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 (13 th.) took 0.06579s; avg 0.02193s ( +/- 8.55/ 9.30 %); best 0.02006s; worst 0.02397s; std dev. 0.001603 (taking best). -Reference operation time is 0.020056 s (0.01915 Mflops) with 13 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: 0.02006 Mflops: 0.019) -Merge (3 -> 1 leaves) took w.c.t. of 3.6e-05s, ~1.097e-05s of computing time (of which 3.099e-06s sorting, 5.96e-06s analysis) -3 iterations (13 th.) took 1.001e-05s; avg 3.338e-06s ( +/- 66.11/114.29 %); best 1.131e-06s; worst 7.153e-06s; std dev. 2.725e-06 (taking best). -Reference operation time is 1.1313e-06 s (339.4 Mflops) with 13 threads. -After merge step 1: tpop: 1.131e-06 s ~Mflops: 339.434 nsubm:1 otn:13 -Applying merge (3 -> 1 leaves, 13 th.) yielded SPEEDUP of 17728.346x: 0.02006s -> 1.131e-06s, so taking this instance. +3 iterations (24 th.) took 0.01293s; avg 0.004311s ( +/- 0.91/ 1.56 %); best 0.004272s; worst 0.004378s; std dev. 4.764e-05 (taking best). +Reference operation time is 0.00427198 s (0.08989 Mflops) with 24 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: 0.004272 Mflops: 0.090) +Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 1.192e-06s analysis) +3 iterations (24 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 42.86/ 71.43 %); best 9.537e-07s; worst 2.861e-06s; std dev. 8.485e-07 (taking best). +Reference operation time is 9.53674e-07 s (402.7 Mflops) with 24 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 402.653 nsubm:1 otn:24 +Applying merge (3 -> 1 leaves, 24 th.) yielded SPEEDUP of 4479.500x: 0.004272s -> 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 0.0742s (of which 4.196e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 3.099e-06s sorting, 5.96e-06s analyzing) -Total merge + benchmarking process took 0.0742s, equivalent to 65588.4/3.7 new/old ops (0.146s for 2 clones -- as 129085.8/7.3 ops, or 64542.9/3.6 ops per clone), SPEEDUP of 17728.346x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 17728.346x (0.02006s -> 1.131e-06s), will amortize in 3.7 ops by saving 0.02005s per op. -In 1 tuning rounds (tot. 0.21s, 0.15s for constructor, 2 clones) obtained a SPEEDUP of 1772734.6% (1.773e+04x) (from 0.01915 to 339.4 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01307s (of which 1.311e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 9.537e-07s sorting, 1.192e-06s analyzing) +Total merge + benchmarking process took 0.01307s, equivalent to 13702.8/3.1 new/old ops (0.02676s for 2 clones -- as 28057.8/6.3 ops, or 14028.9/3.1 ops per clone), SPEEDUP of 4479.500x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 4479.500x (0.004272s -> 9.537e-07s), will amortize in 3.1 ops by saving 0.004271s per op. +In 1 tuning rounds (tot. 0.04s, 0.027s for constructor, 2 clones) obtained a SPEEDUP of 447850.0% (4480x) (from 0.08989 to 402.7 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 0.212017 s (2.006e-02 s -> 1.131e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0397849 s (4.272e-03 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 1.16768 s and estimated a speedup of 1.000000 x (1.131e-06 s -> 1.131e-06 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.218224 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:1.7320508075688772 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 13 3 3 6 0.000001 0.063750 0.048892 0.112642 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.112643 -%:RSB_SUBDIVISION_TIME:A.mtx S N 13 3 3 6 0.063750 -%:RSB_SHUFFLE_TIME:A.mtx S N 13 3 3 6 0.048892 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 13 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 13 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 13 3 3 6 0.112642 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 13 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 13 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 13 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 13 3 3 6 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 24 3 3 6 0.000000 0.010051 0.008732 0.018783 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018783 +%:RSB_SUBDIVISION_TIME:A.mtx S N 24 3 3 6 0.010051 +%:RSB_SHUFFLE_TIME:A.mtx S N 24 3 3 6 0.008732 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 24 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 24 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 24 3 3 6 0.018783 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 24 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 24 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 24 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 24 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 13 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 13 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 13 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 13 3 3 6 276 -%:SM_MINMAXAVGNNZ:A.mtx S N 13 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 24 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 24 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 24 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 24 3 3 6 276 +%:SM_MINMAXAVGNNZ:A.mtx S N 24 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[13] SPMV[13] SPMV[13] -%operation:A.mtx 0.155772 1e+09 1e+09 -%constructor:matrix SORT[13] SCAN[13] SHUFFLE[13] INSERT[13] -%constructor:A.mtx 9.53674e-07 0.06375 0 0.048892 +%operation:matrix CONSTRUCTOR[24] SPMV[24] SPMV[24] +%operation:A.mtx 0.0274851 1e+09 1e+09 +%constructor:matrix SORT[24] SCAN[24] SHUFFLE[24] INSERT[24] +%constructor:A.mtx 0 0.010051 0 0.00873184 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 18.255s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 10.719s/0.000s . +# so far, program took 6.922s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.002s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.1365s (system CPU time used) -ru_utime : 59.77s (user CPU time used) +ru_maxrss: 21 (maximum resident set size -- MB) +ru_stime : 1.119s (system CPU time used) +ru_utime : 58.59s (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 13 13 0 4.0000 4.6667 3 1 21.21 1.207e-02 0.000e+00 1.131e-06 0.000e+00 1.716e-01 1.31e-01 5.17e+00 1 2.40e-05 -pr: 9:R_R A 3 3 6 4 D S N 13 13 0 4.0000 4.6667 3 1 84.86 2.411e-02 0.000e+00 1.131e-06 0.000e+00 2.720e-01 3.22e-01 2.79e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 24 24 0 4.0000 4.6667 3 1 470.06 4.455e-03 0.000e+00 5.106e-08 0.000e+00 3.962e-02 2.90e+00 5.17e+00 1 2.40e-05 +pr: 9:R_R A 3 3 6 4 D S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.319e-03 0.000e+00 5.106e-08 0.000e+00 3.914e-02 7.13e+00 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. 1598856.8 % faster, avg. sp. ratio 15989.568x, max sp. ratio 21311.697x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 196043.7/151679.0/240408.4/392087.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.7/ 11.3/ 14.2/ 25.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.8, min. 11.3, max. 14.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 8592475.3 % faster, avg. sp. ratio 85925.753x, max sp. ratio 87256.596x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 771349.5/766630.9/776068.2/1542699.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 8.9/ 9.1/ 18.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.0, min. 8.9, 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 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 0.173/ 0.110/ 0.237,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.453/ 0.131/ 0.322,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.839/ 2.429/ 5.249,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.028/ 2.899/ 7.129,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.: 0.22 s, min 0.17 s, max 0.27 s, tot 0.44 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.22 s, min 0.17 s, max 0.27 s, tot 0.44 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.304e+01, min 2.121e+01, max 8.486e+01 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.985e-03, min 1.989e-03, max 3.982e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 2.263e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.809e-02s, min 1.207e-02s, max 2.411e-02s, tot 3.618e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 9.133e+00 1.974e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.175e+03, min 4.701e+02, max 1.880e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.381e-02, min 5.387e-03, max 2.223e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.106e-08s, min 5.106e-08s, max 5.106e-08s, tot 1.021e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.387e-03s, min 4.319e-03s, max 4.455e-03s, tot 8.774e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.462e+00 9.644e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+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 13 13 0 4.0000 4.6667 3 1 21.21 1.591e-02 0.000e+00 1.131e-06 0.000e+00 2.399e-01 7.78e-02 3.17e+00 1 2.40e-05 -pr: 11:R_R A 3 3 6 4 S S N 13 13 0 4.0000 4.6667 3 1 84.86 1.225e-02 0.000e+00 1.131e-06 0.000e+00 1.882e-01 1.73e-01 1.54e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 1 S S N 24 24 0 4.0000 4.6667 3 1 470.06 4.214e-03 0.000e+00 5.106e-08 0.000e+00 3.909e-02 1.72e+00 3.17e+00 1 2.40e-05 +pr: 11:R_R A 3 3 6 4 S S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.287e-03 0.000e+00 5.106e-08 0.000e+00 3.932e-02 3.84e+00 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. 1244578.6 % faster, avg. sp. ratio 12446.786x, max sp. ratio 14064.489x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 189199.5/166368.6/212030.3/378398.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 15.2/ 15.1/ 15.4/ 30.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 15.2, min. 15.1, max. 15.4 ops) +#pr: (in succ. cases rsb autotuning gave avg. 8324905.8 % faster, avg. sp. ratio 83250.058x, max sp. ratio 83964.511x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 767910.3/765687.6/770133.1/1535820.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 9.2/ 9.3/ 18.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.2, min. 9.2, max. 9.3 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 0.099/ 0.067/ 0.131,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.251/ 0.078/ 0.173,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.194/ 1.489/ 2.899,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.562/ 1.724/ 3.839,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.: 0.21 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.: 0.21 s, min 0.19 s, max 0.24 s, tot 0.43 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.304e+01, min 2.121e+01, max 8.486e+01 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.672e-03, min 1.508e-03, max 7.836e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 2.263e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.408e-02s, min 1.225e-02s, max 1.591e-02s, tot 2.816e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.654e+01 3.221e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.175e+03, min 4.701e+02, max 1.880e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.404e-02, min 5.695e-03, max 2.239e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.106e-08s, min 5.106e-08s, max 5.106e-08s, tot 1.021e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.251e-03s, min 4.214e-03s, max 4.287e-03s, tot 8.501e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.080e+00 1.573e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+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 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 13 13 0 4.0000 4.6667 3 1 84.86 1.202e-02 0.000e+00 1.131e-06 0.000e+00 2.312e-01 1.31e-01 1.29e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 13 13 0 4.0000 4.6667 3 1 339.43 1.204e-02 0.000e+00 1.131e-06 0.000e+00 2.280e-01 3.22e-01 6.98e-01 1 3.84e-04 +pr: 5:R_R A 3 3 6 1 C S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.369e-03 0.000e+00 5.106e-08 0.000e+00 3.916e-02 2.90e+00 1.29e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 24 24 0 4.0000 4.6667 3 1 402.65 4.277e-03 0.000e+00 9.537e-07 0.000e+00 3.934e-02 3.82e-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. 1063071.8 % faster, avg. sp. ratio 10631.718x, max sp. ratio 10640.042x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 202926.6/201522.9/204330.2/405853.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 19.1/ 18.9/ 19.2/ 38.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 19.1, min. 18.9, max. 19.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4502680.6 % faster, avg. sp. ratio 45027.806x, max sp. ratio 85570.862x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 404139.2/41255.2/767023.1/808278.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 9.0/ 9.2/ 18.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.1, min. 9.0, max. 9.2 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 0.173/ 0.110/ 0.237,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.453/ 0.131/ 0.322,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.355/ 0.281/ 2.429,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 3.280/ 0.382/ 2.899,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.: 0.23 s, min 0.23 s, max 0.23 s, tot 0.46 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.23 s, min 0.23 s, max 0.23 s, tot 0.46 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.121e+02, min 8.486e+01, max 3.394e+02 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.994e-02, min 7.988e-03, max 3.190e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 2.263e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.203e-02s, min 1.202e-02s, max 1.204e-02s, tot 2.406e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 9.133e+00 1.974e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+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.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.141e+03, min 4.027e+02, max 1.880e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.588e-02, min 2.197e-02, max 8.978e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.024e-07s, min 5.106e-08s, max 9.537e-07s, tot 1.005e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.323e-03s, min 4.277e-03s, max 4.369e-03s, tot 8.646e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 9.644e+00 8.335e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.142e-01 x, min 2.142e-01 x, max 2.142e-01 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 13 13 0 4.0000 4.6667 3 1 84.86 2.399e-02 0.000e+00 1.131e-06 0.000e+00 2.080e-01 2.37e-01 2.29e+00 1 9.60e-05 -pr: 15:R_R A 3 3 6 4 Z S N 13 13 0 4.0000 4.6667 3 1 339.43 2.006e-02 0.000e+00 1.131e-06 0.000e+00 2.120e-01 6.19e-01 1.32e+00 1 3.84e-04 +pr: 7:R_R A 3 3 6 1 Z S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.244e-03 0.000e+00 5.106e-08 0.000e+00 3.891e-02 5.25e+00 2.29e+00 1 9.60e-05 +pr: 15:R_R A 3 3 6 4 Z S N 24 24 0 4.0000 4.6667 3 1 402.65 4.272e-03 0.000e+00 9.537e-07 0.000e+00 3.978e-02 7.34e-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. 1946696.6 % faster, avg. sp. ratio 19467.966x, max sp. ratio 21207.587x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 185646.9/183883.0/187410.7/371293.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.6/ 8.7/ 10.6/ 19.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.6, min. 8.7, max. 10.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4380073.9 % faster, avg. sp. ratio 43801.739x, max sp. ratio 83123.979x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 401921.1/41717.5/762124.7/803842.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 9.2/ 9.3/ 18.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.2, min. 9.2, max. 9.3 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 0.322/ 0.194/ 0.449,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.856/ 0.237/ 0.619,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.421/ 0.533/ 4.309,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.983/ 0.734/ 5.249,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.: 0.21 s, min 0.21 s, max 0.21 s, tot 0.42 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.21 s, min 0.21 s, max 0.21 s, tot 0.42 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.121e+02, min 8.486e+01, max 3.394e+02 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.157e-02, min 4.001e-03, max 1.915e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 2.263e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.202e-02s, min 2.006e-02s, max 2.399e-02s, tot 4.405e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.818e+00 1.113e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+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.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.08 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.141e+03, min 4.027e+02, max 1.880e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.625e-02, min 2.262e-02, max 8.989e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.024e-07s, min 5.106e-08s, max 9.537e-07s, tot 1.005e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.258e-03s, min 4.244e-03s, max 4.272e-03s, tot 8.516e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.436e+00 4.397e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.142e-01 x, min 2.142e-01 x, max 2.142e-01 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 13 13 0 4.0000 4.6667 3 1 21.21 1.207e-02 0.000e+00 1.131e-06 0.000e+00 1.716e-01 1.31e-01 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 13 13 0 4.0000 4.6667 3 1 21.21 1.591e-02 0.000e+00 1.131e-06 0.000e+00 2.399e-01 7.78e-02 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 13 13 0 4.0000 4.6667 3 1 84.86 1.202e-02 0.000e+00 1.131e-06 0.000e+00 2.312e-01 1.31e-01 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 13 13 0 4.0000 4.6667 3 1 84.86 2.399e-02 0.000e+00 1.131e-06 0.000e+00 2.080e-01 2.37e-01 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 24 24 0 4.0000 4.6667 3 1 470.06 4.455e-03 0.000e+00 5.106e-08 0.000e+00 3.962e-02 2.90e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 24 24 0 4.0000 4.6667 3 1 470.06 4.214e-03 0.000e+00 5.106e-08 0.000e+00 3.909e-02 1.72e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.369e-03 0.000e+00 5.106e-08 0.000e+00 3.916e-02 2.90e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.244e-03 0.000e+00 5.106e-08 0.000e+00 3.891e-02 5.25e+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. 1413972.7 % faster, avg. sp. ratio 14140.727x, max sp. ratio 21207.587x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 187980.7/151679.0/212030.3/751922.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.3/ 8.7/ 19.2/ 57.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.3, min. 8.7, max. 19.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 8462076.0 % faster, avg. sp. ratio 84621.760x, max sp. ratio 87256.596x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 767725.9/762124.7/776068.2/3070903.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 8.9/ 9.3/ 36.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.1, min. 8.9, max. 9.3 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 0.120/ 0.067/ 0.194,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.576/ 0.078/ 0.237,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.664/ 1.489/ 4.309,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.770/ 1.724/ 5.249,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.: 0.21 s, min 0.17 s, max 0.24 s, tot 0.85 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.21 s, min 0.17 s, max 0.24 s, tot 0.85 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.304e+01, min 2.121e+01, max 8.486e+01 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.872e-03, min 1.508e-03, max 7.988e-03 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 4.525e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.600e-02s, min 1.202e-02s, max 2.399e-02s, tot 6.399e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.113e+01 3.221e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.16 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.16 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.175e+03, min 4.701e+02, max 1.880e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.392e-02, min 5.387e-03, max 2.262e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.106e-08s, min 5.106e-08s, max 5.106e-08s, tot 2.042e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.321e-03s, min 4.214e-03s, max 4.455e-03s, tot 1.728e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.436e+00 1.573e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+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 13 13 0 4.0000 4.6667 3 1 84.86 2.411e-02 0.000e+00 1.131e-06 0.000e+00 2.720e-01 3.22e-01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 13 13 0 4.0000 4.6667 3 1 84.86 1.225e-02 0.000e+00 1.131e-06 0.000e+00 1.882e-01 1.73e-01 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 13 13 0 4.0000 4.6667 3 1 339.43 1.204e-02 0.000e+00 1.131e-06 0.000e+00 2.280e-01 3.22e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 13 13 0 4.0000 4.6667 3 1 339.43 2.006e-02 0.000e+00 1.131e-06 0.000e+00 2.120e-01 6.19e-01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.319e-03 0.000e+00 5.106e-08 0.000e+00 3.914e-02 7.13e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.287e-03 0.000e+00 5.106e-08 0.000e+00 3.932e-02 3.84e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 24 24 0 4.0000 4.6667 3 1 402.65 4.277e-03 0.000e+00 9.537e-07 0.000e+00 3.934e-02 3.82e-01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 24 24 0 4.0000 4.6667 3 1 402.65 4.272e-03 0.000e+00 9.537e-07 0.000e+00 3.978e-02 7.34e-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. 1512629.2 % faster, avg. sp. ratio 15127.292x, max sp. ratio 21311.697x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 198927.7/166368.6/240408.4/795710.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.0/ 10.6/ 18.9/ 56.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.0, min. 10.6, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4437991.8 % faster, avg. sp. ratio 44380.918x, max sp. ratio 84594.910x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 404934.2/41255.2/770133.1/1619736.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 9.1/ 9.3/ 36.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.2, min. 9.1, max. 9.3 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 0.263/ 0.131/ 0.449,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.436/ 0.173/ 0.619,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.240/ 0.281/ 5.249,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.084/ 0.382/ 7.129,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.: 0.23 s, min 0.19 s, max 0.27 s, tot 0.90 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.23 s, min 0.19 s, max 0.27 s, tot 0.90 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.121e+02, min 8.486e+01, max 3.394e+02 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.572e-02, min 3.982e-03, max 3.190e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 4.525e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.711e-02s, min 1.204e-02s, max 2.411e-02s, tot 6.845e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.818e+00 1.654e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+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 (4 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.16 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.16 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.141e+03, min 4.027e+02, max 1.880e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.607e-02, min 2.223e-02, max 8.989e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.024e-07s, min 5.106e-08s, max 9.537e-07s, tot 2.009e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.289e-03s, min 4.272e-03s, max 4.319e-03s, tot 1.716e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.462e+00 8.335e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.107e+00 x, min 2.142e-01 x, max 4.000e+00 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 13 13 0 4.0000 4.6667 3 1 21.21 1.207e-02 0.000e+00 1.131e-06 0.000e+00 1.716e-01 1.31e-01 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 13 13 0 4.0000 4.6667 3 1 21.21 1.591e-02 0.000e+00 1.131e-06 0.000e+00 2.399e-01 7.78e-02 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 13 13 0 4.0000 4.6667 3 1 84.86 1.202e-02 0.000e+00 1.131e-06 0.000e+00 2.312e-01 1.31e-01 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 13 13 0 4.0000 4.6667 3 1 84.86 2.399e-02 0.000e+00 1.131e-06 0.000e+00 2.080e-01 2.37e-01 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 13 13 0 4.0000 4.6667 3 1 84.86 2.411e-02 0.000e+00 1.131e-06 0.000e+00 2.720e-01 3.22e-01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 13 13 0 4.0000 4.6667 3 1 84.86 1.225e-02 0.000e+00 1.131e-06 0.000e+00 1.882e-01 1.73e-01 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 13 13 0 4.0000 4.6667 3 1 339.43 1.204e-02 0.000e+00 1.131e-06 0.000e+00 2.280e-01 3.22e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 13 13 0 4.0000 4.6667 3 1 339.43 2.006e-02 0.000e+00 1.131e-06 0.000e+00 2.120e-01 6.19e-01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 24 24 0 4.0000 4.6667 3 1 470.06 4.455e-03 0.000e+00 5.106e-08 0.000e+00 3.962e-02 2.90e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 24 24 0 4.0000 4.6667 3 1 470.06 4.214e-03 0.000e+00 5.106e-08 0.000e+00 3.909e-02 1.72e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.369e-03 0.000e+00 5.106e-08 0.000e+00 3.916e-02 2.90e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.244e-03 0.000e+00 5.106e-08 0.000e+00 3.891e-02 5.25e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.319e-03 0.000e+00 5.106e-08 0.000e+00 3.914e-02 7.13e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.287e-03 0.000e+00 5.106e-08 0.000e+00 3.932e-02 3.84e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 24 24 0 4.0000 4.6667 3 1 402.65 4.277e-03 0.000e+00 9.537e-07 0.000e+00 3.934e-02 3.82e-01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 24 24 0 4.0000 4.6667 3 1 402.65 4.272e-03 0.000e+00 9.537e-07 0.000e+00 3.978e-02 7.34e-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. 1463300.9 % faster, avg. sp. ratio 14634.009x, max sp. ratio 21311.697x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 193454.2/151679.0/240408.4/1547633.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.2/ 8.7/ 19.2/113.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.2, min. 8.7, max. 19.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 6450033.9 % faster, avg. sp. ratio 64501.339x, max sp. ratio 87256.596x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 586330.0/41255.2/776068.2/4690640.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 8.9/ 9.3/ 73.