Diff of the two buildlogs: -- --- b1/build.log 2024-12-24 01:46:32.396073735 +0000 +++ b2/build.log 2024-12-24 02:03:54.732577237 +0000 @@ -1,6 +1,6 @@ I: pbuilder: network access will be disabled during build -I: Current time: Sun Jan 25 19:54:56 -12 2026 -I: pbuilder-time-stamp: 1769414096 +I: Current time: Mon Jan 26 22:09:34 +14 2026 +I: pbuilder-time-stamp: 1769414974 I: Building the build Environment I: extracting base tarball [/var/cache/pbuilder/trixie-reproducible-base.tgz] I: copying local configuration @@ -29,52 +29,84 @@ dpkg-source: info: applying auto-gitignore I: Not using root during the build. I: Installing the build-deps -I: user script /srv/workspace/pbuilder/3814367/tmp/hooks/D02_print_environment starting +I: user script /srv/workspace/pbuilder/259719/tmp/hooks/D01_modify_environment starting +debug: Running on codethink01-arm64. +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 Jan 26 08:09 /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/259719/tmp/hooks/D01_modify_environment finished +I: user script /srv/workspace/pbuilder/259719/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='arm64' - DEBIAN_FRONTEND='noninteractive' + 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]="aarch64-unknown-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=arm64 + DEBIAN_FRONTEND=noninteractive DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=12 ' - DISTRIBUTION='trixie' - HOME='/root' - HOST_ARCH='arm64' + DIRSTACK=() + DISTRIBUTION=trixie + EUID=0 + FUNCNAME=([0]="Echo" [1]="main") + GROUPS=() + HOME=/root + HOSTNAME=i-capture-the-hostname + HOSTTYPE=aarch64 + HOST_ARCH=arm64 IFS=' ' - INVOCATION_ID='f27e9f1186c04a4cb3053074770d2df3' - LANG='C' - LANGUAGE='en_US:en' - LC_ALL='C' - MAIL='/var/mail/root' - OPTIND='1' - PATH='/usr/sbin:/usr/bin:/sbin:/bin:/usr/games' - PBCURRENTCOMMANDLINEOPERATION='build' - PBUILDER_OPERATION='build' - PBUILDER_PKGDATADIR='/usr/share/pbuilder' - PBUILDER_PKGLIBDIR='/usr/lib/pbuilder' - PBUILDER_SYSCONFDIR='/etc' - PPID='3814367' - PS1='# ' - PS2='> ' + INVOCATION_ID=7e31031cbb4a402a93545ada09171caf + LANG=C + LANGUAGE=nl_BE:nl + LC_ALL=C + MACHTYPE=aarch64-unknown-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=259719 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.Vr6bAkrC/pbuilderrc_ICs4 --distribution trixie --hookdir /etc/pbuilder/first-build-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/trixie-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.Vr6bAkrC/b1 --logfile b1/build.log librsb_1.3.0.2+dfsg-7.dsc' - SUDO_GID='109' - SUDO_UID='104' - SUDO_USER='jenkins' - TERM='unknown' - TZ='/usr/share/zoneinfo/Etc/GMT+12' - USER='root' - _='/usr/bin/systemd-run' - http_proxy='http://192.168.101.4:3128' + 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.Vr6bAkrC/pbuilderrc_vPUz --distribution trixie --hookdir /etc/pbuilder/rebuild-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/trixie-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.Vr6bAkrC/b2 --logfile b2/build.log librsb_1.3.0.2+dfsg-7.dsc' + SUDO_GID=109 + SUDO_UID=104 + SUDO_USER=jenkins + TERM=unknown + TZ=/usr/share/zoneinfo/Etc/GMT-14 + UID=0 + USER=root + _='I: set' + http_proxy=http://192.168.101.4:3128 I: uname -a - Linux codethink03-arm64 6.1.0-28-cloud-arm64 #1 SMP Debian 6.1.119-1 (2024-11-22) aarch64 GNU/Linux + Linux i-capture-the-hostname 6.1.0-28-cloud-arm64 #1 SMP Debian 6.1.119-1 (2024-11-22) aarch64 GNU/Linux I: ls -l /bin lrwxrwxrwx 1 root root 7 Nov 22 2024 /bin -> usr/bin -I: user script /srv/workspace/pbuilder/3814367/tmp/hooks/D02_print_environment finished +I: user script /srv/workspace/pbuilder/259719/tmp/hooks/D02_print_environment finished -> Attempting to satisfy build-dependencies -> Creating pbuilder-satisfydepends-dummy package Package: pbuilder-satisfydepends-dummy @@ -295,7 +327,7 @@ Get: 173 http://deb.debian.org/debian trixie/main arm64 libltdl-dev arm64 2.4.7-8 [165 kB] Get: 174 http://deb.debian.org/debian trixie/main arm64 libhwloc-dev arm64 2.11.2-1 [237 kB] Get: 175 http://deb.debian.org/debian trixie/main arm64 zlib1g-dev arm64 1:1.3.dfsg+really1.3.1-1+b1 [917 kB] -Fetched 364 MB in 3s (131 MB/s) +Fetched 364 MB in 2s (227 MB/s) debconf: delaying package configuration, since apt-utils is not installed 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 ... 20083 files and directories currently installed.) @@ -879,8 +911,8 @@ Setting up tzdata (2024b-4) ... Current default time zone: 'Etc/UTC' -Local time is now: Mon Jan 26 07:56:11 UTC 2026. -Universal Time is now: Mon Jan 26 07:56:11 UTC 2026. +Local time is now: Mon Jan 26 08:10:23 UTC 2026. +Universal Time is now: Mon Jan 26 08:10:23 UTC 2026. Run 'dpkg-reconfigure tzdata' if you wish to change it. Setting up libfontenc1:arm64 (1:1.1.8-1+b1) ... @@ -1044,7 +1076,11 @@ 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/259719/tmp/hooks/A99_set_merged_usr starting +Not re-configuring usrmerge for trixie +I: user script /srv/workspace/pbuilder/259719/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 @@ -1064,62 +1100,62 @@ 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'. @@ -1161,90 +1197,90 @@ 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' @@ -1427,7 +1463,7 @@ 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 @@ -1544,7 +1580,7 @@ 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 @@ -1566,7 +1602,7 @@ 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=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1688,7 +1724,7 @@ 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 @@ -1697,7 +1733,7 @@ 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=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1806,7 +1842,7 @@ 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 @@ -1816,7 +1852,7 @@ 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=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1927,7 +1963,7 @@ 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 @@ -1959,7 +1995,7 @@ ARFLAGS : cru M4 : m4 MAKE : gmake - BASH : /bin/bash + BASH : /bin/sh OCTAVE : false DOXYGEN : doxygen HELP2MAN : help2man @@ -2015,24 +2051,24 @@ Making all in librsbpp gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c -o rsbpp.o rsbpp.cpp -/bin/bash ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_coo.lo rsbpp_coo.cpp -/bin/bash ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_csr.lo rsbpp_csr.cpp +/bin/sh ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_coo.lo rsbpp_coo.cpp +/bin/sh ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_csr.lo rsbpp_csr.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c -o rsbtt.o rsbtt.cpp gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -c -o rsbct.o rsbct.c -libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -fPIC -DPIC -o .libs/rsbpp_coo.o libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c rsbpp_csr.cpp -fPIC -DPIC -o .libs/rsbpp_csr.o +libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -fPIC -DPIC -o .libs/rsbpp_coo.o libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -o rsbpp_coo.o >/dev/null 2>&1 libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -c rsbpp_csr.cpp -o rsbpp_csr.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o librsbpp.la rsbpp_coo.lo rsbpp_csr.lo -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o librsbpp.la rsbpp_coo.lo rsbpp_csr.lo -lpthread -lstdc++fs libtool: link: ar cr .libs/librsbpp.a .libs/rsbpp_coo.o .libs/rsbpp_csr.o libtool: link: ranlib .libs/librsbpp.a libtool: link: ( cd ".libs" && rm -f "librsbpp.la" && ln -s "../librsbpp.la" "librsbpp.la" ) -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbpp rsbpp.o librsbpp.la -lpthread -lstdc++fs -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbtt rsbtt.o librsbpp.la -lpthread -lstdc++fs -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbpp rsbpp.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbtt rsbtt.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbct rsbct.o librsbpp.la -lpthread -lstdc++fs +libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbct rsbct.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbtt rsbtt.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbct rsbct.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' @@ -2050,80 +2086,90 @@ gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o rsbench-rsb_libspblas_tests.o `test -f 'rsb_libspblas_tests.c' || echo './'`rsb_libspblas_tests.c g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -fopenmp -c -o rsb_dummy.o rsb_dummy.cpp gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o ch2icfb-ch2icfb.o `test -f 'ch2icfb.c' || echo './'`ch2icfb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_stropts.lo `test -f 'rsb_stropts.c' || echo './'`rsb_stropts.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_strmif.lo `test -f 'rsb_strmif.c' || echo './'`rsb_strmif.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_unroll.lo `test -f 'rsb_unroll.c' || echo './'`rsb_unroll.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_vb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_vb.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_unroll.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_unroll.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_stropts.lo `test -f 'rsb_stropts.c' || echo './'`rsb_stropts.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_strmif.lo `test -f 'rsb_strmif.c' || echo './'`rsb_strmif.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_unroll.lo `test -f 'rsb_unroll.c' || echo './'`rsb_unroll.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_lb.lo `test -f 'rsb_krnl_lb.c' || echo './'`rsb_krnl_lb.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_strmif.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_strmif.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_unroll.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_unroll.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_vb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_vb.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_unroll.c -o librsb_nounroll_la-rsb_unroll.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_lb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_lb.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_permute.lo `test -f 'rsb_permute.c' || echo './'`rsb_permute.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_lb.c -o librsb_nounroll_la-rsb_krnl_lb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_permute.lo `test -f 'rsb_permute.c' || echo './'`rsb_permute.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_mergesort.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_mergesort.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_bench.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_bench.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_permute.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_permute.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_l.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo `test -f 'rsb_krnl_bcss_misc_u.c' || echo './'`rsb_krnl_bcss_misc_u.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_l.c -o librsb_nounroll_la-rsb_krnl_bcss_l.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo `test -f 'rsb_krnl_bcss_misc_u.c' || echo './'`rsb_krnl_bcss_misc_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo `test -f 'rsb_krnl_bcoo_spmv_u.c' || echo './'`rsb_krnl_bcoo_spmv_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo `test -f 'rsb_krnl_bcoo_spmv_u.c' || echo './'`rsb_krnl_bcoo_spmv_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss.lo `test -f 'rsb_krnl_bcss.c' || echo './'`rsb_krnl_bcss.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_bench.c -o librsb_nounroll_la-rsb_bench.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spmv.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spmv.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss.c -o librsb_nounroll_la-rsb_krnl_bcss.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_ompio.lo `test -f 'rsb_ompio.c' || echo './'`rsb_ompio.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spmv.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spmv.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_ompio.lo `test -f 'rsb_ompio.c' || echo './'`rsb_ompio.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_merge.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_merge.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spgemm_csr.lo `test -f 'rsb_spgemm_csr.c' || echo './'`rsb_spgemm_csr.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_ompio.c -o librsb_nounroll_la-rsb_ompio.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_bench.c -o librsb_nounroll_la-rsb_bench.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spgemm_csr.lo `test -f 'rsb_spgemm_csr.c' || echo './'`rsb_spgemm_csr.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_util.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_util.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spgemm_csr.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spgemm_csr.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_merge.c -o librsb_nounroll_la-rsb_merge.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spsum_misc.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spsum_misc.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mio.lo `test -f 'rsb_mio.c' || echo './'`rsb_mio.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_prec.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_prec.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spgemm_csr.c -o librsb_nounroll_la-rsb_spgemm_csr.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mio.lo `test -f 'rsb_mio.c' || echo './'`rsb_mio.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_mio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mio.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_prec.c -o librsb_nounroll_la-rsb_prec.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_op.lo `test -f 'rsb_op.c' || echo './'`rsb_op.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_op.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_op.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_op.c -o librsb_base_la-rsb_op.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_set.lo `test -f 'rsb_set.c' || echo './'`rsb_set.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_set.lo `test -f 'rsb_set.c' || echo './'`rsb_set.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_bio.c -o librsb_base_la-rsb_bio.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_get.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_get.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_set.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_set.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_set.c -o librsb_base_la-rsb_set.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.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:"", @@ -2142,181 +2188,171 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_bio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_bio.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_get.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_get.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_set.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_set.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_bio.c -o librsb_base_la-rsb_bio.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_set.c -o librsb_base_la-rsb_set.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_csr.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo_check.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_check.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_get.c -o librsb_base_la-rsb_get.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo_check.c -o librsb_base_la-rsb_coo_check.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_coo_symm.lo `test -f 'rsb_coo_symm.c' || echo './'`rsb_coo_symm.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_idx.lo `test -f 'rsb_idx.c' || echo './'`rsb_idx.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_coo_symm.lo `test -f 'rsb_coo_symm.c' || echo './'`rsb_coo_symm.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo_symm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_symm.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_srt.lo `test -f 'rsb_srt.c' || echo './'`rsb_srt.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo_symm.c -o librsb_base_la-rsb_coo_symm.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_srt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srt.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo_symm.c -o librsb_base_la-rsb_coo_symm.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_srtp.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srtp.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_idx.c -o librsb_base_la-rsb_idx.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_srt.c -o librsb_base_la-rsb_srt.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_src.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_src.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_test_accuracy.lo `test -f 'rsb_test_accuracy.c' || echo './'`rsb_test_accuracy.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_clone.lo `test -f 'rsb_clone.c' || echo './'`rsb_clone.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_rec.lo `test -f 'rsb_rec.c' || echo './'`rsb_rec.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_render.lo `test -f 'rsb_render.c' || echo './'`rsb_render.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_clone.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_clone.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_render.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_render.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_clone.lo `test -f 'rsb_clone.c' || echo './'`rsb_clone.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_test_accuracy.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_test_accuracy.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_rec.lo `test -f 'rsb_rec.c' || echo './'`rsb_rec.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_render.lo `test -f 'rsb_render.c' || echo './'`rsb_render.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_clone.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_clone.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_render.c -o librsb_base_la-rsb_render.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_msort_up.lo `test -f 'rsb_msort_up.c' || echo './'`rsb_msort_up.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_render.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_render.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_render.c -o librsb_base_la-rsb_render.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_clone.c -o librsb_base_la-rsb_clone.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_msort_up.lo `test -f 'rsb_msort_up.c' || echo './'`rsb_msort_up.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_msort_up.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_msort_up.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_msort_up.c -o librsb_base_la-rsb_msort_up.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_rec.c -o librsb_base_la-rsb_rec.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_gen.lo `test -f 'rsb_gen.c' || echo './'`rsb_gen.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_msort_up.c -o librsb_base_la-rsb_msort_up.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_sys.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_sys.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_blas_stuff.lo `test -f 'rsb_blas_stuff.c' || echo './'`rsb_blas_stuff.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_blas_stuff.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_blas_stuff.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_sys.c -o librsb_base_la-rsb_sys.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_gen.lo `test -f 'rsb_gen.c' || echo './'`rsb_gen.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_err.lo `test -f 'rsb_err.c' || echo './'`rsb_err.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_gen.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_gen.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_rsb.lo `test -f 'rsb_rsb.c' || echo './'`rsb_rsb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_err.lo `test -f 'rsb_err.c' || echo './'`rsb_err.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_perf.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_perf.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_perf.c -o librsb_base_la-rsb_perf.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_tune.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_tune.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_err.c -o librsb_base_la-rsb_err.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_internals.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_internals.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_gen.c -o librsb_base_la-rsb_gen.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_internals.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_internals.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_garbage.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_garbage.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_garbage.c -o librsb_base_la-rsb_garbage.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_partition.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_partition.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_mmio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mmio.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_garbage.c -o librsb_base_la-rsb_garbage.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_partition.c -o librsb_base_la-rsb_partition.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_mbw.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mbw.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_mmio.c -o librsb_base_la-rsb_mmio.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_tune.c -o librsb_base_la-rsb_tune.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_spgemm.lo `test -f 'rsb_spgemm.c' || echo './'`rsb_spgemm.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spgemm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spgemm.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_partition.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_partition.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_partition.c -o librsb_base_la-rsb_partition.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_mbw.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mbw.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_fpb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_fpb.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_limiter.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_limiter.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_spgemm.lo `test -f 'rsb_spgemm.c' || echo './'`rsb_spgemm.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_limiter.c -o librsb_base_la-rsb_limiter.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spgemm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spgemm.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spsum.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsum.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spsum.c -o librsb_base_la-rsb_spsum.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_swt.lo `test -f 'rsb_swt.c' || echo './'`rsb_swt.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_lock.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_lock.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_dump.lo `test -f 'rsb_dump.c' || echo './'`rsb_dump.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_init.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_init.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.o -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/aarch64-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 ()); - | ~~~~~~~~~~~~~~~~~ +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_swt.lo `test -f 'rsb_swt.c' || echo './'`rsb_swt.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spsv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsv.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_swt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_swt.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_init.lo `test -f 'rsb_init.c' || echo './'`rsb_init.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_dump.lo `test -f 'rsb_dump.c' || echo './'`rsb_dump.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_lock.c -o librsb_base_la-rsb_lock.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_cpmv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_cpmv.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spsv.c -o librsb_base_la-rsb_spsv.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_init.c -o librsb_base_la-rsb_init.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_dump.c -o librsb_base_la-rsb_dump.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_swt.c -o librsb_base_la-rsb_swt.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_init.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_init.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_cpmv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_cpmv.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_user.lo `test -f 'rsb_user.c' || echo './'`rsb_user.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_asm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_asm.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_user.lo `test -f 'rsb_user.c' || echo './'`rsb_user.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_rec2coo.lo `test -f 'rsb_rec2coo.c' || echo './'`rsb_rec2coo.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl.c -o librsb_nounroll_la-rsb_krnl.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_coo2rec.lo `test -f 'rsb_coo2rec.c' || echo './'`rsb_coo2rec.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_user.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_user.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_asm.c -o librsb_base_la-rsb_asm.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_rec2csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2csr.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_asm.c -o librsb_base_la-rsb_asm.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_rec2csr.lo `test -f 'rsb_rec2csr.c' || echo './'`rsb_rec2csr.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_rec2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2coo.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_user.c -o librsb_base_la-rsb_user.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_rec2csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2csr.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo2rec.c -o librsb_base_la-rsb_coo2rec.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_rec2coo.c -o librsb_base_la-rsb_rec2coo.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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_csr2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr2coo.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.c libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.o gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas_handle.c -fPIC -DPIC -o .libs/rsb_libspblas_handle.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas.c -fPIC -DPIC -o .libs/rsb_libspblas.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_coo2rec.c -o librsb_base_la-rsb_coo2rec.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +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/aarch64-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: warning: '-version-info' is ignored for programs libtool: link: gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp if test -f ./rsb_types.h -a ! -f ./rsb_types.h ; then cp -pv ./rsb_types.h ./rsb_types.h ; fi # out-of-dir behaviour varies between installations -if test -f ch2icfb ; then if SED=/usr/bin/sed GREP=/usr/bin/grep /bin/bash ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c -o rsb.lo rsb.F90 +if test -f ch2icfb ; then if SED=/usr/bin/sed GREP=/usr/bin/grep /bin/sh ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c -o rsb.lo rsb.F90 gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c -o rsb.o rsb.F90 -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.o >/dev/null 2>&1 libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c rsb.F90 -fPIC -o .libs/rsb.o libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c rsb.F90 -o rsb.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.o >/dev/null 2>&1 +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm 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 @@ -2341,12 +2377,12 @@ | ~~~~~~~~~~~~~~~~~ libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_nounroll.a .libs/librsb_nounroll_la-rsb_stropts.o .libs/librsb_nounroll_la-rsb_strmif.o .libs/librsb_nounroll_la-rsb_unroll.o .libs/librsb_nounroll_la-rsb_krnl_vb.o .libs/librsb_nounroll_la-rsb_krnl_lb.o .libs/librsb_nounroll_la-rsb_krnl.o .libs/librsb_nounroll_la-rsb_bench.o .libs/librsb_nounroll_la-rsb_mergesort.o .libs/librsb_nounroll_la-rsb_permute.o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss.o .libs/librsb_nounroll_la-rsb_spmv.o .libs/librsb_nounroll_la-rsb_merge.o .libs/librsb_nounroll_la-rsb_ompio.o .libs/librsb_nounroll_la-rsb_util.o .libs/librsb_nounroll_la-rsb_spgemm_csr.o .libs/librsb_nounroll_la-rsb_spsum_misc.o .libs/librsb_nounroll_la-rsb_prec.o libtool: link: ranlib .libs/librsb_nounroll.a libtool: link: ( cd ".libs" && rm -f "librsb_nounroll.la" && ln -s "../librsb_nounroll.la" "librsb_nounroll.la" ) -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/aarch64-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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/aarch64-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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm 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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lpthread -lstdc++fs -lstdc++ -lhwloc -lz -lgfortran -lm -g -O2 -fstack-protector-strong -mbranch-protection=standard -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") @@ -2358,7 +2394,7 @@ libtool: link: ranlib .libs/librsb.a libtool: link: rm -fr .libs/librsb.lax libtool: link: ( cd ".libs" && rm -f "librsb.la" && ln -s "../librsb.la" "librsb.la" ) -/bin/bash ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm libtool: warning: '-version-info' is ignored for programs libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' @@ -2375,27 +2411,27 @@ gfortran -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -I.. -I.. -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c -o fortran.o fortran.F90 gfortran -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -I.. -I.. -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c -o fortran_rsb_fi.o fortran_rsb_fi.F90 g++ -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -fopenmp -c -o cplusplus.o cplusplus.cpp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/14 -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/14/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/14/../../.. -lgfortran -lm -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' Making all in scripts @@ -2413,12 +2449,12 @@ Making all in doc gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/doc' /usr/bin/mkdir -p man -SOURCE_DATE_EPOCH=1767272461 \ -help2man --name="benchmark and test for librsb" --no-info ../rsbench | /usr/bin/sed 's/January //g' > man/rsbench.1 /usr/bin/mkdir -p man -gmake makedox -SOURCE_DATE_EPOCH=1767272461 \ +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=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. @@ -3129,13 +3165,13 @@ g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -c -o rgt-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -c -o rgt_ne-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rgt rgt-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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +libtool: link: g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 @@ -3150,25 +3186,25 @@ g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -c -o mtx2bin.o mtx2bin.cpp g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -c -o render.o render.cpp g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -c -o span.o span.cpp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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' @@ -3178,7 +3214,7 @@ gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' g++ -DHAVE_CONFIG_H -I. -I/build/reproducible-path/librsb-1.3.0.2+dfsg -Wdate-time -D_FORTIFY_SOURCE=2 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -c -o rsbtest.o rsbtest.cpp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lstdc++fs -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lstdc++fs -lstdc++fs libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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' @@ -3254,7 +3290,7 @@ 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 @@ -3264,15 +3300,15 @@ 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 1769414854 +# beginning run at 1769415853 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx -qH -R -n1,4 -T z --verbose --nrhs 1,2 --by-rows # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -# average timer granularity: 8.11e-08 s -# Will write a final performance record to file rsbench_pr__1769414854_gcc-14.