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.1, min. 8.9, max. 9.3 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 0.192/ 0.067/ 0.449,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.012/ 0.078/ 0.619,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.452/ 0.281/ 5.249,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.854/ 0.382/ 7.129,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.: 0.22 s, min 0.17 s, max 0.27 s, tot 1.75 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.22 s, min 0.17 s, max 0.27 s, tot 1.75 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.326e+02, min 2.121e+01, max 3.394e+02 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 9.794e-03, min 1.508e-03, max 3.190e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 9.050e-06s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.656e-02s, min 1.202e-02s, max 2.411e-02s, tot 1.324e-01s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.818e+00 3.221e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+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 (4 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.31 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.31 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.158e+03, min 4.027e+02, max 1.880e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.500e-02, min 5.387e-03, max 8.989e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 2.767e-07s, min 5.106e-08s, max 9.537e-07s, tot 2.214e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.305e-03s, min 4.214e-03s, max 4.455e-03s, tot 3.444e-02s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.462e+00 8.335e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.107e+00 x, min 2.142e-01 x, max 4.000e+00 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 13 13 0 4.0000 4.6667 3 1 21.21 1.207e-02 0.000e+00 1.131e-06 0.000e+00 1.716e-01 1.31e-01 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 13 13 0 4.0000 4.6667 3 1 21.21 1.591e-02 0.000e+00 1.131e-06 0.000e+00 2.399e-01 7.78e-02 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 13 13 0 4.0000 4.6667 3 1 84.86 1.202e-02 0.000e+00 1.131e-06 0.000e+00 2.312e-01 1.31e-01 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 13 13 0 4.0000 4.6667 3 1 84.86 2.399e-02 0.000e+00 1.131e-06 0.000e+00 2.080e-01 2.37e-01 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 24 24 0 4.0000 4.6667 3 1 470.06 4.455e-03 0.000e+00 5.106e-08 0.000e+00 3.962e-02 2.90e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 24 24 0 4.0000 4.6667 3 1 470.06 4.214e-03 0.000e+00 5.106e-08 0.000e+00 3.909e-02 1.72e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.369e-03 0.000e+00 5.106e-08 0.000e+00 3.916e-02 2.90e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.244e-03 0.000e+00 5.106e-08 0.000e+00 3.891e-02 5.25e+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. 1413972.7 % faster, avg. sp. ratio 14140.727x, max sp. ratio 21207.587x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 187980.7/151679.0/212030.3/751922.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.3/ 8.7/ 19.2/ 57.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.3, min. 8.7, max. 19.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 8462076.0 % faster, avg. sp. ratio 84621.760x, max sp. ratio 87256.596x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 767725.9/762124.7/776068.2/3070903.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 8.9/ 9.3/ 36.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.1, min. 8.9, max. 9.3 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 0.120/ 0.067/ 0.194,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.576/ 0.078/ 0.237,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.664/ 1.489/ 4.309,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.770/ 1.724/ 5.249,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.: 0.21 s, min 0.17 s, max 0.24 s, tot 0.85 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.21 s, min 0.17 s, max 0.24 s, tot 0.85 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.304e+01, min 2.121e+01, max 8.486e+01 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.872e-03, min 1.508e-03, max 7.988e-03 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 4.525e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.600e-02s, min 1.202e-02s, max 2.399e-02s, tot 6.399e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.113e+01 3.221e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.16 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.16 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.175e+03, min 4.701e+02, max 1.880e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.392e-02, min 5.387e-03, max 2.262e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.106e-08s, min 5.106e-08s, max 5.106e-08s, tot 2.042e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.321e-03s, min 4.214e-03s, max 4.455e-03s, tot 1.728e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.436e+00 1.573e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+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 13 13 0 4.0000 4.6667 3 1 84.86 2.411e-02 0.000e+00 1.131e-06 0.000e+00 2.720e-01 3.22e-01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 13 13 0 4.0000 4.6667 3 1 84.86 1.225e-02 0.000e+00 1.131e-06 0.000e+00 1.882e-01 1.73e-01 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 13 13 0 4.0000 4.6667 3 1 339.43 1.204e-02 0.000e+00 1.131e-06 0.000e+00 2.280e-01 3.22e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 13 13 0 4.0000 4.6667 3 1 339.43 2.006e-02 0.000e+00 1.131e-06 0.000e+00 2.120e-01 6.19e-01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.319e-03 0.000e+00 5.106e-08 0.000e+00 3.914e-02 7.13e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.287e-03 0.000e+00 5.106e-08 0.000e+00 3.932e-02 3.84e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 24 24 0 4.0000 4.6667 3 1 402.65 4.277e-03 0.000e+00 9.537e-07 0.000e+00 3.934e-02 3.82e-01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 24 24 0 4.0000 4.6667 3 1 402.65 4.272e-03 0.000e+00 9.537e-07 0.000e+00 3.978e-02 7.34e-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. 1512629.2 % faster, avg. sp. ratio 15127.292x, max sp. ratio 21311.697x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 198927.7/166368.6/240408.4/795710.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.0/ 10.6/ 18.9/ 56.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.0, min. 10.6, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4437991.8 % faster, avg. sp. ratio 44380.918x, max sp. ratio 84594.910x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 404934.2/41255.2/770133.1/1619736.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 9.1/ 9.3/ 36.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.2, min. 9.1, max. 9.3 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 0.263/ 0.131/ 0.449,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.436/ 0.173/ 0.619,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.240/ 0.281/ 5.249,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.084/ 0.382/ 7.129,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.: 0.23 s, min 0.19 s, max 0.27 s, tot 0.90 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.23 s, min 0.19 s, max 0.27 s, tot 0.90 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.121e+02, min 8.486e+01, max 3.394e+02 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.572e-02, min 3.982e-03, max 3.190e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 4.525e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.711e-02s, min 1.204e-02s, max 2.411e-02s, tot 6.845e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.818e+00 1.654e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+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 (4 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.16 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.16 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.141e+03, min 4.027e+02, max 1.880e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.607e-02, min 2.223e-02, max 8.989e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.024e-07s, min 5.106e-08s, max 9.537e-07s, tot 2.009e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.289e-03s, min 4.272e-03s, max 4.319e-03s, tot 1.716e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.462e+00 8.335e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.107e+00 x, min 2.142e-01 x, max 4.000e+00 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: @@ -5058,56 +5108,56 @@ #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 13 13 0 4.0000 4.6667 3 1 21.21 1.207e-02 0.000e+00 1.131e-06 0.000e+00 1.716e-01 1.31e-01 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 13 13 0 4.0000 4.6667 3 1 21.21 1.591e-02 0.000e+00 1.131e-06 0.000e+00 2.399e-01 7.78e-02 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 13 13 0 4.0000 4.6667 3 1 84.86 1.202e-02 0.000e+00 1.131e-06 0.000e+00 2.312e-01 1.31e-01 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 13 13 0 4.0000 4.6667 3 1 84.86 2.399e-02 0.000e+00 1.131e-06 0.000e+00 2.080e-01 2.37e-01 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 13 13 0 4.0000 4.6667 3 1 84.86 2.411e-02 0.000e+00 1.131e-06 0.000e+00 2.720e-01 3.22e-01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 13 13 0 4.0000 4.6667 3 1 84.86 1.225e-02 0.000e+00 1.131e-06 0.000e+00 1.882e-01 1.73e-01 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 13 13 0 4.0000 4.6667 3 1 339.43 1.204e-02 0.000e+00 1.131e-06 0.000e+00 2.280e-01 3.22e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 13 13 0 4.0000 4.6667 3 1 339.43 2.006e-02 0.000e+00 1.131e-06 0.000e+00 2.120e-01 6.19e-01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 24 24 0 4.0000 4.6667 3 1 470.06 4.455e-03 0.000e+00 5.106e-08 0.000e+00 3.962e-02 2.90e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 24 24 0 4.0000 4.6667 3 1 470.06 4.214e-03 0.000e+00 5.106e-08 0.000e+00 3.909e-02 1.72e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.369e-03 0.000e+00 5.106e-08 0.000e+00 3.916e-02 2.90e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.244e-03 0.000e+00 5.106e-08 0.000e+00 3.891e-02 5.25e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.319e-03 0.000e+00 5.106e-08 0.000e+00 3.914e-02 7.13e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 24 24 0 4.0000 4.6667 3 1 1880.24 4.287e-03 0.000e+00 5.106e-08 0.000e+00 3.932e-02 3.84e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 24 24 0 4.0000 4.6667 3 1 402.65 4.277e-03 0.000e+00 9.537e-07 0.000e+00 3.934e-02 3.82e-01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 24 24 0 4.0000 4.6667 3 1 402.65 4.272e-03 0.000e+00 9.537e-07 0.000e+00 3.978e-02 7.34e-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. 1463300.9 % faster, avg. sp. ratio 14634.009x, max sp. ratio 21311.697x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 193454.2/151679.0/240408.4/1547633.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.2/ 8.7/ 19.2/113.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.2, min. 8.7, max. 19.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 6450033.9 % faster, avg. sp. ratio 64501.339x, max sp. ratio 87256.596x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 586330.0/41255.2/776068.2/4690640.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 8.9/ 9.3/ 73.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.1, min. 8.9, max. 9.3 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 0.192/ 0.067/ 0.449,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.012/ 0.078/ 0.619,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.452/ 0.281/ 5.249,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.854/ 0.382/ 7.129,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.: 0.22 s, min 0.17 s, max 0.27 s, tot 1.75 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.22 s, min 0.17 s, max 0.27 s, tot 1.75 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.326e+02, min 2.121e+01, max 3.394e+02 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 9.794e-03, min 1.508e-03, max 3.190e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 1.131e-06s, min 1.131e-06s, max 1.131e-06s, tot 9.050e-06s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.656e-02s, min 1.202e-02s, max 2.411e-02s, tot 1.324e-01s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.818e+00 3.221e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.077e+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 (4 samples, the non-min-nrhs ones) -#pr: Record collection took 11.60 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.31 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.04 s, max 0.04 s, tot 0.31 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.158e+03, min 4.027e+02, max 1.880e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.500e-02, min 5.387e-03, max 8.989e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 2.767e-07s, min 5.106e-08s, max 9.537e-07s, tot 2.214e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.305e-03s, min 4.214e-03s, max 4.455e-03s, tot 3.444e-02s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.462e+00 8.335e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.713e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.107e+00 x, min 2.142e-01 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) +#pr: Record collection took 2.29 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4730 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4783 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1740330277_gcc-14.2.rpr -# Removing the temporary record file rsbench_pr__1740330277_gcc-14.2.rpr.tmp. -# terminating run at 1740330296 (after 18.2s 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__1774742845_gcc-14.2.rpr +# Removing the temporary record file rsbench_pr__1774742845_gcc-14.2.rpr.tmp. +# terminating run at 1774742852 (after 6.9s 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 + 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 -+ grep '^[^ ].\{80,\}' + cat /build/reproducible-path/librsb-1.3.0.2+dfsg/README ++ grep '^[^ ].\{80,\}' + true ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h ++ wc -l @@ -5118,8 +5168,8 @@ ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h ++ wc -l + test 182 -ge 157 -++ wc -c ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h +++ wc -c + test 5369 -ge 4600 + exit 0 if ! ./librsb-config --help ; then echo "Problem executing the librsb-config script!"; false; fi; @@ -5154,7 +5204,7 @@ 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 @@ -5164,15 +5214,15 @@ 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 1740330297 +# beginning run at 1774742852 # /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 -Wformat -Werror=format-security -O3 -std=c99 -# average timer granularity: 9.34e-07 s +# average timer granularity: 5.09e-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:/usr/lib/libeatmydata # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -5211,15 +5261,15 @@ # 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: ionos2-i386 +# 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5231,40 +5281,40 @@ # 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 6.272s +# Memory benchmark took 4.473s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 4 samples (1008 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). -# Cache block size total 524288 bytes, per-thread 40329 bytes -# so far, program took 6.311s 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 174762 bytes +# so far, program took 4.475s 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 2.165e-01 s (100.00 %) - analyzed arrays in 5.639e-02 s (26.05 %) - cleaned-up arrays in 2.599e-05 s (0.01 %) - deduplicated arrays in 1.812e-05 s (0.01 %) + converted COO to RSB in 3.035e-02 s (100.00 %) + analyzed arrays in 6.577e-03 s (21.67 %) + cleaned-up arrays in 2.003e-05 s (0.07 %) + deduplicated arrays in 9.060e-06 s (0.03 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.120e-01 s (51.76 %) - memory allocations took 3.386e-05 s (0.02 %) - leafs setup took 1.001e-05 s (0.00 %) - halfword conversion took 4.795e-02 s (22.15 %) -Built (100 x 100)[0x57c10e10]{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 0.217s): (100 x 100)[0x57c10e10]{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 1.712e-02 s (56.43 %) + memory allocations took 1.407e-05 s (0.05 %) + leafs setup took 4.053e-06 s (0.01 %) + halfword conversion took 6.597e-03 s (21.74 %) +Built (100 x 100)[0x56f61e60]{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 0.030s): (100 x 100)[0x56f61e60]{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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5275,11 +5325,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5290,11 +5340,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5304,16 +5354,16 @@ # 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 0.09194s; avg 0.03065s ( +/- 47.83/ 43.27 %); best 0.01599s; worst 0.04391s; std dev. 0.01144 (taking best). -Reference operation time is 0.0159869 s (1.264 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: 0.01599 Mflops: 1.264) -Merge (3 -> 1 leaves) took w.c.t. of 0.0001471s, ~0.000108s of computing time (of which 5.221e-05s sorting, 1.097e-05s analysis) +3 iterations (1 th.) took 0.01306s; avg 0.004355s ( +/- 1.05/ 0.61 %); best 0.004309s; worst 0.004381s; std dev. 3.25e-05 (taking best). +Reference operation time is 0.00430894 s (4.688 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: 0.004309 Mflops: 4.688) +Merge (3 -> 1 leaves) took w.c.t. of 5.817e-05s, ~4.601e-05s of computing time (of which 2.193e-05s sorting, 3.099e-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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5324,11 +5374,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5338,14 +5388,14 @@ # 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 5.698e-05s; avg 1.899e-05s ( +/- 25.94/ 46.86 %); best 1.407e-05s; worst 2.789e-05s; std dev. 6.306e-06 (taking best). -Reference operation time is 1.40667e-05 s (1436 Mflops) with 1 threads. +3 iterations (1 th.) took 3.695e-05s; avg 1.232e-05s ( +/- 3.23/ 6.45 %); best 1.192e-05s; worst 1.311e-05s; std dev. 5.62e-07 (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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5355,25 +5405,25 @@ # 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: 1.407e-05 s ~Mflops: 1436.016 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1136.508x: 0.01599s -> 1.407e-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 361.460x: 0.004309s -> 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 0.2521s (of which 0.0001559s partitioning, 0.18s I/O); computing times: 0.000108s in par. loops, 5.221e-05s sorting, 1.097e-05s analyzing) -Total merge + benchmarking process took 0.2521s, equivalent to 17920.7/15.8 new/old ops (0.1436s for 2 clones -- as 10209.8/9.0 ops, or 5104.9/4.5 ops per clone), SPEEDUP of 1136.508x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1136.508x (0.01599s -> 1.407e-05s), will amortize in 15.8 ops by saving 0.01597s per op. -In 1 tuning rounds (tot. 0.42s, 0.14s for constructor, 2 clones) obtained a SPEEDUP of 113550.8% (1137x) (from 1.264 to 1436 Mflops). Employed 0.15s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04066s (of which 6.199e-05s partitioning, 0.02757s I/O); computing times: 4.601e-05s in par. loops, 2.193e-05s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.04066s, equivalent to 3410.6/9.4 new/old ops (0.02594s for 2 clones -- as 2176.2/6.0 ops, or 1088.1/3.0 ops per clone), SPEEDUP of 361.460x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 361.460x (0.004309s -> 1.192e-05s), will amortize in 9.5 ops by saving 0.004297s per op. +In 1 tuning rounds (tot. 0.067s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 36046.0% (361.5x) (from 4.688 to 1694 Mflops). Employed 0.028s 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 0.568075 s (1.599e-02 s -> 1.407e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0948861 s (4.309e-03 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5384,11 +5434,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5399,13 +5449,13 @@ # 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 13. +Starting with requested 0 threads ; current default 1 ; at most 24. # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5416,11 +5466,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5430,27 +5480,27 @@ # 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 6.914e-05s; avg 2.305e-05s ( +/- 38.97/ 77.93 %); best 1.407e-05s; worst 4.101e-05s; std dev. 1.27e-05 (taking best). -Reference operation time is 1.40667e-05 s (1436 Mflops) with 1 threads. +3 iterations (1 th.) took 3.695e-05s; avg 1.232e-05s ( +/- 10.97/ 12.26 %); best 1.097e-05s; worst 1.383e-05s; std dev. 1.173e-06 (taking best). +Reference operation time is 1.09673e-05 s (1842 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 9.938e-02 s (100.00 %) - analyzed arrays in 3.548e-02 s (35.70 %) - cleaned-up arrays in 1.907e-05 s (0.02 %) - deduplicated arrays in 1.693e-05 s (0.02 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 6.382e-02 s (64.22 %) - memory allocations took 9.298e-06 s (0.01 %) - leafs setup took 8.106e-06 s (0.01 %) - halfword conversion took 2.694e-05 s (0.03 %) -Built (100 x 100)[0x57c19f20]{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 = 13). -# 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: 13 + converted COO to RSB in 1.663e-02 s (100.00 %) + analyzed arrays in 6.204e-03 s (37.30 %) + cleaned-up arrays in 1.097e-05 s (0.07 %) + deduplicated arrays in 1.407e-05 s (0.08 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 1.039e-02 s (62.49 %) + memory allocations took 2.861e-06 s (0.02 %) + leafs setup took 1.192e-06 s (0.01 %) + halfword conversion took 6.914e-06 s (0.04 %) +Built (100 x 100)[0x56f6bcf0]{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 = 24). +# 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5461,12 +5511,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5477,22 +5527,22 @@ # 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 1.837e-01 s (100.00 %) - analyzed arrays in 4.771e-02 s (25.97 %) - cleaned-up arrays in 1.693e-05 s (0.01 %) - deduplicated arrays in 1.717e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 7.595e-02 s (41.35 %) - memory allocations took 1.597e-05 s (0.01 %) - leafs setup took 9.060e-06 s (0.00 %) - halfword conversion took 5.996e-02 s (32.64 %) -Built (100 x 100)[0x57c11150]{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: 13 + converted COO to RSB in 2.320e-02 s (100.00 %) + analyzed arrays in 6.534e-03 s (28.17 %) + cleaned-up arrays in 1.097e-05 s (0.05 %) + deduplicated arrays in 1.407e-05 s (0.06 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 7.882e-03 s (33.98 %) + memory allocations took 2.861e-06 s (0.01 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 8.752e-03 s (37.73 %) +Built (100 x 100)[0x56f62190]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5503,11 +5553,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5518,11 +5568,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5532,16 +5582,16 @@ # 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 0.07988s; avg 0.02663s ( +/- 39.93/ 50.27 %); best 0.01599s; worst 0.04001s; std dev. 0.009997 (taking best). -Reference operation time is 0.0159948 s (1.263 Mflops) with 1 threads. -Challenging best inner round reference (1.40667e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0159948 s/0 threads (speedup 0.000879455 x), same?n. +3 iterations (1 th.) took 0.01309s; avg 0.004365s ( +/- 2.20/ 1.31 %); best 0.004269s; worst 0.004422s; std dev. 6.817e-05 (taking best). +Reference operation time is 0.00426912 s (4.732 Mflops) with 1 threads. +Challenging best inner round reference (1.09673e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00426912 s/0 threads (speedup 0.00256897 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5552,12 +5602,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5568,22 +5618,22 @@ # 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 1.596e-01 s (100.00 %) - analyzed arrays in 7.157e-02 s (44.84 %) - cleaned-up arrays in 1.907e-05 s (0.01 %) - deduplicated arrays in 1.812e-05 s (0.01 %) + converted COO to RSB in 2.394e-02 s (100.00 %) + analyzed arrays in 6.452e-03 s (26.96 %) + cleaned-up arrays in 1.216e-05 s (0.05 %) + deduplicated arrays in 1.287e-05 s (0.05 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.001e-02 s (25.07 %) - memory allocations took 1.860e-05 s (0.01 %) - leafs setup took 1.001e-05 s (0.01 %) - halfword conversion took 4.796e-02 s (30.05 %) -Built (100 x 100)[0x57c119b0]{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 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: 13 + shuffled partitions in 8.721e-03 s (36.44 %) + memory allocations took 2.861e-06 s (0.01 %) + leafs setup took 1.907e-06 s (0.01 %) + halfword conversion took 8.730e-03 s (36.47 %) +Built (100 x 100)[0x56f62920]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5594,11 +5644,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5609,11 +5659,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5623,16 +5673,16 @@ # 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 0.07175s; avg 0.02392s ( +/- 31.27/ 32.00 %); best 0.01644s; worst 0.03157s; std dev. 0.006178 (taking best). -Reference operation time is 0.016438 s (1.229 Mflops) with 1 threads. -Challenging best inner round reference (1.40667e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.016438 s/0 threads (speedup 0.000855742 x), same?n. +3 iterations (1 th.) took 0.01284s; avg 0.00428s ( +/- 0.06/ 0.10 %); best 0.004277s; worst 0.004284s; std dev. 3.171e-06 (taking best). +Reference operation time is 0.00427699 s (4.723 Mflops) with 1 threads. +Challenging best inner round reference (1.09673e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.00427699 s/0 threads (speedup 0.00256425 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5643,12 +5693,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5659,22 +5709,22 @@ # 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 6.760e-02 s (44.50 %) - cleaned-up arrays in 1.693e-05 s (0.01 %) - deduplicated arrays in 1.597e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 3.601e-02 s (23.71 %) - memory allocations took 2.217e-05 s (0.01 %) - leafs setup took 1.192e-05 s (0.01 %) - halfword conversion took 4.822e-02 s (31.74 %) -Built (100 x 100)[0x57c1a000]{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: 25, symflags:'LS' + converted COO to RSB in 2.812e-02 s (100.00 %) + analyzed arrays in 1.078e-02 s (38.34 %) + cleaned-up arrays in 1.097e-05 s (0.04 %) + deduplicated arrays in 1.407e-05 s (0.05 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.644e-03 s (30.74 %) + memory allocations took 5.007e-06 s (0.02 %) + leafs setup took 3.099e-06 s (0.01 %) + halfword conversion took 8.661e-03 s (30.80 %) +Built (100 x 100)[0x56f6bdd0]{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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5685,11 +5735,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5700,11 +5750,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5714,16 +5764,16 @@ # 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 0.07149s; avg 0.02383s ( +/- 32.92/ 32.16 %); best 0.01598s; worst 0.03149s; std dev. 0.006333 (taking best). -Reference operation time is 0.0159841 s (1.264 Mflops) with 1 threads. -Challenging best inner round reference (1.40667e-05 s/1 threads) with: subdivision 1, 25 leaves, 2.317 bytes/nz, 0.0159841 s/0 threads (speedup 0.000880045 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 34 subms, 25 lsubms, 2.3168 bpnz +3 iterations (1 th.) took 0.01293s; avg 0.004312s ( +/- 0.53/ 0.40 %); best 0.004289s; worst 0.004329s; std dev. 1.679e-05 (taking best). +Reference operation time is 0.00428891 s (4.71 Mflops) with 1 threads. +Challenging best inner round reference (1.09673e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.00428891 s/0 threads (speedup 0.00255712 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5734,12 +5784,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5750,22 +5800,22 @@ # 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 1.477e-01 s (100.00 %) - analyzed arrays in 5.962e-02 s (40.37 %) - cleaned-up arrays in 1.812e-05 s (0.01 %) - deduplicated arrays in 1.597e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 4.804e-02 s (32.53 %) - memory allocations took 2.170e-05 s (0.01 %) - leafs setup took 2.193e-05 s (0.01 %) - halfword conversion took 3.994e-02 s (27.05 %) -Built (100 x 100)[0x57c1a000]{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: 36, 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: 13 + converted COO to RSB in 2.812e-02 s (100.00 %) + analyzed arrays in 1.077e-02 s (38.29 %) + cleaned-up arrays in 1.192e-05 s (0.04 %) + deduplicated arrays in 1.311e-05 s (0.05 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.644e-03 s (30.74 %) + memory allocations took 5.007e-06 s (0.02 %) + leafs setup took 2.861e-06 s (0.01 %) + halfword conversion took 8.674e-03 s (30.85 %) +Built (100 x 100)[0x56f6bdd0]{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: 49, 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5776,11 +5826,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5791,11 +5841,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5805,16 +5855,16 @@ # 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 0.05579s; avg 0.0186s ( +/- 35.06/ 49.84 %); best 0.01208s; worst 0.02786s; std dev. 0.006732 (taking best). -Reference operation time is 0.0120759 s (1.673 Mflops) with 1 threads. -Challenging best inner round reference (1.40667e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.0120759 s/0 threads (speedup 0.00116486 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 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 -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 +3 iterations (1 th.) took 0.01292s; avg 0.004305s ( +/- 0.38/ 0.39 %); best 0.004289s; worst 0.004322s; std dev. 1.344e-05 (taking best). +Reference operation time is 0.00428915 s (4.71 Mflops) with 1 threads. +Challenging best inner round reference (1.09673e-05 s/1 threads) with: subdivision 2, 49 leaves, 2.414 bytes/nz, 0.00428915 s/0 threads (speedup 0.00255698 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 67 subms, 49 lsubms, 2.4143 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5825,12 +5875,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5841,22 +5891,22 @@ # 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 1.676e-01 s (100.00 %) - analyzed arrays in 5.956e-02 s (35.53 %) - cleaned-up arrays in 1.693e-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 5.750e-02 s (34.30 %) - memory allocations took 3.409e-05 s (0.02 %) - leafs setup took 1.693e-05 s (0.01 %) - halfword conversion took 5.048e-02 s (30.12 %) -Built (100 x 100)[0x57c40e80]{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: 36, 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: 13 + converted COO to RSB in 2.840e-02 s (100.00 %) + analyzed arrays in 1.094e-02 s (38.52 %) + cleaned-up arrays in 1.097e-05 s (0.04 %) + deduplicated arrays in 1.287e-05 s (0.05 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.652e-03 s (30.46 %) + memory allocations took 7.391e-06 s (0.03 %) + leafs setup took 5.960e-06 s (0.02 %) + halfword conversion took 8.775e-03 s (30.89 %) +Built (100 x 100)[0x56f92c70]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5867,11 +5917,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5882,11 +5932,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5896,17 +5946,17 @@ # 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 0.08755s; avg 0.02918s ( +/- 12.09/ 16.19 %); best 0.02565s; worst 0.03391s; std dev. 0.003474 (taking best). -Reference operation time is 0.0256529 s (0.7874 Mflops) with 1 threads. -Challenging best inner round reference (1.40667e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.0256529 s/0 threads (speedup 0.000548348 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 1436.02 Mflops. +3 iterations (1 th.) took 0.01295s; avg 0.004315s ( +/- 0.49/ 0.73 %); best 0.004294s; worst 0.004347s; std dev. 2.285e-05 (taking best). +Reference operation time is 0.00429416 s (4.704 Mflops) with 1 threads. +Challenging best inner round reference (1.09673e-05 s/1 threads) with: subdivision 4, 102 leaves, 2.653 bytes/nz, 0.00429416 s/0 threads (speedup 0.00255399 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 138 subms, 102 lsubms, 2.6527 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 1841.85 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5916,23 +5966,23 @@ # 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 1.27982 s (eq. to 9e+04/ 9e+04 old/new op.times), gained local/global speedup 1 x (1.40667e-05 : 1.40667e-05) / 1 x (1.40667e-05 : 1.40667e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.214308 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1 x (1.09673e-05 : 1.09673e-05) / 1 x (1.09673e-05 : 1.09673e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 1.3s, 0.91s for constructor, 0 clones) obtained NO speedup (best stays 1436 Mflops). -Second run of RSB Autotuner took 1.27995 s and estimated a speedup of 1.000000 x (1.407e-05 s -> 1.407e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.21s, 0.15s for constructor, 0 clones) obtained NO speedup (best stays 1842 Mflops). +Second run of RSB Autotuner took 0.214348 s and estimated a speedup of 1.000000 x (1.097e-05 s -> 1.097e-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 0.056390 0.112045 0.168435 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.168435 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.056390 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.112045 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.006577 0.017125 0.023702 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.023702 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.006577 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.017125 %: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 0.168435 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.023702 %: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 @@ -5947,45 +5997,45 @@ %: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 0.21648 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.030349 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.05639 0 0.112045 -# so far, program took 8.525s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.848s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00657701 0 0.0171249 +# so far, program took 4.856s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.309s/0.000s . getrusage() stats: -ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.05654s (system CPU time used) -ru_utime : 13.15s (user CPU time used) +ru_maxrss: 21 (maximum resident set size -- MB) +ru_stime : 0.7992s (system CPU time used) +ru_utime : 11.86s (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 8.525s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.848s/0.000s . +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# so far, program took 4.856s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.309s/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 2.228e-01 s (100.00 %) - analyzed arrays in 5.079e-02 s (22.80 %) - cleaned-up arrays in 2.098e-05 s (0.01 %) - deduplicated arrays in 1.812e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 1.142e-01 s (51.27 %) - memory allocations took 2.193e-05 s (0.01 %) - leafs setup took 6.914e-06 s (0.00 %) - halfword conversion took 5.772e-02 s (25.90 %) -Built (100 x 100)[0x57c1a000]{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 0.223s): (100 x 100)[0x57c1a000]{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' + converted COO to RSB in 3.177e-02 s (100.00 %) + analyzed arrays in 5.578e-03 s (17.55 %) + cleaned-up arrays in 1.216e-05 s (0.04 %) + deduplicated arrays in 1.287e-05 s (0.04 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 1.737e-02 s (54.66 %) + memory allocations took 3.815e-06 s (0.01 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 8.799e-03 s (27.69 %) +Built (100 x 100)[0x56f6bdd0]{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 0.032s): (100 x 100)[0x56f6bdd0]{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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5996,11 +6046,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6011,11 +6061,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6025,16 +6075,16 @@ # 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 0.08802s; avg 0.02934s ( +/- 4.57/ 8.87 %); best 0.028s; worst 0.03194s; std dev. 0.00184 (taking best). -Reference operation time is 0.0280011 s (0.7214 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: 0.028 Mflops: 0.721) -Merge (3 -> 1 leaves) took w.c.t. of 0.000124s, ~9.108e-05s of computing time (of which 3.886e-05s sorting, 6.914e-06s analysis) +3 iterations (1 th.) took 0.01289s; avg 0.004297s ( +/- 1.21/ 1.61 %); best 0.004245s; worst 0.004366s; std dev. 5.091e-05 (taking best). +Reference operation time is 0.00424504 s (4.758 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: 0.004245 Mflops: 4.758) +Merge (3 -> 1 leaves) took w.c.t. of 4.697e-05s, ~4.101e-05s of computing time (of which 1.788e-05s sorting, 2.146e-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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6045,11 +6095,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6059,14 +6109,14 @@ # 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 5.889e-05s; avg 1.963e-05s ( +/- 18.62/ 37.25 %); best 1.597e-05s; worst 2.694e-05s; std dev. 5.17e-06 (taking best). -Reference operation time is 1.5974e-05 s (1265 Mflops) with 1 threads. +3 iterations (1 th.) took 3.505e-05s; avg 1.168e-05s ( +/- 6.12/ 4.08 %); best 1.097e-05s; worst 1.216e-05s; std dev. 5.15e-07 (taking best). +Reference operation time is 1.09673e-05 s (1842 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6076,25 +6126,25 @@ # 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: 1.597e-05 s ~Mflops: 1264.551 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1752.910x: 0.028s -> 1.597e-05s, so taking this instance. +After merge step 1: tpop: 1.097e-05 s ~Mflops: 1841.847 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 387.065x: 0.004245s -> 1.097e-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 0.2441s (of which 0.0001299s partitioning, 0.1722s I/O); computing times: 9.108e-05s in par. loops, 3.886e-05s sorting, 6.914e-06s analyzing) -Total merge + benchmarking process took 0.2441s, equivalent to 15278.9/8.7 new/old ops (0.1376s for 2 clones -- as 8615.3/4.9 ops, or 4307.6/2.5 ops per clone), SPEEDUP of 1752.910x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1752.910x (0.028s -> 1.597e-05s), will amortize in 8.7 ops by saving 0.02799s per op. -In 1 tuning rounds (tot. 0.4s, 0.14s for constructor, 2 clones) obtained a SPEEDUP of 175191.0% (1753x) (from 0.7214 to 1265 Mflops). Employed 0.18s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04033s (of which 5.102e-05s partitioning, 0.02729s I/O); computing times: 4.101e-05s in par. loops, 1.788e-05s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.04033s, equivalent to 3677.1/9.5 new/old ops (0.02583s for 2 clones -- as 2355.5/6.1 ops, or 1177.7/3.0 ops per clone), SPEEDUP of 387.065x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 387.065x (0.004245s -> 1.097e-05s), will amortize in 9.5 ops by saving 0.004234s per op. +In 1 tuning rounds (tot. 0.066s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 38606.5% (387.1x) (from 4.758 to 1842 Mflops). Employed 0.029s 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 0.580571 s (2.800e-02 s -> 1.597e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0953341 s (4.245e-03 s -> 1.097e-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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6105,11 +6155,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6120,13 +6170,13 @@ # 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 13. +Starting with requested 0 threads ; current default 1 ; at most 24. # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6137,11 +6187,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6151,27 +6201,27 @@ # 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 5.698e-05s; avg 1.899e-05s ( +/- 30.96/ 56.90 %); best 1.311e-05s; worst 2.98e-05s; std dev. 7.653e-06 (taking best). -Reference operation time is 1.3113e-05 s (1540 Mflops) with 1 threads. +3 iterations (1 th.) took 3.91e-05s; avg 1.303e-05s ( +/- 6.71/ 7.93 %); best 1.216e-05s; worst 1.407e-05s; std dev. 7.867e-07 (taking best). +Reference operation time is 1.21593e-05 s (1661 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 8.708e-02 s (100.00 %) - analyzed arrays in 4.301e-02 s (49.40 %) - cleaned-up arrays in 1.788e-05 s (0.02 %) - deduplicated arrays in 1.812e-05 s (0.02 %) + converted COO to RSB in 1.514e-02 s (100.00 %) + analyzed arrays in 6.319e-03 s (41.74 %) + cleaned-up arrays in 1.502e-05 s (0.10 %) + deduplicated arrays in 1.502e-05 s (0.10 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.399e-02 s (50.52 %) - memory allocations took 1.287e-05 s (0.01 %) - leafs setup took 7.153e-06 s (0.01 %) - halfword conversion took 1.407e-05 s (0.02 %) -Built (100 x 100)[0x57c19f20]{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 = 13). -# 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: 13 + shuffled partitions in 8.769e-03 s (57.93 %) + memory allocations took 1.287e-05 s (0.09 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 5.960e-06 s (0.04 %) +Built (100 x 100)[0x56f6bcf0]{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 = 24). +# 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6182,12 +6232,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6198,22 +6248,22 @@ # 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 6.338e-02 s (100.00 %) - analyzed arrays in 3.132e-02 s (49.42 %) - cleaned-up arrays in 1.693e-05 s (0.03 %) - deduplicated arrays in 1.693e-05 s (0.03 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 3.198e-02 s (50.46 %) - memory allocations took 1.240e-05 s (0.02 %) - leafs setup took 9.060e-06 s (0.01 %) - halfword conversion took 1.693e-05 s (0.03 %) -Built (100 x 100)[0x57c11b50]{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 -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 + converted COO to RSB in 8.976e-03 s (100.00 %) + analyzed arrays in 4.632e-03 s (51.60 %) + cleaned-up arrays in 1.192e-05 s (0.13 %) + deduplicated arrays in 1.311e-05 s (0.15 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 4.305e-03 s (47.96 %) + memory allocations took 2.861e-06 s (0.03 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 1.001e-05 s (0.11 %) +Built (100 x 100)[0x56f62920]{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 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6224,11 +6274,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6239,11 +6289,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6253,16 +6303,15 @@ # 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 5.293e-05s; avg 1.764e-05s ( +/- 21.62/ 41.89 %); best 1.383e-05s; worst 2.503e-05s; std dev. 5.227e-06 (taking best). -Reference operation time is 1.38283e-05 s (1461 Mflops) with 1 threads. -Challenging best inner round reference (1.3113e-05 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 1.38283e-05 s/0 threads (speedup 0.948276 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 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: 13 +3 iterations (1 th.) took 3.719e-05s; avg 1.24e-05s ( +/- 3.85/ 5.77 %); best 1.192e-05s; worst 1.311e-05s; std dev. 5.15e-07 (taking best). +Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. +Challenging best inner round reference (1.21593e-05 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 1.19209e-05 s/0 threads (speedup 1.02 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6273,12 +6322,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6289,22 +6338,22 @@ # 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 1.632e-01 s (100.00 %) - analyzed arrays in 6.317e-02 s (38.71 %) - cleaned-up arrays in 1.717e-05 s (0.01 %) - deduplicated arrays in 1.597e-05 s (0.01 %) + converted COO to RSB in 2.378e-02 s (100.00 %) + analyzed arrays in 6.468e-03 s (27.20 %) + cleaned-up arrays in 1.216e-05 s (0.05 %) + deduplicated arrays in 1.287e-05 s (0.05 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.198e-02 s (31.85 %) - memory allocations took 1.979e-05 s (0.01 %) - leafs setup took 1.097e-05 s (0.01 %) - halfword conversion took 4.797e-02 s (29.40 %) -Built (100 x 100)[0x57c11b50]{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: 13 + shuffled partitions in 8.657e-03 s (36.40 %) + memory allocations took 4.053e-06 s (0.02 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 8.625e-03 s (36.27 %) +Built (100 x 100)[0x56f6bdd0]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6315,11 +6364,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6330,11 +6379,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6344,16 +6393,16 @@ # 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 0.1199s; avg 0.03996s ( +/- 19.85/ 20.04 %); best 0.03203s; worst 0.04797s; std dev. 0.006508 (taking best). -Reference operation time is 0.0320301 s (0.6307 Mflops) with 1 threads. -Challenging best inner round reference (1.3113e-05 s/1 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 0.0320301 s/0 threads (speedup 0.000409397 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 0.01295s; avg 0.004318s ( +/- 1.10/ 1.23 %); best 0.00427s; worst 0.004371s; std dev. 4.137e-05 (taking best). +Reference operation time is 0.00427008 s (4.731 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/0 threads) with: subdivision 0.5, 6 leaves, 2.163 bytes/nz, 0.00427008 s/0 threads (speedup 0.00279174 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6364,12 +6413,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6380,22 +6429,22 @@ # 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 2.035e-01 s (100.00 %) - analyzed arrays in 7.537e-02 s (37.05 %) - cleaned-up arrays in 5.603e-05 s (0.03 %) - deduplicated arrays in 1.597e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 7.203e-02 s (35.40 %) - memory allocations took 2.289e-05 s (0.01 %) - leafs setup took 1.597e-05 s (0.01 %) - halfword conversion took 5.594e-02 s (27.50 %) -Built (100 x 100)[0x57c1a000]{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' + converted COO to RSB in 2.824e-02 s (100.00 %) + analyzed arrays in 1.081e-02 s (38.27 %) + cleaned-up arrays in 1.121e-05 s (0.04 %) + deduplicated arrays in 1.287e-05 s (0.05 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.790e-03 s (31.13 %) + memory allocations took 2.861e-06 s (0.01 %) + leafs setup took 2.146e-06 s (0.01 %) + halfword conversion took 8.611e-03 s (30.49 %) +Built (100 x 100)[0x56f6bdd0]{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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6406,11 +6455,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6421,11 +6470,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6435,16 +6484,16 @@ # 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 0.07193s; avg 0.02398s ( +/- 33.00/ 50.04 %); best 0.01606s; worst 0.03597s; std dev. 0.008625 (taking best). -Reference operation time is 0.016063 s (1.258 Mflops) with 1 threads. -Challenging best inner round reference (1.3113e-05 s/1 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 0.016063 s/0 threads (speedup 0.000816351 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 0.01291s; avg 0.004305s ( +/- 1.95/ 1.26 %); best 0.004221s; worst 0.004359s; std dev. 6.009e-05 (taking best). +Reference operation time is 0.00422096 s (4.786 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/0 threads) with: subdivision 1, 16 leaves, 2.25 bytes/nz, 0.00422096 s/0 threads (speedup 0.00282422 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6455,12 +6504,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6471,22 +6520,22 @@ # 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 5.174e-02 s (30.84 %) - cleaned-up arrays in 1.907e-05 s (0.01 %) - deduplicated arrays in 1.812e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 5.602e-02 s (33.39 %) - memory allocations took 1.788e-05 s (0.01 %) - leafs setup took 1.192e-05 s (0.01 %) - halfword conversion took 5.994e-02 s (35.72 %) -Built (100 x 100)[0x57c1a000]{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 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: 13 + converted COO to RSB in 2.828e-02 s (100.00 %) + analyzed arrays in 1.092e-02 s (38.60 %) + cleaned-up arrays in 1.097e-05 s (0.04 %) + deduplicated arrays in 1.407e-05 s (0.05 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.755e-03 s (30.95 %) + memory allocations took 4.292e-06 s (0.02 %) + leafs setup took 2.861e-06 s (0.01 %) + halfword conversion took 8.578e-03 s (30.33 %) +Built (100 x 100)[0x56f6bdd0]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6497,11 +6546,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6512,11 +6561,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6526,16 +6575,16 @@ # 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 0.1325s; avg 0.04417s ( +/- 21.27/ 20.27 %); best 0.03478s; worst 0.05312s; std dev. 0.007496 (taking best). -Reference operation time is 0.0347772 s (0.5808 Mflops) with 1 threads. -Challenging best inner round reference (1.3113e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.0347772 s/0 threads (speedup 0.000377058 x), same?n. +3 iterations (1 th.) took 0.01312s; avg 0.004372s ( +/- 0.23/ 0.28 %); best 0.004362s; worst 0.004384s; std dev. 9.16e-06 (taking best). +Reference operation time is 0.00436187 s (4.631 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/0 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00436187 s/0 threads (speedup 0.00273299 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 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6546,12 +6595,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6562,22 +6611,22 @@ # 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 2.519e-01 s (100.00 %) - analyzed arrays in 1.078e-01 s (42.81 %) - cleaned-up arrays in 1.717e-05 s (0.01 %) - deduplicated arrays in 1.597e-05 s (0.01 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.605e-02 s (30.19 %) - memory allocations took 3.171e-05 s (0.01 %) - leafs setup took 2.408e-05 s (0.01 %) - halfword conversion took 6.789e-02 s (26.96 %) -Built (100 x 100)[0x57c2d2c0]{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: 33, 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: 13 + converted COO to RSB in 2.852e-02 s (100.00 %) + analyzed arrays in 1.097e-02 s (38.46 %) + cleaned-up arrays in 1.121e-05 s (0.04 %) + deduplicated arrays in 1.287e-05 s (0.05 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 8.845e-03 s (31.01 %) + memory allocations took 1.097e-05 s (0.04 %) + leafs setup took 5.960e-06 s (0.02 %) + halfword conversion took 8.667e-03 s (30.39 %) +Built (100 x 100)[0x56f8dd80]{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: 79, 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6588,11 +6637,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6603,11 +6652,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6617,17 +6666,17 @@ # 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 0.1119s; avg 0.03729s ( +/- 17.43/ 17.68 %); best 0.03079s; worst 0.04388s; std dev. 0.005345 (taking best). -Reference operation time is 0.030793 s (0.656 Mflops) with 1 threads. -Challenging best inner round reference (1.3113e-05 s/1 threads) with: subdivision 4, 33 leaves, 2.361 bytes/nz, 0.030793 s/0 threads (speedup 0.000425845 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 46 subms, 33 lsubms, 2.3612 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 1540.45 Mflops. +3 iterations (1 th.) took 0.01293s; avg 0.004309s ( +/- 1.05/ 0.64 %); best 0.004264s; worst 0.004337s; std dev. 3.225e-05 (taking best). +Reference operation time is 0.00426412 s (4.737 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/0 threads) with: subdivision 4, 79 leaves, 2.556 bytes/nz, 0.00426412 s/0 threads (speedup 0.00279564 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 107 subms, 79 lsubms, 2.5560 bpnz +Best sparse multiply performance with subdivision multiplier of 0.25: 1694.5 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6637,29 +6686,29 @@ # 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 1.37931 s (eq. to 1e+05/ 1e+05 old/new op.times), gained local/global speedup 1 x (1.3113e-05 : 1.3113e-05) / 1 x (1.3113e-05 : 1.3113e-05). This is not amortizable ! -Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 1.4s, 0.94s for constructor, 0 clones) obtained NO speedup (best stays 1540 Mflops). -Second run of RSB Autotuner took 1.37944 s and estimated a speedup of 1.000000 x (1.311e-05 s -> 1.311e-05 s per op) in same matrix (1 -> 1 lsubm) +Last tuner inner round (1 of 1) took 0.18563 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1.02 x (1.21593e-05 : 1.19209e-05) / 1.02 x (1.21593e-05 : 1.19209e-05). This is amortizable in 778589 op.times. +In 1 tuning rounds (tot. 0.19s, 0.13s for constructor, 0 clones) obtained a SPEEDUP of 2.0% (1.02x) (from 1661 to 1694 Mflops). +Second run of RSB Autotuner took 0.185667 s and estimated a speedup of 1.020000 x (1.216e-05 s -> 1.192e-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 0.000001 0.050792 0.114224 0.165016 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.165017 