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1769414854_gcc-14.2-1,4th.rpr.tmp +# average timer granularity: 3.14e-08 s +# Will write a final performance record to file rsbench_pr__1769415853_gcc-14.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1769415853_gcc-14.2-1,4th.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -3311,61 +3347,61 @@ # 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: codethink03-arm64 +# 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 5.390s +# Memory benchmark took 5.343s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 8 samples (2240 bytes). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 5.393s 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 . +# so far, program took 5.344s 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, 36158 nnz/s ) (1.11 MB/s ) -#pre-sorting (6 elements) took 0.00170803 s -#weeding duplicates (to 6 elements) took 1.90735e-06 s (and check, 9.53674e-07 s ) +# file input of A.mtx took 0.00 s (6 nnz, 33689 nnz/s ) (1.03 MB/s ) +#pre-sorting (6 elements) took 0.020973 s +#weeding duplicates (to 6 elements) took 2.14577e-06 s (and check, 1.90735e-06 s ) # multi-nrhs benchmarking (1,2) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads -# Constructed matrix (took 0.007s): (3 x 3)[0xaaab2270a940]{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 0.035s): (3 x 3)[0xaaaaeab96980]{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 0.003698s; avg 0.001233s ( +/- 0.86/ 0.92 %); best 0.001222s; worst 0.001244s; std dev. 8.972e-06 (taking best). -Reference operation time is 0.00122213 s (0.07855 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: 0.001222 Mflops: 0.079) -Merge (3 -> 1 leaves) took w.c.t. of 2.193e-05s, ~9.06e-06s of computing time (of which 1.907e-06s sorting, 2.861e-06s analysis) -3 iterations (1 th.) took 0.0004201s; avg 0.00014s ( +/- 99.32/198.64 %); best 9.537e-07s; worst 0.0004182s; std dev. 0.0001967 (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 1281.500x: 0.001222s -> 9.537e-07s, so taking this instance. +3 iterations (1 th.) took 0.01721s; avg 0.005738s ( +/- 22.39/ 35.73 %); best 0.004453s; worst 0.007788s; std dev. 0.001465 (taking best). +Reference operation time is 0.00445294 s (0.02156 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: 0.004453 Mflops: 0.022) +Merge (3 -> 1 leaves) took w.c.t. of 2.313e-05s, ~8.821e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (1 th.) took 0.0004048s; avg 0.0001349s ( +/- 99.98/200.00 %); best 3.029e-08s; worst 0.0004048s; std dev. 0.0001908 (taking best). +Reference operation time is 3.02911e-08 s (3169 Mflops) with 1 threads. +After merge step 1: tpop: 3.029e-08 s ~Mflops: 3169.250 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 147005.116x: 0.004453s -> 3.029e-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 0.003693s (of which 2.789e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 1.907e-06s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.003693s, equivalent to 3872.2/3.0 new/old ops (0.006739s for 2 clones -- as 7066.2/5.5 ops, or 3533.1/2.8 ops per clone), SPEEDUP of 1281.500x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1281.500x (0.001222s -> 9.537e-07s), will amortize in 3.0 ops by saving 0.001221s per op. -In 1 tuning rounds (tot. 0.011s, 0.0067s for constructor, 2 clones) obtained a SPEEDUP of 128050.0% (1282x) (from 0.07855 to 100.7 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01639s (of which 2.909e-05s partitioning, 0s I/O); computing times: 8.821e-06s in par. loops, 9.537e-07s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.01639s, equivalent to 540952.4/3.7 new/old ops (0.03507s for 2 clones -- as 1157929.9/7.9 ops, or 578965.0/3.9 ops per clone), SPEEDUP of 147005.116x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 147005.116x (0.004453s -> 3.029e-08s), will amortize in 3.7 ops by saving 0.004453s per op. +In 1 tuning rounds (tot. 0.053s, 0.035s for constructor, 2 clones) obtained a SPEEDUP of 14700411.6% (1.47e+05x) (from 0.02156 to 3169 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 0.0110991 s (1.222e-03 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0529361 s (4.453e-03 s -> 3.029e-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 0.0546842 s and estimated a speedup of 1.000000 x (7.905e-08 s -> 7.905e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.124432 s and estimated a speedup of 1.000000 x (3.029e-08 s -> 3.029e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.001570 0.002466 0.004036 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.004036 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.001570 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.002466 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.006332 0.013870 0.020202 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.020202 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.006332 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.013870 %: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 0.004036 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.020202 %: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 @@ -3380,47 +3416,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.006s): (3 x 3)[0xaaab2270a940]{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 0.011s): (3 x 3)[0xaaaaeab96980]{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 0.003225s; avg 0.001075s ( +/- 11.16/ 21.76 %); best 0.0009551s; worst 0.001309s; std dev. 0.0001654 (taking best). -Reference operation time is 0.000955105 s (0.1005 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: 0.0009551 Mflops: 0.101) -Merge (3 -> 1 leaves) took w.c.t. of 8.821e-06s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (4 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 87.57/200.00 %); best 7.905e-08s; worst 1.907e-06s; std dev. 8.991e-07 (taking best). -Reference operation time is 7.90477e-08 s (1214 Mflops) with 4 threads. -After merge step 1: tpop: 7.905e-08 s ~Mflops: 1214.457 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 12082.642x: 0.0009551s -> 7.905e-08s, so taking this instance. +3 iterations (4 th.) took 0.006133s; avg 0.002044s ( +/- 39.16/ 19.60 %); best 0.001244s; worst 0.002445s; std dev. 0.000566 (taking best). +Reference operation time is 0.00124383 s (0.07718 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: 0.001244 Mflops: 0.077) +Merge (3 -> 1 leaves) took w.c.t. of 9.06e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (4 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 95.77/ 66.67 %); best 3.029e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). +Reference operation time is 3.02911e-08 s (3169 Mflops) with 4 threads. +After merge step 1: tpop: 3.029e-08 s ~Mflops: 3169.250 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 41062.574x: 0.001244s -> 3.029e-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 0.002483s (of which 1.311e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.002483s, equivalent to 31413.1/2.6 new/old ops (0.005305s for 2 clones -- as 67112.0/5.6 ops, or 33556.0/2.8 ops per clone), SPEEDUP of 12082.642x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 12082.642x (0.0009551s -> 7.905e-08s), will amortize in 2.6 ops by saving 0.000955s per op. -In 1 tuning rounds (tot. 0.0086s, 0.0053s for constructor, 2 clones) obtained a SPEEDUP of 1208164.2% (1.208e+04x) (from 0.1005 to 1214 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.005679s (of which 1.097e-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 0.005679s, equivalent to 187485.2/4.6 new/old ops (0.01265s for 2 clones -- as 417741.0/10.2 ops, or 208870.5/5.1 ops per clone), SPEEDUP of 41062.574x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 41062.574x (0.001244s -> 3.029e-08s), will amortize in 4.6 ops by saving 0.001244s per op. +In 1 tuning rounds (tot. 0.019s, 0.013s for constructor, 2 clones) obtained a SPEEDUP of 4106157.4% (4.106e+04x) (from 0.07718 to 3169 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 0.00859785 s (9.551e-04 s -> 7.905e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0188401 s (1.244e-03 s -> 3.029e-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 0.0450878 s and estimated a speedup of 1.000000 x (7.905e-08 s -> 7.905e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0749481 s and estimated a speedup of 1.000000 x (3.029e-08 s -> 3.029e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.001556 0.002432 0.003988 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.003988 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.001556 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.002432 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.002191 0.004192 0.006383 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.006383 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.002191 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.004192 %: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 0.003988 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.006383 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 4 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.01 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.01 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 1.01 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.01 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 1.01 1.01 1.01 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 3.17 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 3.17 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 2.89 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 3.31 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 2.89 3.31 3.17 #%: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 @@ -3429,50 +3465,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.00654817 1e+09 1e+09 +%operation:A.mtx 0.0345609 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.00156999 0 0.00246596 +%constructor:A.mtx 0 0.00633216 0 0.01387 # 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 0.004s): (3 x 3)[0xaaab2270a940]{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 0.007s): (3 x 3)[0xaaaaeab96980]{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 0.002398s; avg 0.0007993s ( +/- 0.41/ 0.46 %); best 0.0007961s; worst 0.000803s; std dev. 2.837e-06 (taking best). -Reference operation time is 0.00079608 s (0.2412 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: 0.0007961 Mflops: 0.241) -Merge (3 -> 1 leaves) took w.c.t. of 6.914e-06s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) -3 iterations (1 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 92.35/107.69 %); best 7.905e-08s; worst 2.146e-06s; std dev. 8.778e-07 (taking best). -Reference operation time is 7.90477e-08 s (2429 Mflops) with 1 threads. -After merge step 1: tpop: 7.905e-08 s ~Mflops: 2428.914 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 10070.879x: 0.0007961s -> 7.905e-08s, so taking this instance. +3 iterations (1 th.) took 0.004122s; avg 0.001374s ( +/- 39.60/ 20.23 %); best 0.0008299s; worst 0.001652s; std dev. 0.0003847 (taking best). +Reference operation time is 0.000829935 s (0.2313 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: 0.0008299 Mflops: 0.231) +Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~1.907e-06s of computing time (of which 0s sorting, 1.192e-06s analysis) +3 iterations (1 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 96.82/100.00 %); best 3.029e-08s; worst 1.907e-06s; std dev. 7.787e-07 (taking best). +Reference operation time is 3.02911e-08 s (6338 Mflops) with 1 threads. +After merge step 1: tpop: 3.029e-08 s ~Mflops: 6338.500 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 27398.662x: 0.0008299s -> 3.029e-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 0.002417s (of which 1.097e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) -Total merge + benchmarking process took 0.002417s, equivalent to 30574.6/3.0 new/old ops (0.004658s for 2 clones -- as 58929.3/5.9 ops, or 29464.6/2.9 ops per clone), SPEEDUP of 10070.879x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 10070.879x (0.0007961s -> 7.905e-08s), will amortize in 3.0 ops by saving 0.000796s per op. -In 1 tuning rounds (tot. 0.0071s, 0.0047s for constructor, 2 clones) obtained a SPEEDUP of 1006987.9% (1.007e+04x) (from 0.2412 to 2429 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.003549s (of which 8.106e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 0s sorting, 1.192e-06s analyzing) +Total merge + benchmarking process took 0.003549s, equivalent to 117166.5/4.3 new/old ops (0.007042s for 2 clones -- as 232483.3/8.5 ops, or 116241.6/4.2 ops per clone), SPEEDUP of 27398.662x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 27398.662x (0.0008299s -> 3.029e-08s), will amortize in 4.3 ops by saving 0.0008299s per op. +In 1 tuning rounds (tot. 0.011s, 0.007s for constructor, 2 clones) obtained a SPEEDUP of 2739766.2% (2.74e+04x) (from 0.2313 to 6338 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 0.00711703 s (7.961e-04 s -> 7.905e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0112062 s (8.299e-04 s -> 3.029e-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 0.034919 s and estimated a speedup of 1.000000 x (7.905e-08 s -> 7.905e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0622869 s and estimated a speedup of 1.000000 x (3.029e-08 s -> 3.029e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.000840 0.001636 0.002476 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.002476 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.000840 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.001636 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.002277 0.002282 0.004559 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.004559 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.002277 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.002282 %: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 0.002476 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.004559 %: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 @@ -3487,47 +3523,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.004s): (3 x 3)[0xaaab2270a940]{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 0.012s): (3 x 3)[0xaaaaeab96980]{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 0.001633s; avg 0.0005443s ( +/- 0.44/ 0.31 %); best 0.0005419s; worst 0.000546s; std dev. 1.73e-06 (taking best). -Reference operation time is 0.000541925 s (0.3543 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: 0.0005419 Mflops: 0.354) -Merge (3 -> 1 leaves) took w.c.t. of 7.868e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) -3 iterations (4 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 94.15/111.76 %); best 7.905e-08s; worst 2.861e-06s; std dev. 1.173e-06 (taking best). -Reference operation time is 7.90477e-08 s (2429 Mflops) with 4 threads. -After merge step 1: tpop: 7.905e-08 s ~Mflops: 2428.914 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 6855.678x: 0.0005419s -> 7.905e-08s, so taking this instance. +3 iterations (4 th.) took 0.01041s; avg 0.003469s ( +/- 34.27/ 53.99 %); best 0.00228s; worst 0.005342s; std dev. 0.00134 (taking best). +Reference operation time is 0.00228 s (0.08421 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: 0.00228 Mflops: 0.084) +Merge (3 -> 1 leaves) took w.c.t. of 1.097e-05s, ~4.053e-06s of computing time (of which 1.192e-06s sorting, 1.907e-06s analysis) +3 iterations (4 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 97.07/200.00 %); best 3.029e-08s; worst 3.099e-06s; std dev. 1.461e-06 (taking best). +Reference operation time is 3.02911e-08 s (6338 Mflops) with 4 threads. +After merge step 1: tpop: 3.029e-08 s ~Mflops: 6338.500 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 75269.579x: 0.00228s -> 3.029e-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 0.001771s (of which 1.001e-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 0.001771s, equivalent to 22403.9/3.3 new/old ops (0.003525s for 2 clones -- as 44593.6/6.5 ops, or 22296.8/3.3 ops per clone), SPEEDUP of 6855.678x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 6855.678x (0.0005419s -> 7.905e-08s), will amortize in 3.3 ops by saving 0.0005418s per op. -In 1 tuning rounds (tot. 0.0052s, 0.0035s for constructor, 2 clones) obtained a SPEEDUP of 685467.8% (6856x) (from 0.3543 to 2429 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.006499s (of which 1.407e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 1.192e-06s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.006499s, equivalent to 214553.3/2.9 new/old ops (0.0128s for 2 clones -- as 422565.9/5.6 ops, or 211283.0/2.8 ops per clone), SPEEDUP of 75269.579x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 75269.579x (0.00228s -> 3.029e-08s), will amortize in 2.9 ops by saving 0.00228s per op. +In 1 tuning rounds (tot. 0.023s, 0.013s for constructor, 2 clones) obtained a SPEEDUP of 7526857.9% (7.527e+04x) (from 0.08421 to 6338 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 0.00521088 s (5.419e-04 s -> 7.905e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.023273 s (2.280e-03 s -> 3.029e-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 0.027586 s and estimated a speedup of 1.000000 x (7.905e-08 s -> 7.905e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0548 s and estimated a speedup of 1.000000 x (3.029e-08 s -> 3.029e-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 0.001237 0.001645 0.002882 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.002883 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.001237 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.001645 -%: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 0.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.002882 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.002606 0.004948 0.007554 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.007554 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.002606 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.004948 +%: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 0.007554 %: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 0.86 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.86 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.68 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.99 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 0.00 0.68 0.99 0.86 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.60 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.60 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.87 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.46 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 0.87 0.46 0.60 #%: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 @@ -3536,185 +3572,185 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.00433803 1e+09 1e+09 +%operation:A.mtx 0.00703502 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.000839949 0 0.00163603 +%constructor:A.mtx 0 0.00227714 0 0.0022819 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 5.629s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.194s/0.000s . +# so far, program took 5.878s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.423s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.06343s (system CPU time used) -ru_utime : 7.055s (user CPU time used) +ru_stime : 0.0485s (system CPU time used) +ru_utime : 6.535s (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 1 100.66 1.222e-03 0.000e+00 9.537e-07 0.000e+00 1.110e-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 1214.46 9.551e-04 0.000e+00 7.905e-08 0.000e+00 8.598e-03 3.39e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 3169.25 4.453e-03 0.000e+00 3.029e-08 0.000e+00 5.294e-02 8.85e+00 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 3169.25 1.244e-03 0.000e+00 3.029e-08 0.000e+00 1.884e-02 8.85e+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. 668107.1 % faster, avg. sp. ratio 6682.071x, max sp. ratio 12082.642x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 60203.1/11638.2/108767.9/120406.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 9.0/ 9.1/ 18.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.0, min. 9.0, max. 9.1 ops) +#pr: (in succ. cases rsb autotuning gave avg. 9403284.5 % faster, avg. sp. ratio 94033.845x, max sp. ratio 147005.116x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1184773.7/621967.7/1747579.7/2369547.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.5/ 11.9/ 15.1/ 27.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.5, min. 11.9, max. 15.1 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 1.507/ 0.231/ 2.783,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 3.671/ 0.281/ 3.390,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.263/ 7.263/ 7.263,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.695/ 8.847/ 8.847,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.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.576e+02, min 1.007e+02, max 1.214e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 8.953e-02, min 7.855e-02, max 1.005e-01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.164e-07s, min 7.905e-08s, max 9.537e-07s, tot 1.033e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.089e-03s, min 9.551e-04s, max 1.222e-03s, tot 2.177e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.702e+01 2.053e+02 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.02 s, max 0.05 s, tot 0.07 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.02 s, max 0.05 s, tot 0.07 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.169e+03, min 3.169e+03, max 3.169e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 4.937e-02, min 2.156e-02, max 7.718e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.029e-08s, min 3.029e-08s, max 3.029e-08s, tot 6.058e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.848e-03s, min 1.244e-03s, max 4.453e-03s, tot 5.697e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.516e+00 6.516e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.009e+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 2428.91 7.961e-04 0.000e+00 7.905e-08 0.000e+00 7.117e-03 5.21e+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 2428.91 5.419e-04 0.000e+00 7.905e-08 0.000e+00 5.211e-03 5.21e+00 1.65e+00 1 1.92e-04 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 6338.50 8.299e-04 0.000e+00 3.029e-08 0.000e+00 1.121e-02 1.36e+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 6338.50 2.280e-03 0.000e+00 3.029e-08 0.000e+00 2.327e-02 1.36e+01 1.65e+00 1 1.92e-04 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 846227.9 % faster, avg. sp. ratio 8463.279x, max sp. ratio 10070.879x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 77977.7/65920.7/90034.7/155955.4 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 8.9/ 9.6/ 18.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 8.9, max. 9.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 5133312.0 % faster, avg. sp. ratio 51334.120x, max sp. ratio 75269.579x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 569130.3/369948.8/768311.7/1138260.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.9/ 10.2/ 13.5/ 23.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.9, min. 10.2, max. 13.5 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.998/ 3.998/ 3.998,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.424/ 5.212/ 5.212,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 10.432/ 10.432/ 10.432,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 27.203/ 13.601/ 13.601,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.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.01 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.01 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.429e+03, min 2.429e+03, max 2.429e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.977e-01, min 2.412e-01, max 3.543e-01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 7.905e-08s, min 7.905e-08s, max 7.905e-08s, tot 1.581e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.690e-04s, min 5.419e-04s, max 7.961e-04s, tot 1.338e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.185e+01 1.185e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.306e+01 x, min 2.000e+00 x, max 2.413e+01 x (2 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.01 s, max 0.02 s, tot 0.03 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.02 s, tot 0.03 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.338e+03, min 6.338e+03, max 6.338e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.578e-01, min 8.421e-02, max 2.313e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.029e-08s, min 3.029e-08s, max 3.029e-08s, tot 6.058e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.555e-03s, min 8.299e-04s, max 2.280e-03s, tot 3.110e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.536e+00 4.536e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.009e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=N: #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 1.222e-03 0.000e+00 9.537e-07 0.000e+00 1.110e-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 2428.91 7.961e-04 0.000e+00 7.905e-08 0.000e+00 7.117e-03 5.21e+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 1214.46 9.551e-04 0.000e+00 7.905e-08 0.000e+00 8.598e-03 3.39e+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 2428.91 5.419e-04 0.000e+00 7.905e-08 0.000e+00 5.211e-03 5.21e+00 1.65e+00 1 1.92e-04 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 3169.25 4.453e-03 0.000e+00 3.029e-08 0.000e+00 5.294e-02 8.85e+00 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 6338.50 8.299e-04 0.000e+00 3.029e-08 0.000e+00 1.121e-02 1.36e+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 3169.25 1.244e-03 0.000e+00 3.029e-08 0.000e+00 1.884e-02 8.85e+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 6338.50 2.280e-03 0.000e+00 3.029e-08 0.000e+00 2.327e-02 1.36e+01 1.65e+00 1 1.92e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 757167.5 % faster, avg. sp. ratio 7572.675x, max sp. ratio 12082.642x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 69090.4/11638.2/108767.9/276361.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 8.9/ 9.6/ 36.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.2, min. 8.9, max. 9.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 7268298.3 % faster, avg. sp. ratio 72683.983x, max sp. ratio 147005.116x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 876952.0/369948.8/1747579.7/3507807.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.7/ 10.2/ 15.1/ 50.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.7, min. 10.2, max. 15.1 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 2.752/ 0.231/ 3.998,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.095/ 0.281/ 5.212,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.847/ 7.263/ 10.432,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.898/ 8.847/ 13.601,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.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.03 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.03 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.543e+03, min 1.007e+02, max 2.429e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.936e-01, min 7.855e-02, max 3.543e-01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.977e-07s, min 7.905e-08s, max 9.537e-07s, tot 1.191e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 8.788e-04s, min 5.419e-04s, max 1.222e-03s, tot 3.515e-03s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.185e+01 2.053e+02 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.306e+01 x, min 2.000e+00 x, max 2.413e+01 x (2 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.03 s, min 0.01 s, max 0.05 s, tot 0.11 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.03 s, min 0.01 s, max 0.05 s, tot 0.11 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.754e+03, min 3.169e+03, max 6.338e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.036e-01, min 2.156e-02, max 2.313e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.029e-08s, min 3.029e-08s, max 3.029e-08s, tot 1.212e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.202e-03s, min 8.299e-04s, max 4.453e-03s, tot 8.807e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.536e+00 6.516e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.009e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to both transA=N and nrhs=1: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 1.222e-03 0.000e+00 9.537e-07 0.000e+00 1.110e-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 1214.46 9.551e-04 0.000e+00 7.905e-08 0.000e+00 8.598e-03 3.39e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 3169.25 4.453e-03 0.000e+00 3.029e-08 0.000e+00 5.294e-02 8.85e+00 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 3169.25 1.244e-03 0.000e+00 3.029e-08 0.000e+00 1.884e-02 8.85e+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. 668107.1 % faster, avg. sp. ratio 6682.071x, max sp. ratio 12082.642x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 60203.1/11638.2/108767.9/120406.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 9.0/ 9.1/ 18.