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.050792 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.114224 -%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 -%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.165016 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.005578 0.017368 0.022946 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.022946 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005578 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.017368 +%: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 0.022946 %: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 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -6668,45 +6717,45 @@ %: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 0.222808 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.031775 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 9.53674e-07 0.050792 0 0.114224 -# so far, program took 10.860s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.808s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00557804 0 0.0173681 +# so far, program took 5.209s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.590s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.09324s (system CPU time used) -ru_utime : 22.27s (user CPU time used) +ru_maxrss: 21 (maximum resident set size -- MB) +ru_stime : 0.8161s (system CPU time used) +ru_utime : 19.46s (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 10.860s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.808s/0.000s . +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# so far, program took 5.209s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.590s/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 2.674e-01 s (100.00 %) - analyzed arrays in 3.939e-02 s (14.73 %) - cleaned-up arrays in 1.788e-05 s (0.01 %) - deduplicated arrays in 1.597e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 1.240e-01 s (46.36 %) - memory allocations took 1.717e-05 s (0.01 %) - leafs setup took 9.060e-06 s (0.00 %) - halfword conversion took 1.040e-01 s (38.89 %) -Built (100 x 100)[0x57c1a000]{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 0.268s): (100 x 100)[0x57c1a000]{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' + converted COO to RSB in 3.164e-02 s (100.00 %) + analyzed arrays in 5.644e-03 s (17.84 %) + cleaned-up arrays in 1.192e-05 s (0.04 %) + deduplicated arrays in 1.311e-05 s (0.04 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 1.727e-02 s (54.58 %) + memory allocations took 2.861e-06 s (0.01 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 8.699e-03 s (27.49 %) +Built (100 x 100)[0x56f6bdd0]{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 0.032s): (100 x 100)[0x56f6bdd0]{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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6717,11 +6766,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6732,11 +6781,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6746,16 +6795,16 @@ # 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 0.07594s; avg 0.02531s ( +/- 35.76/ 26.19 %); best 0.01626s; worst 0.03194s; std dev. 0.006627 (taking best). -Reference operation time is 0.0162609 s (4.969 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: 0.01626 Mflops: 4.969) -Merge (3 -> 1 leaves) took w.c.t. of 0.000216s, ~0.0001621s of computing time (of which 8.702e-05s sorting, 7.868e-06s analysis) +3 iterations (1 th.) took 0.01307s; avg 0.004356s ( +/- 1.95/ 1.33 %); best 0.004271s; worst 0.004414s; std dev. 6.137e-05 (taking best). +Reference operation time is 0.00427103 s (18.92 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: 0.004271 Mflops: 18.918) +Merge (3 -> 1 leaves) took w.c.t. of 4.888e-05s, ~4.22e-05s of computing time (of which 2.003e-05s sorting, 9.537e-07s 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6766,11 +6815,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6780,14 +6829,14 @@ # 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 0.00018s; avg 6e-05s ( +/- 6.62/ 11.66 %); best 5.603e-05s; worst 6.7e-05s; std dev. 4.961e-06 (taking best). -Reference operation time is 5.60284e-05 s (1442 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0002029s; avg 6.763e-05s ( +/- 8.34/ 16.69 %); best 6.199e-05s; worst 7.892e-05s; std dev. 7.98e-06 (taking best). +Reference operation time is 6.19888e-05 s (1303 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6797,25 +6846,25 @@ # 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: 5.603e-05 s ~Mflops: 1442.127 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 290.226x: 0.01626s -> 5.603e-05s, so taking this instance. +After merge step 1: tpop: 6.199e-05 s ~Mflops: 1303.461 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 68.900x: 0.004271s -> 6.199e-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 0.2402s (of which 0.000227s partitioning, 0.1641s I/O); computing times: 0.0001621s in par. loops, 8.702e-05s sorting, 7.868e-06s analyzing) -Total merge + benchmarking process took 0.2402s, equivalent to 4286.4/14.8 new/old ops (0.1512s for 2 clones -- as 2698.1/9.3 ops, or 1349.0/4.6 ops per clone), SPEEDUP of 290.226x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 290.226x (0.01626s -> 5.603e-05s), will amortize in 14.8 ops by saving 0.0162s per op. -In 1 tuning rounds (tot. 0.39s, 0.15s for constructor, 2 clones) obtained a SPEEDUP of 28922.6% (290.2x) (from 4.969 to 1442 Mflops). Employed 0.19s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04033s (of which 5.293e-05s partitioning, 0.02726s I/O); computing times: 4.22e-05s in par. loops, 2.003e-05s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.04033s, equivalent to 650.6/9.4 new/old ops (0.02557s for 2 clones -- as 412.5/6.0 ops, or 206.3/3.0 ops per clone), SPEEDUP of 68.900x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 68.900x (0.004271s -> 6.199e-05s), will amortize in 9.6 ops by saving 0.004209s per op. +In 1 tuning rounds (tot. 0.066s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 6790.0% (68.9x) (from 18.92 to 1303 Mflops). Employed 0.028s 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 0.580232 s (1.626e-02 s -> 5.603e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0942531 s (4.271e-03 s -> 6.199e-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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6826,11 +6875,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6841,13 +6890,13 @@ # 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 13. +Starting with requested 0 threads ; current default 1 ; at most 24. # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6858,11 +6907,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6872,27 +6921,27 @@ # 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 0.0001941s; avg 6.469e-05s ( +/- 13.39/ 25.31 %); best 5.603e-05s; worst 8.106e-05s; std dev. 1.158e-05 (taking best). -Reference operation time is 5.60284e-05 s (1442 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001872s; avg 6.239e-05s ( +/- 0.64/ 1.27 %); best 6.199e-05s; worst 6.318e-05s; std dev. 5.62e-07 (taking best). +Reference operation time is 6.19888e-05 s (1303 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.071e-01 s (100.00 %) - analyzed arrays in 5.901e-02 s (55.11 %) - cleaned-up arrays in 1.884e-05 s (0.02 %) - deduplicated arrays in 1.693e-05 s (0.02 %) - sorted arrays in 1.192e-06 s (0.00 %) - shuffled partitions in 4.799e-02 s (44.82 %) - memory allocations took 1.311e-05 s (0.01 %) - leafs setup took 9.060e-06 s (0.01 %) - halfword conversion took 2.003e-05 s (0.02 %) -Built (100 x 100)[0x57c19f20]{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 = 13). -# 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: 13 + converted COO to RSB in 1.474e-02 s (100.00 %) + analyzed arrays in 6.171e-03 s (41.85 %) + cleaned-up arrays in 1.097e-05 s (0.07 %) + deduplicated arrays in 1.383e-05 s (0.09 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.537e-03 s (57.90 %) + memory allocations took 4.292e-06 s (0.03 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 5.007e-06 s (0.03 %) +Built (100 x 100)[0x56f6bcf0]{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 = 24). +# 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6903,12 +6952,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6919,22 +6968,22 @@ # 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 1.277e-01 s (100.00 %) - analyzed arrays in 3.969e-02 s (31.08 %) - cleaned-up arrays in 1.812e-05 s (0.01 %) - deduplicated arrays in 1.693e-05 s (0.01 %) + converted COO to RSB in 2.387e-02 s (100.00 %) + analyzed arrays in 6.409e-03 s (26.84 %) + cleaned-up arrays in 1.216e-05 s (0.05 %) + deduplicated arrays in 1.287e-05 s (0.05 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.793e-02 s (37.54 %) - memory allocations took 1.407e-05 s (0.01 %) - leafs setup took 8.821e-06 s (0.01 %) - halfword conversion took 4.000e-02 s (31.33 %) -Built (100 x 100)[0x57c1a000]{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: 13 + shuffled partitions in 8.631e-03 s (36.15 %) + memory allocations took 3.815e-06 s (0.02 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 8.803e-03 s (36.87 %) +Built (100 x 100)[0x56f6bdd0]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6945,11 +6994,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6960,11 +7009,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6974,16 +7023,16 @@ # 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 0.08787s; avg 0.02929s ( +/- 18.04/ 9.32 %); best 0.02401s; worst 0.03202s; std dev. 0.003736 (taking best). -Reference operation time is 0.0240068 s (3.366 Mflops) with 1 threads. -Challenging best inner round reference (5.60284e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0240068 s/0 threads (speedup 0.00233385 x), same?n. +3 iterations (1 th.) took 0.01304s; avg 0.004348s ( +/- 1.06/ 1.10 %); best 0.004302s; worst 0.004396s; std dev. 3.837e-05 (taking best). +Reference operation time is 0.00430202 s (18.78 Mflops) with 1 threads. +Challenging best inner round reference (6.19888e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00430202 s/0 threads (speedup 0.0144092 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6994,12 +7043,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7010,22 +7059,22 @@ # 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 1.956e-01 s (100.00 %) - analyzed arrays in 5.956e-02 s (30.45 %) - cleaned-up arrays in 1.884e-05 s (0.01 %) - deduplicated arrays in 1.812e-05 s (0.01 %) + converted COO to RSB in 2.358e-02 s (100.00 %) + analyzed arrays in 6.516e-03 s (27.64 %) + cleaned-up arrays in 1.216e-05 s (0.05 %) + deduplicated arrays in 1.287e-05 s (0.05 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.000e-02 s (40.90 %) - memory allocations took 2.599e-05 s (0.01 %) - leafs setup took 8.106e-06 s (0.00 %) - halfword conversion took 5.595e-02 s (28.61 %) -Built (100 x 100)[0x57c1a000]{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 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: 13 + shuffled partitions in 8.735e-03 s (37.05 %) + memory allocations took 4.053e-06 s (0.02 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 8.297e-03 s (35.19 %) +Built (100 x 100)[0x56f6bdd0]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7036,11 +7085,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7051,11 +7100,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7065,16 +7114,16 @@ # 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 0.07188s; avg 0.02396s ( +/- 33.20/ 33.08 %); best 0.01601s; worst 0.03189s; std dev. 0.006483 (taking best). -Reference operation time is 0.016005 s (5.048 Mflops) with 1 threads. -Challenging best inner round reference (5.60284e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.016005 s/0 threads (speedup 0.00350067 x), same?n. +3 iterations (1 th.) took 0.01299s; avg 0.004331s ( +/- 1.22/ 0.68 %); best 0.004278s; worst 0.00436s; std dev. 3.734e-05 (taking best). +Reference operation time is 0.00427794 s (18.89 Mflops) with 1 threads. +Challenging best inner round reference (6.19888e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.00427794 s/0 threads (speedup 0.0144903 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7085,12 +7134,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7101,22 +7150,22 @@ # 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 1.435e-01 s (100.00 %) - analyzed arrays in 4.750e-02 s (33.10 %) - cleaned-up arrays in 2.289e-05 s (0.02 %) - deduplicated arrays in 1.717e-05 s (0.01 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.600e-02 s (39.03 %) - memory allocations took 2.289e-05 s (0.02 %) - leafs setup took 1.097e-05 s (0.01 %) - halfword conversion took 3.991e-02 s (27.81 %) -Built (100 x 100)[0x57c1a000]{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: 25, symflags:'LS' + converted COO to RSB in 2.812e-02 s (100.00 %) + analyzed arrays in 1.070e-02 s (38.07 %) + cleaned-up arrays in 1.097e-05 s (0.04 %) + deduplicated arrays in 1.287e-05 s (0.05 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 8.741e-03 s (31.09 %) + memory allocations took 4.292e-06 s (0.02 %) + leafs setup took 2.146e-06 s (0.01 %) + halfword conversion took 8.642e-03 s (30.73 %) +Built (100 x 100)[0x56f6bdd0]{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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7127,11 +7176,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7142,11 +7191,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7156,16 +7205,16 @@ # 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 0.1119s; avg 0.03731s ( +/- 46.38/ 39.20 %); best 0.02s; worst 0.05193s; std dev. 0.01317 (taking best). -Reference operation time is 0.0200031 s (4.039 Mflops) with 1 threads. -Challenging best inner round reference (5.60284e-05 s/1 threads) with: subdivision 1, 25 leaves, 2.317 bytes/nz, 0.0200031 s/0 threads (speedup 0.00280099 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 34 subms, 25 lsubms, 2.3168 bpnz +3 iterations (1 th.) took 0.01297s; avg 0.004323s ( +/- 0.32/ 0.17 %); best 0.004309s; worst 0.00433s; std dev. 9.726e-06 (taking best). +Reference operation time is 0.00430894 s (18.75 Mflops) with 1 threads. +Challenging best inner round reference (6.19888e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.00430894 s/0 threads (speedup 0.0143861 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7176,12 +7225,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7192,22 +7241,22 @@ # 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 1.756e-01 s (100.00 %) - analyzed arrays in 7.154e-02 s (40.73 %) - cleaned-up arrays in 1.717e-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 5.204e-02 s (29.63 %) - memory allocations took 2.766e-05 s (0.02 %) - leafs setup took 1.287e-05 s (0.01 %) - halfword conversion took 5.197e-02 s (29.59 %) -Built (100 x 100)[0x57c1a000]{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: 36, 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: 13 + converted COO to RSB in 2.858e-02 s (100.00 %) + analyzed arrays in 1.081e-02 s (37.84 %) + cleaned-up arrays in 1.121e-05 s (0.04 %) + deduplicated arrays in 1.383e-05 s (0.05 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.939e-03 s (31.28 %) + memory allocations took 5.007e-06 s (0.02 %) + leafs setup took 4.053e-06 s (0.01 %) + halfword conversion took 8.789e-03 s (30.75 %) +Built (100 x 100)[0x56f6bdd0]{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: 49, 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7218,11 +7267,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7233,11 +7282,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7247,16 +7296,16 @@ # 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 0.06383s; avg 0.02128s ( +/- 6.50/ 12.86 %); best 0.01989s; worst 0.02401s; std dev. 0.001935 (taking best). -Reference operation time is 0.0198929 s (4.062 Mflops) with 1 threads. -Challenging best inner round reference (5.60284e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.0198929 s/0 threads (speedup 0.0028165 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 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 -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 +3 iterations (1 th.) took 0.01295s; avg 0.004316s ( +/- 2.06/ 2.94 %); best 0.004227s; worst 0.004443s; std dev. 9.211e-05 (taking best). +Reference operation time is 0.00422716 s (19.11 Mflops) with 1 threads. +Challenging best inner round reference (6.19888e-05 s/1 threads) with: subdivision 2, 49 leaves, 2.432 bytes/nz, 0.00422716 s/0 threads (speedup 0.0146644 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 67 subms, 49 lsubms, 2.4325 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7267,12 +7316,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7283,22 +7332,22 @@ # 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 1.555e-01 s (100.00 %) - analyzed arrays in 5.548e-02 s (35.67 %) - cleaned-up arrays in 1.812e-05 s (0.01 %) - deduplicated arrays in 1.597e-05 s (0.01 %) + converted COO to RSB in 2.831e-02 s (100.00 %) + analyzed arrays in 1.087e-02 s (38.41 %) + cleaned-up arrays in 1.192e-05 s (0.04 %) + deduplicated arrays in 1.311e-05 s (0.05 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.601e-02 s (36.01 %) - memory allocations took 2.694e-05 s (0.02 %) - leafs setup took 1.216e-05 s (0.01 %) - halfword conversion took 4.396e-02 s (28.27 %) -Built (100 x 100)[0x57c40e80]{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: 36, 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: 13 + shuffled partitions in 8.743e-03 s (30.89 %) + memory allocations took 5.960e-06 s (0.02 %) + leafs setup took 6.914e-06 s (0.02 %) + halfword conversion took 8.654e-03 s (30.57 %) +Built (100 x 100)[0x56f92c70]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7309,11 +7358,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7324,11 +7373,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7338,17 +7387,17 @@ # 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 0.07588s; avg 0.02529s ( +/- 36.29/ 28.38 %); best 0.01611s; worst 0.03247s; std dev. 0.006826 (taking best). -Reference operation time is 0.016114 s (5.014 Mflops) with 1 threads. -Challenging best inner round reference (5.60284e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.016114 s/0 threads (speedup 0.003477 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 1442.13 Mflops. +3 iterations (1 th.) took 0.01313s; avg 0.004377s ( +/- 0.63/ 0.49 %); best 0.004349s; worst 0.004398s; std dev. 2.052e-05 (taking best). +Reference operation time is 0.00434899 s (18.58 Mflops) with 1 threads. +Challenging best inner round reference (6.19888e-05 s/1 threads) with: subdivision 4, 102 leaves, 2.653 bytes/nz, 0.00434899 s/0 threads (speedup 0.0142536 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 138 subms, 102 lsubms, 2.6527 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 1303.46 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7358,29 +7407,29 @@ # 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 1.31966 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1 x (5.60284e-05 : 5.60284e-05) / 1 x (5.60284e-05 : 5.60284e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.213663 s (eq. to 3e+03/ 3e+03 old/new op.times), gained local/global speedup 1 x (6.19888e-05 : 6.19888e-05) / 1 x (6.19888e-05 : 6.19888e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 1.3s, 0.91s for constructor, 0 clones) obtained NO speedup (best stays 1442 Mflops). -Second run of RSB Autotuner took 1.31982 s and estimated a speedup of 1.000000 x (5.603e-05 s -> 5.603e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.21s, 0.15s for constructor, 0 clones) obtained NO speedup (best stays 1303 Mflops). +Second run of RSB Autotuner took 0.213698 s and estimated a speedup of 1.000000 x (6.199e-05 s -> 6.199e-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 0.000001 0.039387 0.123952 0.163339 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.163340 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.039387 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.123952 -%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 -%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.163339 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.005644 0.017271 0.022915 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.022915 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005644 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.017271 +%: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 0.022915 %: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 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -7389,45 +7438,45 @@ %: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 0.267384 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.0316429 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 9.53674e-07 0.039387 0 0.123952 -# so far, program took 13.164s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.708s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00564408 0 0.017271 +# so far, program took 5.588s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.898s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.1081s (system CPU time used) -ru_utime : 32.2s (user CPU time used) +ru_maxrss: 21 (maximum resident set size -- MB) +ru_stime : 0.8512s (system CPU time used) +ru_utime : 27.65s (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 13.164s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.708s/0.000s . +# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# so far, program took 5.588s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.898s/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 2.111e-01 s (100.00 %) - analyzed arrays in 3.515e-02 s (16.65 %) - cleaned-up arrays in 2.003e-05 s (0.01 %) - deduplicated arrays in 1.812e-05 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 1.159e-01 s (54.89 %) - memory allocations took 5.174e-05 s (0.02 %) - leafs setup took 9.060e-06 s (0.00 %) - halfword conversion took 5.997e-02 s (28.41 %) -Built (100 x 100)[0x57c1a000]{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 0.211s): (100 x 100)[0x57c1a000]{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' + converted COO to RSB in 3.173e-02 s (100.00 %) + analyzed arrays in 5.608e-03 s (17.67 %) + cleaned-up arrays in 1.216e-05 s (0.04 %) + deduplicated arrays in 1.287e-05 s (0.04 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 1.742e-02 s (54.90 %) + memory allocations took 1.287e-05 s (0.04 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 8.665e-03 s (27.31 %) +Built (100 x 100)[0x56f6bdd0]{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 0.032s): (100 x 100)[0x56f6bdd0]{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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7438,11 +7487,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7453,11 +7502,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7467,16 +7516,16 @@ # 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 0.0799s; avg 0.02663s ( +/- 53.91/ 34.13 %); best 0.01228s; worst 0.03572s; std dev. 0.01027 (taking best). -Reference operation time is 0.0122759 s (6.582 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: 0.01228 Mflops: 6.582) -Merge (3 -> 1 leaves) took w.c.t. of 0.0002711s, ~0.0001981s of computing time (of which 0.000109s sorting, 6.199e-06s analysis) +3 iterations (1 th.) took 0.01302s; avg 0.004342s ( +/- 1.56/ 1.85 %); best 0.004274s; worst 0.004422s; std dev. 6.11e-05 (taking best). +Reference operation time is 0.00427389 s (18.91 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: 0.004274 Mflops: 18.905) +Merge (3 -> 1 leaves) took w.c.t. of 0.0001011s, ~8.392e-05s of computing time (of which 4.792e-05s sorting, 9.537e-07s 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7487,11 +7536,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7501,14 +7550,14 @@ # 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 0.0001812s; avg 6.04e-05s ( +/- 7.24/ 12.89 %); best 5.603e-05s; worst 6.819e-05s; std dev. 5.521e-06 (taking best). -Reference operation time is 5.60284e-05 s (1442 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001762s; avg 5.873e-05s ( +/- 0.95/ 0.68 %); best 5.817e-05s; worst 5.913e-05s; std dev. 4.052e-07 (taking best). +Reference operation time is 5.81741e-05 s (1389 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7518,25 +7567,25 @@ # 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: 5.603e-05 s ~Mflops: 1442.127 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 219.102x: 0.01228s -> 5.603e-05s, so taking this instance. +After merge step 1: tpop: 5.817e-05 s ~Mflops: 1388.933 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 73.467x: 0.004274s -> 5.817e-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 0.2403s (of which 0.0002868s partitioning, 0.1523s I/O); computing times: 0.0001981s in par. loops, 0.000109s sorting, 6.199e-06s analyzing) -Total merge + benchmarking process took 0.2403s, equivalent to 4288.1/19.6 new/old ops (0.1632s for 2 clones -- as 2911.9/13.3 ops, or 1456.0/6.6 ops per clone), SPEEDUP of 219.102x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 219.102x (0.01228s -> 5.603e-05s), will amortize in 19.7 ops by saving 0.01222s per op. -In 1 tuning rounds (tot. 0.4s, 0.16s for constructor, 2 clones) obtained a SPEEDUP of 21810.2% (219.1x) (from 6.582 to 1442 Mflops). Employed 0.18s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04082s (of which 0.0001059s partitioning, 0.02783s I/O); computing times: 8.392e-05s in par. loops, 4.792e-05s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.04082s, equivalent to 701.7/9.6 new/old ops (0.02551s for 2 clones -- as 438.6/6.0 ops, or 219.3/3.0 ops per clone), SPEEDUP of 73.467x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 73.467x (0.004274s -> 5.817e-05s), will amortize in 9.7 ops by saving 0.004216s per op. +In 1 tuning rounds (tot. 0.067s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 7246.7% (73.47x) (from 18.91 to 1389 Mflops). Employed 0.028s 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 0.572306 s (1.228e-02 s -> 5.603e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.094892 s (4.274e-03 s -> 5.817e-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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7547,11 +7596,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7562,13 +7611,13 @@ # 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 13. +Starting with requested 0 threads ; current default 1 ; at most 24. # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7579,11 +7628,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7593,27 +7642,27 @@ # 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 0.0001981s; avg 6.604e-05s ( +/- 13.72/ 27.44 %); best 5.698e-05s; worst 8.416e-05s; std dev. 1.281e-05 (taking best). -Reference operation time is 5.6982e-05 s (1418 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001762s; avg 5.873e-05s ( +/- 1.35/ 2.30 %); best 5.794e-05s; worst 6.008e-05s; std dev. 9.603e-07 (taking best). +Reference operation time is 5.79357e-05 s (1395 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 9.036e-02 s (100.00 %) - analyzed arrays in 4.633e-02 s (51.27 %) - cleaned-up arrays in 1.907e-05 s (0.02 %) - deduplicated arrays in 1.597e-05 s (0.02 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 4.395e-02 s (48.64 %) - memory allocations took 1.597e-05 s (0.02 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 2.313e-05 s (0.03 %) -Built (100 x 100)[0x57c19f20]{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 = 13). -# 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: 13 + converted COO to RSB in 1.464e-02 s (100.00 %) + analyzed arrays in 5.925e-03 s (40.46 %) + cleaned-up arrays in 1.097e-05 s (0.07 %) + deduplicated arrays in 1.407e-05 s (0.10 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.675e-03 s (59.24 %) + memory allocations took 1.192e-05 s (0.08 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 5.960e-06 s (0.04 %) +Built (100 x 100)[0x56f6bcf0]{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 = 24). +# 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7624,12 +7673,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7640,22 +7689,22 @@ # 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 1.709e-01 s (100.00 %) - analyzed arrays in 7.879e-02 s (46.11 %) - cleaned-up arrays in 1.812e-05 s (0.01 %) - deduplicated arrays in 1.693e-05 s (0.01 %) + converted COO to RSB in 2.358e-02 s (100.00 %) + analyzed arrays in 6.141e-03 s (26.04 %) + cleaned-up arrays in 1.121e-05 s (0.05 %) + deduplicated arrays in 1.287e-05 s (0.05 %) sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 6.002e-02 s (35.13 %) - memory allocations took 2.098e-05 s (0.01 %) - leafs setup took 1.192e-05 s (0.01 %) - halfword conversion took 3.198e-02 s (18.72 %) -Built (100 x 100)[0x57c1a000]{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 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: 13 + shuffled partitions in 8.640e-03 s (36.64 %) + memory allocations took 4.053e-06 s (0.02 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 8.770e-03 s (37.19 %) +Built (100 x 100)[0x56f6f4e0]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7666,11 +7715,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7681,11 +7730,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7695,16 +7744,16 @@ # 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 0.08388s; avg 0.02796s ( +/- 14.12/ 14.44 %); best 0.02401s; worst 0.032s; std dev. 0.00326 (taking best). -Reference operation time is 0.024013 s (3.365 Mflops) with 1 threads. -Challenging best inner round reference (5.6982e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.024013 s/0 threads (speedup 0.00237296 x), same?n. +3 iterations (1 th.) took 0.01286s; avg 0.004286s ( +/- 1.66/ 1.77 %); best 0.004215s; worst 0.004362s; std dev. 6.013e-05 (taking best). +Reference operation time is 0.004215 s (19.17 Mflops) with 1 threads. +Challenging best inner round reference (5.79357e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.004215 s/0 threads (speedup 0.0137451 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 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7715,12 +7764,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7731,22 +7780,22 @@ # 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 1.744e-01 s (100.00 %) - analyzed arrays in 7.437e-02 s (42.63 %) - cleaned-up arrays in 1.812e-05 s (0.01 %) - deduplicated arrays in 1.788e-05 s (0.01 %) + converted COO to RSB in 2.787e-02 s (100.00 %) + analyzed arrays in 1.054e-02 s (37.82 %) + cleaned-up arrays in 1.121e-05 s (0.04 %) + deduplicated arrays in 1.383e-05 s (0.05 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.604e-02 s (32.13 %) - memory allocations took 2.289e-05 s (0.01 %) - leafs setup took 1.287e-05 s (0.01 %) - halfword conversion took 4.395e-02 s (25.20 %) -Built (100 x 100)[0x57c1a000]{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: 18, 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: 13 + shuffled partitions in 8.694e-03 s (31.19 %) + memory allocations took 4.768e-06 s (0.02 %) + leafs setup took 1.907e-06 s (0.01 %) + halfword conversion took 8.604e-03 s (30.87 %) +Built (100 x 100)[0x56f6bdd0]{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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7757,11 +7806,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7772,11 +7821,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7786,16 +7835,16 @@ # 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 0.1001s; avg 0.03336s ( +/- 39.50/ 67.57 %); best 0.02018s; worst 0.05589s; std dev. 0.01601 (taking best). -Reference operation time is 0.0201819 s (4.004 Mflops) with 1 threads. -Challenging best inner round reference (5.6982e-05 s/1 threads) with: subdivision 0.5, 18 leaves, 2.261 bytes/nz, 0.0201819 s/0 threads (speedup 0.00282342 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 25 subms, 18 lsubms, 2.2614 bpnz +3 iterations (1 th.) took 0.01296s; avg 0.00432s ( +/- 1.00/ 1.87 %); best 0.004277s; worst 0.004401s; std dev. 5.73e-05 (taking best). +Reference operation time is 0.00427699 s (18.89 Mflops) with 1 threads. +Challenging best inner round reference (5.79357e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 0.00427699 s/0 threads (speedup 0.0135459 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7806,12 +7855,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7822,22 +7871,22 @@ # 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 1.785e-01 s (100.00 %) - analyzed arrays in 7.052e-02 s (39.50 %) - cleaned-up arrays in 2.098e-05 s (0.01 %) - deduplicated arrays in 1.812e-05 s (0.01 %) + converted COO to RSB in 2.796e-02 s (100.00 %) + analyzed arrays in 1.046e-02 s (37.40 %) + cleaned-up arrays in 1.097e-05 s (0.04 %) + deduplicated arrays in 1.287e-05 s (0.05 %) sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 5.997e-02 s (33.59 %) - memory allocations took 3.290e-05 s (0.02 %) - leafs setup took 1.192e-05 s (0.01 %) - halfword conversion took 4.796e-02 s (26.86 %) -Built (100 x 100)[0x57c685d0]{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' + shuffled partitions in 8.770e-03 s (31.36 %) + memory allocations took 5.245e-06 s (0.02 %) + leafs setup took 4.053e-06 s (0.01 %) + halfword conversion took 8.699e-03 s (31.11 %) +Built (100 x 100)[0x56f6bdd0]{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: 34, 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7848,11 +7897,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7863,11 +7912,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7877,16 +7926,16 @@ # 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 0.08794s; avg 0.02931s ( +/- 5.05/ 8.95 %); best 0.02783s; worst 0.03194s; std dev. 0.00186 (taking best). -Reference operation time is 0.0278339 s (2.903 Mflops) with 1 threads. -Challenging best inner round reference (5.6982e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 0.0278339 s/0 threads (speedup 0.00204721 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 +3 iterations (1 th.) took 0.01289s; avg 0.004297s ( +/- 1.67/ 1.38 %); best 0.004225s; worst 0.004356s; std dev. 5.416e-05 (taking best). +Reference operation time is 0.00422502 s (19.12 Mflops) with 1 threads. +Challenging best inner round reference (5.79357e-05 s/1 threads) with: subdivision 1, 34 leaves, 2.363 bytes/nz, 0.00422502 s/0 threads (speedup 0.0137125 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 47 subms, 34 lsubms, 2.3628 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7897,12 +7946,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7913,22 +7962,22 @@ # 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 1.826e-01 s (100.00 %) - analyzed arrays in 8.653e-02 s (47.39 %) - cleaned-up arrays in 1.693e-05 s (0.01 %) - deduplicated arrays in 1.597e-05 s (0.01 %) - sorted arrays in 1.192e-06 s (0.00 %) - shuffled partitions in 4.404e-02 s (24.12 %) - memory allocations took 3.791e-05 s (0.02 %) - leafs setup took 1.788e-05 s (0.01 %) - halfword conversion took 5.192e-02 s (28.44 %) -Built (100 x 100)[0x57c685d0]{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 -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 + converted COO to RSB in 2.812e-02 s (100.00 %) + analyzed arrays in 1.073e-02 s (38.15 %) + cleaned-up arrays in 1.192e-05 s (0.04 %) + deduplicated arrays in 1.311e-05 s (0.05 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.809e-03 s (31.32 %) + memory allocations took 9.775e-06 s (0.03 %) + leafs setup took 5.007e-06 s (0.02 %) + halfword conversion took 8.546e-03 s (30.39 %) +Built (100 x 100)[0x56fba3c0]{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: 72, 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7939,11 +7988,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7954,11 +8003,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7968,16 +8017,16 @@ # 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 0.07592s; avg 0.02531s ( +/- 51.87/ 57.68 %); best 0.01218s; worst 0.0399s; std dev. 0.01137 (taking best). -Reference operation time is 0.012181 s (6.633 Mflops) with 1 threads. -Challenging best inner round reference (5.6982e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.012181 s/0 threads (speedup 0.00467793 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 -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 +3 iterations (1 th.) took 0.01318s; avg 0.004393s ( +/- 0.60/ 0.86 %); best 0.004367s; worst 0.004431s; std dev. 2.749e-05 (taking best). +Reference operation time is 0.00436687 s (18.5 Mflops) with 1 threads. +Challenging best inner round reference (5.79357e-05 s/1 threads) with: subdivision 2, 72 leaves, 2.52 bytes/nz, 0.00436687 s/0 threads (speedup 0.0132671 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 98 subms, 72 lsubms, 2.5204 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7988,12 +8037,12 @@ # 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 40329 bytes +# Cache block size total 4194304 bytes, per-thread 174762 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 -# RSB_IO_WANT_EXECUTING_THREADS: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 +# RSB_IO_WANT_EXECUTING_THREADS: 24 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -8004,22 +8053,22 @@ # 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 1.538e-01 s (100.00 %) - analyzed arrays in 5.784e-02 s (37.61 %) - cleaned-up arrays in 1.788e-05 s (0.01 %) - deduplicated arrays in 1.502e-05 s (0.01 %) - sorted arrays in 1.192e-06 s (0.00 %) - shuffled partitions in 4.784e-02 s (31.11 %) - memory allocations took 6.795e-05 s (0.04 %) - leafs setup took 1.216e-05 s (0.01 %) - halfword conversion took 4.797e-02 s (31.20 %) -Built (100 x 100)[0x57c685d0]{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 -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 65536 -# avg_leaf_matrix_bytes : 1048576 -# rsb_g_threads: 13 + converted COO to RSB in 2.836e-02 s (100.00 %) + analyzed arrays in 1.073e-02 s (37.84 %) + cleaned-up arrays in 1.192e-05 s (0.04 %) + deduplicated arrays in 1.407e-05 s (0.05 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.797e-03 s (31.02 %) + memory allocations took 2.193e-05 s (0.08 %) + leafs setup took 6.914e-06 s (0.02 %) + halfword conversion took 8.776e-03 s (30.95 %) +Built (100 x 100)[0x56fba3c0]{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 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: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8030,11 +8079,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8045,11 +8094,11 @@ # 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8059,17 +8108,17 @@ # 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 0.07589s; avg 0.0253s ( +/- 52.14/ 55.67 %); best 0.01211s; worst 0.03938s; std dev. 0.01115 (taking best). -Reference operation time is 0.0121062 s (6.674 Mflops) with 1 threads. -Challenging best inner round reference (5.6982e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.0121062 s/0 threads (speedup 0.00470686 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 -Best sparse multiply performance with subdivision multiplier of 1: 1417.99 Mflops. +3 iterations (1 th.) took 0.01293s; avg 0.00431s ( +/- 1.07/ 1.90 %); best 0.004264s; worst 0.004392s; std dev. 5.803e-05 (taking best). +Reference operation time is 0.00426412 s (18.95 Mflops) with 1 threads. +Challenging best inner round reference (5.79357e-05 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.00426412 s/0 threads (speedup 0.0135868 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: 1394.65 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: 13 +# min_leaf_matrix_bytes : 32768 +# avg_leaf_matrix_bytes : 8388608 +# rsb_g_threads: 24 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8079,29 +8128,29 @@ # 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 1.38407 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1 x (5.6982e-05 : 5.6982e-05) / 1 x (5.6982e-05 : 5.6982e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.218198 s (eq. to 4e+03/ 4e+03 old/new op.times), gained local/global speedup 1 x (5.79357e-05 : 5.79357e-05) / 1 x (5.79357e-05 : 5.79357e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 1.4s, 0.96s for constructor, 0 clones) obtained NO speedup (best stays 1418 Mflops). -Second run of RSB Autotuner took 1.38422 s and estimated a speedup of 1.000000 x (5.698e-05 s -> 5.698e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.22s, 0.15s for constructor, 0 clones) obtained NO speedup (best stays 1395 Mflops). +Second run of RSB Autotuner took 0.218233 s and estimated a speedup of 1.000000 x (5.794e-05 s -> 5.794e-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 0.000001 0.035148 0.115888 0.151036 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.151037 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.035148 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.115888 -%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 -%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.151036 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.005608 0.017421 0.023029 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.023029 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005608 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.017421 +%: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 0.023029 %: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 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -8110,69 +8159,68 @@ %: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 0.211117 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.031734 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 9.53674e-07 0.0351479 0 0.115888 -# so far, program took 15.460s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 7.665s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00560784 0 0.017421 +# so far, program took 5.973s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.211s/0.000s . getrusage() stats: -ru_maxrss: 7 (maximum resident set size -- MB) -ru_stime : 0.1118s (system CPU time used) -ru_utime : 41.58s (user CPU time used) +ru_maxrss: 21 (maximum resident set size -- MB) +ru_stime : 0.8985s (system CPU time used) +ru_utime : 35.97s (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 1436.02 1.599e-02 0.000e+00 1.407e-05 0.000e+00 5.681e-01 3.79e+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 1264.55 2.800e-02 0.000e+00 1.597e-05 0.000e+00 5.806e-01 2.00e+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 1442.13 1.626e-02 0.000e+00 5.603e-05 0.000e+00 5.802e-01 9.51e-01 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 1442.13 1.228e-02 0.000e+00 5.603e-05 0.000e+00 5.723e-01 1.72e+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 4.309e-03 0.000e+00 1.192e-05 0.000e+00 9.489e-02 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 1841.85 4.245e-03 0.000e+00 1.097e-05 0.000e+00 9.533e-02 2.91e+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 1303.46 4.271e-03 0.000e+00 6.199e-05 0.000e+00 9.425e-02 8.60e-01 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 1388.93 4.274e-03 0.000e+00 5.817e-05 0.000e+00 9.489e-02 1.65e+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. 84868.7 % faster, avg. sp. ratio 849.687x, max sp. ratio 1752.910x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 24324.9/10214.6/40384.4/97299.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 34.6/ 20.7/ 46.6/138.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 34.7, min. 20.7, max. 46.8 ops) +#pr: (in succ. cases rsb autotuning gave avg. 22172.3 % faster, avg. sp. ratio 222.723x, max sp. ratio 387.065x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4951.0/1520.5/8692.6/19803.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 22.2/ 22.0/ 22.5/ 88.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 22.4, min. 22.1, max. 22.5 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 2.082/ 0.937/ 3.733,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 8.453/ 0.951/ 3.789,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.437/ 0.847/ 4.404,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.892/ 0.860/ 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 0.57 s, max 0.58 s, tot 2.30 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.58 s, min 0.57 s, max 0.58 s, tot 2.30 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.396e+03, min 1.265e+03, max 1.442e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.384e+00, min 7.214e-01, max 6.582e+00 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.552e-05s, min 1.407e-05s, max 5.603e-05s, tot 1.421e-04s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.813e-02s, min 1.228e-02s, max 2.800e-02s, tot 7.252e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.251e-01 1.693e+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: 4.506e+00 -#pr: Record collection took 7.64 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.09 s, min 0.09 s, max 0.10 s, tot 0.38 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.09 s, min 0.09 s, max 0.10 s, tot 0.38 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.557e+03, min 1.303e+03, max 1.842e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.182e+01, min 4.688e+00, max 1.892e+01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.576e-05s, min 1.097e-05s, max 6.199e-05s, tot 1.431e-04s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.275e-03s, min 4.245e-03s, max 4.309e-03s, tot 1.710e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.242e+00 2.726e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.776e+00 +#pr: Record collection took 1.24 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 99 environment variables in 4776 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 99 environment variables in 4829 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 1740330313 (after 15.4s of w.c.t.) +# terminating run at 1774742858 (after 6.0s 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 85627 Feb 23 05:05 test-tuning-lower-100x100-5050nz--D-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84549 Feb 23 05:05 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85627 Feb 23 05:05 test-tuning-lower-100x100-5050nz--S-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84549 Feb 23 05:05 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85627 Feb 23 05:05 test-tuning-lower-100x100-5050nz--C-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84549 Feb 23 05:05 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85627 Feb 23 05:05 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84549 Feb 23 05:05 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85638 Mar 29 14:07 test-tuning-lower-100x100-5050nz--D-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84561 Mar 29 14:07 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85638 Mar 29 14:07 test-tuning-lower-100x100-5050nz--S-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84561 Mar 29 14:07 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85639 Mar 29 14:07 test-tuning-lower-100x100-5050nz--C-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84561 Mar 29 14:07 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85639 Mar 29 14:07 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84561 Mar 29 14:07 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 4199 Feb 23 05:05 test.txt +-rw-r--r-- 1 pbuilder2 pbuilder2 4092 Mar 29 14:07 test.txt + RSB_PR_WLTC=2 + RSB_PR_SR=0 + rsbench --read-performance-record test.rpr @@ -8182,29 +8230,29 @@ /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 @@ -8219,7 +8267,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x5779e530]{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)[0x56f8a540]{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. @@ -8234,7 +8282,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x574d1530]{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)[0x56cdf540]{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. @@ -8298,51 +8346,51 @@ Done. Building a matrix with 5 nnz, 5 x 5 Duplicates check: 5 - 0 = 5 - converted COO to RSB in 2.203e-01 s (100.00 %) - analyzed arrays in 7.995e-02 s (36.30 %) - cleaned-up arrays in 1.907e-06 s (0.00 %) - deduplicated arrays in 1.907e-06 s (0.00 %) - sorted arrays in 1.227e-02 s (5.57 %) - shuffled partitions in 6.401e-02 s (29.06 %) - memory allocations took 3.791e-05 s (0.02 %) - leafs setup took 7.868e-06 s (0.00 %) - halfword conversion took 6.397e-02 s (29.04 %) -Built (5 x 5)[0x574d2d50]{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:'' + converted COO to RSB in 3.052e-02 s (100.00 %) + analyzed arrays in 1.105e-02 s (36.21 %) + cleaned-up arrays in 9.537e-07 s (0.00 %) + deduplicated arrays in 0.000e+00 s (0.00 %) + sorted arrays in 2.186e-03 s (7.16 %) + shuffled partitions in 8.677e-03 s (28.43 %) + memory allocations took 3.099e-06 s (0.01 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 8.604e-03 s (28.19 %) +Built (5 x 5)[0x56ce1b80]{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)[0x574d2d50]{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)[0x56ce1b80]{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 1.123762s. +Before auto-tuning, 100 multiplications took 0.434986s. 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.=1.94554e-06), 13 suggested as starting thread count(default). -3 iterations (13 th.) took 0.1421s; avg 0.04735s ( +/- 40.77/ 26.61 %); best 0.02805s; worst 0.05995s; std dev. 0.01386 (taking best). -Reference operation time is 0.0280471 s (0.0007131 Mflops) with 13 threads. -3 iterations (13 th.) took 0.116s; avg 0.03866s ( +/- 27.57/ 55.10 %); best 0.028s; worst 0.05996s; std dev. 0.01506 (taking best). -Reference operation time is 0.0280011 s (0.0007143 Mflops) with 13 threads. -After 0.704056s, autotuning routine did not find a better threads count configuration. -(5 x 5)[0x574d2d50]{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 3.060085s -- effective speedup of 0.367232 x -Matrix autotuning (may take more than 1.500000s; using 13 threads )... +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=8.25047e-08), 24 suggested as starting thread count(default). +3 iterations (24 th.) took 0.01303s; avg 0.004345s ( +/- 0.66/ 0.95 %); best 0.004316s; worst 0.004386s; std dev. 2.989e-05 (taking best). +Reference operation time is 0.00431609 s (0.004634 Mflops) with 24 threads. +3 iterations (24 th.) took 0.01299s; avg 0.004329s ( +/- 1.82/ 2.96 %); best 0.00425s; worst 0.004457s; std dev. 9.135e-05 (taking best). +Reference operation time is 0.00425005 s (0.004706 Mflops) with 24 threads. +After 0.026071s, autotuning routine did not find a better threads count configuration. +(5 x 5)[0x56ce1b80]{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 0.435741s -- effective speedup of 0.998267 x +Matrix autotuning (may take more than 1.500000s; using 24 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.=1.94554e-06), 13 suggested as starting thread count. -3 iterations (13 th.) took 0.124s; avg 0.04132s ( +/- 51.59/ 64.49 %); best 0.02s; worst 0.06797s; std dev. 0.01994 (taking best). -Reference operation time is 0.020005 s (0.0009998 Mflops) with 13 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: 0.02 Mflops: 0.001) -Merge (2 -> 1 leaves) took w.c.t. of 4.482e-05s, ~6.914e-06s of computing time (of which 1.192e-06s sorting, 9.06e-06s analysis) -3 iterations (13 th.) took 8.106e-06s; avg 2.702e-06s ( +/- 28.00/129.41 %); best 1.946e-06s; worst 6.199e-06s; std dev. 2.473e-06 (taking best). -Reference operation time is 1.94554e-06 s (10.28 Mflops) with 13 threads. -After merge step 1: tpop: 1.946e-06 s ~Mflops: 10.280 nsubm:1 otn:13 -Applying merge (2 -> 1 leaves, 13 th.) yielded SPEEDUP of 10282.469x: 0.02s -> 1.946e-06s, so taking this instance. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=8.25047e-08), 24 suggested as starting thread count. +3 iterations (24 th.) took 0.01308s; avg 0.004362s ( +/- 1.09/ 0.95 %); best 0.004314s; worst 0.004403s; std dev. 3.659e-05 (taking best). +Reference operation time is 0.00431395 s (0.004636 Mflops) with 24 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: 0.004314 Mflops: 0.005) +Merge (2 -> 1 leaves) took w.c.t. of 1.192e-05s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (24 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 87.02/ 50.00 %); best 8.25e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 8.25047e-08 s (242.4 Mflops) with 24 threads. +After merge step 1: tpop: 8.25e-08 s ~Mflops: 242.410 nsubm:1 otn:24 +Applying merge (2 -> 1 leaves, 24 th.) yielded SPEEDUP of 52287.242x: 0.004314s -> 8.25e-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 0.07998s (of which 7.606e-05s partitioning, 0s I/O); computing times: 6.914e-06s in par. loops, 1.192e-06s sorting, 9.06e-06s analyzing) -Total merge + benchmarking process took 0.07998s, equivalent to 41106.8/4.0 new/old ops (0.1797s for 2 clones -- as 92348.5/9.0 ops, or 46174.2/4.5 ops per clone), SPEEDUP of 10282.469x -Applying multi-merge (2 -> 1 leaves, 1 steps, 13 -> 13 th.sp.) yielded SPEEDUP of 10282.469x (0.02s -> 1.946e-06s), will amortize in 4.0 ops by saving 0.02s per op. -In 1 tuning rounds (tot. 0.3s, 0.18s for constructor, 2 clones) obtained a SPEEDUP of 1028146.9% (1.028e+04x) (from 0.0009998 to 10.28 Mflops). -After 0.303878s, autotuning routine declared speedup of 10282.5 x, when using threads count of 13. -(5 x 5)[0x574d4d40]{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 0.000038s -- further speedup of 80722.8 x +A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.01294s (of which 2.599e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.01294s, equivalent to 156792.4/3.0 new/old ops (0.02587s for 2 clones -- as 313509.6/6.0 ops, or 156754.8/3.0 ops per clone), SPEEDUP of 52287.242x +Applying multi-merge (2 -> 1 leaves, 1 steps, 24 -> 24 th.sp.) yielded SPEEDUP of 52287.242x (0.004314s -> 8.25e-08s), will amortize in 3.0 ops by saving 0.004314s per op. +In 1 tuning rounds (tot. 0.039s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 5228624.2% (5.229e+04x) (from 0.004636 to 242.4 Mflops). +After 0.039050s, autotuning routine declared speedup of 52287.2 x, when using threads count of 24. +(5 x 5)[0x56ce3ca0]{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 0.000034s -- further speedup of 12780.6 x 0/2 0 0 -> 0 1/2 1 0 -> 5 0/2 0 3 -> 0 @@ -8353,7 +8401,7 @@ Correctly initialized the library. Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0x574d2d50]{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)[0x56ce1b80]{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 @@ -8507,67 +8555,61 @@ 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 4.148e-01 s (100.00 %) - analyzed arrays in 8.355e-02 s (20.14 %) - cleaned-up arrays in 2.308e-04 s (0.06 %) - deduplicated arrays in 2.000e-04 s (0.05 %) - sorted arrays in 1.508e-01 s (36.34 %) - shuffled partitions in 1.081e-01 s (26.05 %) - memory allocations took 9.704e-05 s (0.02 %) - leafs setup took 3.791e-05 s (0.01 %) - halfword conversion took 7.190e-02 s (17.33 %) -Built (500 x 500)[0x565f8360]{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: 58, symflags:'' + converted COO to RSB in 5.767e-02 s (100.00 %) + analyzed arrays in 1.051e-02 s (18.23 %) + cleaned-up arrays in 9.298e-05 s (0.16 %) + deduplicated arrays in 1.459e-04 s (0.25 %) + sorted arrays in 2.215e-02 s (38.41 %) + shuffled partitions in 1.744e-02 s (30.24 %) + memory allocations took 3.028e-05 s (0.05 %) + leafs setup took 2.861e-06 s (0.00 %) + halfword conversion took 7.285e-03 s (12.63 %) +Built (500 x 500)[0x58449370]{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: 28, symflags:'' Allocated matrix of 62500 nonzeroes: -(500 x 500)[0x565f8360]{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: 58, symflags:'' +(500 x 500)[0x58449370]{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: 28, symflags:'' -Before auto-tuning, 100 multiplications took 2.647843s. +Before auto-tuning, 100 multiplications took 0.455535s. 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, 79 subms, 58 lsubms, 2.1238 bpnz. +Will use autotuning routine to sample matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 39 subms, 28 lsubms, 2.0819 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.=1.9985e-06), 13 suggested as starting thread count(default). -3 iterations (13 th.) took 0.0804s; avg 0.0268s ( +/- 41.46/ 64.23 %); best 0.01569s; worst 0.04401s; std dev. 0.01234 (taking best). -Reference operation time is 0.0156891 s (15.93 Mflops) with 13 threads. -3 iterations (13 th.) took 0.09768s; avg 0.03256s ( +/- 4.06/ 4.47 %); best 0.03124s; worst 0.03401s; std dev. 0.001138 (taking best). -Reference operation time is 0.0312359 s (8.004 Mflops) with 13 threads. -After 0.178226s, autotuning routine did not find a better threads count configuration. -(500 x 500)[0x565f8360]{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: 58, symflags:'' -After threads auto-tuning, 100 multiplications took 2.485547s -- effective speedup of 1.0653 x -Matrix autotuning (may take more than 1.500000s; using 13 threads )... -Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 79 subms, 58 lsubms, 2.1238 bpnz. +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.19514e-08), 24 suggested as starting thread count(default). +3 iterations (24 th.) took 0.0135s; avg 0.004499s ( +/- 1.58/ 0.80 %); best 0.004428s; worst 0.004535s; std dev. 5.024e-05 (taking best). +Reference operation time is 0.00442791 s (56.46 Mflops) with 24 threads. +3 iterations (24 th.) took 0.01343s; avg 0.004478s ( +/- 1.54/ 2.10 %); best 0.004409s; worst 0.004572s; std dev. 6.88e-05 (taking best). +Reference operation time is 0.00440907 s (56.7 Mflops) with 24 threads. +After 0.026985s, autotuning routine did not find a better threads count configuration. +(500 x 500)[0x58449370]{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: 28, symflags:'' +After threads auto-tuning, 100 multiplications took 0.454698s -- effective speedup of 1.00184 x +Matrix autotuning (may take more than 1.500000s; using 24 threads )... +Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 39 subms, 28 lsubms, 2.0819 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.=1.9985e-06), 13 suggested as starting thread count. -3 iterations (13 th.) took 0.064s; avg 0.02133s ( +/- 25.07/ 50.00 %); best 0.01599s; worst 0.032s; std dev. 0.007543 (taking best). -Reference operation time is 0.015986 s (15.64 Mflops) with 13 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, 79 subms, 58 lsubms, 2.1238 bpnz (tpop: 0.01599 Mflops: 15.639) -Merge (58 -> 37 leaves) took w.c.t. of 0.07994s, ~0.1992s of computing time (of which 0.02749s sorting, 1.812e-05s analysis) -3 iterations (13 th.) took 0.156s; avg 0.05199s ( +/- 15.47/ 23.14 %); best 0.04394s; worst 0.06402s; std dev. 0.008667 (taking best). -Reference operation time is 0.043942 s (5.689 Mflops) with 13 threads. -After merge step 1: tpop: 0.04394 s ~Mflops: 5.689 nsubm:37 otn:13 -Applying merge (58 -> 37 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.749x: 0.01599s -> 0.04394s. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.19514e-08), 24 suggested as starting thread count. +3 iterations (24 th.) took 0.01342s; avg 0.004472s ( +/- 1.28/ 0.96 %); best 0.004415s; worst 0.004515s; std dev. 4.214e-05 (taking best). +Reference operation time is 0.00441504 s (56.62 Mflops) with 24 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, 39 subms, 28 lsubms, 2.0819 bpnz (tpop: 0.004415 Mflops: 56.625) +Merge (28 -> 22 leaves) took w.c.t. of 0.002432s, ~0.0005369s of computing time (of which 8.678e-05s sorting, 5.007e-06s analysis) +3 iterations (24 th.) took 0.01284s; avg 0.004279s ( +/- 1.85/ 1.63 %); best 0.0042s; worst 0.004349s; std dev. 6.121e-05 (taking best). +Reference operation time is 0.00419998 s (59.52 Mflops) with 24 threads. +After merge step 1: tpop: 0.0042 s ~Mflops: 59.524 nsubm:22 otn:24 +Applying merge (28 -> 22 leaves, 24 th.) yielded SPEEDUP of 1.051x: 0.004415s -> 0.0042s, so taking this instance. +Merge (22 -> 16 leaves) took w.c.t. of 0.002185s, ~0.0001521s of computing time (of which 8.512e-05s sorting, 4.053e-06s analysis) +3 iterations (24 th.) took 0.01155s; avg 0.00385s ( +/- 21.76/ 11.29 %); best 0.003012s; worst 0.004284s; std dev. 0.0005925 (taking best). +Reference operation time is 0.00301194 s (83 Mflops) with 24 threads. +After merge step 2: tpop: 0.003012 s ~Mflops: 83.003 nsubm:16 otn:24 +Applying merge (22 -> 16 leaves, 24 th.) yielded SPEEDUP of 1.394x: 0.0042s -> 0.003012s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.002366s, ~0.00054s of computing time (of which 0.0003648s sorting, 4.053e-06s analysis) +3 iterations (24 th.) took 0.01269s; avg 0.004231s ( +/- 3.17/ 1.71 %); best 0.004097s; worst 0.004304s; std dev. 9.496e-05 (taking best). +Reference operation time is 0.00409722 s (61.02 Mflops) with 24 threads. +After merge step 3: tpop: 0.004097 s ~Mflops: 61.017 nsubm:10 otn:24 +Applying merge (16 -> 10 leaves, 24 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.360x: 0.003012s -> 0.004097s. 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) (58 -> 37 subms) took 0.236s (of which 0.07996s partitioning, 0s I/O); computing times: 0.1992s in par. loops, 0.02749s sorting, 1.812e-05s analyzing) -Total merge + benchmarking process took 0.236s, equivalent to 14.8/14.8 new/old ops (0.07994s for 1 clones -- as 5.0/5.0 ops, or 5.0/5.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (13 th.) took 0.072s; avg 0.024s ( +/- 33.34/ 16.70 %); best 0.016s; worst 0.02801s; std dev. 0.005659 (taking best). -Reference operation time is 0.0159991 s (15.63 Mflops) with 13 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, 79 subms, 58 lsubms, 2.1238 bpnz (tpop: 0.016 Mflops: 15.626) -Split (58 -> 145 leaves, 79 -> 195 subms) took 0.04791s (of which: 1.788e-05s analysis, -5.047e+10s mem.mgmt); compute time: 0.002776s overall, 0.000366s searches, 0.00241s shuffle, 0.0007396s switch, 0.0002165s quadrants. -3 iterations (13 th.) took 0.07974s; avg 0.02658s ( +/- 39.54/ 20.14 %); best 0.01607s; worst 0.03193s; std dev. 0.007431 (taking best). -Reference operation time is 0.0160711 s (15.56 Mflops) with 13 threads. -After split step 1: tpop: 0.01607 s ~Mflops: 15.556 nsubm:145 otn:13 -Applying split (58 -> 145 leaves, 13 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99552x): 0.016s -> 0.01607s, so IGNORING this instance. -Split (145 -> 361 leaves, 195 -> 483 subms) took 0.03186s (of which: 3.6e-05s analysis, -1.253e+11s mem.mgmt); compute time: 0.003157s overall, 0.0006168s searches, 0.00254s shuffle, 0.0007901s switch, 0.0003593s quadrants. -3 iterations (13 th.) took 0.09564s; avg 0.03188s ( +/- 0.75/ 0.43 %); best 0.03164s; worst 0.03202s; std dev. 0.0001701 (taking best). -Reference operation time is 0.0316391 s (7.902 Mflops) with 13 threads. -After split step 2: tpop: 0.03164 s ~Mflops: 7.902 nsubm:361 otn:13 -Applying split (145 -> 361 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.978x: 0.016s -> 0.03164s. -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) (58 -> 361 subms) took 0.256s (of which 0.08053s partitioning, 0s I/O); computing times: 0.005933s in par. loops, 0.0009828s sorting, 5.388e-05s analyzing) -Total split + benchmarking process took 0.256s, equivalent to 16.0/16.0 new/old ops (0.08791s for 1 clones -- as 5.5/5.5 ops, or 5.5/5.5 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.8s, 0.17s for constructor, 2 clones) obtained NO speedup (best stays 15.63 Mflops). -After 0.800013s, autotuning routine declared speedup of 1 x, when using threads count of 13. -(500 x 500)[0x565f8360]{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: 58, symflags:'' -After threads auto-tuning, 100 multiplications took 3.611961s -- further speedup of 0.688143 x +A total of 3 merge steps (of max 6) (28 -> 10 subms) took 0.06983s (of which 0.007001s partitioning, 0s I/O); computing times: 0.001229s in par. loops, 0.0005367s sorting, 1.311e-05s analyzing) +Total merge + benchmarking process took 0.06983s, equivalent to 23.2/15.8 new/old ops (0.03873s for 3 clones -- as 12.9/8.8 ops, or 4.3/2.9 ops per clone), SPEEDUP of 1.466x +Applying multi-merge (28 -> 16 leaves, 2 steps, 24 -> 24 th.sp.) yielded SPEEDUP of 1.466x (0.004415s -> 0.003012s), will amortize in 49.8 ops by saving 0.001403s per op. +In 1 tuning rounds (tot. 0.097s, 0.039s for constructor, 3 clones) obtained a SPEEDUP of 46.6% (1.466x) (from 56.62 to 83 Mflops). +After 0.096579s, autotuning routine declared speedup of 1.46584 x, when using threads count of 24. +(500 x 500)[0x585461b0]{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: 16, symflags:'' +After threads auto-tuning, 100 multiplications took 0.434903s -- further speedup of 1.04552 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! @@ -8575,19 +8617,19 @@ Correctly initialized the library. Building a matrix with 7 nnz, 6 x 6 Duplicates check: 1 - 0 = 1 - converted COO to RSB in 1.568e-01 s (100.00 %) - analyzed arrays in 1.007e-01 s (64.21 %) - cleaned-up arrays in 1.502e-05 s (0.01 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 3.099e-06 s (0.00 %) - shuffled partitions in 5.604e-02 s (35.75 %) - memory allocations took 2.813e-05 s (0.02 %) - leafs setup took 1.001e-05 s (0.01 %) - halfword conversion took 1.097e-05 s (0.01 %) -Built (6 x 6)[0x56d61540]{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 1.523e-02 s (100.00 %) + analyzed arrays in 1.090e-02 s (71.54 %) + cleaned-up arrays in 7.868e-06 s (0.05 %) + deduplicated arrays in 0.000e+00 s (0.00 %) + sorted arrays in 1.192e-06 s (0.01 %) + shuffled partitions in 4.307e-03 s (28.28 %) + memory allocations took 1.001e-05 s (0.07 %) + leafs setup took 1.907e-06 s (0.01 %) + halfword conversion took 5.007e-06 s (0.03 %) +Built (6 x 6)[0x57fee550]{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)[0x56d61540]{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)[0x57fee550]{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 @@ -8613,20 +8655,20 @@ 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:9.659e-07 -3 iterations (13 th.) took 4.911e-05s; avg 1.637e-05s ( +/- 92.72/181.07 %); best 1.192e-06s; worst 4.601e-05s; std dev. 2.096e-05 (taking best). -Reference operation time is 1.19209e-06 s (1.678 Mflops) with 13 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: 1.192e-06 Mflops: 1.678) -Merge (1 -> 1 leaves) took w.c.t. of 9.537e-07s, ~0s of computing time (of which 0s sorting, 0s analysis) -3 iterations (13 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 28.51/ 58.82 %); best 9.659e-07s; worst 2.146e-06s; std dev. 5.62e-07 (taking best). -Reference operation time is 9.65858e-07 s (2.071 Mflops) with 13 threads. -After merge step 1: tpop: 9.659e-07 s ~Mflops: 2.071 nsubm:1 otn:13 -Applying merge (1 -> 1 leaves, 13 th.) yielded SPEEDUP of 1.234x: 1.192e-06s -> 9.659e-07s, so taking this instance. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:5.105e-08 +3 iterations (24 th.) took 2.48e-05s; avg 8.265e-06s ( +/- 88.46/176.92 %); best 9.537e-07s; worst 2.289e-05s; std dev. 1.034e-05 (taking best). +Reference operation time is 9.53674e-07 s (2.097 Mflops) with 24 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: 9.537e-07 Mflops: 2.097) +Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) +3 iterations (24 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.97/ 50.00 %); best 5.105e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 5.10454e-08 s (39.18 Mflops) with 24 threads. +After merge step 1: tpop: 5.105e-08 s ~Mflops: 39.181 nsubm:1 otn:24 +Applying merge (1 -> 1 leaves, 24 th.) yielded SPEEDUP of 18.683x: 9.537e-07s -> 5.105e-08s, so taking 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 0.1079s (of which 6.914e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 0.1079s, equivalent to 111707.9/90508.0 new/old ops (0.2676s for 2 clones -- as 277074.9/224491.6 ops, or 138537.4/112245.8 ops per clone), SPEEDUP of 1.234x -Applying multi-merge (1 -> 1 leaves, 1 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 1.234x (1.192e-06s -> 9.659e-07s), will amortize in 476910.1 ops by saving 2.262e-07s per op. -In 1 tuning rounds (tot. 0.27s, 0.27s for constructor, 2 clones) obtained a SPEEDUP of 23.4% (1.234x) (from 1.678 to 2.071 Mflops). +A total of 1 merge steps (of max 6) (1 -> 1 subms) took 0.01289s (of which 4.053e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 0.01289s, equivalent to 252578.2/13519.2 new/old ops (0.02567s for 2 clones -- as 502807.1/26912.8 ops, or 251403.5/13456.4 ops per clone), SPEEDUP of 18.683x +Applying multi-merge (1 -> 1 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 18.683x (9.537e-07s -> 5.105e-08s), will amortize in 14283.8 ops by saving 9.026e-07s per op. +In 1 tuning rounds (tot. 0.026s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 1768.3% (18.68x) (from 2.097 to 39.18 Mflops). Backsolving we should get a unitary vector: %%MatrixMarket matrix array real general @@ -8661,123 +8703,163 @@ /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 4.615e-01 s (100.00 %) - analyzed arrays in 1.080e-01 s (23.39 %) - cleaned-up arrays in 1.192e-05 s (0.00 %) - deduplicated arrays in 4.053e-06 s (0.00 %) - sorted arrays in 1.094e-01 s (23.71 %) - shuffled partitions in 9.999e-02 s (21.66 %) - memory allocations took 8.607e-05 s (0.02 %) - leafs setup took 1.502e-05 s (0.00 %) - halfword conversion took 1.440e-01 s (31.20 %) -Built (20 x 20)[0x56d83440]{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' + converted COO to RSB in 3.087e-02 s (100.00 %) + analyzed arrays in 1.076e-02 s (34.84 %) + cleaned-up arrays in 4.053e-06 s (0.01 %) + deduplicated arrays in 1.907e-06 s (0.01 %) + sorted arrays in 4.300e-03 s (13.93 %) + shuffled partitions in 7.204e-03 s (23.34 %) + memory allocations took 2.265e-05 s (0.07 %) + leafs setup took 4.053e-06 s (0.01 %) + halfword conversion took 8.566e-03 s (27.75 %) +Built (20 x 20)[0x57ac7450]{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:2.302e-06 -Starting autotuning (16 x 2.3015e-06 s stages, transA=N, nrhs=1, timer gran.=2.3015e-06), 13 suggested as starting thread count(default). -3 iterations (13 th.) took 0.132s; avg 0.04399s ( +/- 45.04/ 54.55 %); best 0.02418s; worst 0.06799s; std dev. 0.01813 (taking best). -Reference operation time is 0.0241778 s (0.03474 Mflops) with 13 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: 0.02418 Mflops: 0.035) -Merge (22 -> 16 leaves) took w.c.t. of 0.0279s, ~0.0001161s of computing time (of which 1.097e-05s sorting, 1.502e-05s analysis) -3 iterations (13 th.) took 0.16s; avg 0.05333s ( +/- 32.50/ 49.93 %); best 0.036s; worst 0.07996s; std dev. 0.01911 (taking best). -Reference operation time is 0.0359969 s (0.02334 Mflops) with 13 threads. -After merge step 1: tpop: 0.036 s ~Mflops: 0.023 nsubm:16 otn:13 -Applying merge (22 -> 16 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.489x: 0.02418s -> 0.036s. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:5.35e-08 +Starting autotuning (16 x 5.35011e-08 s stages, transA=N, nrhs=1, timer gran.=5.35011e-08), 24 suggested as starting thread count(default). +3 iterations (24 th.) took 0.01336s; avg 0.004452s ( +/- 1.29/ 2.26 %); best 0.004395s; worst 0.004553s; std dev. 7.132e-05 (taking best). +Reference operation time is 0.00439501 s (0.1911 Mflops) with 24 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: 0.004395 Mflops: 0.191) +Merge (22 -> 16 leaves) took w.c.t. of 0.002455s, ~0.0003681s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) +3 iterations (24 th.) took 0.01277s; avg 0.004258s ( +/- 0.87/ 0.52 %); best 0.004221s; worst 0.00428s; std dev. 2.635e-05 (taking best). +Reference operation time is 0.00422096 s (0.199 Mflops) with 24 threads. +After merge step 1: tpop: 0.004221 s ~Mflops: 0.199 nsubm:16 otn:24 +Applying merge (22 -> 16 leaves, 24 th.) yielded SPEEDUP of 1.041x: 0.004395s -> 0.004221s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.002104s, ~1.097e-05s of computing time (of which 2.146e-06s sorting, 4.053e-06s analysis) +3 iterations (24 th.) took 0.01236s; avg 0.004121s ( +/- 5.92/ 6.79 %); best 0.003877s; worst 0.004401s; std dev. 0.0002154 (taking best). +Reference operation time is 0.00387692 s (0.2167 Mflops) with 24 threads. +After merge step 2: tpop: 0.003877 s ~Mflops: 0.217 nsubm:10 otn:24 +Applying merge (16 -> 10 leaves, 24 th.) yielded SPEEDUP of 1.089x: 0.004221s -> 0.003877s, so taking this instance. +Merge (10 -> 8 leaves) took w.c.t. of 1.502e-05s, ~5.007e-06s of computing time (of which 2.146e-06s sorting, 1.907e-06s analysis) +3 iterations (24 th.) took 0.01097s; avg 0.003658s ( +/- 37.83/ 19.12 %); best 0.002274s; worst 0.004357s; std dev. 0.0009784 (taking best). +Reference operation time is 0.00227404 s (0.3694 Mflops) with 24 threads. +After merge step 3: tpop: 0.002274 s ~Mflops: 0.369 nsubm:8 otn:24 +Applying merge (10 -> 8 leaves, 24 th.) yielded SPEEDUP of 1.705x: 0.003877s -> 0.002274s, so taking this instance. +Merge (8 -> 6 leaves) took w.c.t. of 1.192e-05s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (24 th.) took 0.0131s; avg 0.004368s ( +/- 0.12/ 0.14 %); best 0.004363s; worst 0.004374s; std dev. 4.616e-06 (taking best). +Reference operation time is 0.00436282 s (0.1925 Mflops) with 24 threads. +After merge step 4: tpop: 0.004363 s ~Mflops: 0.193 nsubm:6 otn:24 +Applying merge (8 -> 6 leaves, 24 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.919x: 0.002274s -> 0.004363s. 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 0.188s (of which 0.02793s partitioning, 0s I/O); computing times: 0.0001161s in par. loops, 1.097e-05s sorting, 1.502e-05s analyzing) -Total merge + benchmarking process took 0.188s, equivalent to 7.8/7.8 new/old ops (0.1479s for 1 clones -- as 6.1/6.1 ops, or 6.1/6.1 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (13 th.) took 0.1531s; avg 0.05102s ( +/- 29.46/ 19.71 %); best 0.03599s; worst 0.06108s; std dev. 0.01083 (taking best). -Reference operation time is 0.0359929 s (0.02334 Mflops) with 13 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: 0.03599 Mflops: 0.023) -Split (22 -> 51 leaves, 30 -> 70 subms) took 0.09189s (of which: 9.06e-06s analysis, -1.914e+10s mem.mgmt); compute time: 0.0668s overall, 3.409e-05s searches, 0.06676s shuffle, 0.06655s switch, 3.052e-05s quadrants. -3 iterations (13 th.) took 0.2159s; avg 0.07196s ( +/- 5.44/ 5.53 %); best 0.06804s; worst 0.07594s; std dev. 0.003222 (taking best). -Reference operation time is 0.0680439 s (0.01234 Mflops) with 13 threads. -After split step 1: tpop: 0.06804 s ~Mflops: 0.012 nsubm:51 otn:13 -Applying split (22 -> 51 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.890x: 0.03599s -> 0.06804s. -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 0.308s (of which 0.09204s partitioning, 0s I/O); computing times: 0.0668s in par. loops, 3.409e-05s sorting, 9.06e-06s analyzing) -Total split + benchmarking process took 0.308s, equivalent to 8.6/8.6 new/old ops (0.1748s for 1 clones -- as 4.9/4.9 ops, or 4.9/4.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 1.1s, 0.32s for constructor, 2 clones) obtained NO speedup (best stays 0.02334 Mflops). - autotuner chose 13 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:2.302e-06 -Starting autotuning (16 x 2.3015e-06 s stages, transA=N, nrhs=1, timer gran.=2.3015e-06), 13 suggested as starting thread count(default). -3 iterations (13 th.) took 0.1418s; avg 0.04726s ( +/- 32.36/ 60.69 %); best 0.03197s; worst 0.07595s; std dev. 0.0203 (taking best). -~ 13 threads: 0.03197s (0.026 Mflops) (0/2 degradations so far) - -3 iterations (12 th.) took 0.139s; avg 0.04632s ( +/- 22.20/ 18.67 %); best 0.03604s; worst 0.05497s; std dev. 0.007813 (taking best). - 12 threads: 0.03604s (0.023 Mflops) (1/2 degradations so far) - -3 iterations (11 th.) took 0.161s; avg 0.05367s ( +/- 55.21/ 56.46 %); best 0.02404s; worst 0.08397s; std dev. 0.02447 (taking best). - 11 threads: 0.02404s (0.035 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 0.1759s; avg 0.05864s ( +/- 13.90/ 25.19 %); best 0.05049s; worst 0.07341s; std dev. 0.01046 (taking best). - 10 threads: 0.05049s (0.017 Mflops) (1/2 degradations so far) - -3 iterations (9 th.) took 0.176s; avg 0.05865s ( +/- 31.88/ 22.76 %); best 0.03995s; worst 0.072s; std dev. 0.01362 (taking best). - 9 threads: 0.03995s (0.021 Mflops) (2/2 degradations so far) - -Best threads choice is 11; starting threads were 13; max speed gap is 2.1x; search took 0.79s. -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: 0.02404 Mflops: 0.035) -Merge (22 -> 16 leaves) took w.c.t. of 0.02397s, ~5.698e-05s of computing time (of which 1.192e-05s sorting, 1.216e-05s analysis) -3 iterations (13 th.) took 0.1519s; avg 0.05064s ( +/- 36.72/ 34.09 %); best 0.03205s; worst 0.06791s; std dev. 0.01467 (taking best). -~ 13 threads: 0.03205s (0.026 Mflops) (0/2 degradations so far) - -3 iterations (12 th.) took 0.1279s; avg 0.04264s ( +/- 34.27/ 31.19 %); best 0.02803s; worst 0.05594s; std dev. 0.01143 (taking best). - 12 threads: 0.02803s (0.03 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.132s; avg 0.04399s ( +/- 9.04/ 9.12 %); best 0.04001s; worst 0.048s; std dev. 0.003262 (taking best). - 11 threads: 0.04001s (0.021 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.3279s; avg 0.1093s ( +/- 63.36/104.89 %); best 0.04005s; worst 0.224s; std dev. 0.08166 (taking best). - 10 threads: 0.04005s (0.021 Mflops) (2/2 degradations so far) - -Best threads choice is 12; starting threads were 13; max speed gap is 1.4x; search took 0.74s. -After merge step 1: tpop: 0.02803 s ~Mflops: 0.030 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.166x: 0.02404s -> 0.02803s. -Merge (16 -> 10 leaves) took w.c.t. of 0.02006s, ~5.913e-05s of computing time (of which 1.311e-05s sorting, 1.907e-05s analysis) -3 iterations (13 th.) took 0.1918s; avg 0.06393s ( +/- 18.74/ 37.37 %); best 0.05195s; worst 0.08782s; std dev. 0.01689 (taking best). -~ 13 threads: 0.05195s (0.016 Mflops) (0/2 degradations so far) - -3 iterations (12 th.) took 0.09992s; avg 0.03331s ( +/- 40.01/ 42.91 %); best 0.01998s; worst 0.0476s; std dev. 0.0113 (taking best). - 12 threads: 0.01998s (0.042 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.09996s; avg 0.03332s ( +/- 52.12/ 56.14 %); best 0.01595s; worst 0.05202s; std dev. 0.01476 (taking best). - 11 threads: 0.01595s (0.053 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 0.1359s; avg 0.04532s ( +/- 10.65/ 14.66 %); best 0.04049s; worst 0.05196s; std dev. 0.004856 (taking best). - 10 threads: 0.04049s (0.021 Mflops) (1/2 degradations so far) - -3 iterations (9 th.) took 0.1003s; avg 0.03344s ( +/- 16.46/ 19.66 %); best 0.02793s; worst 0.04001s; std dev. 0.004989 (taking best). - 9 threads: 0.02793s (0.03 Mflops) (2/2 degradations so far) - -Best threads choice is 11; starting threads were 13; max speed gap is 3.3x; search took 0.63s. -After merge step 2: tpop: 0.01595 s ~Mflops: 0.053 nsubm:10 otn:11 -Applying merge (16 -> 10 leaves, 11 th.) yielded SPEEDUP of 1.507x: 0.02404s -> 0.01595s, so taking this instance. -Merge (10 -> 8 leaves) took w.c.t. of 0.0001731s, ~7.915e-05s of computing time (of which 1.001e-05s sorting, 1.097e-05s analysis) -3 iterations (13 th.) took 0.1118s; avg 0.03727s ( +/- 33.60/ 36.96 %); best 0.02475s; worst 0.05104s; std dev. 0.01077 (taking best). -~ 13 threads: 0.02475s (0.034 Mflops) (0/2 degradations so far) - -3 iterations (12 th.) took 0.2439s; avg 0.08131s ( +/- 31.11/ 57.36 %); best 0.05601s; worst 0.1279s; std dev. 0.03302 (taking best). - 12 threads: 0.05601s (0.015 Mflops) (1/2 degradations so far) - -3 iterations (11 th.) took 0.2s; avg 0.06666s ( +/- 16.04/ 20.09 %); best 0.05597s; worst 0.08005s; std dev. 0.01002 (taking best). - 11 threads: 0.05597s (0.015 Mflops) (2/2 degradations so far) - -Best threads choice is 13; starting threads were 13; max speed gap is 2.3x; search took 0.56s. -After merge step 3: tpop: 0.02475 s ~Mflops: 0.034 nsubm:8 otn:13 -Applying merge (10 -> 8 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.551x: 0.01595s -> 0.02475s. -Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 merge steps (of max 6) (22 -> 8 subms) took 2.06s (of which 0.04427s partitioning, 0s I/O); computing times: 0.0001953s in par. loops, 3.505e-05s sorting, 4.22e-05s analyzing) -Total merge + benchmarking process took 2.06s, equivalent to 129.1/85.7 new/old ops (0.252s for 2 clones -- as 15.8/10.5 ops, or 7.9/5.2 ops per clone), SPEEDUP of 1.507x -Applying multi-merge (22 -> 10 leaves, 2 steps, 11 -> 11 th.sp.) yielded SPEEDUP of 1.507x (0.02404s -> 0.01595s), will amortize in 254.8 ops by saving 0.008085s per op. -In 1 tuning rounds (tot. 3s, 0.25s for constructor, 2 clones) obtained a SPEEDUP of 50.7% (1.507x) (from 0.03494 to 0.05265 Mflops). +A total of 4 merge steps (of max 6) (22 -> 6 subms) took 0.09485s (of which 0.004609s partitioning, 0s I/O); computing times: 0.000387s in par. loops, 7.153e-06s sorting, 1.287e-05s analyzing) +Total merge + benchmarking process took 0.09485s, equivalent to 41.7/21.6 new/old ops (0.05384s for 4 clones -- as 23.7/12.3 ops, or 5.9/3.1 ops per clone), SPEEDUP of 1.933x +Applying multi-merge (22 -> 8 leaves, 3 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 1.933x (0.004395s -> 0.002274s), will amortize in 44.7 ops by saving 0.002121s per op. +In 1 tuning rounds (tot. 0.12s, 0.054s for constructor, 4 clones) obtained a SPEEDUP of 93.3% (1.933x) (from 0.1911 to 0.3694 Mflops). + autotuner chose 24 threads +Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 11 subms, 8 lsubms, 3.0095 bpnz. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:5.35e-08 +Starting autotuning (16 x 5.35011e-08 s stages, transA=N, nrhs=1, timer gran.=5.35011e-08), 24 suggested as starting thread count(default). +3 iterations (24 th.) took 0.01301s; avg 0.004337s ( +/- 0.27/ 0.51 %); best 0.004325s; worst 0.004359s; std dev. 1.58e-05 (taking best). +~ 24 threads: 0.004325s (0.19 Mflops) (0/2 degradations so far) - +3 iterations (23 th.) took 0.01305s; avg 0.00435s ( +/- 0.67/ 0.41 %); best 0.004321s; worst 0.004368s; std dev. 2.082e-05 (taking best). + 23 threads: 0.004321s (0.19 Mflops) (0/2 degradations so far) - +3 iterations (22 th.) took 0.01306s; avg 0.004353s ( +/- 2.92/ 2.23 %); best 0.004226s; worst 0.00445s; std dev. 9.393e-05 (taking best). + 22 threads: 0.004226s (0.2 Mflops) (0/2 degradations so far) - +3 iterations (21 th.) took 0.01308s; avg 0.004361s ( +/- 0.52/ 0.92 %); best 0.004338s; worst 0.004401s; std dev. 2.856e-05 (taking best). + 21 threads: 0.004338s (0.19 Mflops) (1/2 degradations so far) - +3 iterations (20 th.) took 0.01313s; avg 0.004377s ( +/- 1.17/ 0.78 %); best 0.004326s; worst 0.004411s; std dev. 3.679e-05 (taking best). + 20 threads: 0.004326s (0.19 Mflops) (2/2 degradations so far) - +Best threads choice is 22; starting threads were 24; max speed gap is 1x; search took 0.065s. +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, 11 subms, 8 lsubms, 3.0095 bpnz (tpop: 0.004226 Mflops: 0.199) +Merge (8 -> 6 leaves) took w.c.t. of 1.216e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (24 th.) took 0.01296s; avg 0.004319s ( +/- 1.90/ 1.53 %); best 0.004237s; worst 0.004385s; std dev. 6.149e-05 (taking best). +~ 24 threads: 0.004237s (0.2 Mflops) (0/2 degradations so far) - +3 iterations (23 th.) took 0.01298s; avg 0.004327s ( +/- 1.13/ 1.50 %); best 0.004278s; worst 0.004392s; std dev. 4.786e-05 (taking best). + 23 threads: 0.004278s (0.2 Mflops) (1/2 degradations so far) - +3 iterations (22 th.) took 0.01295s; avg 0.004315s ( +/- 0.84/ 1.54 %); best 0.004279s; worst 0.004382s; std dev. 4.716e-05 (taking best). + 22 threads: 0.004279s (0.2 Mflops) (2/2 degradations so far) - +Best threads choice is 24; starting threads were 24; max speed gap is 1x; search took 0.039s. +After merge step 1: tpop: 0.004237 s ~Mflops: 0.198 nsubm:6 otn:24 +Applying merge (8 -> 6 leaves, 24 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99741x): 0.004226s -> 0.004237s, so IGNORING this instance. +Merge (6 -> 3 leaves) took w.c.t. of 1.192e-05s, ~5.007e-06s of computing time (of which 1.907e-06s sorting, 9.537e-07s analysis) +3 iterations (24 th.) took 0.01206s; avg 0.00402s ( +/- 15.61/ 7.93 %); best 0.003393s; worst 0.004339s; std dev. 0.0004437 (taking best). +~ 24 threads: 0.003393s (0.25 Mflops) (0/2 degradations so far) - +3 iterations (23 th.) took 0.01315s; avg 0.004384s ( +/- 1.51/ 1.07 %); best 0.004318s; worst 0.004431s; std dev. 4.807e-05 (taking best). + 23 threads: 0.004318s (0.19 Mflops) (1/2 degradations so far) - +3 iterations (22 th.) took 0.01298s; avg 0.004328s ( +/- 0.48/ 0.86 %); best 0.004307s; worst 0.004365s; std dev. 2.646e-05 (taking best). + 22 threads: 0.004307s (0.2 Mflops) (2/2 degradations so far) - +Best threads choice is 24; starting threads were 24; max speed gap is 1.3x; search took 0.038s. +After merge step 2: tpop: 0.003393 s ~Mflops: 0.248 nsubm:3 otn:24 +Applying merge (6 -> 3 leaves, 24 th.) yielded SPEEDUP of 1.246x: 0.004226s -> 0.003393s, so taking this instance. +Merge (3 -> 1 leaves) took w.c.t. of 1.287e-05s, ~6.199e-06s of computing time (of which 2.861e-06s sorting, 1.907e-06s analysis) +3 iterations (24 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 29.41/ 58.82 %); best 9.537e-07s; worst 2.146e-06s; std dev. 5.62e-07 (taking best). +~ 24 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (23 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). + 23 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (22 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). + 22 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 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) (0/2 degradations so far) - +3 iterations (20 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). + 20 threads: 9.537e-07s (8.8e+02 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) (0/2 degradations so far) - +3 iterations (18 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). + 18 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (17 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). + 17 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (16 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). + 16 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (15 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). + 15 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (14 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). + 14 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (13 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). + 13 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (12 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). + 12 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (11 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). + 11 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (10 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). + 10 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (9 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). + 9 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (8 th.) took 1.502e-05s; avg 5.007e-06s ( +/- 80.95/157.14 %); best 9.537e-07s; worst 1.287e-05s; std dev. 5.564e-06 (taking best). + 8 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (7 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). + 7 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (6 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). + 6 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (5 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). + 5 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (4 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). + 4 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (3 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). + 3 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (2 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). + 2 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (1 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). + 1 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +Best threads choice is 24; starting threads were 24; max speed gap is 1x; search took 0.00026s. +After merge step 3: tpop: 9.537e-07 s ~Mflops: 880.804 nsubm:1 otn:24 +Applying merge (3 -> 1 leaves, 24 th.) yielded SPEEDUP of 3557.750x: 0.003393s -> 9.537e-07s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 3 merge steps (of max 6) (8 -> 1 subms) took 0.1032s (of which 4.911e-05s partitioning, 0s I/O); computing times: 1.526e-05s in par. loops, 5.722e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.1032s, equivalent to 108236.2/24.4 new/old ops (0.0375s for 3 clones -- as 39324.0/8.9 ops, or 13108.0/3.0 ops per clone), SPEEDUP of 4431.250x +Applying multi-merge (8 -> 1 leaves, 3 steps, 22 -> 24 th.sp.) yielded SPEEDUP of 4431.250x (0.004226s -> 9.537e-07s), will amortize in 24.4 ops by saving 0.004225s per op. +In 1 tuning rounds (tot. 0.18s, 0.038s for constructor, 3 clones) obtained a SPEEDUP of 443025.0% (4431x) (from 0.1988 to 880.8 Mflops). check results are ok Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.590e-01 s (100.00 %) - analyzed arrays in 5.582e-02 s (35.11 %) - cleaned-up arrays in 3.099e-06 s (0.00 %) - deduplicated arrays in 5.007e-06 s (0.00 %) - sorted arrays in 3.121e-02 s (19.63 %) - shuffled partitions in 7.190e-02 s (45.22 %) - memory allocations took 3.290e-05 s (0.02 %) - leafs setup took 1.502e-05 s (0.01 %) - halfword conversion took 1.097e-05 s (0.01 %) -Built (6 x 6)[0x56d822d0]{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' + converted COO to RSB in 1.507e-02 s (100.00 %) + analyzed arrays in 6.570e-03 s (43.61 %) + cleaned-up arrays in 9.537e-07 s (0.01 %) + deduplicated arrays in 9.537e-07 s (0.01 %) + sorted arrays in 4.113e-03 s (27.30 %) + shuffled partitions in 4.373e-03 s (29.02 %) + memory allocations took 4.768e-06 s (0.03 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 1.907e-06 s (0.01 %) +Built (6 x 6)[0x57acb330]{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 0.4985E-02 s -A single USMM took 0.3314E-04 s -USMM-to-USMV speed ratio is is 150.4 x +Repeated USMV took 0.7730E-03 s +A single USMM took 0.1693E-04 s +USMM-to-USMV speed ratio is is 45.66 x Call auto-tuning routine.. Repeat measurement. -Tuned USMM took 0.8106E-05 s -Tuned-to-untuned speed ratio is is 4.088 x +Tuned USMM took 0.3099E-05 s +Tuned-to-untuned speed ratio is is 5.462 x FAILED: 0 PASSED: 2 /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran_rsb_fi @@ -8826,250 +8908,223 @@ 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 3.650e-01 s (100.00 %) - analyzed arrays in 1.239e-01 s (33.94 %) - cleaned-up arrays in 1.001e-05 s (0.00 %) - deduplicated arrays in 3.815e-06 s (0.00 %) - sorted arrays in 5.684e-02 s (15.57 %) - shuffled partitions in 8.798e-02 s (24.11 %) - memory allocations took 3.314e-05 s (0.01 %) - leafs setup took 1.502e-05 s (0.00 %) - halfword conversion took 9.620e-02 s (26.36 %) -Built (6 x 6)[0x571b09b0]{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 3.234e-02 s (100.00 %) + analyzed arrays in 1.078e-02 s (33.32 %) + cleaned-up arrays in 4.053e-06 s (0.01 %) + deduplicated arrays in 9.537e-07 s (0.00 %) + sorted arrays in 4.391e-03 s (13.58 %) + shuffled partitions in 8.631e-03 s (26.69 %) + memory allocations took 8.106e-06 s (0.03 %) + leafs setup took 4.053e-06 s (0.01 %) + halfword conversion took 8.519e-03 s (26.34 %) +Built (6 x 6)[0x578279c0]{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)[0x571b3520]{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)[0x5782b320]{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, 4.2778 bpnz. +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 (13 th.) took 0.1399s; avg 0.04663s ( +/- 5.80/ 2.93 %); best 0.04393s; worst 0.048s; std dev. 0.001913 (taking best). -Reference operation time is 0.0439289 s (0.003278 Mflops) with 13 threads. -After 0.140002s, autotuning routine did not find a better threads count configuration. +3 iterations (24 th.) took 0.01425s; avg 0.00475s ( +/- 2.55/ 3.89 %); best 0.004629s; worst 0.004935s; std dev. 0.0001329 (taking best). +Reference operation time is 0.0046289 s (0.03111 Mflops) with 24 threads. +After 0.014292s, 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, 4.2778 bpnz. +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 (13 th.) took 0.156s; avg 0.052s ( +/- 7.69/ 7.72 %); best 0.048s; worst 0.05602s; std dev. 0.003271 (taking best). -Reference operation time is 0.048003 s (0.003 Mflops) with 13 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, 4.2778 bpnz (tpop: 0.048 Mflops: 0.003) -Merge (22 -> 19 leaves) took w.c.t. of 5.317e-05s, ~1.502e-05s of computing time (of which 2.146e-06s sorting, 1.097e-05s analysis) -3 iterations (13 th.) took 0.1439s; avg 0.04798s ( +/- 11.30/ 8.39 %); best 0.04256s; worst 0.052s; std dev. 0.00398 (taking best). -Reference operation time is 0.042556 s (0.003384 Mflops) with 13 threads. -After merge step 1: tpop: 0.04256 s ~Mflops: 0.003 nsubm:19 otn:13 -Applying merge (22 -> 19 leaves, 13 th.) yielded SPEEDUP of 1.128x: 0.048s -> 0.04256s, so taking this instance. -Merge (19 -> 16 leaves) took w.c.t. of 5.794e-05s, ~1.407e-05s of computing time (of which 3.815e-06s sorting, 1.717e-05s analysis) -3 iterations (13 th.) took 0.1008s; avg 0.03358s ( +/- 29.67/ 42.93 %); best 0.02362s; worst 0.048s; std dev. 0.01044 (taking best). -Reference operation time is 0.0236211 s (0.006096 Mflops) with 13 threads. -After merge step 2: tpop: 0.02362 s ~Mflops: 0.006 nsubm:16 otn:13 -Applying merge (19 -> 16 leaves, 13 th.) yielded SPEEDUP of 1.802x: 0.04256s -> 0.02362s, so taking this instance. -Merge (16 -> 13 leaves) took w.c.t. of 4.506e-05s, ~1.097e-05s of computing time (of which 2.861e-06s sorting, 1.311e-05s analysis) -3 iterations (13 th.) took 0.0682s; avg 0.02273s ( +/- 12.17/ 6.59 %); best 0.01997s; worst 0.02423s; std dev. 0.001958 (taking best). -Reference operation time is 0.0199661 s (0.007212 Mflops) with 13 threads. -After merge step 3: tpop: 0.01997 s ~Mflops: 0.007 nsubm:13 otn:13 -Applying merge (16 -> 13 leaves, 13 th.) yielded SPEEDUP of 1.183x: 0.02362s -> 0.01997s, so taking this instance. -Merge (13 -> 10 leaves) took w.c.t. of 7.296e-05s, ~3.314e-05s of computing time (of which 3.099e-06s sorting, 1.216e-05s analysis) -3 iterations (13 th.) took 0.08783s; avg 0.02928s ( +/- 4.44/ 8.75 %); best 0.02798s; worst 0.03184s; std dev. 0.001812 (taking best). -Reference operation time is 0.0279772 s (0.005147 Mflops) with 13 threads. -After merge step 4: tpop: 0.02798 s ~Mflops: 0.005 nsubm:10 otn:13 -Applying merge (13 -> 10 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.401x: 0.01997s -> 0.02798s. +3 iterations (24 th.) took 0.01326s; avg 0.004421s ( +/- 4.00/ 4.68 %); best 0.004244s; worst 0.004628s; std dev. 0.0001581 (taking best). +Reference operation time is 0.00424409 s (0.03393 Mflops) with 24 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: 0.004244 Mflops: 0.034) +Merge (22 -> 16 leaves) took w.c.t. of 0.002605s, ~0.0008681s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) +3 iterations (24 th.) took 0.01283s; avg 0.004278s ( +/- 47.36/ 49.94 %); best 0.002252s; worst 0.006414s; std dev. 0.001701 (taking best). +Reference operation time is 0.00225186 s (0.06395 Mflops) with 24 threads. +After merge step 1: tpop: 0.002252 s ~Mflops: 0.064 nsubm:16 otn:24 +Applying merge (22 -> 16 leaves, 24 th.) yielded SPEEDUP of 1.885x: 0.004244s -> 0.002252s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.002091s, ~1.097e-05s of computing time (of which 1.907e-06s sorting, 3.099e-06s analysis) +3 iterations (24 th.) took 0.01289s; avg 0.004297s ( +/- 1.81/ 1.47 %); best 0.004219s; worst 0.00436s; std dev. 5.842e-05 (taking best). +Reference operation time is 0.00421906 s (0.03413 Mflops) with 24 threads. +After merge step 2: tpop: 0.004219 s ~Mflops: 0.034 nsubm:10 otn:24 +Applying merge (16 -> 10 leaves, 24 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.874x: 0.002252s -> 0.004219s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 4 merge steps (of max 6) (22 -> 10 subms) took 0.6921s (of which 0.0002611s partitioning, 0s I/O); computing times: 7.319e-05s in par. loops, 1.192e-05s sorting, 5.341e-05s analyzing) -Total merge + benchmarking process took 0.6921s, equivalent to 34.7/14.4 new/old ops (0.4747s for 4 clones -- as 23.8/9.9 ops, or 5.9/2.5 ops per clone), SPEEDUP of 2.404x -Applying multi-merge (22 -> 13 leaves, 3 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 2.404x (0.048s -> 0.01997s), will amortize in 24.7 ops by saving 0.02804s per op. -In 1 tuning rounds (tot. 1s, 0.47s for constructor, 4 clones) obtained a SPEEDUP of 140.4% (2.404x) (from 0.003 to 0.007212 Mflops). -After 1.032072s, global autotuning declared speedup of 2.40422 x, when using threads count of 13 and a new matrix: -(6 x 6)[0x571b4f50]{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: 13, symflags:'' +A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.04347s (of which 0.004705s partitioning, 0s I/O); computing times: 0.000879s in par. loops, 3.815e-06s sorting, 7.153e-06s analyzing) +Total merge + benchmarking process took 0.04347s, equivalent to 19.3/10.2 new/old ops (0.02689s for 2 clones -- as 11.9/6.3 ops, or 6.0/3.2 ops per clone), SPEEDUP of 1.885x +Applying multi-merge (22 -> 16 leaves, 1 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 1.885x (0.004244s -> 0.002252s), will amortize in 21.8 ops by saving 0.001992s per op. +In 1 tuning rounds (tot. 0.071s, 0.027s for constructor, 2 clones) obtained a SPEEDUP of 88.5% (1.885x) (from 0.03393 to 0.06395 Mflops). +After 0.070676s, global autotuning declared speedup of 1.8847 x, when using threads count of 24 and a new matrix: +(6 x 6)[0x5782ce60]{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: 16, symflags:'' Considering S clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.838e-01 s (100.00 %) - analyzed arrays in 5.408e-02 s (29.43 %) - cleaned-up arrays in 2.146e-06 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 5.368e-02 s (29.21 %) - memory allocations took 2.408e-05 s (0.01 %) - leafs setup took 8.106e-06 s (0.00 %) - halfword conversion took 7.595e-02 s (41.33 %) -Built (6 x 6)[0x571b3520]{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:'' + converted COO to RSB in 2.811e-02 s (100.00 %) + analyzed arrays in 1.078e-02 s (38.36 %) + cleaned-up arrays in 9.537e-07 s (0.00 %) + deduplicated arrays in 0.000e+00 s (0.00 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.620e-03 s (30.66 %) + memory allocations took 4.053e-06 s (0.01 %) + leafs setup took 1.907e-06 s (0.01 %) + halfword conversion took 8.700e-03 s (30.95 %) +Built (6 x 6)[0x5782ce60]{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)[0x571b3520]{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)[0x5782ce60]{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, 4.5000 bpnz. +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 (13 th.) took 0.09591s; avg 0.03197s ( +/- 12.71/ 25.11 %); best 0.02791s; worst 0.04s; std dev. 0.005677 (taking best). -Reference operation time is 0.027909 s (0.00516 Mflops) with 13 threads. -After 0.095997s, autotuning routine did not find a better threads count configuration. +3 iterations (24 th.) took 0.01314s; avg 0.004379s ( +/- 0.42/ 0.56 %); best 0.004361s; worst 0.004404s; std dev. 1.812e-05 (taking best). +Reference operation time is 0.00436115 s (0.03302 Mflops) with 24 threads. +After 0.013160s, 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, 4.5000 bpnz. +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 (13 th.) took 0.1122s; avg 0.03742s ( +/- 36.98/ 50.09 %); best 0.02358s; worst 0.05616s; std dev. 0.01374 (taking best). -Reference operation time is 0.0235782 s (0.006107 Mflops) with 13 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, 4.5000 bpnz (tpop: 0.02358 Mflops: 0.006) -Merge (16 -> 13 leaves) took w.c.t. of 4.101e-05s, ~1.192e-05s of computing time (of which 3.815e-06s sorting, 9.06e-06s analysis) -3 iterations (13 th.) took 0.1077s; avg 0.03589s ( +/- 21.88/ 11.27 %); best 0.02804s; worst 0.03993s; std dev. 0.005553 (taking best). -Reference operation time is 0.0280361 s (0.005136 Mflops) with 13 threads. -After merge step 1: tpop: 0.02804 s ~Mflops: 0.005 nsubm:13 otn:13 -Applying merge (16 -> 13 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.189x: 0.02358s -> 0.02804s. -Merge (13 -> 10 leaves) took w.c.t. of 5.317e-05s, ~1.693e-05s of computing time (of which 3.099e-06s sorting, 1.001e-05s analysis) -3 iterations (13 th.) took 0.1142s; avg 0.03807s ( +/- 36.19/ 42.06 %); best 0.02429s; worst 0.05409s; std dev. 0.01227 (taking best). -Reference operation time is 0.0242929 s (0.005928 Mflops) with 13 threads. -After merge step 2: tpop: 0.02429 s ~Mflops: 0.006 nsubm:10 otn:13 -Applying merge (13 -> 10 leaves, 13 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.030x: 0.02358s -> 0.02429s. -Merge (10 -> 7 leaves) took w.c.t. of 4.697e-05s, ~1.311e-05s of computing time (of which 2.861e-06s sorting, 1.001e-05s analysis) -3 iterations (13 th.) took 0.1135s; avg 0.03783s ( +/- 35.41/ 19.05 %); best 0.02444s; worst 0.04504s; std dev. 0.00948 (taking best). -Reference operation time is 0.024436 s (0.005893 Mflops) with 13 threads. -After merge step 3: tpop: 0.02444 s ~Mflops: 0.006 nsubm:7 otn:13 -Applying merge (10 -> 7 leaves, 13 th.) yielded SLOWDOWN (3th of 3 tolerable) of 1.036x: 0.02358s -> 0.02444s. -Merge (7 -> 4 leaves) took w.c.t. of 8.297e-05s, ~2.193e-05s of computing time (of which 4.053e-06s sorting, 2.098e-05s analysis) -3 iterations (13 th.) took 0.1038s; avg 0.0346s ( +/- 7.40/ 4.01 %); best 0.03204s; worst 0.03599s; std dev. 0.001812 (taking best). -Reference operation time is 0.0320449 s (0.004494 Mflops) with 13 threads. -After merge step 4: tpop: 0.03204 s ~Mflops: 0.004 nsubm:4 otn:13 -Applying merge (7 -> 4 leaves, 13 th.) yielded SLOWDOWN (4th of 3 tolerable) of 1.359x: 0.02358s -> 0.03204s. -Skipping further merge based tests after 4 definite performance degradations in a row (and last exceeding limit). -A total of 4 merge steps (of max 6) (16 -> 4 subms) took 0.4398s (of which 0.000252s partitioning, 0s I/O); computing times: 6.39e-05s in par. loops, 1.383e-05s sorting, 5.007e-05s analyzing) -Total merge + benchmarking process took 0.4398s, equivalent to 18.7/18.7 new/old ops (0.09592s for 1 clones -- as 4.1/4.1 ops, or 4.1/4.1 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (13 th.) took 0.09204s; avg 0.03068s ( +/- 21.91/ 29.02 %); best 0.02396s; worst 0.03958s; std dev. 0.006563 (taking best). -Reference operation time is 0.023958 s (0.006011 Mflops) with 13 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 S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.5000 bpnz (tpop: 0.02396 Mflops: 0.006) -Split (16 -> 25 leaves, 21 -> 33 subms) took 0.04162s (of which: 8.821e-06s analysis, -5.221e+09s mem.mgmt); compute time: 0.07619s overall, 1.097e-05s searches, 0.07618s shuffle, 0.04804s switch, 6.914e-06s quadrants. -3 iterations (13 th.) took 0.1102s; avg 0.03672s ( +/- 12.83/ 19.78 %); best 0.03201s; worst 0.04399s; std dev. 0.005213 (taking best). -Reference operation time is 0.032011 s (0.004498 Mflops) with 13 threads. -After split step 1: tpop: 0.03201 s ~Mflops: 0.004 nsubm:25 otn:13 -Applying split (16 -> 25 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.336x: 0.02396s -> 0.03201s. -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) (16 -> 25 subms) took 0.1519s (of which 0.04172s partitioning, 0s I/O); computing times: 0.07619s in par. loops, 1.097e-05s sorting, 8.821e-06s analyzing) -Total split + benchmarking process took 0.1519s, equivalent to 6.3/6.3 new/old ops (0.09991s for 1 clones -- as 4.2/4.2 ops, or 4.2/4.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.99s, 0.2s for constructor, 2 clones) obtained NO speedup (best stays 0.006011 Mflops). -After 0.992036s, global autotuning found old matrix optimal, with declared speedup 1 x when using 13 threads +3 iterations (24 th.) took 0.01303s; avg 0.004343s ( +/- 1.16/ 1.95 %); best 0.004293s; worst 0.004428s; std dev. 6.02e-05 (taking best). +Reference operation time is 0.00429296 s (0.03354 Mflops) with 24 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: 0.004293 Mflops: 0.034) +Merge (16 -> 10 leaves) took w.c.t. of 0.002166s, ~1.407e-05s of computing time (of which 5.96e-06s sorting, 2.146e-06s analysis) +3 iterations (24 th.) took 0.01583s; avg 0.005278s ( +/- 19.00/ 21.98 %); best 0.004275s; worst 0.006438s; std dev. 0.00089 (taking best). +Reference operation time is 0.00427508 s (0.03368 Mflops) with 24 threads. +After merge step 1: tpop: 0.004275 s ~Mflops: 0.034 nsubm:10 otn:24 +Applying merge (16 -> 10 leaves, 24 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00418x): 0.004293s -> 0.004275s, so IGNORING this instance. +Merge (10 -> 7 leaves) took w.c.t. of 1.287e-05s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (24 th.) took 0.01076s; avg 0.003588s ( +/- 37.79/ 19.09 %); best 0.002232s; worst 0.004273s; std dev. 0.0009588 (taking best). +Reference operation time is 0.00223207 s (0.06451 Mflops) with 24 threads. +After merge step 2: tpop: 0.002232 s ~Mflops: 0.065 nsubm:7 otn:24 +Applying merge (10 -> 7 leaves, 24 th.) yielded SPEEDUP of 1.923x: 0.004293s -> 0.002232s, so taking this instance. +Merge (7 -> 4 leaves) took w.c.t. of 1.097e-05s, ~3.099e-06s of computing time (of which 0s sorting, 2.146e-06s analysis) +3 iterations (24 th.) took 0.01297s; avg 0.004324s ( +/- 47.83/ 46.71 %); best 0.002256s; worst 0.006344s; std dev. 0.001669 (taking best). +Reference operation time is 0.00225592 s (0.06383 Mflops) with 24 threads. +After merge step 3: tpop: 0.002256 s ~Mflops: 0.064 nsubm:4 otn:24 +Applying merge (7 -> 4 leaves, 24 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98943x): 0.002232s -> 0.002256s, so IGNORING this instance. +Merge (4 -> 1 leaves) took w.c.t. of 1.001e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (24 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). +Reference operation time is 9.53674e-07 s (151 Mflops) with 24 threads. +After merge step 4: tpop: 9.537e-07 s ~Mflops: 150.995 nsubm:1 otn:24 +Applying merge (4 -> 1 leaves, 24 th.) yielded SPEEDUP of 2340.500x: 0.002232s -> 9.537e-07s, 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 0.0679s (of which 0.002217s partitioning, 0s I/O); computing times: 2.432e-05s in par. loops, 7.868e-06s sorting, 9.298e-06s analyzing) +Total merge + benchmarking process took 0.0679s, equivalent to 71195.2/15.8 new/old ops (0.03921s for 3 clones -- as 41115.8/9.1 ops, or 13705.2/3.0 ops per clone), SPEEDUP of 4501.500x +Applying multi-merge (16 -> 1 leaves, 4 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 4501.500x (0.004293s -> 9.537e-07s), will amortize in 15.8 ops by saving 0.004292s per op. +In 1 tuning rounds (tot. 0.094s, 0.039s for constructor, 3 clones) obtained a SPEEDUP of 450050.0% (4502x) (from 0.03354 to 151 Mflops). +After 0.094161s, global autotuning declared speedup of 4501.5 x, when using threads count of 24 and a new matrix: +(6 x 6)[0x5782f150]{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 1.959e-01 s (100.00 %) - analyzed arrays in 9.199e-02 s (46.96 %) - cleaned-up arrays in 1.907e-06 s (0.00 %) - deduplicated arrays in 1.907e-06 s (0.00 %) - sorted arrays in 1.192e-06 s (0.00 %) - shuffled partitions in 4.398e-02 s (22.45 %) - memory allocations took 1.693e-05 s (0.01 %) - leafs setup took 8.106e-06 s (0.00 %) - halfword conversion took 5.989e-02 s (30.57 %) -Built (6 x 6)[0x571b8980]{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:'' + converted COO to RSB in 2.863e-02 s (100.00 %) + analyzed arrays in 1.088e-02 s (38.02 %) + cleaned-up arrays in 9.537e-07 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.888e-03 s (31.05 %) + memory allocations took 1.311e-05 s (0.05 %) + leafs setup took 2.861e-06 s (0.01 %) + halfword conversion took 8.837e-03 s (30.87 %) +Built (6 x 6)[0x578315b0]{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)[0x571b8980]{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)[0x578315b0]{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 (13 th.) took 0.08389s; avg 0.02796s ( +/- 0.73/ 0.66 %); best 0.02776s; worst 0.02815s; std dev. 0.0001583 (taking best). -Reference operation time is 0.0277598 s (0.02075 Mflops) with 13 threads. -After 0.083963s, autotuning routine did not find a better threads count configuration. +3 iterations (24 th.) took 0.01337s; avg 0.004455s ( +/- 0.76/ 1.44 %); best 0.004421s; worst 0.004519s; std dev. 4.527e-05 (taking best). +Reference operation time is 0.004421 s (0.1303 Mflops) with 24 threads. +After 0.013386s, 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 (13 th.) took 0.08003s; avg 0.02668s ( +/- 39.83/ 34.84 %); best 0.01605s; worst 0.03597s; std dev. 0.008186 (taking best). -Reference operation time is 0.016052 s (0.03588 Mflops) with 13 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: 0.01605 Mflops: 0.036) -Merge (22 -> 16 leaves) took w.c.t. of 0.01598s, ~4.005e-05s of computing time (of which 8.106e-06s sorting, 1.502e-05s analysis) -3 iterations (13 th.) took 0.09191s; avg 0.03064s ( +/- 47.74/ 43.23 %); best 0.01601s; worst 0.04388s; std dev. 0.01142 (taking best). -Reference operation time is 0.016011 s (0.03598 Mflops) with 13 threads. -After merge step 1: tpop: 0.01601 s ~Mflops: 0.036 nsubm:16 otn:13 -Applying merge (22 -> 16 leaves, 13 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00256x): 0.01605s -> 0.01601s, so IGNORING this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.02421s, ~4.601e-05s of computing time (of which 1.097e-05s sorting, 1.001e-05s analysis) -3 iterations (13 th.) took 0.1s; avg 0.03333s ( +/- 37.67/ 67.58 %); best 0.02078s; worst 0.05586s; std dev. 0.01596 (taking best). -Reference operation time is 0.020777 s (0.02772 Mflops) with 13 threads. -After merge step 2: tpop: 0.02078 s ~Mflops: 0.028 nsubm:10 otn:13 -Applying merge (16 -> 10 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.294x: 0.01605s -> 0.02078s. -Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.2322s (of which 0.04024s partitioning, 0s I/O); computing times: 8.607e-05s in par. loops, 1.907e-05s sorting, 2.503e-05s analyzing) -Total merge + benchmarking process took 0.2322s, equivalent to 14.5/14.5 new/old ops (0.07996s for 1 clones -- as 5.0/5.0 ops, or 5.0/5.