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.0, min. 9.0, max. 9.1 ops) +#pr: (in succ. cases rsb autotuning gave avg. 9403284.5 % faster, avg. sp. ratio 94033.845x, max sp. ratio 147005.116x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1184773.7/621967.7/1747579.7/2369547.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.5/ 11.9/ 15.1/ 27.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.5, min. 11.9, max. 15.1 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 1.507/ 0.231/ 2.783,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 3.671/ 0.281/ 3.390,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.263/ 7.263/ 7.263,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.695/ 8.847/ 8.847,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.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.576e+02, min 1.007e+02, max 1.214e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 8.953e-02, min 7.855e-02, max 1.005e-01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.164e-07s, min 7.905e-08s, max 9.537e-07s, tot 1.033e-06s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.089e-03s, min 9.551e-04s, max 1.222e-03s, tot 2.177e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.702e+01 2.053e+02 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.02 s, max 0.05 s, tot 0.07 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.02 s, max 0.05 s, tot 0.07 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.169e+03, min 3.169e+03, max 3.169e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 4.937e-02, min 2.156e-02, max 7.718e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.029e-08s, min 3.029e-08s, max 3.029e-08s, tot 6.058e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.848e-03s, min 1.244e-03s, max 4.453e-03s, tot 5.697e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.516e+00 6.516e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.009e+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 2428.91 7.961e-04 0.000e+00 7.905e-08 0.000e+00 7.117e-03 5.21e+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 2428.91 5.419e-04 0.000e+00 7.905e-08 0.000e+00 5.211e-03 5.21e+00 1.65e+00 1 1.92e-04 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 6338.50 8.299e-04 0.000e+00 3.029e-08 0.000e+00 1.121e-02 1.36e+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 6338.50 2.280e-03 0.000e+00 3.029e-08 0.000e+00 2.327e-02 1.36e+01 1.65e+00 1 1.92e-04 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 846227.9 % faster, avg. sp. ratio 8463.279x, max sp. ratio 10070.879x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 77977.7/65920.7/90034.7/155955.4 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 8.9/ 9.6/ 18.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 8.9, max. 9.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 5133312.0 % faster, avg. sp. ratio 51334.120x, max sp. ratio 75269.579x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 569130.3/369948.8/768311.7/1138260.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.9/ 10.2/ 13.5/ 23.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.9, min. 10.2, max. 13.5 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.998/ 3.998/ 3.998,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.424/ 5.212/ 5.212,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 10.432/ 10.432/ 10.432,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 27.203/ 13.601/ 13.601,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.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.01 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.01 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.429e+03, min 2.429e+03, max 2.429e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.977e-01, min 2.412e-01, max 3.543e-01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 7.905e-08s, min 7.905e-08s, max 7.905e-08s, tot 1.581e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.690e-04s, min 5.419e-04s, max 7.961e-04s, tot 1.338e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.185e+01 1.185e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.306e+01 x, min 2.000e+00 x, max 2.413e+01 x (2 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.01 s, max 0.02 s, tot 0.03 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.02 s, tot 0.03 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.338e+03, min 6.338e+03, max 6.338e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.578e-01, min 8.421e-02, max 2.313e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.029e-08s, min 3.029e-08s, max 3.029e-08s, tot 6.058e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.555e-03s, min 8.299e-04s, max 2.280e-03s, tot 3.110e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.536e+00 4.536e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.009e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 4) matched the dump criteria -- skipping dump round. #pr: ======== Limiting to both transA=T and nrhs=1: @@ -3724,44 +3760,44 @@ #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 1 100.66 1.222e-03 0.000e+00 9.537e-07 0.000e+00 1.110e-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 2428.91 7.961e-04 0.000e+00 7.905e-08 0.000e+00 7.117e-03 5.21e+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 1214.46 9.551e-04 0.000e+00 7.905e-08 0.000e+00 8.598e-03 3.39e+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 2428.91 5.419e-04 0.000e+00 7.905e-08 0.000e+00 5.211e-03 5.21e+00 1.65e+00 1 1.92e-04 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 3169.25 4.453e-03 0.000e+00 3.029e-08 0.000e+00 5.294e-02 8.85e+00 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 6338.50 8.299e-04 0.000e+00 3.029e-08 0.000e+00 1.121e-02 1.36e+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 3169.25 1.244e-03 0.000e+00 3.029e-08 0.000e+00 1.884e-02 8.85e+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 6338.50 2.280e-03 0.000e+00 3.029e-08 0.000e+00 2.327e-02 1.36e+01 1.65e+00 1 1.92e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 757167.5 % faster, avg. sp. ratio 7572.675x, max sp. ratio 12082.642x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 69090.4/11638.2/108767.9/276361.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 8.9/ 9.6/ 36.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.2, min. 8.9, max. 9.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 7268298.3 % faster, avg. sp. ratio 72683.983x, max sp. ratio 147005.116x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 876952.0/369948.8/1747579.7/3507807.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.7/ 10.2/ 15.1/ 50.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.7, min. 10.2, max. 15.1 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 2.752/ 0.231/ 3.998,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.095/ 0.281/ 5.212,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.847/ 7.263/ 10.432,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.898/ 8.847/ 13.601,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.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.03 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.03 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.543e+03, min 1.007e+02, max 2.429e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.936e-01, min 7.855e-02, max 3.543e-01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.977e-07s, min 7.905e-08s, max 9.537e-07s, tot 1.191e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 8.788e-04s, min 5.419e-04s, max 1.222e-03s, tot 3.515e-03s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.185e+01 2.053e+02 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.306e+01 x, min 2.000e+00 x, max 2.413e+01 x (2 samples, the non-min-nrhs ones) -#pr: Record collection took 0.20 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.03 s, min 0.01 s, max 0.05 s, tot 0.11 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.03 s, min 0.01 s, max 0.05 s, tot 0.11 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.754e+03, min 3.169e+03, max 6.338e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.036e-01, min 2.156e-02, max 2.313e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.029e-08s, min 3.029e-08s, max 3.029e-08s, tot 1.212e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.202e-03s, min 8.299e-04s, max 4.453e-03s, tot 8.807e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.536e+00 6.516e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.009e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) +#pr: Record collection took 0.47 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 5416 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 5470 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1769414854_gcc-14.2-1,4th.rpr -# Removing the temporary record file rsbench_pr__1769414854_gcc-14.2-1,4th.rpr.tmp. -# terminating run at 1769414860 (after 5.6s of w.c.t.) +#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1769415853_gcc-14.2-1,4th.rpr +# Removing the temporary record file rsbench_pr__1769415853_gcc-14.2-1,4th.rpr.tmp. +# terminating run at 1769415859 (after 5.9s 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. @@ -4033,10 +4069,10 @@ L1 size: 24576 L2 size: 524288 sysconf() : 4096 bytes per pagesize -sysconf() : 15402651 physical pages -sysconf() : 63089258496 bytes (60166 MB) of physical memory -sysconf() : 7779555 available (free) physical pages -sysconf() : 31865057280 available (free) physical memory +sysconf() : 15402653 physical pages +sysconf() : 63089266688 bytes (60166 MB) of physical memory +sysconf() : 4005133 available (free) physical pages +sysconf() : 16405024768 available (free) physical memory sysconf() , processors : 12 sysconf() , processors online : 12 sysconf() : no level 1 cache @@ -4061,30 +4097,30 @@ RSB_SUBM_IDX_MARKER : 2147483647 RSB_MAX_ALLOCATABLE_MEMORY_CHUNK: 18446744073709551615 timing min delta (if negative, don't complain with us) : 0 s -timing granularity : 7.46965e-08 s +timing granularity : 3.06487e-08 s CFLAGS : -g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 CXXFLAGS : -g -O2 -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -fopenmp CC : gcc memhinfo : L2:4/64/512K,L1:8/64/24K -detected free memory : 31865057280 -detected total memory : 63089258496 -for array sized 524288 elems, took 0.000401974 s for linear search and 0 s for binary search for element 524287, in 150 tries, for a total of 0.100203 s (ignore this:157286100) -for array sized 524288 elems, took 0.000174999 s for linear search and 0 s for binary search for element 262143, in 556 tries, for a total of 0.100103 s (ignore this:448789116) -for array sized 524288 elems, took 8.67844e-05 s for linear search and 0 s for binary search for element 131071, in 1135 tries, for a total of 0.100073 s (ignore this:746320286) -for array sized 524288 elems, took 4.29153e-05 s for linear search and 0 s for binary search for element 65535, in 2276 tries, for a total of 0.100042 s (ignore this:1044635606) -for array sized 524288 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 32767, in 4539 tries, for a total of 0.100012 s (ignore this:1342094432) -for array sized 524288 elems, took 1.09673e-05 s for linear search and 0 s for binary search for element 16383, in 9000 tries, for a total of 0.100002 s (ignore this:1636988432) -for array sized 524288 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 8191, in 17953 tries, for a total of 0.100001 s (ignore this:1931094478) -for array sized 524288 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 4095, in 35314 tries, for a total of 0.100002 s (ignore this:-2074651158) -for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 2047, in 68284 tries, for a total of 0.100001 s (ignore this:-1795096462) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 128568 tries, for a total of 0.100000 s (ignore this:-1532046334) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 511, in 229432 tries, for a total of 0.100000 s (ignore this:-1297566830) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 389058 tries, for a total of 0.100001 s (ignore this:-1099147250) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 588304 tries, for a total of 0.100000 s (ignore this:-949718034) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 720465 tries, for a total of 0.100000 s (ignore this:-858939444) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 891717 tries, for a total of 0.100001 s (ignore this:-803652990) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 944335 tries, for a total of 0.100000 s (ignore this:-775322940) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 1024832 tries, for a total of 0.100000 s (ignore this:-760975292) +detected free memory : 16405024768 +detected total memory : 63089266688 +for array sized 524288 elems, took 0.000349998 s for linear search and 0 s for binary search for element 524287, in 281 tries, for a total of 0.100073 s (ignore this:294649294) +for array sized 524288 elems, took 0.000174999 s for linear search and 0 s for binary search for element 262143, in 568 tries, for a total of 0.100070 s (ignore this:592443742) +for array sized 524288 elems, took 8.67844e-05 s for linear search and 0 s for binary search for element 131071, in 1137 tries, for a total of 0.100055 s (ignore this:890499196) +for array sized 524288 elems, took 4.29153e-05 s for linear search and 0 s for binary search for element 65535, in 2272 tries, for a total of 0.100018 s (ignore this:1188290236) +for array sized 524288 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 32767, in 4537 tries, for a total of 0.100008 s (ignore this:1485617994) +for array sized 524288 elems, took 1.09673e-05 s for linear search and 0 s for binary search for element 16383, in 9005 tries, for a total of 0.100000 s (ignore this:1780675824) +for array sized 524288 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 8191, in 17943 tries, for a total of 0.100000 s (ignore this:2074618050) +for array sized 524288 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 4095, in 35266 tries, for a total of 0.100002 s (ignore this:-1931520706) +for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 2047, in 68417 tries, for a total of 0.100001 s (ignore this:-1651421508) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 128337 tries, for a total of 0.100001 s (ignore this:-1388844006) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 511, in 229482 tries, for a total of 0.100000 s (ignore this:-1154313402) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 348479 tries, for a total of 0.100000 s (ignore this:-976589112) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 588574 tries, for a total of 0.100001 s (ignore this:-827091316) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 787743 tries, for a total of 0.100001 s (ignore this:-727835698) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 973298 tries, for a total of 0.100000 s (ignore this:-667491222) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 1064005 tries, for a total of 0.100001 s (ignore this:-635571072) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 1132099 tries, for a total of 0.100000 s (ignore this:-619721686) + ./rsbench -C /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench version: 1.3.0 format switches:br @@ -4131,17 +4167,17 @@ 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 1769414862 +# beginning run at 1769415861 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx --verbose --nrhs 1,4 --by-rows # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 # User did not specify threads; assuming 1. Environment provides max 12 threads; this build supports max 128. # User did not specify threads; assuming 1. Environment provides max 12 threads; this build supports max 128. -# average timer granularity: 3.1e-08 s -# Will write a final performance record to file rsbench_pr__1769414862_gcc-14.2.rpr and periodic checkpoints to rsbench_pr__1769414862_gcc-14.2.rpr.tmp +# average timer granularity: 3.54e-08 s +# Will write a final performance record to file rsbench_pr__1769415861_gcc-14.2.rpr and periodic checkpoints to rsbench_pr__1769415861_gcc-14.2.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -4180,61 +4216,61 @@ # 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: codethink03-arm64 +# 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 5.340s +# Memory benchmark took 5.366s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 16 samples (4480 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 5.341s 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 . +# so far, program took 5.367s 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, 77913 nnz/s ) (2.39 MB/s ) -#pre-sorting (6 elements) took 0.0249181 s -#weeding duplicates (to 6 elements) took 3.09944e-06 s (and check, 9.53674e-07 s ) +# file input of A.mtx took 0.00 s (6 nnz, 76030 nnz/s ) (2.33 MB/s ) +#pre-sorting (6 elements) took 0.014235 s +#weeding duplicates (to 6 elements) took 2.14577e-06 s (and check, 1.90735e-06 s ) # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.048s): (3 x 3)[0xaaaad5eea110]{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' +# Constructed matrix (took 0.030s): (3 x 3)[0xaaaae1777110]{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 (12 th.) took 0.02797s; avg 0.009323s ( +/- 16.96/ 24.60 %); best 0.007742s; worst 0.01162s; std dev. 0.00166 (taking best). -Reference operation time is 0.00774193 s (0.0031 Mflops) with 12 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: 0.007742 Mflops: 0.003) -Merge (3 -> 1 leaves) took w.c.t. of 2.313e-05s, ~8.106e-06s of computing time (of which 1.907e-06s sorting, 5.96e-06s analysis) -3 iterations (12 th.) took 0.0001371s; avg 4.57e-05s ( +/- 99.93/200.00 %); best 2.996e-08s; worst 0.0001371s; std dev. 6.463e-05 (taking best). -Reference operation time is 2.99573e-08 s (801.1 Mflops) with 12 threads. -After merge step 1: tpop: 2.996e-08 s ~Mflops: 801.140 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 258432.153x: 0.007742s -> 2.996e-08s, so taking this instance. +3 iterations (12 th.) took 0.006196s; avg 0.002065s ( +/- 4.75/ 5.12 %); best 0.001967s; worst 0.002171s; std dev. 8.339e-05 (taking best). +Reference operation time is 0.00196719 s (0.0122 Mflops) with 12 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: 0.001967 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 2.193e-05s, ~8.106e-06s of computing time (of which 9.537e-07s sorting, 3.815e-06s analysis) +3 iterations (12 th.) took 0.0001519s; avg 5.062e-05s ( +/- 99.93/198.12 %); best 3.655e-08s; worst 0.0001509s; std dev. 7.092e-05 (taking best). +Reference operation time is 3.65496e-08 s (656.6 Mflops) with 12 threads. +After merge step 1: tpop: 3.655e-08 s ~Mflops: 656.643 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 53822.570x: 0.001967s -> 3.655e-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 0.02041s (of which 2.503e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 1.907e-06s sorting, 5.96e-06s analyzing) -Total merge + benchmarking process took 0.02041s, equivalent to 681440.5/2.6 new/old ops (0.0361s for 2 clones -- as 1204942.3/4.7 ops, or 602471.2/2.3 ops per clone), SPEEDUP of 258432.153x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 258432.153x (0.007742s -> 2.996e-08s), will amortize in 2.6 ops by saving 0.007742s per op. -In 1 tuning rounds (tot. 0.064s, 0.036s for constructor, 2 clones) obtained a SPEEDUP of 25843115.3% (2.584e+05x) (from 0.0031 to 801.1 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.005925s (of which 2.599e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 9.537e-07s sorting, 3.815e-06s analyzing) +Total merge + benchmarking process took 0.005925s, equivalent to 162113.5/3.0 new/old ops (0.01278s for 2 clones -- as 349582.5/6.5 ops, or 174791.3/3.2 ops per clone), SPEEDUP of 53822.570x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 53822.570x (0.001967s -> 3.655e-08s), will amortize in 3.0 ops by saving 0.001967s per op. +In 1 tuning rounds (tot. 0.019s, 0.013s for constructor, 2 clones) obtained a SPEEDUP of 5382157.0% (5.382e+04x) (from 0.0122 to 656.6 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 0.0643361 s (7.742e-03 s -> 2.996e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0192659 s (1.967e-03 s -> 3.655e-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 0.230841 s and estimated a speedup of 1.000000 x (2.996e-08 s -> 2.996e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.08393 s and estimated a speedup of 1.000000 x (3.655e-08 s -> 3.655e-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 12 3 3 6 0.000000 0.019840 0.012242 0.032082 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.032082 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.019840 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.012242 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.017388 0.007259 0.024647 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.024647 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.017388 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.007259 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.032082 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.024647 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4249,50 +4285,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.047965 1e+09 1e+09 +%operation:A.mtx 0.029675 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.01984 0 0.0122421 +%constructor:A.mtx 0 0.0173881 0 0.00725913 # 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 12 threads -# Constructed matrix (took 0.017s): (3 x 3)[0xaaaad5eea110]{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' +# Constructed matrix (took 0.008s): (3 x 3)[0xaaaae1777110]{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 (12 th.) took 0.004147s; avg 0.001382s ( +/- 37.06/ 18.71 %); best 0.00087s; worst 0.001641s; std dev. 0.0003623 (taking best). -Reference operation time is 0.000869989 s (0.1103 Mflops) with 12 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: 0.00087 Mflops: 0.110) -Merge (3 -> 1 leaves) took w.c.t. of 6.914e-06s, ~1.907e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) -3 iterations (12 th.) took 1.407e-05s; avg 4.689e-06s ( +/- 99.36/179.66 %); best 2.996e-08s; worst 1.311e-05s; std dev. 5.969e-06 (taking best). -Reference operation time is 2.99573e-08 s (3205 Mflops) with 12 threads. -After merge step 1: tpop: 2.996e-08 s ~Mflops: 3204.562 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 29040.987x: 0.00087s -> 2.996e-08s, so taking this instance. +3 iterations (12 th.) took 0.004119s; avg 0.001373s ( +/- 39.47/ 20.03 %); best 0.0008311s; worst 0.001648s; std dev. 0.0003832 (taking best). +Reference operation time is 0.000831127 s (0.1155 Mflops) with 12 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: 0.0008311 Mflops: 0.116) +Merge (3 -> 1 leaves) took w.c.t. of 6.914e-06s, ~2.146e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 1.693e-05s; avg 5.643e-06s ( +/- 99.35/183.10 %); best 3.655e-08s; worst 1.597e-05s; std dev. 7.316e-06 (taking best). +Reference operation time is 3.65496e-08 s (2627 Mflops) with 12 threads. +After merge step 1: tpop: 3.655e-08 s ~Mflops: 2626.570 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 22739.726x: 0.0008311s -> 3.655e-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 0.003536s (of which 9.06e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.003536s, equivalent to 118034.2/4.1 new/old ops (0.00681s for 2 clones -- as 227329.9/7.8 ops, or 113664.9/3.9 ops per clone), SPEEDUP of 29040.987x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 29040.987x (0.00087s -> 2.996e-08s), will amortize in 4.1 ops by saving 0.00087s per op. -In 1 tuning rounds (tot. 0.011s, 0.0068s for constructor, 2 clones) obtained a SPEEDUP of 2903998.7% (2.904e+04x) (from 0.1103 to 3205 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.003539s (of which 9.06e-06s partitioning, 0s I/O); computing times: 2.146e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.003539s, equivalent to 96823.2/4.3 new/old ops (0.006811s for 2 clones -- as 186347.0/8.2 ops, or 93173.5/4.1 ops per clone), SPEEDUP of 22739.726x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 22739.726x (0.0008311s -> 3.655e-08s), will amortize in 4.3 ops by saving 0.0008311s per op. +In 1 tuning rounds (tot. 0.011s, 0.0068s for constructor, 2 clones) obtained a SPEEDUP of 2273872.6% (2.274e+04x) (from 0.1155 to 2627 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 0.011014 s (8.700e-04 s -> 2.996e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0109892 s (8.311e-04 s -> 3.655e-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 0.179732 s and estimated a speedup of 1.000000 x (2.996e-08 s -> 2.996e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0627849 s and estimated a speedup of 1.000000 x (3.655e-08 s -> 3.655e-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 12 3 3 6 0.000000 0.009184 0.005098 0.014282 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.014282 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.009184 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.005098 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.003223 0.002479 0.005702 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005702 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.003223 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.002479 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.014282 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005702 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4307,59 +4343,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0169709 1e+09 1e+09 +%operation:A.mtx 0.0082109 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00918388 0 0.0050981 +%constructor:A.mtx 0 0.00322294 0 0.00247908 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 5.942s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.486s/0.000s . +# so far, program took 5.612s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.177s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.01639s (system CPU time used) -ru_utime : 5.902s (user CPU time used) +ru_stime : 0.03599s (system CPU time used) +ru_utime : 5.96s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 5.942s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.486s/0.000s . +# so far, program took 5.612s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.177s/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 12 threads -# Constructed matrix (took 0.008s): (3 x 3)[0xaaaad5eea110]{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' +# Constructed matrix (took 0.008s): (3 x 3)[0xaaaae1777110]{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 (12 th.) took 0.004142s; avg 0.001381s ( +/- 39.32/ 20.75 %); best 0.0008378s; worst 0.001667s; std dev. 0.000384 (taking best). -Reference operation time is 0.000837803 s (0.02865 Mflops) with 12 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: 0.0008378 Mflops: 0.029) -Merge (3 -> 1 leaves) took w.c.t. of 8.106e-06s, ~2.861e-06s of computing time (of which 0s sorting, 9.537e-07s analysis) -3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 97.78/129.41 %); best 2.996e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). -Reference operation time is 2.99573e-08 s (801.1 Mflops) with 12 threads. -After merge step 1: tpop: 2.996e-08 s ~Mflops: 801.140 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 27966.574x: 0.0008378s -> 2.996e-08s, so taking this instance. +3 iterations (12 th.) took 0.004316s; avg 0.001439s ( +/- 41.48/ 27.28 %); best 0.0008419s; worst 0.001831s; std dev. 0.0004289 (taking best). +Reference operation time is 0.000841856 s (0.02851 Mflops) with 12 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: 0.0008419 Mflops: 0.029) +Merge (3 -> 1 leaves) took w.c.t. of 7.153e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 0s analysis) +3 iterations (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 96.46/200.00 %); best 3.655e-08s; worst 3.099e-06s; std dev. 1.461e-06 (taking best). +Reference operation time is 3.65496e-08 s (656.6 Mflops) with 12 threads. +After merge step 1: tpop: 3.655e-08 s ~Mflops: 656.643 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 23033.268x: 0.0008419s -> 3.655e-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 0.003325s (of which 1.001e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 0s sorting, 9.537e-07s analyzing) -Total merge + benchmarking process took 0.003325s, equivalent to 110990.8/4.0 new/old ops (0.006656s for 2 clones -- as 222180.7/7.9 ops, or 111090.3/4.0 ops per clone), SPEEDUP of 27966.574x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 27966.574x (0.0008378s -> 2.996e-08s), will amortize in 4.0 ops by saving 0.0008378s per op. -In 1 tuning rounds (tot. 0.011s, 0.0067s for constructor, 2 clones) obtained a SPEEDUP of 2796557.4% (2.797e+04x) (from 0.02865 to 801.1 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.003543s (of which 9.06e-06s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 9.537e-07s sorting, 0s analyzing) +Total merge + benchmarking process took 0.003543s, equivalent to 96940.6/4.2 new/old ops (0.007031s for 2 clones -- as 192367.9/8.4 ops, or 96184.0/4.2 ops per clone), SPEEDUP of 23033.268x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 23033.268x (0.0008419s -> 3.655e-08s), will amortize in 4.2 ops by saving 0.0008418s per op. +In 1 tuning rounds (tot. 0.011s, 0.007s for constructor, 2 clones) obtained a SPEEDUP of 2303226.8% (2.303e+04x) (from 0.02851 to 656.6 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 0.011024 s (8.378e-04 s -> 2.996e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.011456 s (8.419e-04 s -> 3.655e-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 0.0546851 s and estimated a speedup of 1.000000 x (2.996e-08 s -> 2.996e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0546708 s and estimated a speedup of 1.000000 x (3.655e-08 s -> 3.655e-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 12 3 3 6 0.000000 0.003167 0.002487 0.005654 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005654 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.003167 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.002487 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.002734 0.002493 0.005227 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005227 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.002734 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.002493 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005654 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005227 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4374,56 +4410,56 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.00804901 1e+09 1e+09 +%operation:A.mtx 0.00771117 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00316691 0 0.00248718 +%constructor:A.mtx 0 0.00273395 0 0.00249314 # 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 12 threads -# Constructed matrix (took 0.008s): (3 x 3)[0xaaaad5eea4a0]{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' +# Constructed matrix (took 0.008s): (3 x 3)[0xaaaae1777110]{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 (12 th.) took 0.004114s; avg 0.001371s ( +/- 39.25/ 19.74 %); best 0.000833s; worst 0.001642s; std dev. 0.0003806 (taking best). -Reference operation time is 0.000833035 s (0.1152 Mflops) with 12 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: 0.000833 Mflops: 0.115) -Merge (3 -> 1 leaves) took w.c.t. of 6.914e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) -3 iterations (12 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 96.86/100.00 %); best 2.996e-08s; worst 1.907e-06s; std dev. 7.787e-07 (taking best). -Reference operation time is 2.99573e-08 s (3205 Mflops) with 12 threads. -After merge step 1: tpop: 2.996e-08 s ~Mflops: 3204.562 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 27807.402x: 0.000833s -> 2.996e-08s, so taking this instance. +3 iterations (12 th.) took 0.003514s; avg 0.001171s ( +/- 29.06/ 40.19 %); best 0.0008309s; worst 0.001642s; std dev. 0.0003437 (taking best). +Reference operation time is 0.000830889 s (0.1155 Mflops) with 12 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: 0.0008309 Mflops: 0.116) +Merge (3 -> 1 leaves) took w.c.t. of 5.96e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.25/200.00 %); best 3.655e-08s; worst 1.907e-06s; std dev. 8.991e-07 (taking best). +Reference operation time is 3.65496e-08 s (2627 Mflops) with 12 threads. +After merge step 1: tpop: 3.655e-08 s ~Mflops: 2626.570 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 22733.203x: 0.0008309s -> 3.655e-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 0.003533s (of which 7.868e-06s 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 0.003533s, equivalent to 117930.8/4.2 new/old ops (0.006615s for 2 clones -- as 220819.7/7.9 ops, or 110409.9/4.0 ops per clone), SPEEDUP of 27807.402x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 27807.402x (0.000833s -> 2.996e-08s), will amortize in 4.2 ops by saving 0.000833s per op. -In 1 tuning rounds (tot. 0.011s, 0.0066s for constructor, 2 clones) obtained a SPEEDUP of 2780640.2% (2.781e+04x) (from 0.1152 to 3205 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.004447s (of which 8.106e-06s 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 0.004447s, equivalent to 121669.9/5.4 new/old ops (0.007662s for 2 clones -- as 209634.7/9.2 ops, or 104817.4/4.6 ops per clone), SPEEDUP of 22733.203x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 22733.203x (0.0008309s -> 3.655e-08s), will amortize in 5.4 ops by saving 0.0008309s per op. +In 1 tuning rounds (tot. 0.011s, 0.0077s for constructor, 2 clones) obtained a SPEEDUP of 2273220.3% (2.273e+04x) (from 0.1155 to 2627 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 0.010989 s (8.330e-04 s -> 2.996e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.011308 s (8.309e-04 s -> 3.655e-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 0.054564 s and estimated a speedup of 1.000000 x (2.996e-08 s -> 2.996e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.053781 s and estimated a speedup of 1.000000 x (3.655e-08 s -> 3.655e-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 12 3 3 6 0.000000 0.002919 0.002475 0.005394 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005394 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.002919 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000001 0.003341 0.002475 0.005816 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005817 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.003341 %:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.002475 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005394 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005816 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:RSB_SUBDIVISION_SCALING:A.mtx S N 12 3 3 6 1.00 %:RSB_SHUFFLE_SCALING:A.mtx S N 12 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 12 3 3 6 nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 12 3 3 6 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 12 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 12 3 3 6 28 48 36 @@ -4432,59 +4468,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.00786901 1e+09 1e+09 +%operation:A.mtx 0.00828791 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00291896 0 0.00247502 +%constructor:A.mtx 9.53674e-07 0.00334096 0 0.00247502 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 6.104s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.617s/0.000s . +# so far, program took 5.774s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.308s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.02457s (system CPU time used) -ru_utime : 6.378s (user CPU time used) +ru_stime : 0.03996s (system CPU time used) +ru_utime : 6.442s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was S). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 6.104s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.617s/0.000s . +# so far, program took 5.774s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.308s/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 12 threads -# Constructed matrix (took 0.009s): (3 x 3)[0xaaaad5eed500]{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' +# Constructed matrix (took 0.006s): (3 x 3)[0xaaaae177a520]{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 (12 th.) took 0.002647s; avg 0.0008823s ( +/- 26.91/ 32.03 %); best 0.0006449s; worst 0.001165s; std dev. 0.0002147 (taking best). -Reference operation time is 0.000644922 s (0.1489 Mflops) with 12 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: 0.0006449 Mflops: 0.149) -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 (12 th.) took 9.179e-05s; avg 3.06e-05s ( +/- 99.90/196.88 %); best 2.996e-08s; worst 9.084e-05s; std dev. 4.26e-05 (taking best). -Reference operation time is 2.99573e-08 s (3205 Mflops) with 12 threads. -After merge step 1: tpop: 2.996e-08 s ~Mflops: 3204.562 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 21528.054x: 0.0006449s -> 2.996e-08s, so taking this instance. +3 iterations (12 th.) took 0.002472s; avg 0.0008241s ( +/- 1.34/ 0.74 %); best 0.000813s; worst 0.0008302s; std dev. 7.826e-06 (taking best). +Reference operation time is 0.000813007 s (0.1181 Mflops) with 12 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: 0.000813 Mflops: 0.118) +Merge (3 -> 1 leaves) took w.c.t. of 7.153e-06s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 0.000102s; avg 3.401e-05s ( +/- 99.89/197.20 %); best 3.655e-08s; worst 0.0001011s; std dev. 4.743e-05 (taking best). +Reference operation time is 3.65496e-08 s (2627 Mflops) with 12 threads. +After merge step 1: tpop: 3.655e-08 s ~Mflops: 2626.570 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 22243.966x: 0.000813s -> 3.655e-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 0.002417s (of which 1.097e-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 0.002417s, equivalent to 80684.4/3.7 new/old ops (0.006188s for 2 clones -- as 206565.9/9.6 ops, or 103282.9/4.8 ops per clone), SPEEDUP of 21528.054x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 21528.054x (0.0006449s -> 2.996e-08s), will amortize in 3.7 ops by saving 0.0006449s per op. -In 1 tuning rounds (tot. 0.009s, 0.0062s for constructor, 2 clones) obtained a SPEEDUP of 2152705.4% (2.153e+04x) (from 0.1489 to 3205 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.003025s (of which 9.06e-06s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.003025s, equivalent to 82765.8/3.7 new/old ops (0.005416s for 2 clones -- as 148180.0/6.7 ops, or 74090.0/3.3 ops per clone), SPEEDUP of 22243.966x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 22243.966x (0.000813s -> 3.655e-08s), will amortize in 3.7 ops by saving 0.000813s per op. +In 1 tuning rounds (tot. 0.008s, 0.0054s for constructor, 2 clones) obtained a SPEEDUP of 2224296.6% (2.224e+04x) (from 0.1181 to 2627 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 0.008986 s (6.449e-04 s -> 2.996e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00803208 s (8.130e-04 s -> 3.655e-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 0.041765 s and estimated a speedup of 1.000000 x (2.996e-08 s -> 2.996e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.041719 s and estimated a speedup of 1.000000 x (3.655e-08 s -> 3.655e-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 12 3 3 6 0.000000 0.003515 0.002472 0.005987 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005987 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.003515 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.002472 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.002018 0.001864 0.003882 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.003882 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.002018 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.001864 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005987 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.003882 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4499,50 +4535,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.00849581 1e+09 1e+09 +%operation:A.mtx 0.00552702 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00351501 0 0.00247216 +%constructor:A.mtx 0 0.00201797 0 0.00186396 # 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 12 threads -# Constructed matrix (took 0.008s): (3 x 3)[0xaaaad5eed500]{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' +# Constructed matrix (took 0.005s): (3 x 3)[0xaaaae177a520]{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 (12 th.) took 0.003799s; avg 0.001266s ( +/- 34.46/ 29.20 %); best 0.0008299s; worst 0.001636s; std dev. 0.0003324 (taking best). -Reference operation time is 0.000829935 s (0.4627 Mflops) with 12 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: 0.0008299 Mflops: 0.463) -Merge (3 -> 1 leaves) took w.c.t. of 6.914e-06s, ~2.146e-06s of computing time (of which 1.192e-06s sorting, 9.537e-07s analysis) -3 iterations (12 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 96.86/200.00 %); best 2.996e-08s; worst 2.861e-06s; std dev. 1.349e-06 (taking best). -Reference operation time is 2.99573e-08 s (1.282e+04 Mflops) with 12 threads. -After merge step 1: tpop: 2.996e-08 s ~Mflops: 12818.247 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 27703.940x: 0.0008299s -> 2.996e-08s, so taking this instance. +3 iterations (12 th.) took 0.002812s; avg 0.0009373s ( +/- 10.49/ 10.12 %); best 0.000839s; worst 0.001032s; std dev. 7.888e-05 (taking best). +Reference operation time is 0.000838995 s (0.4577 Mflops) with 12 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: 0.000839 Mflops: 0.458) +Merge (3 -> 1 leaves) took w.c.t. of 5.96e-06s, ~2.861e-06s of computing time (of which 0s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 96.46/200.00 %); best 3.655e-08s; worst 3.099e-06s; std dev. 1.461e-06 (taking best). +Reference operation time is 3.65496e-08 s (1.051e+04 Mflops) with 12 threads. +After merge step 1: tpop: 3.655e-08 s ~Mflops: 10506.280 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 22954.990x: 0.000839s -> 3.655e-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 0.003513s (of which 7.868e-06s 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 0.003513s, equivalent to 117262.2/4.2 new/old ops (0.007595s for 2 clones -- as 253521.7/9.2 ops, or 126760.8/4.6 ops per clone), SPEEDUP of 27703.940x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 27703.940x (0.0008299s -> 2.996e-08s), will amortize in 4.2 ops by saving 0.0008299s per op. -In 1 tuning rounds (tot. 0.011s, 0.0076s for constructor, 2 clones) obtained a SPEEDUP of 2770294.0% (2.77e+04x) (from 0.4627 to 1.282e+04 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.002114s (of which 7.868e-06s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 0s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.002114s, equivalent to 57834.3/2.5 new/old ops (0.004593s for 2 clones -- as 125668.6/5.5 ops, or 62834.3/2.7 ops per clone), SPEEDUP of 22954.990x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 22954.990x (0.000839s -> 3.655e-08s), will amortize in 2.5 ops by saving 0.000839s per op. +In 1 tuning rounds (tot. 0.0074s, 0.0046s for constructor, 2 clones) obtained a SPEEDUP of 2295399.0% (2.295e+04x) (from 0.4577 to 1.051e+04 Mflops). #pr: updating sample at index 13 (5^th of 16), 0^th touch for (0,0,0,0,1,2,0). -First run of RSB Autotuner took 0.011441 s (8.299e-04 s -> 2.996e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00744605 s (8.390e-04 s -> 3.655e-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 0.0471389 s and estimated a speedup of 1.000000 x (2.996e-08 s -> 2.996e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0418022 s and estimated a speedup of 1.000000 x (3.655e-08 s -> 3.655e-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 12 3 3 6 0.000000 0.002600 0.002684 0.005284 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005284 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.002600 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.002684 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.001701 0.001873 0.003574 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.003574 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.001701 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.001873 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005284 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.003574 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4557,59 +4593,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.00776386 1e+09 1e+09 +%operation:A.mtx 0.00544596 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00260019 0 0.00268388 +%constructor:A.mtx 0 0.00170112 0 0.00187302 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 6.241s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.727s/0.000s . +# so far, program took 5.894s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.407s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.03281s (system CPU time used) -ru_utime : 6.867s (user CPU time used) +ru_stime : 0.04796s (system CPU time used) +ru_utime : 6.912s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was C). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 6.241s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.727s/0.000s . +# so far, program took 5.894s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.407s/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 12 threads -# Constructed matrix (took 0.012s): (3 x 3)[0xaaaad5eed500]{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 0.020s): (3 x 3)[0xaaaae177a520]{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 (12 th.) took 0.004436s; avg 0.001479s ( +/- 8.35/ 10.84 %); best 0.001355s; worst 0.001639s; std dev. 0.0001187 (taking best). -Reference operation time is 0.00135517 s (0.07084 Mflops) with 12 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: 0.001355 Mflops: 0.071) -Merge (3 -> 1 leaves) took w.c.t. of 1.097e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (12 th.) took 1.001e-05s; avg 3.338e-06s ( +/- 99.10/200.00 %); best 2.996e-08s; worst 1.001e-05s; std dev. 4.72e-06 (taking best). -Reference operation time is 2.99573e-08 s (3205 Mflops) with 12 threads. -After merge step 1: tpop: 2.996e-08 s ~Mflops: 3204.562 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 45236.769x: 0.001355s -> 2.996e-08s, so taking this instance. +3 iterations (12 th.) took 0.00776s; avg 0.002587s ( +/- 20.87/ 40.95 %); best 0.002047s; worst 0.003646s; std dev. 0.0007491 (taking best). +Reference operation time is 0.00204682 s (0.0469 Mflops) with 12 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: 0.002047 Mflops: 0.047) +Merge (3 -> 1 leaves) took w.c.t. of 1.192e-05s, ~3.099e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 2.003e-05s; avg 6.676e-06s ( +/- 99.45/185.71 %); best 3.655e-08s; worst 1.907e-05s; std dev. 8.775e-06 (taking best). +Reference operation time is 3.65496e-08 s (2627 Mflops) with 12 threads. +After merge step 1: tpop: 3.655e-08 s ~Mflops: 2626.570 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 56001.305x: 0.002047s -> 3.655e-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 0.003784s (of which 1.192e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.003784s, equivalent to 126311.2/2.8 new/old ops (0.007262s for 2 clones -- as 242411.5/5.4 ops, or 121205.7/2.7 ops per clone), SPEEDUP of 45236.769x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 45236.769x (0.001355s -> 2.996e-08s), will amortize in 2.8 ops by saving 0.001355s per op. -In 1 tuning rounds (tot. 0.012s, 0.0073s for constructor, 2 clones) obtained a SPEEDUP of 4523576.9% (4.524e+04x) (from 0.07084 to 3205 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.006435s (of which 1.383e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 0s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.006435s, equivalent to 176060.0/3.1 new/old ops (0.01897s for 2 clones -- as 519073.7/9.3 ops, or 259536.9/4.6 ops per clone), SPEEDUP of 56001.305x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 56001.305x (0.002047s -> 3.655e-08s), will amortize in 3.1 ops by saving 0.002047s per op. +In 1 tuning rounds (tot. 0.027s, 0.019s for constructor, 2 clones) obtained a SPEEDUP of 5600030.5% (5.6e+04x) (from 0.0469 to 2627 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 0.011764 s (1.355e-03 s -> 2.996e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0268209 s (2.047e-03 s -> 3.655e-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 0.0615292 s and estimated a speedup of 1.000000 x (2.996e-08 s -> 2.996e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.098695 s and estimated a speedup of 1.000000 x (3.655e-08 s -> 3.655e-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 12 3 3 6 0.000000 0.007103 0.002475 0.009578 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.009578 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.007103 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.002475 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.006076 0.001870 0.007946 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.007946 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.006076 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.001870 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.009578 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.007946 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4624,50 +4660,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.011858 1e+09 1e+09 +%operation:A.mtx 0.0195692 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00710297 0 0.00247478 +%constructor:A.mtx 0 0.0060761 0 0.00187016 # 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 12 threads -# Constructed matrix (took 0.015s): (3 x 3)[0xaaaad5eed500]{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 0.013s): (3 x 3)[0xaaaae177a520]{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 (12 th.) took 0.006371s; avg 0.002124s ( +/- 3.43/ 6.84 %); best 0.002051s; worst 0.002269s; std dev. 0.0001028 (taking best). -Reference operation time is 0.00205088 s (0.1872 Mflops) with 12 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: 0.002051 Mflops: 0.187) -Merge (3 -> 1 leaves) took w.c.t. of 1.097e-05s, ~4.053e-06s of computing time (of which 1.192e-06s sorting, 1.907e-06s analysis) -3 iterations (12 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 96.86/200.00 %); best 2.996e-08s; worst 2.861e-06s; std dev. 1.349e-06 (taking best). -Reference operation time is 2.99573e-08 s (1.282e+04 Mflops) with 12 threads. -After merge step 1: tpop: 2.996e-08 s ~Mflops: 12818.247 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 68460.008x: 0.002051s -> 2.996e-08s, so taking this instance. +3 iterations (12 th.) took 0.005963s; avg 0.001988s ( +/- 37.71/ 23.61 %); best 0.001238s; worst 0.002457s; std dev. 0.0005356 (taking best). +Reference operation time is 0.00123811 s (0.3102 Mflops) with 12 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: 0.001238 Mflops: 0.310) +Merge (3 -> 1 leaves) took w.c.t. of 6.199e-06s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 1.192e-06s analysis) +3 iterations (12 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 94.89/200.00 %); best 3.655e-08s; worst 2.146e-06s; std dev. 1.012e-06 (taking best). +Reference operation time is 3.65496e-08 s (1.051e+04 Mflops) with 12 threads. +After merge step 1: tpop: 3.655e-08 s ~Mflops: 10506.280 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 33874.755x: 0.001238s -> 3.655e-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 0.006152s (of which 1.311e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 1.192e-06s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.006152s, equivalent to 205356.1/3.0 new/old ops (0.01296s for 2 clones -- as 432455.2/6.3 ops, or 216227.6/3.2 ops per clone), SPEEDUP of 68460.008x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 68460.008x (0.002051s -> 2.996e-08s), will amortize in 3.0 ops by saving 0.002051s per op. -In 1 tuning rounds (tot. 0.019s, 0.013s for constructor, 2 clones) obtained a SPEEDUP of 6845900.8% (6.846e+04x) (from 0.1872 to 1.282e+04 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.004338s (of which 9.06e-06s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 9.537e-07s sorting, 1.192e-06s analyzing) +Total merge + benchmarking process took 0.004338s, equivalent to 118688.8/3.5 new/old ops (0.01086s for 2 clones -- as 296999.3/8.8 ops, or 148499.7/4.4 ops per clone), SPEEDUP of 33874.755x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 33874.755x (0.001238s -> 3.655e-08s), will amortize in 3.5 ops by saving 0.001238s per op. +In 1 tuning rounds (tot. 0.017s, 0.011s for constructor, 2 clones) obtained a SPEEDUP of 3387375.5% (3.387e+04x) (from 0.3102 to 1.051e+04 Mflops). #pr: updating sample at index 15 (7^th of 16), 0^th touch for (0,0,0,0,1,3,0). -First run of RSB Autotuner took 0.0194108 s (2.051e-03 s -> 2.996e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0168929 s (1.238e-03 s -> 3.655e-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 0.250051 s and estimated a speedup of 1.000000 x (2.996e-08 s -> 2.996e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.052351 s and estimated a speedup of 1.000000 x (3.655e-08 s -> 3.655e-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 12 3 3 6 0.000000 0.005012 0.005728 0.010740 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.010740 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.005012 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.005728 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.005185 0.004090 0.009275 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.009275 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.005185 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.004090 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.010740 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.009275 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4682,71 +4718,71 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0150452 1e+09 1e+09 +%operation:A.mtx 0.013375 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00501204 0 0.00572801 +%constructor:A.mtx 0 0.00518513 0 0.00409007 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 6.635s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.069s/0.000s . +# so far, program took 6.133s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.602s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.04538s (system CPU time used) -ru_utime : 7.43s (user CPU time used) +ru_stime : 0.05609s (system CPU time used) +ru_utime : 7.46s (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 12 12 0 4.0000 4.6667 3 1 801.14 7.742e-03 0.000e+00 2.996e-08 0.000e+00 6.434e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 3204.56 8.700e-04 0.000e+00 2.996e-08 0.000e+00 1.101e-02 1.22e+01 2.79e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 656.64 1.967e-03 0.000e+00 3.655e-08 0.000e+00 1.927e-02 4.05e+00 5.17e+00 1 2.40e-05 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.311e-04 0.000e+00 3.655e-08 0.000e+00 1.099e-02 9.96e+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. 14373557.0 % faster, avg. sp. ratio 143736.570x, max sp. ratio 258432.153x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1257624.4/367656.2/2147592.5/2515248.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.5/ 8.3/ 12.7/ 21.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.5, min. 8.3, max. 12.7 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3828014.8 % faster, avg. sp. ratio 38281.148x, max sp. ratio 53822.570x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 413891.1/300665.4/527116.8/827782.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.5/ 9.8/ 13.2/ 23.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.5, min. 9.8, max. 13.2 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 6.543/ 4.139/ 8.946,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.091/ 4.940/ 12.151,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.363/ 3.393/ 7.333,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.008/ 4.049/ 9.959,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.: 0.04 s, min 0.01 s, max 0.06 s, tot 0.08 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.01 s, max 0.06 s, tot 0.08 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.003e+03, min 8.011e+02, max 3.205e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 5.672e-02, min 3.100e-03, max 1.103e-01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 5.991e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.306e-03s, min 8.700e-04s, max 7.742e-03s, tot 8.612e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.312e+00 1.148e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.01 s, max 0.02 s, tot 0.03 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.02 s, tot 0.03 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.642e+03, min 6.566e+02, max 2.627e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.385e-02, min 1.220e-02, max 1.155e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 7.310e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.399e-03s, min 8.311e-04s, max 1.967e-03s, tot 2.798e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.420e+00 1.387e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+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 12 12 0 4.0000 4.6667 3 1 801.14 8.378e-04 0.000e+00 2.996e-08 0.000e+00 1.102e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3204.56 8.330e-04 0.000e+00 2.996e-08 0.000e+00 1.099e-02 6.54e+00 1.54e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 656.64 8.419e-04 0.000e+00 3.655e-08 0.000e+00 1.146e-02 2.41e+00 3.17e+00 1 2.40e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.309e-04 0.000e+00 3.655e-08 0.000e+00 1.131e-02 5.36e+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. 2788598.8 % faster, avg. sp. ratio 27886.988x, max sp. ratio 27966.574x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 367405.5/366820.5/367990.4/734811.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.2/ 13.2/ 13.2/ 26.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 13.2, min. 13.2, max. 13.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2288223.5 % faster, avg. sp. ratio 22883.235x, max sp. ratio 23033.268x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 311412.3/309386.8/313437.7/622824.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.6/ 13.6/ 13.6/ 27.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.6, min. 13.6, max. 13.6 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 3.739/ 2.537/ 4.940,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.480/ 2.938/ 6.543,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.064/ 2.079/ 4.049,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 7.770/ 2.408/ 5.363,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) @@ -4754,33 +4790,33 @@ #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) #pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) #pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.003e+03, min 8.011e+02, max 3.205e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 7.194e-02, min 2.865e-02, max 1.152e-01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 5.991e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 8.354e-04s, min 8.330e-04s, max 8.378e-04s, tot 1.671e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 9.619e+00 1.873e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: best tun. rsb canon. mflops were: on avg. 1.642e+03, min 6.566e+02, max 2.627e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.202e-02, min 2.851e-02, max 1.155e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 7.310e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.364e-04s, min 8.309e-04s, max 8.419e-04s, tot 1.673e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.162e+01 2.264e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+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 12 12 0 4.0000 4.6667 3 1 3204.56 6.449e-04 0.000e+00 2.996e-08 0.000e+00 8.986e-03 4.94e+00 1.29e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12818.25 8.299e-04 0.000e+00 2.996e-08 0.000e+00 1.144e-02 1.22e+01 6.98e-01 1 3.84e-04 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.130e-04 0.000e+00 3.655e-08 0.000e+00 8.032e-03 4.05e+00 1.29e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10506.28 8.390e-04 0.000e+00 3.655e-08 0.000e+00 7.446e-03 9.96e+00 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. 2461499.7 % faster, avg. sp. ratio 24615.997x, max sp. ratio 27703.940x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 340935.1/299960.2/381910.1/681870.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.9/ 13.8/ 13.9/ 27.7 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 13.9, min. 13.8, max. 13.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2259847.8 % faster, avg. sp. ratio 22599.478x, max sp. ratio 22954.990x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 211741.7/203724.7/219758.6/423483.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.4/ 8.9/ 9.9/ 18.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.4, min. 8.9, max. 9.9 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 6.543/ 4.139/ 8.946,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.091/ 4.940/ 12.151,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.363/ 3.393/ 7.333,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.008/ 4.049/ 9.959,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) @@ -4788,104 +4824,104 @@ #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) #pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) #pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.011e+03, min 3.205e+03, max 1.282e+04 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.058e-01, min 1.489e-01, max 4.627e-01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 5.991e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.374e-04s, min 6.449e-04s, max 8.299e-04s, tot 1.475e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.312e+00 1.148e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: best tun. rsb canon. mflops were: on avg. 6.566e+03, min 2.627e+03, max 1.051e+04 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.879e-01, min 1.181e-01, max 4.577e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 7.310e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.260e-04s, min 8.130e-04s, max 8.390e-04s, tot 1.652e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.420e+00 1.387e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+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 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 12 12 0 4.0000 4.6667 3 1 3204.56 1.355e-03 0.000e+00 2.996e-08 0.000e+00 1.176e-02 8.95e+00 2.29e+00 1 9.60e-05 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12818.25 2.051e-03 0.000e+00 2.996e-08 0.000e+00 1.941e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2626.57 2.047e-03 0.000e+00 3.655e-08 0.000e+00 2.682e-02 7.33e+00 2.29e+00 1 9.60e-05 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10506.28 1.238e-03 0.000e+00 3.655e-08 0.000e+00 1.689e-02 1.92e+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. 5684738.8 % faster, avg. sp. ratio 56848.388x, max sp. ratio 68460.008x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 520322.3/392694.0/647950.7/1040644.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 8.7/ 9.5/ 18.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.1, min. 8.7, max. 9.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4493703.0 % faster, avg. sp. ratio 44938.030x, max sp. ratio 56001.305x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 598007.2/462191.8/733822.6/1196014.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.4/ 13.1/ 13.6/ 26.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.4, min. 13.1, max. 13.6 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 12.151/ 7.344/ 16.957,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 32.313/ 8.946/ 23.367,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 9.959/ 6.019/ 13.899,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 26.485/ 7.333/ 19.152,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.: 0.02 s, min 0.01 s, max 0.02 s, tot 0.03 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.02 s, tot 0.03 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.011e+03, min 3.205e+03, max 1.282e+04 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.290e-01, min 7.084e-02, max 1.872e-01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 5.991e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.703e-03s, min 1.355e-03s, max 2.051e-03s, tot 3.406e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.802e+00 6.471e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.02 s, max 0.03 s, tot 0.04 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.02 s, max 0.03 s, tot 0.04 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.566e+03, min 2.627e+03, max 1.051e+04 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.785e-01, min 4.690e-02, max 3.102e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 7.310e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.642e-03s, min 1.238e-03s, max 2.047e-03s, tot 3.285e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.387e+00 7.820e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to nrhs=1: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 801.14 7.742e-03 0.000e+00 2.996e-08 0.000e+00 6.434e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 801.14 8.378e-04 0.000e+00 2.996e-08 0.000e+00 1.102e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 3204.56 6.449e-04 0.000e+00 2.996e-08 0.000e+00 8.986e-03 4.94e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 3204.56 1.355e-03 0.000e+00 2.996e-08 0.000e+00 1.176e-02 8.95e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 656.64 1.967e-03 0.000e+00 3.655e-08 0.000e+00 1.927e-02 4.05e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 656.64 8.419e-04 0.000e+00 3.655e-08 0.000e+00 1.146e-02 2.41e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.130e-04 0.000e+00 3.655e-08 0.000e+00 8.032e-03 4.05e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2626.57 2.047e-03 0.000e+00 3.655e-08 0.000e+00 2.682e-02 7.33e+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. 8828988.7 % faster, avg. sp. ratio 88290.887x, max sp. ratio 258432.153x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 802059.3/299960.2/2147592.5/3208237.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.0/ 8.3/ 13.9/ 44.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.0, min. 8.3, max. 13.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3877427.7 % faster, avg. sp. ratio 38775.277x, max sp. ratio 56001.305x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 448533.9/219758.6/733822.6/1794135.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.6/ 9.8/ 13.6/ 46.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.6, min. 9.8, max. 13.6 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 4.540/ 2.537/ 7.344,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 21.764/ 2.938/ 8.946,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.721/ 2.079/ 6.019,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.839/ 2.408/ 7.333,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.: 0.02 s, min 0.01 s, max 0.06 s, tot 0.10 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.06 s, tot 0.10 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.003e+03, min 8.011e+02, max 3.205e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 6.286e-02, min 3.100e-03, max 1.489e-01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 1.198e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.645e-03s, min 6.449e-04s, max 7.742e-03s, tot 1.058e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.471e+00 1.873e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.01 s, max 0.03 s, tot 0.07 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.03 s, tot 0.07 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.642e+03, min 6.566e+02, max 2.627e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.142e-02, min 1.220e-02, max 1.181e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 1.462e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.417e-03s, min 8.130e-04s, max 2.047e-03s, tot 5.669e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.820e+00 2.264e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+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 12 12 0 4.0000 4.6667 3 1 3204.56 8.700e-04 0.000e+00 2.996e-08 0.000e+00 1.101e-02 1.22e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3204.56 8.330e-04 0.000e+00 2.996e-08 0.000e+00 1.099e-02 6.54e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12818.25 8.299e-04 0.000e+00 2.996e-08 0.000e+00 1.144e-02 1.22e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12818.25 2.051e-03 0.000e+00 2.996e-08 0.000e+00 1.941e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.311e-04 0.000e+00 3.655e-08 0.000e+00 1.099e-02 9.96e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.309e-04 0.000e+00 3.655e-08 0.000e+00 1.131e-02 5.36e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10506.28 8.390e-04 0.000e+00 3.655e-08 0.000e+00 7.446e-03 9.96e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10506.28 1.238e-03 0.000e+00 3.655e-08 0.000e+00 1.689e-02 1.92e+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. 3825208.4 % faster, avg. sp. ratio 38253.084x, max sp. ratio 68460.008x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 441084.4/366820.5/647950.7/1764337.4 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.3/ 9.5/ 13.8/ 49.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.3, min. 9.5, max. 13.8 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2557466.9 % faster, avg. sp. ratio 25575.669x, max sp. ratio 33874.755x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 318992.2/203724.7/462191.8/1275968.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.3/ 8.9/ 13.6/ 49.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.3, min. 8.9, max. 13.6 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 9.947/ 4.940/ 16.957,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 54.211/ 6.543/ 23.367,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.153/ 4.049/ 13.899,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.433/ 5.363/ 19.152,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) @@ -4893,108 +4929,108 @@ #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) #pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.02 s, tot 0.05 s (4 samples) #pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.02 s, tot 0.05 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.011e+03, min 3.205e+03, max 1.282e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.189e-01, min 1.103e-01, max 4.627e-01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 1.198e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.146e-03s, min 8.299e-04s, max 2.051e-03s, tot 4.584e-03s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.802e+00 9.619e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: best tun. rsb canon. mflops were: on avg. 6.566e+03, min 2.627e+03, max 1.051e+04 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.497e-01, min 1.155e-01, max 4.577e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 1.462e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.348e-04s, min 8.309e-04s, max 1.238e-03s, tot 3.739e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.387e+00 1.162e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+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: ======== 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 12 12 0 4.0000 4.6667 3 1 801.14 7.742e-03 0.000e+00 2.996e-08 0.000e+00 6.434e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 801.14 8.378e-04 0.000e+00 2.996e-08 0.000e+00 1.102e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 3204.56 6.449e-04 0.000e+00 2.996e-08 0.000e+00 8.986e-03 4.94e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 3204.56 1.355e-03 0.000e+00 2.996e-08 0.000e+00 1.176e-02 8.95e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 3204.56 8.700e-04 0.000e+00 2.996e-08 0.000e+00 1.101e-02 1.22e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3204.56 8.330e-04 0.000e+00 2.996e-08 0.000e+00 1.099e-02 6.54e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12818.25 8.299e-04 0.000e+00 2.996e-08 0.000e+00 1.144e-02 1.22e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12818.25 2.051e-03 0.000e+00 2.996e-08 0.000e+00 1.941e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 656.64 1.967e-03 0.000e+00 3.655e-08 0.000e+00 1.927e-02 4.05e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 656.64 8.419e-04 0.000e+00 3.655e-08 0.000e+00 1.146e-02 2.41e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.130e-04 0.000e+00 3.655e-08 0.000e+00 8.032e-03 4.05e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2626.57 2.047e-03 0.000e+00 3.655e-08 0.000e+00 2.682e-02 7.33e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.311e-04 0.000e+00 3.655e-08 0.000e+00 1.099e-02 9.96e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.309e-04 0.000e+00 3.655e-08 0.000e+00 1.131e-02 5.36e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10506.28 8.390e-04 0.000e+00 3.655e-08 0.000e+00 7.446e-03 9.96e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10506.28 1.238e-03 0.000e+00 3.655e-08 0.000e+00 1.689e-02 1.92e+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. 6327098.6 % faster, avg. sp. ratio 63271.986x, max sp. ratio 258432.153x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 621571.8/299960.2/2147592.5/4972574.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.6/ 8.3/ 13.9/ 93.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.6, min. 8.3, max. 13.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3217447.3 % faster, avg. sp. ratio 32175.473x, max sp. ratio 56001.305x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 383763.0/203724.7/733822.6/3070104.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.0/ 8.9/ 13.6/ 95.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.0, min. 8.9, max. 13.6 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 7.244/ 2.537/ 16.957,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 75.975/ 2.938/ 23.367,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.937/ 2.079/ 13.899,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 62.272/ 2.408/ 19.152,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.: 0.02 s, min 0.01 s, max 0.06 s, tot 0.15 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.06 s, tot 0.15 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.007e+03, min 8.011e+02, max 1.282e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.409e-01, min 3.100e-03, max 4.627e-01 (8 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 2.397e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.895e-03s, min 6.449e-04s, max 7.742e-03s, tot 1.516e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.802e+00 1.873e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.03 s, tot 0.11 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.03 s, tot 0.11 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.104e+03, min 6.566e+02, max 1.051e+04 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.506e-01, min 1.220e-02, max 4.577e-01 (8 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 2.924e-07s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.176e-03s, min 8.130e-04s, max 2.047e-03s, tot 9.408e-03s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.387e+00 2.264e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+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: ======== 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 12 12 0 4.0000 4.6667 3 1 801.14 7.742e-03 0.000e+00 2.996e-08 0.000e+00 6.434e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 801.14 8.378e-04 0.000e+00 2.996e-08 0.000e+00 1.102e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 3204.56 6.449e-04 0.000e+00 2.996e-08 0.000e+00 8.986e-03 4.94e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 3204.56 1.355e-03 0.000e+00 2.996e-08 0.000e+00 1.176e-02 8.95e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 656.64 1.967e-03 0.000e+00 3.655e-08 0.000e+00 1.927e-02 4.05e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 656.64 8.419e-04 0.000e+00 3.655e-08 0.000e+00 1.146e-02 2.41e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.130e-04 0.000e+00 3.655e-08 0.000e+00 8.032e-03 4.05e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2626.57 2.047e-03 0.000e+00 3.655e-08 0.000e+00 2.682e-02 7.33e+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. 8828988.7 % faster, avg. sp. ratio 88290.887x, max sp. ratio 258432.153x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 802059.3/299960.2/2147592.5/3208237.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.0/ 8.3/ 13.9/ 44.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.0, min. 8.3, max. 13.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3877427.7 % faster, avg. sp. ratio 38775.277x, max sp. ratio 56001.305x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 448533.9/219758.6/733822.6/1794135.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.6/ 9.8/ 13.6/ 46.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.6, min. 9.8, max. 13.6 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 4.540/ 2.537/ 7.344,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 21.764/ 2.938/ 8.946,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.721/ 2.079/ 6.019,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.839/ 2.408/ 7.333,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.: 0.02 s, min 0.01 s, max 0.06 s, tot 0.10 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.06 s, tot 0.10 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.003e+03, min 8.011e+02, max 3.205e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 6.286e-02, min 3.100e-03, max 1.489e-01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 1.198e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.645e-03s, min 6.449e-04s, max 7.742e-03s, tot 1.058e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.471e+00 1.873e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.01 s, max 0.03 s, tot 0.07 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.03 s, tot 0.07 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.642e+03, min 6.566e+02, max 2.627e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.142e-02, min 1.220e-02, max 1.181e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 1.462e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.417e-03s, min 8.130e-04s, max 2.047e-03s, tot 5.669e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.820e+00 2.264e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+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 12 12 0 4.0000 4.6667 3 1 3204.56 8.700e-04 0.000e+00 2.996e-08 0.000e+00 1.101e-02 1.22e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3204.56 8.330e-04 0.000e+00 2.996e-08 0.000e+00 1.099e-02 6.54e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12818.25 8.299e-04 0.000e+00 2.996e-08 0.000e+00 1.144e-02 1.22e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12818.25 2.051e-03 0.000e+00 2.996e-08 0.000e+00 1.941e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.311e-04 0.000e+00 3.655e-08 0.000e+00 1.099e-02 9.96e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.309e-04 0.000e+00 3.655e-08 0.000e+00 1.131e-02 5.36e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10506.28 8.390e-04 0.000e+00 3.655e-08 0.000e+00 7.446e-03 9.96e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10506.28 1.238e-03 0.000e+00 3.655e-08 0.000e+00 1.689e-02 1.92e+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. 3825208.4 % faster, avg. sp. ratio 38253.084x, max sp. ratio 68460.008x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 441084.4/366820.5/647950.7/1764337.4 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.3/ 9.5/ 13.8/ 49.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.3, min. 9.5, max. 13.8 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2557466.9 % faster, avg. sp. ratio 25575.669x, max sp. ratio 33874.755x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 318992.2/203724.7/462191.8/1275968.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.3/ 8.9/ 13.6/ 49.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.3, min. 8.9, max. 13.6 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 9.947/ 4.940/ 16.957,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 54.211/ 6.543/ 23.367,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.153/ 4.049/ 13.899,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.433/ 5.363/ 19.152,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) @@ -5002,12 +5038,12 @@ #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) #pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.02 s, tot 0.05 s (4 samples) #pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.02 s, tot 0.05 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.011e+03, min 3.205e+03, max 1.282e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.189e-01, min 1.103e-01, max 4.627e-01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 1.198e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.146e-03s, min 8.299e-04s, max 2.051e-03s, tot 4.584e-03s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.802e+00 9.619e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: best tun. rsb canon. mflops were: on avg. 6.566e+03, min 2.627e+03, max 1.051e+04 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.497e-01, min 1.155e-01, max 4.577e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 1.462e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.348e-04s, min 8.309e-04s, max 1.238e-03s, tot 3.739e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.387e+00 1.162e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+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: ======== Limiting to transA=T: #pr: No sample (out of 8) matched the dump criteria -- skipping dump round. @@ -5018,68 +5054,68 @@ #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 12 12 0 4.0000 4.6667 3 1 801.14 7.742e-03 0.000e+00 2.996e-08 0.000e+00 6.434e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 801.14 8.378e-04 0.000e+00 2.996e-08 0.000e+00 1.102e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 3204.56 6.449e-04 0.000e+00 2.996e-08 0.000e+00 8.986e-03 4.94e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 3204.56 1.355e-03 0.000e+00 2.996e-08 0.000e+00 1.176e-02 8.95e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 3204.56 8.700e-04 0.000e+00 2.996e-08 0.000e+00 1.101e-02 1.22e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3204.56 8.330e-04 0.000e+00 2.996e-08 0.000e+00 1.099e-02 6.54e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12818.25 8.299e-04 0.000e+00 2.996e-08 0.000e+00 1.144e-02 1.22e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12818.25 2.051e-03 0.000e+00 2.996e-08 0.000e+00 1.941e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 656.64 1.967e-03 0.000e+00 3.655e-08 0.000e+00 1.927e-02 4.05e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 656.64 8.419e-04 0.000e+00 3.655e-08 0.000e+00 1.146e-02 2.41e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.130e-04 0.000e+00 3.655e-08 0.000e+00 8.032e-03 4.05e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2626.57 2.047e-03 0.000e+00 3.655e-08 0.000e+00 2.682e-02 7.33e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.311e-04 0.000e+00 3.655e-08 0.000e+00 1.099e-02 9.96e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2626.57 8.309e-04 0.000e+00 3.655e-08 0.000e+00 1.131e-02 5.36e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10506.28 8.390e-04 0.000e+00 3.655e-08 0.000e+00 7.446e-03 9.96e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10506.28 1.238e-03 0.000e+00 3.655e-08 0.000e+00 1.689e-02 1.92e+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. 6327098.6 % faster, avg. sp. ratio 63271.986x, max sp. ratio 258432.153x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 621571.8/299960.2/2147592.5/4972574.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.6/ 8.3/ 13.9/ 93.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.6, min. 8.3, max. 13.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3217447.3 % faster, avg. sp. ratio 32175.473x, max sp. ratio 56001.305x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 383763.0/203724.7/733822.6/3070104.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.0/ 8.9/ 13.6/ 95.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.0, min. 8.9, max. 13.6 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 7.244/ 2.537/ 16.957,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 75.975/ 2.938/ 23.367,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.937/ 2.079/ 13.899,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 62.272/ 2.408/ 19.152,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.: 0.02 s, min 0.01 s, max 0.06 s, tot 0.15 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.06 s, tot 0.15 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.007e+03, min 8.011e+02, max 1.282e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.409e-01, min 3.100e-03, max 4.627e-01 (8 samples) -#pr: best tun. rsb operation time was: on avg. 2.996e-08s, min 2.996e-08s, max 2.996e-08s, tot 2.397e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.895e-03s, min 6.449e-04s, max 7.742e-03s, tot 1.516e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.802e+00 1.873e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.962e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.03 s, tot 0.11 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.03 s, tot 0.11 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.104e+03, min 6.566e+02, max 1.051e+04 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.506e-01, min 1.220e-02, max 4.577e-01 (8 samples) +#pr: best tun. rsb operation time was: on avg. 3.655e-08s, min 3.655e-08s, max 3.655e-08s, tot 2.924e-07s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.176e-03s, min 8.130e-04s, max 2.047e-03s, tot 9.408e-03s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.387e+00 2.264e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.014e+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 1.03 s. +#pr: Record collection took 0.71 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 5416 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 5470 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1769414862_gcc-14.2.rpr -# Removing the temporary record file rsbench_pr__1769414862_gcc-14.2.rpr.tmp. -# terminating run at 1769414868 (after 6.6s 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__1769415861_gcc-14.2.rpr +# Removing the temporary record file rsbench_pr__1769415861_gcc-14.2.rpr.tmp. +# terminating run at 1769415867 (after 6.1s of w.c.t.) +srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/sh ./scripts/doc-tests.sh + set -o pipefail + test x/build/reproducible-path/librsb-1.3.0.2+dfsg = x -+ grep '^.\{71,\}' + cat /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/autotune.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/backsolve.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/hello-spblas.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/hello.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/io-spblas.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/power.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/snippets.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/transpose.c ++ grep '^.\{71,\}' + true -+ grep '^[^ ].\{80,\}' + cat /build/reproducible-path/librsb-1.3.0.2+dfsg/README ++ grep '^[^ ].\{80,\}' + true -++ wc -l ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h +++ wc -l + test 63 -ge 61 ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h ++ wc -c + test 2014 -ge 1966 -++ wc -l ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h +++ wc -l + test 182 -ge 157 -++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h ++ wc -c +++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h + test 5369 -ge 4600 + exit 0 if ! ./librsb-config --help ; then echo "Problem executing the librsb-config script!"; false; fi; @@ -5114,7 +5150,7 @@ 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 @@ -5124,15 +5160,15 @@ 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 1769414869 +# beginning run at 1769415867 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench --lower 100 --as-symmetric --types : -n 1 --notranspose --compare-competitors --verbose --verbose --write-performance-record=test.rpr # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -# average timer granularity: 3e-08 s +# average timer granularity: 3.6e-08 s # Will write a final performance record to file test.rpr and periodic checkpoints to test.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -5171,7 +5207,7 @@ # 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: codethink03-arm64 +# 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 43690 bytes @@ -5191,29 +5227,29 @@ # 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 5.485s +# Memory benchmark took 5.334s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 4 samples (1120 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 5.486s 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 . +# so far, program took 5.335s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.003e-02 s (100.00 %) - analyzed arrays in 2.425e-03 s (24.19 %) - cleaned-up arrays in 1.001e-05 s (0.10 %) - deduplicated arrays in 7.868e-06 s (0.08 %) + converted COO to RSB in 1.976e-02 s (100.00 %) + analyzed arrays in 5.105e-03 s (25.84 %) + cleaned-up arrays in 1.121e-05 s (0.06 %) + deduplicated arrays in 7.868e-06 s (0.04 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.029e-03 s (50.16 %) - memory allocations took 1.335e-05 s (0.13 %) - leafs setup took 9.060e-06 s (0.09 %) - halfword conversion took 2.529e-03 s (25.22 %) -Built (100 x 100)[0xaaaaed90c940]{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 0.010s): (100 x 100)[0xaaaaed90c940]{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 9.110e-03 s (46.11 %) + memory allocations took 1.478e-05 s (0.07 %) + leafs setup took 6.914e-06 s (0.03 %) + halfword conversion took 5.499e-03 s (27.83 %) +Built (100 x 100)[0xaaaadbacc970]{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 0.020s): (100 x 100)[0xaaaadbacc970]{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. @@ -5264,10 +5300,10 @@ # 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 0.003765s; avg 0.001255s ( +/- 4.08/ 2.48 %); best 0.001204s; worst 0.001286s; std dev. 3.647e-05 (taking best). -Reference operation time is 0.00120378 s (16.78 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: 0.001204 Mflops: 16.781) -Merge (3 -> 1 leaves) took w.c.t. of 9.584e-05s, ~8.106e-05s of computing time (of which 3.386e-05s sorting, 5.007e-06s analysis) +3 iterations (1 th.) took 0.007027s; avg 0.002342s ( +/- 15.85/ 19.79 %); best 0.001971s; worst 0.002806s; std dev. 0.0003471 (taking best). +Reference operation time is 0.00197101 s (10.25 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: 0.001971 Mflops: 10.249) +Merge (3 -> 1 leaves) took w.c.t. of 4.792e-05s, ~3.791e-05s of computing time (of which 1.693e-05s sorting, 4.053e-06s analysis) # 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 @@ -5298,7 +5334,7 @@ # 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 2.694e-05s; avg 8.98e-06s ( +/- 44.25/ 77.88 %); best 5.007e-06s; worst 1.597e-05s; std dev. 4.961e-06 (taking best). +3 iterations (1 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 28.41/ 43.18 %); best 5.007e-06s; worst 1.001e-05s; std dev. 2.171e-06 (taking best). Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5316,15 +5352,15 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success After merge step 1: tpop: 5.007e-06 s ~Mflops: 4034.521 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 240.429x: 0.001204s -> 5.007e-06s, so taking this instance. +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 393.667x: 0.001971s -> 5.007e-06s, 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 0.01562s (of which 0.000102s partitioning, 0.01119s I/O); computing times: 8.106e-05s in par. loops, 3.386e-05s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.01562s, equivalent to 3120.4/13.0 new/old ops (0.007259s for 2 clones -- as 1449.9/6.0 ops, or 724.9/3.0 ops per clone), SPEEDUP of 240.429x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 240.429x (0.001204s -> 5.007e-06s), will amortize in 13.0 ops by saving 0.001199s per op. -In 1 tuning rounds (tot. 0.023s, 0.0073s for constructor, 2 clones) obtained a SPEEDUP of 23942.9% (240.4x) (from 16.78 to 4035 Mflops). Employed 0.013s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02172s (of which 5.102e-05s partitioning, 0.01475s I/O); computing times: 3.791e-05s in par. loops, 1.693e-05s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.02172s, equivalent to 4337.3/11.0 new/old ops (0.01403s for 2 clones -- as 2803.0/7.1 ops, or 1401.5/3.6 ops per clone), SPEEDUP of 393.667x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 393.667x (0.001971s -> 5.007e-06s), will amortize in 11.0 ops by saving 0.001966s per op. +In 1 tuning rounds (tot. 0.036s, 0.014s for constructor, 2 clones) obtained a SPEEDUP of 39266.7% (393.7x) (from 10.25 to 4035 Mflops). Employed 0.016s 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 0.0361149 s (1.204e-03 s -> 5.007e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.052527 s (1.971e-03 s -> 5.007e-06 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 @@ -5390,20 +5426,20 @@ # 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 0.000138s; avg 4.601e-05s ( +/- 17.10/ 25.91 %); best 3.815e-05s; worst 5.794e-05s; std dev. 8.572e-06 (taking best). -Reference operation time is 3.8147e-05 s (529.5 Mflops) with 1 threads. +3 iterations (1 th.) took 2.48e-05s; avg 8.265e-06s ( +/- 27.88/ 55.77 %); best 5.96e-06s; worst 1.287e-05s; std dev. 3.259e-06 (taking best). +Reference operation time is 5.96046e-06 s (3389 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 3.898e-03 s (100.00 %) - analyzed arrays in 1.289e-03 s (33.07 %) - cleaned-up arrays in 4.697e-05 s (1.20 %) - deduplicated arrays in 3.600e-05 s (0.92 %) + converted COO to RSB in 6.370e-03 s (100.00 %) + analyzed arrays in 3.239e-03 s (50.85 %) + cleaned-up arrays in 1.001e-05 s (0.16 %) + deduplicated arrays in 6.914e-06 s (0.11 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.513e-03 s (64.47 %) - memory allocations took 6.199e-06 s (0.16 %) - leafs setup took 9.537e-07 s (0.02 %) - halfword conversion took 5.007e-06 s (0.13 %) -Built (100 x 100)[0xaaaaed917110]{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' + shuffled partitions in 3.106e-03 s (48.76 %) + memory allocations took 2.861e-06 s (0.04 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 2.861e-06 s (0.04 %) +Built (100 x 100)[0xaaaadbad7160]{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 = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5437,16 +5473,16 @@ # 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 6.951e-03 s (100.00 %) - analyzed arrays in 1.883e-03 s (27.09 %) - cleaned-up arrays in 9.060e-06 s (0.13 %) - deduplicated arrays in 7.868e-06 s (0.11 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.619e-03 s (37.68 %) - memory allocations took 3.815e-06 s (0.05 %) - leafs setup took 2.861e-06 s (0.04 %) - halfword conversion took 2.424e-03 s (34.87 %) -Built (100 x 100)[0xaaaaed90cc90]{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' + converted COO to RSB in 1.230e-02 s (100.00 %) + analyzed arrays in 4.096e-03 s (33.30 %) + cleaned-up arrays in 8.106e-06 s (0.07 %) + deduplicated arrays in 6.914e-06 s (0.06 %) + sorted arrays in 9.537e-07 s (0.01 %) + shuffled partitions in 4.097e-03 s (33.31 %) + memory allocations took 9.537e-07 s (0.01 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 4.089e-03 s (33.24 %) +Built (100 x 100)[0xaaaadbaccca0]{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 @@ -5492,9 +5528,9 @@ # 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 0.003095s; avg 0.001032s ( +/- 39.24/ 24.47 %); best 0.0006268s; worst 0.001284s; std dev. 0.0002892 (taking best). -Reference operation time is 0.000626802 s (32.23 Mflops) with 1 threads. -Challenging best inner round reference (3.8147e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.000626802 s/0 threads (speedup 0.0608596 x), same?n. +3 iterations (1 th.) took 0.006017s; avg 0.002006s ( +/- 27.55/ 22.90 %); best 0.001453s; worst 0.002465s; std dev. 0.0004183 (taking best). +Reference operation time is 0.00145316 s (13.9 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00145316 s/0 threads (speedup 0.00410172 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 @@ -5528,16 +5564,16 @@ # 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 6.897e-03 s (100.00 %) - analyzed arrays in 2.965e-03 s (42.99 %) - cleaned-up arrays in 2.503e-05 s (0.36 %) - deduplicated arrays in 2.193e-05 s (0.32 %) + converted COO to RSB in 1.309e-02 s (100.00 %) + analyzed arrays in 5.049e-03 s (38.57 %) + cleaned-up arrays in 9.060e-06 s (0.07 %) + deduplicated arrays in 8.106e-06 s (0.06 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.247e-03 s (32.58 %) - memory allocations took 5.007e-06 s (0.07 %) - leafs setup took 3.099e-06 s (0.04 %) - halfword conversion took 1.629e-03 s (23.62 %) -Built (100 x 100)[0xaaaaed90d680]{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' + shuffled partitions in 4.331e-03 s (33.09 %) + memory allocations took 2.861e-06 s (0.02 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 3.688e-03 s (28.17 %) +Built (100 x 100)[0xaaaadbacd690]{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 @@ -5583,9 +5619,9 @@ # 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 0.002284s; avg 0.0007613s ( +/- 13.57/ 7.07 %); best 0.000658s; worst 0.0008152s; std dev. 7.308e-05 (taking best). -Reference operation time is 0.000658035 s (30.7 Mflops) with 1 threads. -Challenging best inner round reference (3.8147e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.000658035 s/0 threads (speedup 0.057971 x), same?n. +3 iterations (1 th.) took 0.006083s; avg 0.002028s ( +/- 28.53/ 22.36 %); best 0.001449s; worst 0.002481s; std dev. 0.0004305 (taking best). +Reference operation time is 0.00144911 s (13.94 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.00144911 s/0 threads (speedup 0.0041132 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 @@ -5619,16 +5655,16 @@ # 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 5.268e-03 s (100.00 %) - analyzed arrays in 1.945e-03 s (36.92 %) - cleaned-up arrays in 2.503e-05 s (0.48 %) - deduplicated arrays in 2.217e-05 s (0.42 %) + converted COO to RSB in 1.319e-02 s (100.00 %) + analyzed arrays in 5.610e-03 s (42.54 %) + cleaned-up arrays in 9.060e-06 s (0.07 %) + deduplicated arrays in 8.106e-06 s (0.06 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.646e-03 s (31.25 %) - memory allocations took 4.768e-06 s (0.09 %) - leafs setup took 3.815e-06 s (0.07 %) - halfword conversion took 1.621e-03 s (30.77 %) -Built (100 x 100)[0xaaaaed917230]{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: 24, symflags:'LS' + shuffled partitions in 3.925e-03 s (29.76 %) + memory allocations took 3.815e-06 s (0.03 %) + leafs setup took 1.907e-06 s (0.01 %) + halfword conversion took 3.629e-03 s (27.52 %) +Built (100 x 100)[0xaaaadbad7280]{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' # 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 @@ -5674,10 +5710,10 @@ # 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 0.002266s; avg 0.0007554s ( +/- 15.13/ 7.91 %); best 0.0006411s; worst 0.0008152s; std dev. 8.084e-05 (taking best). -Reference operation time is 0.000641108 s (31.51 Mflops) with 1 threads. -Challenging best inner round reference (3.8147e-05 s/1 threads) with: subdivision 1, 24 leaves, 2.306 bytes/nz, 0.000641108 s/0 threads (speedup 0.0595017 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 33 subms, 24 lsubms, 2.3057 bpnz +3 iterations (1 th.) took 0.005294s; avg 0.001765s ( +/- 15.18/ 11.02 %); best 0.001497s; worst 0.001959s; std dev. 0.0001957 (taking best). +Reference operation time is 0.00149679 s (13.5 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 1, 25 leaves, 2.317 bytes/nz, 0.00149679 s/0 threads (speedup 0.00398216 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 # 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 @@ -5710,16 +5746,16 @@ # 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 5.299e-03 s (100.00 %) - analyzed arrays in 1.973e-03 s (37.24 %) - cleaned-up arrays in 2.289e-05 s (0.43 %) - deduplicated arrays in 2.003e-05 s (0.38 %) + converted COO to RSB in 1.132e-02 s (100.00 %) + analyzed arrays in 4.494e-03 s (39.69 %) + cleaned-up arrays in 9.060e-06 s (0.08 %) + deduplicated arrays in 8.106e-06 s (0.07 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.655e-03 s (31.23 %) - memory allocations took 5.007e-06 s (0.09 %) - leafs setup took 2.861e-06 s (0.05 %) - halfword conversion took 1.619e-03 s (30.55 %) -Built (100 x 100)[0xaaaaed93dea0]{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' + shuffled partitions in 2.942e-03 s (25.98 %) + memory allocations took 2.861e-06 s (0.03 %) + leafs setup took 1.907e-06 s (0.02 %) + halfword conversion took 3.866e-03 s (34.14 %) +Built (100 x 100)[0xaaaadbafdf20]{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 @@ -5765,9 +5801,9 @@ # 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 0.00234s; avg 0.0007799s ( +/- 10.65/ 5.89 %); best 0.0006969s; worst 0.0008259s; std dev. 5.883e-05 (taking best). -Reference operation time is 0.000696898 s (28.99 Mflops) with 1 threads. -Challenging best inner round reference (3.8147e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000696898 s/0 threads (speedup 0.0547383 x), same?n. +3 iterations (1 th.) took 0.004896s; avg 0.001632s ( +/- 3.80/ 3.62 %); best 0.00157s; worst 0.001691s; std dev. 4.949e-05 (taking best). +Reference operation time is 0.00156999 s (12.87 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00156999 s/0 threads (speedup 0.00379651 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 @@ -5801,16 +5837,16 @@ # 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 5.762e-03 s (100.00 %) - analyzed arrays in 2.041e-03 s (35.42 %) - cleaned-up arrays in 1.907e-05 s (0.33 %) - deduplicated arrays in 1.693e-05 s (0.29 %) + converted COO to RSB in 1.016e-02 s (100.00 %) + analyzed arrays in 3.988e-03 s (39.23 %) + cleaned-up arrays in 9.060e-06 s (0.09 %) + deduplicated arrays in 6.914e-06 s (0.07 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.029e-03 s (35.21 %) - memory allocations took 5.960e-06 s (0.10 %) - leafs setup took 6.199e-06 s (0.11 %) - halfword conversion took 1.644e-03 s (28.53 %) -Built (100 x 100)[0xaaaaed93dea0]{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' + shuffled partitions in 2.650e-03 s (26.07 %) + memory allocations took 5.007e-06 s (0.05 %) + leafs setup took 3.099e-06 s (0.03 %) + halfword conversion took 3.503e-03 s (34.46 %) +Built (100 x 100)[0xaaaadbafdf20]{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 @@ -5856,11 +5892,11 @@ # 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 0.00647s; avg 0.002157s ( +/- 74.92/136.06 %); best 0.000541s; worst 0.005091s; std dev. 0.002078 (taking best). -Reference operation time is 0.000540972 s (37.34 Mflops) with 1 threads. -Challenging best inner round reference (3.8147e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000540972 s/0 threads (speedup 0.0705156 x), same?n. +3 iterations (1 th.) took 0.004358s; avg 0.001453s ( +/- 36.12/ 30.25 %); best 0.0009279s; worst 0.001892s; std dev. 0.0003982 (taking best). +Reference operation time is 0.000927925 s (21.77 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000927925 s/0 threads (speedup 0.00642343 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: 529.531 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 3389 Mflops. # 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 @@ -5876,23 +5912,23 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.053242 s (eq. to 1e+03/ 1e+03 old/new op.times), gained local/global speedup 1 x (3.8147e-05 : 3.8147e-05) / 1 x (3.8147e-05 : 3.8147e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.0946119 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1 x (5.96046e-06 : 5.96046e-06) / 1 x (5.96046e-06 : 5.96046e-06). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.053s, 0.036s for constructor, 0 clones) obtained NO speedup (best stays 529.5 Mflops). -Second run of RSB Autotuner took 0.053303 s and estimated a speedup of 1.000000 x (3.815e-05 s -> 3.815e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.095s, 0.068s for constructor, 0 clones) obtained NO speedup (best stays 3389 Mflops). +Second run of RSB Autotuner took 0.0946321 s and estimated a speedup of 1.000000 x (5.960e-06 s -> 5.960e-06 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 0.002425 0.005029 0.007454 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.007454 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.002425 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005029 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.005105 0.009110 0.014215 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.014215 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005105 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.009110 %: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 0.007454 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.014215 %: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 @@ -5907,34 +5943,34 @@ %: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 0.010026 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.0197592 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.00242496 0 0.00502896 -# so far, program took 5.595s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.089s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00510502 0 0.00911021 +# so far, program took 5.511s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.147s/0.000s . getrusage() stats: -ru_maxrss: 8 (maximum resident set size -- MB) -ru_stime : 0.03642s (system CPU time used) -ru_utime : 6.008s (user CPU time used) +ru_maxrss: 6 (maximum resident set size -- MB) +ru_stime : 0.05589s (system CPU time used) +ru_utime : 5.805s (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 5.595s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.089s/0.000s . +# so far, program took 5.511s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.147s/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 7.491e-03 s (100.00 %) - analyzed arrays in 1.079e-03 s (14.40 %) - cleaned-up arrays in 1.693e-05 s (0.23 %) - deduplicated arrays in 1.407e-05 s (0.19 %) + converted COO to RSB in 9.518e-03 s (100.00 %) + analyzed arrays in 1.570e-03 s (16.50 %) + cleaned-up arrays in 9.060e-06 s (0.10 %) + deduplicated arrays in 7.868e-06 s (0.08 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.154e-03 s (55.45 %) - memory allocations took 5.960e-06 s (0.08 %) + shuffled partitions in 5.933e-03 s (62.33 %) + memory allocations took 4.053e-06 s (0.04 %) leafs setup took 9.537e-07 s (0.01 %) - halfword conversion took 2.219e-03 s (29.62 %) -Built (100 x 100)[0xaaaaed917230]{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 0.008s): (100 x 100)[0xaaaaed917230]{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' + halfword conversion took 1.992e-03 s (20.93 %) +Built (100 x 100)[0xaaaadbad7280]{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 0.010s): (100 x 100)[0xaaaadbad7280]{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. @@ -5985,10 +6021,10 @@ # 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 0.003333s; avg 0.001111s ( +/- 1.18/ 1.35 %); best 0.001098s; worst 0.001126s; std dev. 1.156e-05 (taking best). -Reference operation time is 0.00109792 s (18.4 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: 0.001098 Mflops: 18.398) -Merge (3 -> 1 leaves) took w.c.t. of 6.413e-05s, ~5.794e-05s of computing time (of which 2.885e-05s sorting, 1.192e-06s analysis) +3 iterations (1 th.) took 0.00372s; avg 0.00124s ( +/- 17.50/ 16.84 %); best 0.001023s; worst 0.001449s; std dev. 0.0001739 (taking best). +Reference operation time is 0.00102305 s (19.74 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: 0.001023 Mflops: 19.745) +Merge (3 -> 1 leaves) took w.c.t. of 3.695e-05s, ~3.219e-05s of computing time (of which 1.216e-05s sorting, 9.537e-07s analysis) # 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 @@ -6019,8 +6055,8 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 3.004e-05s; avg 1.001e-05s ( +/- 9.52/ 9.52 %); best 9.06e-06s; worst 1.097e-05s; std dev. 7.787e-07 (taking best). -Reference operation time is 9.05991e-06 s (2230 Mflops) with 1 threads. +3 iterations (1 th.) took 1.884e-05s; avg 6.278e-06s ( +/- 5.06/ 10.13 %); best 5.96e-06s; worst 6.914e-06s; std dev. 4.496e-07 (taking best). +Reference operation time is 5.96046e-06 s (3389 Mflops) with 1 threads. # 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 @@ -6036,16 +6072,16 @@ # 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: 9.06e-06 s ~Mflops: 2229.604 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 121.184x: 0.001098s -> 9.06e-06s, so taking this instance. +After merge step 1: tpop: 5.96e-06 s ~Mflops: 3388.998 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 171.640x: 0.001023s -> 5.96e-06s, 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 0.01407s (of which 6.795e-05s partitioning, 0.009729s I/O); computing times: 5.794e-05s in par. loops, 2.885e-05s sorting, 1.192e-06s analyzing) -Total merge + benchmarking process took 0.01407s, equivalent to 1552.9/12.8 new/old ops (0.006741s for 2 clones -- as 744.1/6.1 ops, or 372.0/3.1 ops per clone), SPEEDUP of 121.184x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 121.184x (0.001098s -> 9.06e-06s), will amortize in 12.9 ops by saving 0.001089s per op. -In 1 tuning rounds (tot. 0.021s, 0.0067s for constructor, 2 clones) obtained a SPEEDUP of 12018.4% (121.2x) (from 18.4 to 2230 Mflops). Employed 0.0097s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01567s (of which 3.982e-05s partitioning, 0.01091s I/O); computing times: 3.219e-05s in par. loops, 1.216e-05s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.01567s, equivalent to 2628.8/15.3 new/old ops (0.008889s for 2 clones -- as 1491.3/8.7 ops, or 745.7/4.3 ops per clone), SPEEDUP of 171.640x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 171.640x (0.001023s -> 5.96e-06s), will amortize in 15.4 ops by saving 0.001017s per op. +In 1 tuning rounds (tot. 0.024s, 0.0089s for constructor, 2 clones) obtained a SPEEDUP of 17064.0% (171.6x) (from 19.74 to 3389 Mflops). Employed 0.0099s 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 0.0303771 s (1.098e-03 s -> 9.060e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.033761 s (1.023e-03 s -> 5.960e-06 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 @@ -6111,20 +6147,20 @@ # 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 2.98e-05s; avg 9.934e-06s ( +/- 11.20/ 10.40 %); best 8.821e-06s; worst 1.097e-05s; std dev. 8.778e-07 (taking best). -Reference operation time is 8.82149e-06 s (2290 Mflops) with 1 threads. +3 iterations (1 th.) took 2.313e-05s; avg 7.709e-06s ( +/- 22.68/ 45.36 %); best 5.96e-06s; worst 1.121e-05s; std dev. 2.473e-06 (taking best). +Reference operation time is 5.96046e-06 s (3389 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 6.872e-03 s (100.00 %) - analyzed arrays in 2.568e-03 s (37.37 %) - cleaned-up arrays in 1.502e-05 s (0.22 %) - deduplicated arrays in 1.311e-05 s (0.19 %) + converted COO to RSB in 4.646e-03 s (100.00 %) + analyzed arrays in 1.489e-03 s (32.05 %) + cleaned-up arrays in 1.001e-05 s (0.22 %) + deduplicated arrays in 8.106e-06 s (0.17 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.260e-03 s (61.99 %) - memory allocations took 5.007e-06 s (0.07 %) - leafs setup took 4.053e-06 s (0.06 %) - halfword conversion took 5.960e-06 s (0.09 %) -Built (100 x 100)[0xaaaaed917110]{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' + shuffled partitions in 3.092e-03 s (66.55 %) + memory allocations took 4.292e-05 s (0.92 %) + leafs setup took 9.537e-07 s (0.02 %) + halfword conversion took 2.146e-06 s (0.05 %) +Built (100 x 100)[0xaaaadbad7160]{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 = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6158,16 +6194,16 @@ # 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 1.419e-02 s (100.00 %) - analyzed arrays in 9.784e-03 s (68.97 %) - cleaned-up arrays in 2.599e-05 s (0.18 %) - deduplicated arrays in 2.193e-05 s (0.15 %) + converted COO to RSB in 4.260e-03 s (100.00 %) + analyzed arrays in 2.795e-03 s (65.61 %) + cleaned-up arrays in 8.821e-06 s (0.21 %) + deduplicated arrays in 8.106e-06 s (0.19 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.340e-03 s (30.59 %) - memory allocations took 5.960e-06 s (0.04 %) - leafs setup took 2.861e-06 s (0.02 %) - halfword conversion took 4.053e-06 s (0.03 %) -Built (100 x 100)[0xaaaaed90d680]{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' + shuffled partitions in 1.442e-03 s (33.85 %) + memory allocations took 2.146e-06 s (0.05 %) + leafs setup took 1.192e-06 s (0.03 %) + halfword conversion took 1.907e-06 s (0.04 %) +Built (100 x 100)[0xaaaadbacd690]{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 @@ -6213,9 +6249,10 @@ # 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 2.313e-05s; avg 7.709e-06s ( +/- 22.68/ 45.36 %); best 5.96e-06s; worst 1.121e-05s; std dev. 2.473e-06 (taking best). +3 iterations (1 th.) took 2.289e-05s; avg 7.629e-06s ( +/- 21.88/ 43.75 %); best 5.96e-06s; worst 1.097e-05s; std dev. 2.36e-06 (taking best). Reference operation time is 5.96046e-06 s (3389 Mflops) with 1 threads. -Challenging best inner round reference (8.82149e-06 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 5.96046e-06 s/0 threads (speedup 1.48 x), same?n. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 5.96046e-06 s/0 threads (speedup 1 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 @@ -6248,16 +6285,16 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 9.792e-03 s (100.00 %) - analyzed arrays in 5.035e-03 s (51.42 %) - cleaned-up arrays in 9.060e-06 s (0.09 %) - deduplicated arrays in 7.868e-06 s (0.08 %) + converted COO to RSB in 9.119e-03 s (100.00 %) + analyzed arrays in 3.678e-03 s (40.33 %) + cleaned-up arrays in 7.868e-06 s (0.09 %) + deduplicated arrays in 8.106e-06 s (0.09 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.337e-03 s (23.87 %) - memory allocations took 3.815e-06 s (0.04 %) - leafs setup took 5.960e-06 s (0.06 %) - halfword conversion took 2.392e-03 s (24.43 %) -Built (100 x 100)[0xaaaaed917230]{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' + shuffled partitions in 2.699e-03 s (29.60 %) + memory allocations took 2.384e-06 s (0.03 %) + leafs setup took 2.146e-06 s (0.02 %) + halfword conversion took 2.721e-03 s (29.84 %) +Built (100 x 100)[0xaaaadbacd690]{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 @@ -6303,9 +6340,9 @@ # 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 0.003606s; avg 0.001202s ( +/- 49.34/ 42.92 %); best 0.0006089s; worst 0.001718s; std dev. 0.000456 (taking best). -Reference operation time is 0.000608921 s (33.17 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/0 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 0.000608921 s/0 threads (speedup 0.00978857 x), same?n. +3 iterations (1 th.) took 0.004099s; avg 0.001366s ( +/- 20.29/ 34.96 %); best 0.001089s; worst 0.001844s; std dev. 0.0003392 (taking best). +Reference operation time is 0.0010891 s (18.55 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 0.0010891 s/0 threads (speedup 0.00547285 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 # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6339,16 +6376,16 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 8.477e-03 s (100.00 %) - analyzed arrays in 3.651e-03 s (43.07 %) - cleaned-up arrays in 2.599e-05 s (0.31 %) - deduplicated arrays in 2.193e-05 s (0.26 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.888e-03 s (22.27 %) - memory allocations took 5.960e-06 s (0.07 %) - leafs setup took 4.053e-06 s (0.05 %) - halfword conversion took 2.879e-03 s (33.96 %) -Built (100 x 100)[0xaaaaed917230]{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 9.135e-03 s (100.00 %) + analyzed arrays in 3.235e-03 s (35.41 %) + cleaned-up arrays in 9.060e-06 s (0.10 %) + deduplicated arrays in 6.914e-06 s (0.08 %) + sorted arrays in 9.537e-07 s (0.01 %) + shuffled partitions in 3.344e-03 s (36.61 %) + memory allocations took 4.053e-06 s (0.04 %) + leafs setup took 1.907e-06 s (0.02 %) + halfword conversion took 2.533e-03 s (27.73 %) +Built (100 x 100)[0xaaaadbad7280]{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' # 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 @@ -6394,9 +6431,9 @@ # 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 0.003276s; avg 0.001092s ( +/- 12.27/ 21.62 %); best 0.000958s; worst 0.001328s; std dev. 0.0001674 (taking best). -Reference operation time is 0.000957966 s (21.09 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/0 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 0.000957966 s/0 threads (speedup 0.006222 x), same?n. +3 iterations (1 th.) took 0.003731s; avg 0.001244s ( +/- 31.01/ 28.73 %); best 0.0008581s; worst 0.001601s; std dev. 0.000304 (taking best). +Reference operation time is 0.000858068 s (23.54 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 0.000858068 s/0 threads (speedup 0.00694637 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 # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6430,16 +6467,16 @@ # 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 6.909e-03 s (100.00 %) - analyzed arrays in 2.232e-03 s (32.31 %) - cleaned-up arrays in 1.812e-05 s (0.26 %) - deduplicated arrays in 1.502e-05 s (0.22 %) + converted COO to RSB in 8.467e-03 s (100.00 %) + analyzed arrays in 3.474e-03 s (41.03 %) + cleaned-up arrays in 9.060e-06 s (0.11 %) + deduplicated arrays in 7.868e-06 s (0.09 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.251e-03 s (32.58 %) - memory allocations took 3.815e-06 s (0.06 %) - leafs setup took 5.007e-06 s (0.07 %) - halfword conversion took 2.383e-03 s (34.49 %) -Built (100 x 100)[0xaaaaed917230]{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' + shuffled partitions in 2.494e-03 s (29.45 %) + memory allocations took 3.099e-06 s (0.04 %) + leafs setup took 2.146e-06 s (0.03 %) + halfword conversion took 2.476e-03 s (29.24 %) +Built (100 x 100)[0xaaaadbad7280]{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 @@ -6485,9 +6522,9 @@ # 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 0.002751s; avg 0.000917s ( +/- 41.89/ 30.89 %); best 0.0005329s; worst 0.0012s; std dev. 0.0002816 (taking best). -Reference operation time is 0.000532866 s (37.91 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/0 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000532866 s/0 threads (speedup 0.0111857 x), same?n. +3 iterations (1 th.) took 0.003787s; avg 0.001262s ( +/- 31.80/ 30.87 %); best 0.0008609s; worst 0.001652s; std dev. 0.0003231 (taking best). +Reference operation time is 0.000860929 s (23.46 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000860929 s/0 threads (speedup 0.00692329 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 @@ -6521,16 +6558,16 @@ # 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 6.743e-03 s (100.00 %) - analyzed arrays in 2.417e-03 s (35.85 %) - cleaned-up arrays in 2.003e-05 s (0.30 %) - deduplicated arrays in 1.693e-05 s (0.25 %) + converted COO to RSB in 7.718e-03 s (100.00 %) + analyzed arrays in 2.712e-03 s (35.14 %) + cleaned-up arrays in 9.060e-06 s (0.12 %) + deduplicated arrays in 7.868e-06 s (0.10 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.100e-03 s (31.14 %) - memory allocations took 5.960e-06 s (0.09 %) - leafs setup took 4.053e-06 s (0.06 %) - halfword conversion took 2.179e-03 s (32.31 %) -Built (100 x 100)[0xaaaaed938fb0]{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' + shuffled partitions in 2.491e-03 s (32.27 %) + memory allocations took 4.292e-06 s (0.06 %) + leafs setup took 1.907e-06 s (0.02 %) + halfword conversion took 2.491e-03 s (32.27 %) +Built (100 x 100)[0xaaaadbaea360]{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 @@ -6576,11 +6613,11 @@ # 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 0.003128s; avg 0.001043s ( +/- 4.58/ 5.89 %); best 0.0009949s; worst 0.001104s; std dev. 4.561e-05 (taking best). -Reference operation time is 0.000994921 s (20.3 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/0 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000994921 s/0 threads (speedup 0.00599089 x), same?n. +3 iterations (1 th.) took 0.003583s; avg 0.001194s ( +/- 29.09/ 56.41 %); best 0.0008469s; worst 0.001868s; std dev. 0.0004765 (taking best). +Reference operation time is 0.000846863 s (23.85 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000846863 s/0 threads (speedup 0.00703829 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 -Best sparse multiply performance with subdivision multiplier of 0.25: 3389 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 3389 Mflops. # 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 @@ -6596,23 +6633,23 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.066829 s (eq. to 8e+03/ 1e+04 old/new op.times), gained local/global speedup 1.48 x (8.82149e-06 : 5.96046e-06) / 1.48 x (8.82149e-06 : 5.96046e-06). This is amortizable in 23359 op.times. -In 1 tuning rounds (tot. 0.067s, 0.053s for constructor, 0 clones) obtained a SPEEDUP of 48.0% (1.48x) (from 2290 to 3389 Mflops). -Second run of RSB Autotuner took 0.0668621 s and estimated a speedup of 1.480000 x (8.821e-06 s -> 5.960e-06 s per op) in new matrix (1 -> 1 lsubm) -RSB Autotuner suggested a new matrix: freeing the old one. +Last tuner inner round (1 of 1) took 0.0600269 s (eq. to 1e+04/ 1e+04 old/new op.times), gained local/global speedup 1 x (5.96046e-06 : 5.96046e-06) / 1 x (5.96046e-06 : 5.96046e-06). This is not amortizable ! +Auto tuning inner round 1 did not find a configuration better than the original. +In 1 tuning rounds (tot. 0.06s, 0.044s for constructor, 0 clones) obtained NO speedup (best stays 3389 Mflops). +Second run of RSB Autotuner took 0.06005 s and estimated a speedup of 1.000000 x (5.960e-06 s -> 5.960e-06 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 0.001079 0.004154 0.005233 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005233 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.001079 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.004154 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.001570 0.005933 0.007503 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.007503 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.001570 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005933 %: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 0.005233 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.007503 %: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 @@ -6627,34 +6664,34 @@ %: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 0.00749111 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.00951815 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.00107908 0 0.00415397 -# so far, program took 5.707s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.187s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00157022 0 0.00593305 +# so far, program took 5.622s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.241s/0.000s . getrusage() stats: -ru_maxrss: 8 (maximum resident set size -- MB) -ru_stime : 0.03665s (system CPU time used) -ru_utime : 6.654s (user CPU time used) +ru_maxrss: 6 (maximum resident set size -- MB) +ru_stime : 0.05991s (system CPU time used) +ru_utime : 6.129s (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 5.707s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.187s/0.000s . +# so far, program took 5.622s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.241s/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 7.850e-03 s (100.00 %) - analyzed arrays in 1.958e-03 s (24.94 %) - cleaned-up arrays in 1.979e-05 s (0.25 %) - deduplicated arrays in 1.812e-05 s (0.23 %) + converted COO to RSB in 8.971e-03 s (100.00 %) + analyzed arrays in 1.292e-03 s (14.40 %) + cleaned-up arrays in 9.060e-06 s (0.10 %) + deduplicated arrays in 6.914e-06 s (0.08 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.888e-03 s (49.53 %) - memory allocations took 4.053e-06 s (0.05 %) - leafs setup took 1.192e-06 s (0.02 %) - halfword conversion took 1.960e-03 s (24.97 %) -Built (100 x 100)[0xaaaaed917230]{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 0.008s): (100 x 100)[0xaaaaed917230]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + shuffled partitions in 5.188e-03 s (57.83 %) + memory allocations took 2.861e-06 s (0.03 %) + leafs setup took 1.907e-06 s (0.02 %) + halfword conversion took 2.468e-03 s (27.51 %) +Built (100 x 100)[0xaaaadbad7280]{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 0.009s): (100 x 100)[0xaaaadbad7280]{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. @@ -6705,10 +6742,10 @@ # 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 0.002497s; avg 0.0008323s ( +/- 22.74/ 