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (13 th.) took 0.08032s; avg 0.02677s ( +/- 24.87/ 34.13 %); best 0.02011s; worst 0.03591s; std dev. 0.006683 (taking best). -Reference operation time is 0.0201149 s (0.02864 Mflops) with 13 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: 0.02011 Mflops: 0.029) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.03771s (of which: 1.001e-05s analysis, -3.481e+09s mem.mgmt); compute time: 0.000248s overall, 4.292e-06s searches, 0.0002437s shuffle, 0.0001242s switch, 5.245e-06s quadrants. -3 iterations (13 th.) took 0.09814s; avg 0.03271s ( +/- 26.60/ 21.07 %); best 0.02401s; worst 0.0396s; std dev. 0.006493 (taking best). -Reference operation time is 0.024013 s (0.02399 Mflops) with 13 threads. -After split step 1: tpop: 0.02401 s ~Mflops: 0.024 nsubm:28 otn:13 -Applying split (22 -> 28 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.194x: 0.02011s -> 0.02401s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.05987s (of which: 1.192e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (13 th.) took 0.09391s; avg 0.0313s ( +/- 23.48/ 15.02 %); best 0.02395s; worst 0.03601s; std dev. 0.005265 (taking best). -Reference operation time is 0.023953 s (0.02405 Mflops) with 13 threads. -After split step 2: tpop: 0.02395 s ~Mflops: 0.024 nsubm:28 otn:13 -Applying split (28 -> 28 leaves, 13 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.191x: 0.02011s -> 0.02395s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03365s (of which: 1.097e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (13 th.) took 0.07988s; avg 0.02663s ( +/- 39.89/ 34.78 %); best 0.01601s; worst 0.03589s; std dev. 0.008174 (taking best). -Reference operation time is 0.016006 s (0.03599 Mflops) with 13 threads. -After split step 3: tpop: 0.01601 s ~Mflops: 0.036 nsubm:28 otn:13 -Applying split (28 -> 28 leaves, 13 th.) yielded SPEEDUP of 1.257x: 0.02011s -> 0.01601s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03587s (of which: 1.192e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (13 th.) took 0.08794s; avg 0.02931s ( +/- 45.67/ 36.56 %); best 0.01592s; worst 0.04003s; std dev. 0.01002 (taking best). -Reference operation time is 0.015924 s (0.03617 Mflops) with 13 threads. -After split step 4: tpop: 0.01592 s ~Mflops: 0.036 nsubm:28 otn:13 -Applying split (28 -> 28 leaves, 13 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00515x): 0.01601s -> 0.01592s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.02793s (of which: 1.192e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (13 th.) took 0.09589s; avg 0.03196s ( +/- 33.53/ 25.18 %); best 0.02125s; worst 0.04001s; std dev. 0.007891 (taking best). -Reference operation time is 0.0212462 s (0.02711 Mflops) with 13 threads. -After split step 5: tpop: 0.02125 s ~Mflops: 0.027 nsubm:28 otn:13 -Applying split (28 -> 28 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.327x: 0.01601s -> 0.02125s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 5 split steps (of max 6) (22 -> 28 subms) took 0.7559s (of which 0.1955s partitioning, 0s I/O); computing times: 0.000248s in par. loops, 4.292e-06s sorting, 5.674e-05s analyzing) -Total split + benchmarking process took 0.7559s, equivalent to 47.2/37.6 new/old ops (0.1793s for 2 clones -- as 11.2/8.9 ops, or 5.6/4.5 ops per clone), SPEEDUP of 1.257x -Applying multi-split (22 -> 28 leaves, 3 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 1.257x (0.02011s -> 0.01601s), will amortize in 184.0 ops by saving 0.004109s per op. -In 1 tuning rounds (tot. 1.3s, 0.26s for constructor, 3 clones) obtained a SPEEDUP of 25.7% (1.257x) (from 0.02864 to 0.03599 Mflops). -After 1.304080s, global autotuning declared speedup of 1.25671 x, when using threads count of 13 and a new matrix: -(6 x 6)[0x571ba6d0]{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: 28, symflags:'' +3 iterations (24 th.) took 0.01353s; avg 0.004511s ( +/- 0.58/ 0.48 %); best 0.004485s; worst 0.004533s; std dev. 1.986e-05 (taking best). +Reference operation time is 0.00448489 s (0.1284 Mflops) with 24 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: 0.004485 Mflops: 0.128) +Merge (22 -> 16 leaves) took w.c.t. of 0.002143s, ~6.676e-06s of computing time (of which 0s sorting, 2.861e-06s analysis) +3 iterations (24 th.) took 0.01341s; avg 0.004469s ( +/- 4.91/ 9.26 %); best 0.00425s; worst 0.004883s; std dev. 0.0002927 (taking best). +Reference operation time is 0.00425005 s (0.1355 Mflops) with 24 threads. +After merge step 1: tpop: 0.00425 s ~Mflops: 0.136 nsubm:16 otn:24 +Applying merge (22 -> 16 leaves, 24 th.) yielded SPEEDUP of 1.055x: 0.004485s -> 0.00425s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.002142s, ~1.216e-05s of computing time (of which 1.907e-06s sorting, 2.146e-06s analysis) +3 iterations (24 th.) took 0.01273s; avg 0.004242s ( +/- 1.38/ 1.00 %); best 0.004183s; worst 0.004284s; std dev. 4.283e-05 (taking best). +Reference operation time is 0.00418305 s (0.1377 Mflops) with 24 threads. +After merge step 2: tpop: 0.004183 s ~Mflops: 0.138 nsubm:10 otn:24 +Applying merge (16 -> 10 leaves, 24 th.) yielded SPEEDUP of 1.016x: 0.00425s -> 0.004183s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 1.216e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (24 th.) took 0.0131s; avg 0.004368s ( +/- 1.34/ 0.70 %); best 0.004309s; worst 0.004398s; std dev. 4.154e-05 (taking best). +Reference operation time is 0.00430894 s (0.1337 Mflops) with 24 threads. +After merge step 3: tpop: 0.004309 s ~Mflops: 0.134 nsubm:7 otn:24 +Applying merge (10 -> 7 leaves, 24 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.030x: 0.004183s -> 0.004309s. +Merge (7 -> 4 leaves) took w.c.t. of 9.06e-06s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (24 th.) took 0.01313s; avg 0.004378s ( +/- 1.08/ 0.73 %); best 0.004331s; worst 0.00441s; std dev. 3.403e-05 (taking best). +Reference operation time is 0.00433087 s (0.133 Mflops) with 24 threads. +After merge step 4: tpop: 0.004331 s ~Mflops: 0.133 nsubm:4 otn:24 +Applying merge (7 -> 4 leaves, 24 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.035x: 0.004183s -> 0.004331s. +Merge (4 -> 1 leaves) took w.c.t. of 1.192e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +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). +Reference operation time is 9.53674e-07 s (604 Mflops) with 24 threads. +After merge step 5: tpop: 9.537e-07 s ~Mflops: 603.980 nsubm:1 otn:24 +Applying merge (4 -> 1 leaves, 24 th.) yielded SPEEDUP of 4386.250x: 0.004183s -> 9.537e-07s, 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 0.09568s (of which 0.004343s partitioning, 0s I/O); computing times: 3.076e-05s in par. loops, 4.768e-06s sorting, 1.097e-05s analyzing) +Total merge + benchmarking process took 0.09568s, equivalent to 100325.8/21.3 new/old ops (0.05196s for 4 clones -- as 54487.2/11.6 ops, or 13621.8/2.9 ops per clone), SPEEDUP of 4702.750x +Applying multi-merge (22 -> 1 leaves, 5 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 4702.750x (0.004485s -> 9.537e-07s), will amortize in 21.3 ops by saving 0.004484s per op. +In 1 tuning rounds (tot. 0.12s, 0.052s for constructor, 4 clones) obtained a SPEEDUP of 470175.0% (4703x) (from 0.1284 to 604 Mflops). +After 0.122357s, global autotuning declared speedup of 4702.75 x, when using threads count of 24 and a new matrix: +(6 x 6)[0x578298d0]{C} @ (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 Z clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.598e-01 s (100.00 %) - analyzed arrays in 6.379e-02 s (39.91 %) - cleaned-up arrays in 1.907e-06 s (0.00 %) + converted COO to RSB in 2.874e-02 s (100.00 %) + analyzed arrays in 1.097e-02 s (38.17 %) + cleaned-up arrays in 9.537e-07 s (0.00 %) deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 3.604e-02 s (22.55 %) - memory allocations took 2.933e-05 s (0.02 %) - leafs setup took 1.097e-05 s (0.01 %) - halfword conversion took 5.995e-02 s (37.51 %) -Built (6 x 6)[0x571b8980]{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:'' + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.924e-03 s (31.05 %) + memory allocations took 4.053e-06 s (0.01 %) + leafs setup took 1.907e-06 s (0.01 %) + halfword conversion took 8.837e-03 s (30.75 %) +Built (6 x 6)[0x57830b70]{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)[0x571b8980]{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)[0x57830b70]{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 (13 th.) took 0.08787s; avg 0.02929s ( +/- 31.73/ 49.72 %); best 0.02s; worst 0.04385s; std dev. 0.01043 (taking best). -Reference operation time is 0.0199971 s (0.0288 Mflops) with 13 threads. -After 0.088395s, autotuning routine did not find a better threads count configuration. +3 iterations (24 th.) took 0.01365s; avg 0.00455s ( +/- 0.45/ 0.36 %); best 0.004529s; worst 0.004566s; std dev. 1.54e-05 (taking best). +Reference operation time is 0.004529 s (0.1272 Mflops) with 24 threads. +After 0.013670s, 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 (13 th.) took 0.08798s; avg 0.02933s ( +/- 18.05/ 9.08 %); best 0.02403s; worst 0.03199s; std dev. 0.003744 (taking best). -Reference operation time is 0.0240328 s (0.02397 Mflops) with 13 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: 0.02403 Mflops: 0.024) -Merge (28 -> 22 leaves) took w.c.t. of 9.203e-05s, ~5.698e-05s of computing time (of which 1.788e-05s sorting, 1.001e-05s analysis) -3 iterations (13 th.) took 0.09182s; avg 0.03061s ( +/- 21.63/ 19.50 %); best 0.02398s; worst 0.03657s; std dev. 0.005159 (taking best). -Reference operation time is 0.0239849 s (0.02402 Mflops) with 13 threads. -After merge step 1: tpop: 0.02398 s ~Mflops: 0.024 nsubm:22 otn:13 -Applying merge (28 -> 22 leaves, 13 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00200x): 0.02403s -> 0.02398s, so IGNORING this instance. -Merge (22 -> 16 leaves) took w.c.t. of 0.01603s, ~4.315e-05s of computing time (of which 1.311e-05s sorting, 1.693e-05s analysis) -3 iterations (13 th.) took 0.1199s; avg 0.03996s ( +/- 59.95/ 60.02 %); best 0.01601s; worst 0.06395s; std dev. 0.01957 (taking best). -Reference operation time is 0.0160069 s (0.03598 Mflops) with 13 threads. -After merge step 2: tpop: 0.01601 s ~Mflops: 0.036 nsubm:16 otn:13 -Applying merge (22 -> 16 leaves, 13 th.) yielded SPEEDUP of 1.501x: 0.02403s -> 0.01601s, so taking this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.01167s, ~0.0001001s of computing time (of which 2.623e-05s sorting, 1.788e-05s analysis) -3 iterations (13 th.) took 0.09626s; avg 0.03209s ( +/- 12.69/ 24.53 %); best 0.02801s; worst 0.03996s; std dev. 0.005567 (taking best). -Reference operation time is 0.028013 s (0.02056 Mflops) with 13 threads. -After merge step 3: tpop: 0.02801 s ~Mflops: 0.021 nsubm:10 otn:13 -Applying merge (16 -> 10 leaves, 13 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.750x: 0.01601s -> 0.02801s. +3 iterations (24 th.) took 0.01356s; avg 0.00452s ( +/- 1.88/ 1.26 %); best 0.004435s; worst 0.004577s; std dev. 6.122e-05 (taking best). +Reference operation time is 0.00443506 s (0.1299 Mflops) with 24 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: 0.004435 Mflops: 0.130) +Merge (28 -> 22 leaves) took w.c.t. of 0.002164s, ~6.676e-06s of computing time (of which 1.907e-06s sorting, 2.861e-06s analysis) +3 iterations (24 th.) took 0.01345s; avg 0.004484s ( +/- 1.83/ 1.88 %); best 0.004402s; worst 0.004568s; std dev. 6.786e-05 (taking best). +Reference operation time is 0.00440192 s (0.1309 Mflops) with 24 threads. +After merge step 1: tpop: 0.004402 s ~Mflops: 0.131 nsubm:22 otn:24 +Applying merge (28 -> 22 leaves, 24 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00753x): 0.004435s -> 0.004402s, so IGNORING this instance. +Merge (22 -> 16 leaves) took w.c.t. of 0.002089s, ~6.914e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (24 th.) took 0.0141s; avg 0.0047s ( +/- 6.64/ 11.38 %); best 0.004388s; worst 0.005235s; std dev. 0.0003801 (taking best). +Reference operation time is 0.00438786 s (0.1313 Mflops) with 24 threads. +After merge step 2: tpop: 0.004388 s ~Mflops: 0.131 nsubm:16 otn:24 +Applying merge (22 -> 16 leaves, 24 th.) yielded SPEEDUP of 1.011x: 0.004435s -> 0.004388s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.00215s, ~8.821e-06s of computing time (of which 1.907e-06s sorting, 2.146e-06s analysis) +3 iterations (24 th.) took 0.01409s; avg 0.004698s ( +/- 8.61/ 15.38 %); best 0.004293s; worst 0.00542s; std dev. 0.000512 (taking best). +Reference operation time is 0.00429296 s (0.1342 Mflops) with 24 threads. +After merge step 3: tpop: 0.004293 s ~Mflops: 0.134 nsubm:10 otn:24 +Applying merge (16 -> 10 leaves, 24 th.) yielded SPEEDUP of 1.022x: 0.004388s -> 0.004293s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 1.097e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) +3 iterations (24 th.) took 0.01071s; avg 0.003571s ( +/- 38.65/ 20.04 %); best 0.002191s; worst 0.004287s; std dev. 0.0009762 (taking best). +Reference operation time is 0.00219107 s (0.2629 Mflops) with 24 threads. +After merge step 4: tpop: 0.002191 s ~Mflops: 0.263 nsubm:7 otn:24 +Applying merge (10 -> 7 leaves, 24 th.) yielded SPEEDUP of 1.959x: 0.004293s -> 0.002191s, so taking this instance. +Merge (7 -> 4 leaves) took w.c.t. of 9.06e-06s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (24 th.) took 0.0131s; avg 0.004367s ( +/- 0.16/ 0.13 %); best 0.00436s; worst 0.004373s; std dev. 5.315e-06 (taking best). +Reference operation time is 0.00435996 s (0.1321 Mflops) with 24 threads. +After merge step 5: tpop: 0.00436 s ~Mflops: 0.132 nsubm:4 otn:24 +Applying merge (7 -> 4 leaves, 24 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.990x: 0.002191s -> 0.00436s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 merge steps (of max 6) (28 -> 10 subms) took 0.4323s (of which 0.02786s partitioning, 0s I/O); computing times: 0.0002003s in par. loops, 5.722e-05s sorting, 4.482e-05s analyzing) -Total merge + benchmarking process took 0.4323s, equivalent to 27.0/18.0 new/old ops (0.1797s for 2 clones -- as 11.2/7.5 ops, or 5.6/3.7 ops per clone), SPEEDUP of 1.501x -Applying multi-merge (28 -> 16 leaves, 2 steps, 0 -> 13 th.sp.) yielded SPEEDUP of 1.501x (0.02403s -> 0.01601s), will amortize in 53.9 ops by saving 0.008026s per op. -In 1 tuning rounds (tot. 0.6s, 0.18s for constructor, 2 clones) obtained a SPEEDUP of 50.1% (1.501x) (from 0.02397 to 0.03598 Mflops). -After 0.603872s, global autotuning declared speedup of 1.5014 x, when using threads count of 13 and a new matrix: -(6 x 6)[0x571bb3d0]{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: 16, symflags:'' +A total of 5 merge steps (of max 6) (28 -> 4 subms) took 0.1114s (of which 0.006443s partitioning, 0s I/O); computing times: 2.933e-05s in par. loops, 6.676e-06s sorting, 1.407e-05s analyzing) +Total merge + benchmarking process took 0.1114s, equivalent to 50.9/25.1 new/old ops (0.05253s for 4 clones -- as 24.0/11.8 ops, or 6.0/3.0 ops per clone), SPEEDUP of 2.024x +Applying multi-merge (28 -> 7 leaves, 4 steps, 0 -> 24 th.sp.) yielded SPEEDUP of 2.024x (0.004435s -> 0.002191s), will amortize in 49.7 ops by saving 0.002244s per op. +In 1 tuning rounds (tot. 0.14s, 0.053s for constructor, 4 clones) obtained a SPEEDUP of 102.4% (2.024x) (from 0.1299 to 0.2629 Mflops). +After 0.138143s, global autotuning declared speedup of 2.02416 x, when using threads count of 24 and a new matrix: +(6 x 6)[0x5782f990]{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: 7, 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' @@ -9200,10 +9255,10 @@ 4 0 DIFF PRINT TEST END Beginning large binary search test. -Detected 4014092288 bytes of memory, comprehensive of 1176166400 of free memory. +Detected 3995713536 bytes of memory, comprehensive of 2792656896 of free memory. On this system, maximal array of coordinates can have 2147483137 elements and occupy 4294965252 bytes. -Will perform the test using less memory (841 MB) than on the maximal coordinate indices array (882124800) allows. -(c)allocated 220531200 nnz (882124800 bytes) +Will perform the test using less memory (973 MB) than on the maximal coordinate indices array (1020750848) allows. +(c)allocated 255187712 nnz (1020750848 bytes) Succeeded retrieving array last element. Successfully performed large binary search test. BASIC SPARSE BLAS TEST: BEGIN @@ -9212,7 +9267,7 @@ got RSB_IO_WANT_IS_INITIALIZED_MARKER: 1 INIT INTERFACE TEST: END (SUCCESS) DEVEL PRINT TEST: BEGIN -(4 x 4)[0x57533770]{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)[0x5789b8c0]{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 | @@ -9221,8 +9276,8 @@ RSB_FLAG_ASSEMBLED_IN_COO_ARRAYS | RSB_FLAG_OWN_PARTITIONING_ARRAYS | RSB_FLAG_SORT_INPUT -(2 x 2)[0x57533840]{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)[0x57533910]{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)[0x5789b990]{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)[0x5789ba60]{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, 416 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%) @@ -9230,9 +9285,9 @@ ( 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)[0x57533840]{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)[0x57533910]{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)[0x57533770]{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)[0x5789b990]{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)[0x5789ba60]{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)[0x5789b8c0]{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 | @@ -9250,8 +9305,8 @@ 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 30.024083 s, max allowed was 30.000000. - PASSED:266 +Terminating testing earlier due to user timeout request: test took 30.035289 s, max allowed was 30.000000. + PASSED:25109 FAILED:0 ADVANCED SPARSE BLAS TEST: END (SUCCESS) gmake qtests -C librsbpp @@ -9260,87 +9315,87 @@ 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 +++ wc -l + test 27 = 27 -++ grep Z-sort ++ ./rsbpp Td,z G.mtx +++ grep Z-sort ++ wc -l + test 54 = 54 ++ ./rsbpp vTd,z G.mtx ++ grep Z-sort ++ wc -l + test 54 = 54 +++ ./rsbpp vTd,z G.mtx ++ grep Z-sort ++ wc -l -++ ./rsbpp vTd,z G.mtx + test 54 = 54 -++ wc -l -++ grep Zorted ++ ./rsbpp vvvTd,z G.mtx +++ grep Zorted +++ wc -l + test 8 = 8 ++ ./rsbpp vvTd,z G.mtx ++ grep Z-sort ++ wc -l + test 54 = 54 -++ grep Range ++ ./rsbpp vvTd,z G.mtx +++ grep Range ++ wc -l + test 0 = 0 -++ wc -l -++ grep Range ++ ./rsbpp vvvTd,z G.mtx +++ grep Range +++ wc -l + test 258 -gt 0 ++ ./rsbpp vvvTd,z S.mtx ++ grep Range ++ wc -l + test 0 -eq 0 ++ ./rsbpp vvvTd,z G.mtx -++ wc -l ++ grep Range +++ wc -l + test 258 = 258 ++ OMP_NUM_THREADS=1 ++ ./rsbpp m10M10I1r1,4,8sFv -++ wc -l ++ grep spmm- -+ test 9 = 9 ++ wc -l -++ grep spmm- ++ test 9 = 9 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1,4,8sFv +++ grep spmm- +++ wc -l + test 9 = 9 ++ OMP_NUM_THREADS=1 +++ ./rsbpp C1000m100M100I1r1sFvtN,T ++ grep spmm- ++ wc -l -++ ./rsbpp C1000m100M100I1r1sFvtN,T + test 3 = 3 -++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1vtN,TsF +++ grep spmm- ++ wc -l + test 2 = 2 -++ wc -l -++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r0vtN,TsF -+ test 0 = 0 +++ grep spmm- ++ wc -l ++ test 0 = 0 ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF ++ grep Recursing -+ test 4 = 4 ++ wc -l -++ grep Recursing ++ test 4 = 4 ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF +++ grep Recursing +++ wc -l + test 4 = 4 ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 @@ -9349,9 +9404,9 @@ ++ wc -l + test 208 = 208 ++ OMP_NUM_THREADS=2 -++ grep Recursing ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF +++ grep Recursing ++ wc -l + test 410 = 410 echo "Skipping tests based on Google Test (not detected at configure time)" @@ -9399,7 +9454,7 @@ 0 0 0 0 before tuning for SPMV: -(3 x 3)[0x5805c920]{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)[0x5829a770]{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 @@ -9488,18 +9543,18 @@ BEGIN Rsb_Matrix_test_multimatrix_ms_mnrhs BEGIN -(3 x 3)[0x5808c210]{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)[0x582c7420]{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 4.61628: +(3 x 3)[0x582cbcb0]{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)[0x582c7420]{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 253.186: +(3 x 3)[0x582ce8b0]{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)[0x582c7420]{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)[0x5808c210]{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)[0x5808c560]{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 2.33438: -(3 x 3)[0x5808f830]{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)[0x5808c560]{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 1.30191: -(3 x 3)[0x5808f830]{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)[0x5808c560]{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 1.22222: -(3 x 3)[0x5808f830]{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)[0x582c7420]{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)[0x582c9eb0]{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 1.50858: +(3 x 3)[0x582cbcb0]{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 ! @@ -9516,10 +9571,10 @@ ./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 ionos2-i386 +running on i-capture-the-hostname Built without the MKL. ( ! ./rsbtest --unrecognized-option-triggers-abort ) -running on ionos2-i386 +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 ) @@ -9528,7 +9583,7 @@ ( ! ./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 ionos2-i386 +running on i-capture-the-hostname Will not invoke autotuning routine. Benchmark will sample for at most 0.01 s Built without render support! @@ -9580,7 +9635,7 @@ 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/i386-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/i386-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/i386-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/i386-linux-gnu/librsb.so.0.0.0 libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/i386-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/i386-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; }; }) @@ -9590,7 +9645,7 @@ libtool: install: ranlib /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/i386-linux-gnu/librsb.a libtool: warning: remember to run 'libtool --finish /usr/lib/i386-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/i386-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' @@ -9717,12 +9772,12 @@ dh_gencontrol dh_md5sums dh_builddeb -dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-7_i386.deb'. dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-7_i386.deb'. -dpkg-deb: building package 'librsb0t64' in '../librsb0t64_1.3.0.2+dfsg-7_i386.deb'. +dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-7_i386.deb'. dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-7_i386.deb'. +dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-7_i386.deb'. dpkg-deb: building package 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-7_all.deb'. -dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-7_i386.deb'. +dpkg-deb: building package 'librsb0t64' in '../librsb0t64_1.3.0.2+dfsg-7_i386.deb'. dpkg-genbuildinfo --build=binary -O../librsb_1.3.0.2+dfsg-7_i386.buildinfo dpkg-genchanges --build=binary -O../librsb_1.3.0.2+dfsg-7_i386.changes dpkg-genchanges: info: binary-only upload (no source code included) @@ -9731,12 +9786,14 @@ 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/67525/tmp/hooks/B01_cleanup starting +I: user script /srv/workspace/pbuilder/67525/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/14633 and its subdirectories -I: Current time: Sun Feb 23 05:33:14 -12 2025 -I: pbuilder-time-stamp: 1740331994 +I: removing directory /srv/workspace/pbuilder/67525 and its subdirectories +I: Current time: Sun Mar 29 14:10:22 +14 2026 +I: pbuilder-time-stamp: 1774743022