16.53 %); best 0.000643s; worst 0.0009699s; std dev. 0.0001384 (taking best). -Reference operation time is 0.000643015 s (125.7 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: 0.000643 Mflops: 125.658) -Merge (3 -> 1 leaves) took w.c.t. of 6.39e-05s, ~5.484e-05s of computing time (of which 2.408e-05s sorting, 1.907e-06s analysis) +3 iterations (1 th.) took 0.003619s; avg 0.001206s ( +/- 10.89/ 6.36 %); best 0.001075s; worst 0.001283s; std dev. 9.333e-05 (taking best). +Reference operation time is 0.00107503 s (75.16 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: 0.001075 Mflops: 75.161) +Merge (3 -> 1 leaves) took w.c.t. of 4.482e-05s, ~3.815e-05s of computing time (of which 1.907e-05s sorting, 1.907e-06s analysis) # 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 @@ -6739,8 +6776,8 @@ # 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 0.0001152s; avg 3.839e-05s ( +/- 6.21/ 9.94 %); best 3.6e-05s; worst 4.22e-05s; std dev. 2.725e-06 (taking best). -Reference operation time is 3.60012e-05 s (2244 Mflops) with 1 threads. +3 iterations (1 th.) took 6.914e-05s; avg 2.305e-05s ( +/- 13.10/ 22.07 %); best 2.003e-05s; worst 2.813e-05s; std dev. 3.618e-06 (taking best). +Reference operation time is 2.00272e-05 s (4035 Mflops) with 1 threads. # 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 @@ -6756,16 +6793,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -After merge step 1: tpop: 3.6e-05 s ~Mflops: 2244.369 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 17.861x: 0.000643s -> 3.6e-05s, so taking this instance. +After merge step 1: tpop: 2.003e-05 s ~Mflops: 4034.521 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 53.679x: 0.001075s -> 2.003e-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 0.01223s (of which 6.7e-05s partitioning, 0.009437s I/O); computing times: 5.484e-05s in par. loops, 2.408e-05s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.01223s, equivalent to 339.8/19.0 new/old ops (0.005471s for 2 clones -- as 152.0/8.5 ops, or 76.0/4.3 ops per clone), SPEEDUP of 17.861x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 17.861x (0.000643s -> 3.6e-05s), will amortize in 20.2 ops by saving 0.000607s per op. -In 1 tuning rounds (tot. 0.018s, 0.0055s for constructor, 2 clones) obtained a SPEEDUP of 1686.1% (17.86x) (from 125.7 to 2244 Mflops). Employed 0.0096s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01308s (of which 4.601e-05s partitioning, 0.009151s I/O); computing times: 3.815e-05s in par. loops, 1.907e-05s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.01308s, equivalent to 652.9/12.2 new/old ops (0.007417s for 2 clones -- as 370.3/6.9 ops, or 185.2/3.4 ops per clone), SPEEDUP of 53.679x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 53.679x (0.001075s -> 2.003e-05s), will amortize in 12.4 ops by saving 0.001055s per op. +In 1 tuning rounds (tot. 0.02s, 0.0074s for constructor, 2 clones) obtained a SPEEDUP of 5267.9% (53.68x) (from 75.16 to 4035 Mflops). Employed 0.0097s 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 0.0275631 s (6.430e-04 s -> 3.600e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0301421 s (1.075e-03 s -> 2.003e-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 @@ -6831,20 +6868,20 @@ # 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 0.0001161s; avg 3.87e-05s ( +/- 6.98/ 10.88 %); best 3.6e-05s; worst 4.292e-05s; std dev. 3.018e-06 (taking best). -Reference operation time is 3.60012e-05 s (2244 Mflops) with 1 threads. +3 iterations (1 th.) took 6.39e-05s; avg 2.13e-05s ( +/- 11.57/ 17.54 %); best 1.884e-05s; worst 2.503e-05s; std dev. 2.686e-06 (taking best). +Reference operation time is 1.88351e-05 s (4290 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 8.527e-03 s (100.00 %) - analyzed arrays in 6.983e-03 s (81.89 %) - cleaned-up arrays in 1.717e-05 s (0.20 %) - deduplicated arrays in 1.383e-05 s (0.16 %) + converted COO to RSB in 3.772e-03 s (100.00 %) + analyzed arrays in 1.257e-03 s (33.32 %) + cleaned-up arrays in 9.060e-06 s (0.24 %) + deduplicated arrays in 6.914e-06 s (0.18 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.505e-03 s (17.65 %) - memory allocations took 4.053e-06 s (0.05 %) - leafs setup took 9.537e-07 s (0.01 %) - halfword conversion took 3.099e-06 s (0.04 %) -Built (100 x 100)[0xaaaaed917110]{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' + shuffled partitions in 2.495e-03 s (66.15 %) + memory allocations took 2.146e-06 s (0.06 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 1.907e-06 s (0.05 %) +Built (100 x 100)[0xaaaadbad7160]{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 = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6878,16 +6915,16 @@ # 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 7.824e-03 s (100.00 %) - analyzed arrays in 1.080e-03 s (13.80 %) - cleaned-up arrays in 1.907e-05 s (0.24 %) - deduplicated arrays in 1.502e-05 s (0.19 %) + converted COO to RSB in 7.040e-03 s (100.00 %) + analyzed arrays in 2.472e-03 s (35.11 %) + cleaned-up arrays in 8.821e-06 s (0.13 %) + deduplicated arrays in 7.153e-06 s (0.10 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.599e-03 s (20.44 %) - memory allocations took 2.861e-06 s (0.04 %) - leafs setup took 9.537e-07 s (0.01 %) - halfword conversion took 5.106e-03 s (65.26 %) -Built (100 x 100)[0xaaaaed917230]{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' + shuffled partitions in 2.492e-03 s (35.40 %) + memory allocations took 9.537e-07 s (0.01 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 2.059e-03 s (29.25 %) +Built (100 x 100)[0xaaaadbacda60]{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 @@ -6933,9 +6970,9 @@ # 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 0.002885s; avg 0.0009617s ( +/- 25.23/ 13.87 %); best 0.0007191s; worst 0.001095s; std dev. 0.0001718 (taking best). -Reference operation time is 0.00071907 s (112.4 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00071907 s/0 threads (speedup 0.0500663 x), same?n. +3 iterations (1 th.) took 0.003795s; avg 0.001265s ( +/- 31.70/ 47.34 %); best 0.000864s; worst 0.001864s; std dev. 0.0004315 (taking best). +Reference operation time is 0.000864029 s (93.52 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.000864029 s/0 threads (speedup 0.0217991 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 @@ -6969,16 +7006,16 @@ # 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 6.543e-03 s (100.00 %) - analyzed arrays in 1.931e-03 s (29.51 %) - cleaned-up arrays in 1.979e-05 s (0.30 %) - deduplicated arrays in 1.717e-05 s (0.26 %) + converted COO to RSB in 7.885e-03 s (100.00 %) + analyzed arrays in 2.895e-03 s (36.72 %) + cleaned-up arrays in 9.060e-06 s (0.11 %) + deduplicated arrays in 7.868e-06 s (0.10 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.932e-03 s (29.53 %) - memory allocations took 5.245e-06 s (0.08 %) - leafs setup took 2.146e-06 s (0.03 %) - halfword conversion took 2.635e-03 s (40.27 %) -Built (100 x 100)[0xaaaaed917230]{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' + shuffled partitions in 2.490e-03 s (31.58 %) + memory allocations took 9.537e-07 s (0.01 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 2.481e-03 s (31.46 %) +Built (100 x 100)[0xaaaadbad7280]{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 @@ -7024,9 +7061,9 @@ # 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 0.002369s; avg 0.0007896s ( +/- 39.58/ 25.60 %); best 0.0004771s; worst 0.0009918s; std dev. 0.0002242 (taking best). -Reference operation time is 0.000477076 s (169.4 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.000477076 s/0 threads (speedup 0.0754623 x), same?n. +3 iterations (1 th.) took 0.004425s; avg 0.001475s ( +/- 41.63/ 27.79 %); best 0.0008609s; worst 0.001885s; std dev. 0.0004423 (taking best). +Reference operation time is 0.000860929 s (93.85 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.000860929 s/0 threads (speedup 0.0218776 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 @@ -7060,16 +7097,16 @@ # 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 6.416e-03 s (100.00 %) - analyzed arrays in 2.892e-03 s (45.07 %) - cleaned-up arrays in 1.693e-05 s (0.26 %) - deduplicated arrays in 1.407e-05 s (0.22 %) + converted COO to RSB in 8.088e-03 s (100.00 %) + analyzed arrays in 3.103e-03 s (38.37 %) + cleaned-up arrays in 8.106e-06 s (0.10 %) + deduplicated arrays in 7.868e-06 s (0.10 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.962e-03 s (30.58 %) - memory allocations took 5.007e-06 s (0.08 %) - leafs setup took 1.907e-06 s (0.03 %) - halfword conversion took 1.523e-03 s (23.74 %) -Built (100 x 100)[0xaaaaed917230]{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: 24, symflags:'LS' + shuffled partitions in 2.488e-03 s (30.76 %) + memory allocations took 2.861e-06 s (0.04 %) + leafs setup took 1.907e-06 s (0.02 %) + halfword conversion took 2.475e-03 s (30.60 %) +Built (100 x 100)[0xaaaadbad7280]{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' # 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 @@ -7115,10 +7152,10 @@ # 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 0.003173s; avg 0.001058s ( +/- 12.92/ 18.66 %); best 0.000921s; worst 0.001255s; std dev. 0.0001429 (taking best). -Reference operation time is 0.000921011 s (87.73 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 1, 24 leaves, 2.306 bytes/nz, 0.000921011 s/0 threads (speedup 0.0390888 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 33 subms, 24 lsubms, 2.3057 bpnz +3 iterations (1 th.) took 0.003616s; avg 0.001205s ( +/- 27.90/ 39.80 %); best 0.000869s; worst 0.001685s; std dev. 0.0003483 (taking best). +Reference operation time is 0.000869036 s (92.98 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 1, 25 leaves, 2.317 bytes/nz, 0.000869036 s/0 threads (speedup 0.0216735 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 # 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 @@ -7151,16 +7188,16 @@ # 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 6.334e-03 s (100.00 %) - analyzed arrays in 2.366e-03 s (37.36 %) - cleaned-up arrays in 1.812e-05 s (0.29 %) - deduplicated arrays in 1.502e-05 s (0.24 %) + converted COO to RSB in 8.304e-03 s (100.00 %) + analyzed arrays in 2.900e-03 s (34.92 %) + cleaned-up arrays in 9.060e-06 s (0.11 %) + deduplicated arrays in 6.914e-06 s (0.08 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.961e-03 s (30.96 %) - memory allocations took 4.768e-06 s (0.08 %) - leafs setup took 4.053e-06 s (0.06 %) - halfword conversion took 1.964e-03 s (31.01 %) -Built (100 x 100)[0xaaaaed93dea0]{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' + shuffled partitions in 2.500e-03 s (30.11 %) + memory allocations took 2.146e-06 s (0.03 %) + leafs setup took 3.099e-06 s (0.04 %) + halfword conversion took 2.883e-03 s (34.72 %) +Built (100 x 100)[0xaaaadbafdf20]{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 @@ -7206,9 +7243,9 @@ # 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 0.003092s; avg 0.001031s ( +/- 26.05/ 32.04 %); best 0.0007622s; worst 0.001361s; std dev. 0.0002483 (taking best). -Reference operation time is 0.000762224 s (106 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000762224 s/0 threads (speedup 0.0472318 x), same?n. +3 iterations (1 th.) took 0.003217s; avg 0.001072s ( +/- 18.29/ 19.08 %); best 0.0008762s; worst 0.001277s; std dev. 0.0001637 (taking best). +Reference operation time is 0.000876188 s (92.22 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000876188 s/0 threads (speedup 0.0214966 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 @@ -7242,16 +7279,16 @@ # 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 5.598e-03 s (100.00 %) - analyzed arrays in 2.134e-03 s (38.12 %) - cleaned-up arrays in 1.717e-05 s (0.31 %) - deduplicated arrays in 1.502e-05 s (0.27 %) + converted COO to RSB in 8.719e-03 s (100.00 %) + analyzed arrays in 3.727e-03 s (42.75 %) + cleaned-up arrays in 9.060e-06 s (0.10 %) + deduplicated arrays in 6.914e-06 s (0.08 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.723e-03 s (30.78 %) - memory allocations took 2.861e-06 s (0.05 %) - leafs setup took 3.099e-06 s (0.06 %) - halfword conversion took 1.702e-03 s (30.40 %) -Built (100 x 100)[0xaaaaed93dea0]{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' + shuffled partitions in 2.496e-03 s (28.63 %) + memory allocations took 3.099e-06 s (0.04 %) + leafs setup took 1.907e-06 s (0.02 %) + halfword conversion took 2.475e-03 s (28.39 %) +Built (100 x 100)[0xaaaadbafdf20]{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 @@ -7297,11 +7334,11 @@ # 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 0.002753s; avg 0.0009177s ( +/- 4.42/ 7.77 %); best 0.0008771s; worst 0.000989s; std dev. 5.057e-05 (taking best). -Reference operation time is 0.000877142 s (92.12 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000877142 s/0 threads (speedup 0.0410438 x), same?n. +3 iterations (1 th.) took 0.003823s; avg 0.001274s ( +/- 32.36/ 48.24 %); best 0.0008619s; worst 0.001889s; std dev. 0.0004431 (taking best). +Reference operation time is 0.000861883 s (93.75 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000861883 s/0 threads (speedup 0.0218534 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: 2244.37 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 4289.87 Mflops. # 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 @@ -7317,23 +7354,23 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.0571651 s (eq. to 2e+03/ 2e+03 old/new op.times), gained local/global speedup 1 x (3.60012e-05 : 3.60012e-05) / 1 x (3.60012e-05 : 3.60012e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.0635519 s (eq. to 3e+03/ 3e+03 old/new op.times), gained local/global speedup 1 x (1.88351e-05 : 1.88351e-05) / 1 x (1.88351e-05 : 1.88351e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.057s, 0.042s for constructor, 0 clones) obtained NO speedup (best stays 2244 Mflops). -Second run of RSB Autotuner took 0.0571961 s and estimated a speedup of 1.000000 x (3.600e-05 s -> 3.600e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.064s, 0.044s for constructor, 0 clones) obtained NO speedup (best stays 4290 Mflops). +Second run of RSB Autotuner took 0.0635731 s and estimated a speedup of 1.000000 x (1.884e-05 s -> 1.884e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:100 0 #norm:10 0 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.001958 0.003888 0.005846 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005846 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.001958 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.003888 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.001292 0.005188 0.006480 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.006480 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.001292 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005188 %: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 0.005846 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.006480 %: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 @@ -7348,34 +7385,34 @@ %: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 0.00784993 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.00897098 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.00195813 0 0.00388789 -# so far, program took 5.804s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.271s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00129199 0 0.00518799 +# so far, program took 5.732s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.335s/0.000s . getrusage() stats: -ru_maxrss: 8 (maximum resident set size -- MB) -ru_stime : 0.05707s (system CPU time used) -ru_utime : 7.215s (user CPU time used) +ru_maxrss: 6 (maximum resident set size -- MB) +ru_stime : 0.06388s (system CPU time used) +ru_utime : 6.449s (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 5.804s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.271s/0.000s . +# so far, program took 5.732s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.335s/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 5.372e-03 s (100.00 %) - analyzed arrays in 6.909e-04 s (12.86 %) - cleaned-up arrays in 1.502e-05 s (0.28 %) - deduplicated arrays in 1.287e-05 s (0.24 %) + converted COO to RSB in 9.578e-03 s (100.00 %) + analyzed arrays in 1.466e-03 s (15.31 %) + cleaned-up arrays in 9.060e-06 s (0.09 %) + deduplicated arrays in 8.106e-06 s (0.08 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.755e-03 s (51.28 %) - memory allocations took 3.099e-06 s (0.06 %) - leafs setup took 9.537e-07 s (0.02 %) - halfword conversion took 1.893e-03 s (35.24 %) -Built (100 x 100)[0xaaaaed917230]{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 0.005s): (100 x 100)[0xaaaaed917230]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + shuffled partitions in 5.618e-03 s (58.65 %) + memory allocations took 3.815e-06 s (0.04 %) + leafs setup took 1.192e-06 s (0.01 %) + halfword conversion took 2.471e-03 s (25.80 %) +Built (100 x 100)[0xaaaadbad7280]{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 0.010s): (100 x 100)[0xaaaadbad7280]{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. @@ -7426,10 +7463,10 @@ # 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 0.001674s; avg 0.000558s ( +/- 2.66/ 3.92 %); best 0.0005431s; worst 0.0005798s; std dev. 1.578e-05 (taking best). -Reference operation time is 0.000543118 s (148.8 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: 0.0005431 Mflops: 148.771) -Merge (3 -> 1 leaves) took w.c.t. of 5.603e-05s, ~4.888e-05s of computing time (of which 2.408e-05s sorting, 9.537e-07s analysis) +3 iterations (1 th.) took 0.004026s; avg 0.001342s ( +/- 19.07/ 24.52 %); best 0.001086s; worst 0.001671s; std dev. 0.0002444 (taking best). +Reference operation time is 0.001086 s (74.4 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: 0.001086 Mflops: 74.402) +Merge (3 -> 1 leaves) took w.c.t. of 4.506e-05s, ~3.886e-05s of computing time (of which 1.884e-05s sorting, 1.907e-06s analysis) # 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 @@ -7460,8 +7497,8 @@ # 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 8.893e-05s; avg 2.964e-05s ( +/- 2.68/ 1.34 %); best 2.885e-05s; worst 3.004e-05s; std dev. 5.62e-07 (taking best). -Reference operation time is 2.88486e-05 s (2801 Mflops) with 1 threads. +3 iterations (1 th.) took 6.008e-05s; avg 2.003e-05s ( +/- 4.76/ 4.76 %); best 1.907e-05s; worst 2.098e-05s; std dev. 7.787e-07 (taking best). +Reference operation time is 1.90735e-05 s (4236 Mflops) with 1 threads. # 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 @@ -7477,16 +7514,16 @@ # 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: 2.885e-05 s ~Mflops: 2800.824 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 18.826x: 0.0005431s -> 2.885e-05s, so taking this instance. +After merge step 1: tpop: 1.907e-05 s ~Mflops: 4236.247 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 56.938x: 0.001086s -> 1.907e-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 0.009877s (of which 6.008e-05s partitioning, 0.008157s I/O); computing times: 4.888e-05s in par. loops, 2.408e-05s sorting, 9.537e-07s analyzing) -Total merge + benchmarking process took 0.009877s, equivalent to 342.4/18.2 new/old ops (0.002976s for 2 clones -- as 103.2/5.5 ops, or 51.6/2.7 ops per clone), SPEEDUP of 18.826x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 18.826x (0.0005431s -> 2.885e-05s), will amortize in 19.2 ops by saving 0.0005143s per op. -In 1 tuning rounds (tot. 0.013s, 0.003s for constructor, 2 clones) obtained a SPEEDUP of 1782.6% (18.83x) (from 148.8 to 2801 Mflops). Employed 0.0067s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01333s (of which 4.697e-05s partitioning, 0.009216s I/O); computing times: 3.886e-05s in par. loops, 1.884e-05s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.01333s, equivalent to 699.0/12.3 new/old ops (0.007283s for 2 clones -- as 381.8/6.7 ops, or 190.9/3.4 ops per clone), SPEEDUP of 56.938x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 56.938x (0.001086s -> 1.907e-05s), will amortize in 12.5 ops by saving 0.001067s per op. +In 1 tuning rounds (tot. 0.021s, 0.0073s for constructor, 2 clones) obtained a SPEEDUP of 5593.8% (56.94x) (from 74.4 to 4236 Mflops). Employed 0.0086s 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 0.0198829 s (5.431e-04 s -> 2.885e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0294931 s (1.086e-03 s -> 1.907e-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 @@ -7552,20 +7589,20 @@ # 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 8.488e-05s; avg 2.829e-05s ( +/- 8.15/ 12.92 %); best 2.599e-05s; worst 3.195e-05s; std dev. 2.614e-06 (taking best). -Reference operation time is 2.59876e-05 s (3109 Mflops) with 1 threads. +3 iterations (1 th.) took 6.509e-05s; avg 2.17e-05s ( +/- 12.09/ 19.78 %); best 1.907e-05s; worst 2.599e-05s; std dev. 3.059e-06 (taking best). +Reference operation time is 1.90735e-05 s (4236 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.774e-03 s (100.00 %) - analyzed arrays in 1.182e-03 s (42.60 %) - cleaned-up arrays in 1.311e-05 s (0.47 %) - deduplicated arrays in 1.001e-05 s (0.36 %) + converted COO to RSB in 3.788e-03 s (100.00 %) + analyzed arrays in 1.294e-03 s (34.16 %) + cleaned-up arrays in 9.060e-06 s (0.24 %) + deduplicated arrays in 8.106e-06 s (0.21 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.559e-03 s (56.20 %) - memory allocations took 4.053e-06 s (0.15 %) - leafs setup took 2.861e-06 s (0.10 %) - halfword conversion took 2.146e-06 s (0.08 %) -Built (100 x 100)[0xaaaaed917110]{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' + shuffled partitions in 2.471e-03 s (65.23 %) + memory allocations took 1.907e-06 s (0.05 %) + leafs setup took 1.192e-06 s (0.03 %) + halfword conversion took 1.907e-06 s (0.05 %) +Built (100 x 100)[0xaaaadbad7160]{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 = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7599,16 +7636,16 @@ # 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 5.791e-03 s (100.00 %) - analyzed arrays in 1.744e-03 s (30.12 %) - cleaned-up arrays in 1.597e-05 s (0.28 %) - deduplicated arrays in 1.407e-05 s (0.24 %) + converted COO to RSB in 8.701e-03 s (100.00 %) + analyzed arrays in 3.723e-03 s (42.79 %) + cleaned-up arrays in 9.060e-06 s (0.10 %) + deduplicated arrays in 6.914e-06 s (0.08 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.452e-03 s (42.34 %) - memory allocations took 4.053e-06 s (0.07 %) - leafs setup took 1.907e-06 s (0.03 %) - halfword conversion took 1.558e-03 s (26.91 %) -Built (100 x 100)[0xaaaaed917230]{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' + shuffled partitions in 2.485e-03 s (28.56 %) + memory allocations took 9.537e-07 s (0.01 %) + leafs setup took 1.192e-06 s (0.01 %) + halfword conversion took 2.474e-03 s (28.43 %) +Built (100 x 100)[0xaaaadbad7280]{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 @@ -7654,9 +7691,9 @@ # 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 0.002103s; avg 0.000701s ( +/- 19.25/ 11.12 %); best 0.000566s; worst 0.0007789s; std dev. 9.58e-05 (taking best). -Reference operation time is 0.000566006 s (142.8 Mflops) with 1 threads. -Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.000566006 s/0 threads (speedup 0.0459141 x), same?n. +3 iterations (1 th.) took 0.00365s; avg 0.001217s ( +/- 29.40/ 37.34 %); best 0.000859s; worst 0.001671s; std dev. 0.0003385 (taking best). +Reference operation time is 0.000859022 s (94.06 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.000859022 s/0 threads (speedup 0.0222037 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 @@ -7690,16 +7727,16 @@ # 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 4.912e-03 s (100.00 %) - analyzed arrays in 1.790e-03 s (36.44 %) - cleaned-up arrays in 8.821e-06 s (0.18 %) - deduplicated arrays in 8.106e-06 s (0.17 %) + converted COO to RSB in 8.106e-03 s (100.00 %) + analyzed arrays in 3.111e-03 s (38.38 %) + cleaned-up arrays in 9.060e-06 s (0.11 %) + deduplicated arrays in 6.914e-06 s (0.09 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.572e-03 s (32.00 %) - memory allocations took 1.907e-06 s (0.04 %) - leafs setup took 1.192e-06 s (0.02 %) - halfword conversion took 1.530e-03 s (31.15 %) -Built (100 x 100)[0xaaaaed917230]{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' + shuffled partitions in 2.503e-03 s (30.88 %) + memory allocations took 3.099e-06 s (0.04 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 2.472e-03 s (30.50 %) +Built (100 x 100)[0xaaaadbad7280]{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 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7745,9 +7782,9 @@ # 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 0.002398s; avg 0.0007993s ( +/- 29.94/ 33.60 %); best 0.00056s; worst 0.001068s; std dev. 0.0002084 (taking best). -Reference operation time is 0.000560045 s (144.3 Mflops) with 1 threads. -Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 0.000560045 s/0 threads (speedup 0.0464027 x), same?n. +3 iterations (1 th.) took 0.004025s; avg 0.001342s ( +/- 34.18/ 39.21 %); best 0.0008831s; worst 0.001868s; std dev. 0.0004048 (taking best). +Reference operation time is 0.000883102 s (91.5 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 0.000883102 s/0 threads (speedup 0.0215983 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 @@ -7781,16 +7818,16 @@ # 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 5.047e-03 s (100.00 %) - analyzed arrays in 1.713e-03 s (33.94 %) - cleaned-up arrays in 9.060e-06 s (0.18 %) - deduplicated arrays in 7.868e-06 s (0.16 %) + converted COO to RSB in 7.554e-03 s (100.00 %) + analyzed arrays in 2.541e-03 s (33.64 %) + cleaned-up arrays in 9.060e-06 s (0.12 %) + deduplicated arrays in 7.153e-06 s (0.09 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.610e-03 s (31.90 %) - memory allocations took 4.053e-06 s (0.08 %) - leafs setup took 2.146e-06 s (0.04 %) - halfword conversion took 1.701e-03 s (33.70 %) -Built (100 x 100)[0xaaaaed9655f0]{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 2.519e-03 s (33.35 %) + memory allocations took 1.907e-06 s (0.03 %) + leafs setup took 1.907e-06 s (0.03 %) + halfword conversion took 2.473e-03 s (32.74 %) +Built (100 x 100)[0xaaaadbb25670]{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 @@ -7836,9 +7873,9 @@ # 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 0.002686s; avg 0.0008953s ( +/- 11.65/ 20.84 %); best 0.0007911s; worst 0.001082s; std dev. 0.0001323 (taking best). -Reference operation time is 0.000791073 s (102.1 Mflops) with 1 threads. -Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 0.000791073 s/0 threads (speedup 0.0328511 x), same?n. +3 iterations (1 th.) took 0.003625s; avg 0.001208s ( +/- 27.91/ 54.75 %); best 0.0008712s; worst 0.00187s; std dev. 0.0004678 (taking best). +Reference operation time is 0.000871181 s (92.75 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 0.000871181 s/0 threads (speedup 0.0218938 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 @@ -7872,16 +7909,16 @@ # 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 5.490e-03 s (100.00 %) - analyzed arrays in 1.884e-03 s (34.32 %) - cleaned-up arrays in 1.502e-05 s (0.27 %) - deduplicated arrays in 1.192e-05 s (0.22 %) + converted COO to RSB in 8.121e-03 s (100.00 %) + analyzed arrays in 2.911e-03 s (35.84 %) + cleaned-up arrays in 9.060e-06 s (0.11 %) + deduplicated arrays in 6.914e-06 s (0.09 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.837e-03 s (33.46 %) - memory allocations took 4.053e-06 s (0.07 %) - leafs setup took 3.099e-06 s (0.06 %) - halfword conversion took 1.735e-03 s (31.60 %) -Built (100 x 100)[0xaaaaed9655f0]{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 2.515e-03 s (30.97 %) + memory allocations took 5.007e-06 s (0.06 %) + leafs setup took 3.099e-06 s (0.04 %) + halfword conversion took 2.671e-03 s (32.89 %) +Built (100 x 100)[0xaaaadbb25670]{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 @@ -7927,9 +7964,9 @@ # 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 0.002226s; avg 0.000742s ( +/- 9.17/ 6.19 %); best 0.000674s; worst 0.000788s; std dev. 4.908e-05 (taking best). -Reference operation time is 0.000674009 s (119.9 Mflops) with 1 threads. -Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000674009 s/0 threads (speedup 0.0385568 x), same?n. +3 iterations (1 th.) took 0.00423s; avg 0.00141s ( +/- 38.59/ 19.72 %); best 0.0008659s; worst 0.001688s; std dev. 0.0003847 (taking best). +Reference operation time is 0.000865936 s (93.31 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000865936 s/0 threads (speedup 0.0220264 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 @@ -7963,16 +8000,16 @@ # 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 4.871e-03 s (100.00 %) - analyzed arrays in 1.717e-03 s (35.25 %) - cleaned-up arrays in 1.001e-05 s (0.21 %) - deduplicated arrays in 8.106e-06 s (0.17 %) + converted COO to RSB in 7.517e-03 s (100.00 %) + analyzed arrays in 3.116e-03 s (41.45 %) + cleaned-up arrays in 9.060e-06 s (0.12 %) + deduplicated arrays in 6.914e-06 s (0.09 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.880e-03 s (38.60 %) - memory allocations took 3.815e-06 s (0.08 %) - leafs setup took 2.146e-06 s (0.04 %) - halfword conversion took 1.249e-03 s (25.64 %) -Built (100 x 100)[0xaaaaed9655f0]{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 2.510e-03 s (33.39 %) + memory allocations took 5.007e-06 s (0.07 %) + leafs setup took 1.907e-06 s (0.03 %) + halfword conversion took 1.868e-03 s (24.85 %) +Built (100 x 100)[0xaaaadbb25670]{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 @@ -8018,11 +8055,11 @@ # 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 0.001817s; avg 0.0006057s ( +/- 0.93/ 0.72 %); best 0.0006001s; worst 0.0006101s; std dev. 4.186e-06 (taking best). -Reference operation time is 0.0006001 s (134.6 Mflops) with 1 threads. -Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.0006001 s/0 threads (speedup 0.0433055 x), same?n. +3 iterations (1 th.) took 0.003667s; avg 0.001222s ( +/- 28.73/ 38.17 %); best 0.0008712s; worst 0.001689s; std dev. 0.0003437 (taking best). +Reference operation time is 0.000871181 s (92.75 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000871181 s/0 threads (speedup 0.0218938 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: 3109.17 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 4236.25 Mflops. # 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 @@ -8038,23 +8075,23 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.0414011 s (eq. to 2e+03/ 2e+03 old/new op.times), gained local/global speedup 1 x (2.59876e-05 : 2.59876e-05) / 1 x (2.59876e-05 : 2.59876e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.06464 s (eq. to 3e+03/ 3e+03 old/new op.times), gained local/global speedup 1 x (1.90735e-05 : 1.90735e-05) / 1 x (1.90735e-05 : 1.90735e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.041s, 0.029s for constructor, 0 clones) obtained NO speedup (best stays 3109 Mflops). -Second run of RSB Autotuner took 0.0414259 s and estimated a speedup of 1.000000 x (2.599e-05 s -> 2.599e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.065s, 0.044s for constructor, 0 clones) obtained NO speedup (best stays 4236 Mflops). +Second run of RSB Autotuner took 0.064661 s and estimated a speedup of 1.000000 x (1.907e-05 s -> 1.907e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:100 0 #norm:10 0 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.000691 0.002755 0.003446 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.003446 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000691 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.002755 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.001466 0.005618 0.007084 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.007084 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.001466 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005618 %: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 0.003446 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.007084 %: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 @@ -8069,68 +8106,68 @@ %: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 0.00537181 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.00957799 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.000690937 0 0.00275493 -# so far, program took 5.880s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.333s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00146604 0 0.00561786 +# so far, program took 5.843s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.429s/0.000s . getrusage() stats: -ru_maxrss: 8 (maximum resident set size -- MB) -ru_stime : 0.06507s (system CPU time used) -ru_utime : 7.675s (user CPU time used) +ru_maxrss: 6 (maximum resident set size -- MB) +ru_stime : 0.06392s (system CPU time used) +ru_utime : 6.778s (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 4034.52 1.204e-03 0.000e+00 5.007e-06 0.000e+00 3.611e-02 1.06e+01 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 2229.60 1.098e-03 0.000e+00 9.060e-06 0.000e+00 3.038e-02 3.52e+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 2244.37 6.430e-04 0.000e+00 3.600e-05 0.000e+00 2.756e-02 1.48e+00 6.50e-01 1 8.08e-02 -pr: 4:R_R lower-100x100-5050nz 100 100 5050 1 Z S N 1 1 0 2.1212 2.0800 3 1 2800.82 5.431e-04 0.000e+00 2.885e-05 0.000e+00 1.988e-02 3.33e+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 4034.52 1.971e-03 0.000e+00 5.007e-06 0.000e+00 5.253e-02 1.06e+01 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 3389.00 1.023e-03 0.000e+00 5.960e-06 0.000e+00 3.376e-02 5.35e+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 4034.52 1.075e-03 0.000e+00 2.003e-05 0.000e+00 3.014e-02 2.66e+00 6.50e-01 1 8.08e-02 +pr: 4:R_R lower-100x100-5050nz 100 100 5050 1 Z S N 1 1 0 2.1212 2.0800 3 1 4236.25 1.086e-03 0.000e+00 1.907e-05 0.000e+00 2.949e-02 5.04e+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. 9857.5 % faster, avg. sp. ratio 99.575x, max sp. ratio 240.429x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 3005.2/689.2/7213.2/12020.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 34.3/ 27.7/ 42.9/137.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 35.5, min. 27.9, max. 45.4 ops) +#pr: (in succ. cases rsb autotuning gave avg. 16798.1 % faster, avg. sp. ratio 168.981x, max sp. ratio 393.667x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4801.7/1505.1/10491.1/19206.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 28.7/ 26.6/ 33.0/114.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 29.0, min. 26.7, max. 33.2 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 1683/ 1683/ 1683) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 5050/ 5050/ 5050) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 15150/ 6733/ 26933) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 45450/ 20200/ 80800) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 2.121/ 2.121/ 2.121) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.675/ 1.458/ 10.487,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.980/ 1.481/ 10.646,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.837/ 2.622/ 10.487,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 23.699/ 2.662/ 10.646,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.: 0.03 s, min 0.02 s, max 0.04 s, tot 0.11 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.03 s, min 0.02 s, max 0.04 s, tot 0.11 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.827e+03, min 2.230e+03, max 4.035e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 7.740e+01, min 1.678e+01, max 1.488e+02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.973e-05s, min 5.007e-06s, max 3.600e-05s, tot 7.892e-05s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 8.720e-04s, min 5.431e-04s, max 1.204e-03s, tot 3.488e-03s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.513e+00 3.245e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.009e+00 -#pr: Record collection took 0.34 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.03 s, max 0.05 s, tot 0.15 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.03 s, max 0.05 s, tot 0.15 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.924e+03, min 3.389e+03, max 4.236e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 4.489e+01, min 1.025e+01, max 7.516e+01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 1.252e-05s, min 5.007e-06s, max 2.003e-05s, tot 5.007e-05s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.289e-03s, min 1.023e-03s, max 1.971e-03s, tot 5.155e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.516e+00 1.806e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+00 +#pr: Record collection took 0.44 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 99 environment variables in 5462 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 99 environment variables in 5516 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 1769414875 (after 5.9s of w.c.t.) +# terminating run at 1769415873 (after 5.8s 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 85638 Jan 25 20:07 test-tuning-lower-100x100-5050nz--D-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84560 Jan 25 20:07 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85639 Jan 25 20:07 test-tuning-lower-100x100-5050nz--S-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84561 Jan 25 20:07 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85639 Jan 25 20:07 test-tuning-lower-100x100-5050nz--C-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84561 Jan 25 20:07 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85639 Jan 25 20:07 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84561 Jan 25 20:07 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Jan 26 22:24 test-tuning-lower-100x100-5050nz--D-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84565 Jan 26 22:24 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85644 Jan 26 22:24 test-tuning-lower-100x100-5050nz--S-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84565 Jan 26 22:24 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85643 Jan 26 22:24 test-tuning-lower-100x100-5050nz--C-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84566 Jan 26 22:24 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85644 Jan 26 22:24 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Jan 26 22:24 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 4093 Jan 25 20:07 test.txt +-rw-r--r-- 1 pbuilder2 pbuilder2 4097 Jan 26 22:24 test.txt + RSB_PR_WLTC=2 + RSB_PR_SR=0 + rsbench --read-performance-record test.rpr @@ -8140,29 +8177,29 @@ /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 @@ -8177,7 +8214,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0xaaaaf6a184a0]{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)[0xaaab06edb4a0]{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. @@ -8192,7 +8229,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0xaaaae21914a0]{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)[0xaaaaeba064a0]{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. @@ -8256,51 +8293,51 @@ Done. Building a matrix with 5 nnz, 5 x 5 Duplicates check: 5 - 0 = 5 - converted COO to RSB in 1.129e-02 s (100.00 %) - analyzed arrays in 4.243e-03 s (37.60 %) + converted COO to RSB in 1.152e-02 s (100.00 %) + analyzed arrays in 3.461e-03 s (30.04 %) cleaned-up arrays in 9.537e-07 s (0.01 %) - deduplicated arrays in 9.537e-07 s (0.01 %) - sorted arrays in 1.237e-03 s (10.96 %) - shuffled partitions in 3.375e-03 s (29.91 %) - memory allocations took 1.001e-05 s (0.09 %) - leafs setup took 1.907e-06 s (0.02 %) - halfword conversion took 2.416e-03 s (21.41 %) -Built (5 x 5)[0xaaaae2193820]{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:'' + deduplicated arrays in 0.000e+00 s (0.00 %) + sorted arrays in 1.478e-03 s (12.83 %) + shuffled partitions in 3.911e-03 s (33.95 %) + memory allocations took 3.099e-06 s (0.03 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 2.666e-03 s (23.14 %) +Built (5 x 5)[0xaaaaeba08820]{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)[0xaaaae2193820]{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)[0xaaaaeba08820]{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 0.107380s. +Before auto-tuning, 100 multiplications took 0.151160s. 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.=8.0657e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.002311s; avg 0.0007703s ( +/- 4.46/ 2.69 %); best 0.000736s; worst 0.0007911s; std dev. 2.445e-05 (taking best). -Reference operation time is 0.000735998 s (0.02717 Mflops) with 12 threads. -3 iterations (12 th.) took 0.002402s; avg 0.0008006s ( +/- 3.22/ 3.81 %); best 0.0007749s; worst 0.0008311s; std dev. 2.322e-05 (taking best). -Reference operation time is 0.00077486 s (0.02581 Mflops) with 12 threads. -After 0.004764s, autotuning routine did not find a better threads count configuration. -(5 x 5)[0xaaaae2193820]{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 0.069253s -- effective speedup of 1.55055 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=2.99931e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.003517s; avg 0.001172s ( +/- 28.70/ 57.13 %); best 0.0008359s; worst 0.001842s; std dev. 0.0004736 (taking best). +Reference operation time is 0.000835896 s (0.02393 Mflops) with 12 threads. +3 iterations (12 th.) took 0.00411s; avg 0.00137s ( +/- 39.05/ 19.63 %); best 0.0008349s; worst 0.001639s; std dev. 0.0003783 (taking best). +Reference operation time is 0.000834942 s (0.02395 Mflops) with 12 threads. +After 0.007675s, autotuning routine did not find a better threads count configuration. +(5 x 5)[0xaaaaeba08820]{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 0.123250s -- effective speedup of 1.22645 x Matrix autotuning (may take more than 1.500000s; using 12 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.=8.0657e-08), 12 suggested as starting thread count. -3 iterations (12 th.) took 0.00184s; avg 0.0006133s ( +/- 2.50/ 1.43 %); best 0.000598s; worst 0.000622s; std dev. 1.088e-05 (taking best). -Reference operation time is 0.000597954 s (0.03345 Mflops) with 12 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: 0.000598 Mflops: 0.033) -Merge (2 -> 1 leaves) took w.c.t. of 1.502e-05s, ~3.099e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 79.70/200.00 %); best 8.066e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). -Reference operation time is 8.0657e-08 s (248 Mflops) with 12 threads. -After merge step 1: tpop: 8.066e-08 s ~Mflops: 247.964 nsubm:1 otn:12 -Applying merge (2 -> 1 leaves, 12 th.) yielded SPEEDUP of 7413.538x: 0.000598s -> 8.066e-08s, so taking this instance. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=2.99931e-08), 12 suggested as starting thread count. +3 iterations (12 th.) took 0.003326s; avg 0.001109s ( +/- 24.67/ 49.17 %); best 0.0008352s; worst 0.001654s; std dev. 0.0003855 (taking best). +Reference operation time is 0.00083518 s (0.02395 Mflops) with 12 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: 0.0008352 Mflops: 0.024) +Merge (2 -> 1 leaves) took w.c.t. of 1.597e-05s, ~2.861e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 97.10/200.00 %); best 2.999e-08s; worst 3.099e-06s; std dev. 1.461e-06 (taking best). +Reference operation time is 2.99931e-08 s (666.8 Mflops) with 12 threads. +After merge step 1: tpop: 2.999e-08 s ~Mflops: 666.821 nsubm:1 otn:12 +Applying merge (2 -> 1 leaves, 12 th.) yielded SPEEDUP of 27845.787x: 0.0008352s -> 2.999e-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 0.002195s (of which 3.481e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 0s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.002195s, equivalent to 27212.5/3.7 new/old ops (0.004605s for 2 clones -- as 57094.3/7.7 ops, or 28547.1/3.9 ops per clone), SPEEDUP of 7413.538x -Applying multi-merge (2 -> 1 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 7413.538x (0.000598s -> 8.066e-08s), will amortize in 3.7 ops by saving 0.0005979s per op. -In 1 tuning rounds (tot. 0.0065s, 0.0046s for constructor, 2 clones) obtained a SPEEDUP of 741253.8% (7414x) (from 0.03345 to 248 Mflops). -After 0.006538s, autotuning routine declared speedup of 7413.54 x, when using threads count of 12. -(5 x 5)[0xaaaae2196de0]{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 0.000014s -- further speedup of 4923.19 x +A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.004113s (of which 0.0004542s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 0s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.004113s, equivalent to 137138.3/4.9 new/old ops (0.007758s for 2 clones -- as 258664.5/9.3 ops, or 129332.3/4.6 ops per clone), SPEEDUP of 27845.787x +Applying multi-merge (2 -> 1 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 27845.787x (0.0008352s -> 2.999e-08s), will amortize in 4.9 ops by saving 0.0008352s per op. +In 1 tuning rounds (tot. 0.012s, 0.0078s for constructor, 2 clones) obtained a SPEEDUP of 2784478.7% (2.785e+04x) (from 0.02395 to 666.8 Mflops). +After 0.011586s, autotuning routine declared speedup of 27845.8 x, when using threads count of 12. +(5 x 5)[0xaaaaeba0bde0]{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 0.000010s -- further speedup of 12308.3 x 0/2 0 0 -> 0 1/2 1 0 -> 5 0/2 0 3 -> 0 @@ -8311,7 +8348,7 @@ Correctly initialized the library. Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0xaaaae2193820]{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)[0xaaaaeba08820]{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 @@ -8462,61 +8499,56 @@ 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 2.507e-02 s (100.00 %) - analyzed arrays in 9.918e-03 s (39.56 %) - cleaned-up arrays in 1.781e-04 s (0.71 %) - deduplicated arrays in 1.152e-04 s (0.46 %) - sorted arrays in 7.825e-03 s (31.21 %) - shuffled partitions in 4.919e-03 s (19.62 %) - memory allocations took 3.791e-05 s (0.15 %) - leafs setup took 1.121e-05 s (0.04 %) - halfword conversion took 2.063e-03 s (8.23 %) -Built (500 x 500)[0xaaaaee2452d0]{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: 55, symflags:'' + converted COO to RSB in 2.765e-02 s (100.00 %) + analyzed arrays in 4.932e-03 s (17.84 %) + cleaned-up arrays in 1.791e-04 s (0.65 %) + deduplicated arrays in 1.228e-04 s (0.44 %) + sorted arrays in 1.237e-02 s (44.72 %) + shuffled partitions in 7.189e-03 s (26.00 %) + memory allocations took 4.816e-05 s (0.17 %) + leafs setup took 1.001e-05 s (0.04 %) + halfword conversion took 2.801e-03 s (10.13 %) +Built (500 x 500)[0xaaaad2f792d0]{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: 55, symflags:'' Allocated matrix of 62500 nonzeroes: -(500 x 500)[0xaaaaee2452d0]{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: 55, symflags:'' +(500 x 500)[0xaaaad2f792d0]{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: 55, symflags:'' -Before auto-tuning, 100 multiplications took 0.107122s. +Before auto-tuning, 100 multiplications took 0.155189s. 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, 75 subms, 55 lsubms, 2.1196 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.8651e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.002423s; avg 0.0008077s ( +/- 23.34/ 40.27 %); best 0.0006192s; worst 0.001133s; std dev. 0.000231 (taking best). -Reference operation time is 0.000619173 s (403.8 Mflops) with 12 threads. -3 iterations (12 th.) took 0.00269s; avg 0.0008966s ( +/- 28.87/ 25.46 %); best 0.0006378s; worst 0.001125s; std dev. 0.0002 (taking best). -Reference operation time is 0.00063777 s (392 Mflops) with 12 threads. -After 0.005167s, autotuning routine did not find a better threads count configuration. -(500 x 500)[0xaaaaee2452d0]{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: 55, symflags:'' -After threads auto-tuning, 100 multiplications took 0.063359s -- effective speedup of 1.69071 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=4.62532e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.003574s; avg 0.001191s ( +/- 23.11/ 12.82 %); best 0.000916s; worst 0.001344s; std dev. 0.000195 (taking best). +Reference operation time is 0.000916004 s (272.9 Mflops) with 12 threads. +3 iterations (12 th.) took 0.003941s; avg 0.001314s ( +/- 31.65/ 16.54 %); best 0.0008979s; worst 0.001531s; std dev. 0.0002941 (taking best). +Reference operation time is 0.000897884 s (278.4 Mflops) with 12 threads. +After 0.007577s, autotuning routine did not find a better threads count configuration. +(500 x 500)[0xaaaad2f792d0]{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: 55, symflags:'' +After threads auto-tuning, 100 multiplications took 0.152698s -- effective speedup of 1.01631 x Matrix autotuning (may take more than 1.500000s; using 12 threads )... Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 75 subms, 55 lsubms, 2.1196 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.8651e-08), 12 suggested as starting thread count. -3 iterations (12 th.) took 0.001987s; avg 0.0006624s ( +/- 3.50/ 4.60 %); best 0.0006392s; worst 0.0006928s; std dev. 2.249e-05 (taking best). -Reference operation time is 0.0006392 s (391.1 Mflops) with 12 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, 75 subms, 55 lsubms, 2.1196 bpnz (tpop: 0.0006392 Mflops: 391.114) -Merge (55 -> 37 leaves) took w.c.t. of 0.001047s, ~0.002323s of computing time (of which 0.0005007s sorting, 1.001e-05s analysis) -3 iterations (12 th.) took 0.004134s; avg 0.001378s ( +/- 59.43/118.21 %); best 0.0005591s; worst 0.003007s; std dev. 0.001152 (taking best). -Reference operation time is 0.000559092 s (447.2 Mflops) with 12 threads. -After merge step 1: tpop: 0.0005591 s ~Mflops: 447.154 nsubm:37 otn:12 -Applying merge (55 -> 37 leaves, 12 th.) yielded SPEEDUP of 1.143x: 0.0006392s -> 0.0005591s, so taking this instance. -Merge (37 -> 28 leaves) took w.c.t. of 0.0002441s, ~0.0001171s of computing time (of which 5.603e-05s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.001757s; avg 0.0005857s ( +/- 40.08/ 58.79 %); best 0.000351s; worst 0.0009301s; std dev. 0.0002488 (taking best). -Reference operation time is 0.000350952 s (712.3 Mflops) with 12 threads. -After merge step 2: tpop: 0.000351 s ~Mflops: 712.348 nsubm:28 otn:12 -Applying merge (37 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.593x: 0.0005591s -> 0.000351s, so taking this instance. -Merge (28 -> 22 leaves) took w.c.t. of 0.0002801s, ~6.986e-05s of computing time (of which 3.695e-05s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.001954s; avg 0.0006514s ( +/- 30.60/ 17.75 %); best 0.000452s; worst 0.000767s; std dev. 0.0001415 (taking best). -Reference operation time is 0.000452042 s (553 Mflops) with 12 threads. -After merge step 3: tpop: 0.000452 s ~Mflops: 553.046 nsubm:22 otn:12 -Applying merge (28 -> 22 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.288x: 0.000351s -> 0.000452s. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=4.62532e-08), 12 suggested as starting thread count. +3 iterations (12 th.) took 0.004303s; avg 0.001434s ( +/- 7.35/ 9.52 %); best 0.001329s; worst 0.001571s; std dev. 0.0001012 (taking best). +Reference operation time is 0.00132895 s (188.1 Mflops) with 12 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, 75 subms, 55 lsubms, 2.1196 bpnz (tpop: 0.001329 Mflops: 188.119) +Merge (55 -> 37 leaves) took w.c.t. of 0.001435s, ~0.004677s of computing time (of which 0.000221s sorting, 1.287e-05s analysis) +3 iterations (12 th.) took 0.004423s; avg 0.001474s ( +/- 36.38/ 32.46 %); best 0.0009379s; worst 0.001953s; std dev. 0.0004164 (taking best). +Reference operation time is 0.000937939 s (266.5 Mflops) with 12 threads. +After merge step 1: tpop: 0.0009379 s ~Mflops: 266.542 nsubm:37 otn:12 +Applying merge (55 -> 37 leaves, 12 th.) yielded SPEEDUP of 1.417x: 0.001329s -> 0.0009379s, so taking this instance. +Merge (37 -> 28 leaves) took w.c.t. of 0.000742s, ~0.0001531s of computing time (of which 9.394e-05s sorting, 7.153e-06s analysis) +3 iterations (12 th.) took 0.008325s; avg 0.002775s ( +/- 36.47/ 50.59 %); best 0.001763s; worst 0.004179s; std dev. 0.001025 (taking best). +Reference operation time is 0.00176311 s (141.8 Mflops) with 12 threads. +After merge step 2: tpop: 0.001763 s ~Mflops: 141.795 nsubm:28 otn:12 +Applying merge (37 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.880x: 0.0009379s -> 0.001763s. 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) (55 -> 22 subms) took 0.01224s (of which 0.001596s partitioning, 0s I/O); computing times: 0.00251s in par. loops, 0.0005937s sorting, 1.907e-05s analyzing) -Total merge + benchmarking process took 0.01224s, equivalent to 34.9/19.2 new/old ops (0.0041s for 3 clones -- as 11.7/6.4 ops, or 3.9/2.1 ops per clone), SPEEDUP of 1.821x -Applying multi-merge (55 -> 28 leaves, 2 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 1.821x (0.0006392s -> 0.000351s), will amortize in 42.5 ops by saving 0.0002882s per op. -In 1 tuning rounds (tot. 0.016s, 0.0041s for constructor, 3 clones) obtained a SPEEDUP of 82.1% (1.821x) (from 391.1 to 712.3 Mflops). -After 0.015866s, autotuning routine declared speedup of 1.82133 x, when using threads count of 12. -(500 x 500)[0xaaaaee348bf0]{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 0.078990s -- further speedup of 0.802115 x +A total of 2 merge steps (of max 6) (55 -> 28 subms) took 0.0192s (of which 0.002192s partitioning, 0s I/O); computing times: 0.00483s in par. loops, 0.000315s sorting, 2.003e-05s analyzing) +Total merge + benchmarking process took 0.0192s, equivalent to 20.5/14.4 new/old ops (0.007889s for 2 clones -- as 8.4/5.9 ops, or 4.2/3.0 ops per clone), SPEEDUP of 1.417x +Applying multi-merge (55 -> 37 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 1.417x (0.001329s -> 0.0009379s), will amortize in 49.1 ops by saving 0.000391s per op. +In 1 tuning rounds (tot. 0.028s, 0.0079s for constructor, 2 clones) obtained a SPEEDUP of 41.7% (1.417x) (from 188.1 to 266.5 Mflops). +After 0.027714s, autotuning routine declared speedup of 1.41688 x, when using threads count of 12. +(500 x 500)[0xaaaad2f819f0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 37, symflags:'' +After threads auto-tuning, 100 multiplications took 0.152124s -- further speedup of 1.00377 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! @@ -8524,19 +8556,19 @@ Correctly initialized the library. Building a matrix with 7 nnz, 6 x 6 Duplicates check: 1 - 0 = 1 - converted COO to RSB in 3.176e-03 s (100.00 %) - analyzed arrays in 1.872e-03 s (58.94 %) - cleaned-up arrays in 3.815e-06 s (0.12 %) - deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 2.146e-06 s (0.07 %) - shuffled partitions in 1.274e-03 s (40.12 %) - memory allocations took 1.001e-05 s (0.32 %) - leafs setup took 5.007e-06 s (0.16 %) - halfword conversion took 6.914e-06 s (0.22 %) -Built (6 x 6)[0xaaab032e34d0]{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 4.845e-03 s (100.00 %) + analyzed arrays in 3.586e-03 s (74.01 %) + cleaned-up arrays in 5.007e-06 s (0.10 %) + deduplicated arrays in 1.192e-06 s (0.02 %) + sorted arrays in 9.537e-07 s (0.02 %) + shuffled partitions in 1.231e-03 s (25.41 %) + memory allocations took 8.821e-06 s (0.18 %) + leafs setup took 2.861e-06 s (0.06 %) + halfword conversion took 7.153e-06 s (0.15 %) +Built (6 x 6)[0xaaaadfb634d0]{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)[0xaaab032e34d0]{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)[0xaaaadfb634d0]{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 @@ -8563,22 +8595,22 @@ 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:2.999e-08 -3 iterations (12 th.) took 2.003e-05s; avg 6.676e-06s ( +/- 99.55/182.14 %); best 2.999e-08s; worst 1.884e-05s; std dev. 8.612e-06 (taking best). +3 iterations (12 th.) took 1.693e-05s; avg 5.643e-06s ( +/- 99.47/200.00 %); best 2.999e-08s; worst 1.693e-05s; std dev. 7.98e-06 (taking best). Reference operation time is 2.99931e-08 s (66.68 Mflops) with 12 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: 2.999e-08 Mflops: 66.682) -Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) -3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.999e-08s; worst 0s; std dev. 0 (taking best). +Merge (1 -> 1 leaves) took w.c.t. of 9.537e-07s, ~0s of computing time (of which 0s sorting, 0s analysis) +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.57/200.00 %); best 2.999e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). Reference operation time is 2.99931e-08 s (66.68 Mflops) with 12 threads. After merge step 1: tpop: 2.999e-08 s ~Mflops: 66.682 nsubm:1 otn:12 Applying merge (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 2.999e-08s -> 2.999e-08s, so IGNORING this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (1 -> 1 subms) took 9.06e-06s (of which 1.907e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 9.06e-06s, equivalent to 302.1/302.1 new/old ops (0.001402s for 1 clones -- as 46748.8/46748.8 ops, or 46748.8/46748.8 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (1 -> 1 subms) took 1.001e-05s (of which 1.907e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 1.001e-05s, equivalent to 333.9/333.9 new/old ops (0.004324s for 1 clones -- as 144173.3/144173.3 ops, or 144173.3/144173.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 97.78/129.41 %); best 2.999e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.57/200.00 %); best 2.999e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). Reference operation time is 2.99931e-08 s (66.68 Mflops) with 12 threads. Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 2.999e-08 Mflops: 66.682) -Split (1 -> 1 leaves, 1 -> 1 subms) took 1.287e-05s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +Split (1 -> 1 leaves, 1 -> 1 subms) took 1.192e-05s (of which: 1.907e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. 3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.57/200.00 %); best 2.999e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). Reference operation time is 2.99931e-08 s (66.68 Mflops) with 12 threads. After split step 1: tpop: 2.999e-08 s ~Mflops: 66.682 nsubm:1 otn:12 @@ -8588,13 +8620,13 @@ Reference operation time is 2.99931e-08 s (66.68 Mflops) with 12 threads. After split step 2: tpop: 2.999e-08 s ~Mflops: 66.682 nsubm:1 otn:12 Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 2.999e-08s -> 2.999e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 5.007e-06s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 95.81/ 66.67 %); best 2.999e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). +Split (1 -> 1 leaves, 1 -> 1 subms) took 1.907e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.57/200.00 %); best 2.999e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). Reference operation time is 2.99931e-08 s (66.68 Mflops) with 12 threads. After split step 3: tpop: 2.999e-08 s ~Mflops: 66.682 nsubm:1 otn:12 Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 2.999e-08s -> 2.999e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 1.192e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.999e-08s; worst 0s; std dev. 0 (taking best). +Split (1 -> 1 leaves, 1 -> 1 subms) took 9.537e-07s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.57/200.00 %); best 2.999e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). Reference operation time is 2.99931e-08 s (66.68 Mflops) with 12 threads. After split step 4: tpop: 2.999e-08 s ~Mflops: 66.682 nsubm:1 otn:12 Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 2.999e-08s -> 2.999e-08s, so IGNORING this instance. @@ -8603,14 +8635,14 @@ Reference operation time is 2.99931e-08 s (66.68 Mflops) with 12 threads. After split step 5: tpop: 2.999e-08 s ~Mflops: 66.682 nsubm:1 otn:12 Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 2.999e-08s -> 2.999e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 9.537e-07s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.57/200.00 %); best 2.999e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Split (1 -> 1 leaves, 1 -> 1 subms) took 9.537e-07s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.999e-08s; worst 0s; std dev. 0 (taking best). Reference operation time is 2.99931e-08 s (66.68 Mflops) with 12 threads. After split step 6: tpop: 2.999e-08 s ~Mflops: 66.682 nsubm:1 otn:12 Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 2.999e-08s -> 2.999e-08s, so IGNORING this instance. -A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.0002811s (of which 3.695e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.907e-06s analyzing) -Total split + benchmarking process took 0.0002811s, equivalent to 9372.0/9372.0 new/old ops (0.001196s for 1 clones -- as 39880.8/39880.8 ops, or 39880.8/39880.8 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.003s, 0.0026s for constructor, 2 clones) obtained NO speedup (best stays 66.68 Mflops). +A total of 6 split steps (of max 6) (1 -> 1 subms) took 7.796e-05s (of which 5.198e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 2.861e-06s analyzing) +Total split + benchmarking process took 7.796e-05s, equivalent to 2599.4/2599.4 new/old ops (0.003341s for 1 clones -- as 111391.1/111391.1 ops, or 111391.1/111391.1 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.0078s, 0.0077s for constructor, 2 clones) obtained NO speedup (best stays 66.68 Mflops). Backsolving we should get a unitary vector: %%MatrixMarket matrix array real general @@ -8645,170 +8677,177 @@ /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 3.436e-02 s (100.00 %) - analyzed arrays in 1.237e-03 s (3.60 %) - cleaned-up arrays in 1.907e-06 s (0.01 %) - deduplicated arrays in 2.146e-06 s (0.01 %) - sorted arrays in 1.241e-03 s (3.61 %) - shuffled partitions in 1.830e-02 s (53.25 %) - memory allocations took 3.290e-05 s (0.10 %) - leafs setup took 8.821e-06 s (0.03 %) - halfword conversion took 1.353e-02 s (39.38 %) -Built (20 x 20)[0xaaaaed5a19f0]{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 1.290e-02 s (100.00 %) + analyzed arrays in 3.838e-03 s (29.74 %) + cleaned-up arrays in 9.537e-07 s (0.01 %) + deduplicated arrays in 1.907e-06 s (0.01 %) + sorted arrays in 2.403e-03 s (18.62 %) + shuffled partitions in 3.173e-03 s (24.59 %) + memory allocations took 2.694e-05 s (0.21 %) + leafs setup took 4.053e-06 s (0.03 %) + halfword conversion took 3.444e-03 s (26.69 %) +Built (20 x 20)[0xaaaab82d49f0]{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:3.736e-08 -Starting autotuning (16 x 3.73602e-08 s stages, transA=N, nrhs=1, timer gran.=3.73602e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.01781s; avg 0.005937s ( +/- 61.58/ 33.22 %); best 0.002281s; worst 0.00791s; std dev. 0.002588 (taking best). -Reference operation time is 0.00228095 s (0.3683 Mflops) with 12 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: 0.002281 Mflops: 0.368) -Merge (22 -> 16 leaves) took w.c.t. of 0.001172s, ~0.001267s of computing time (of which 2.861e-06s sorting, 6.914e-06s analysis) -3 iterations (12 th.) took 0.0189s; avg 0.0063s ( +/- 73.71/124.17 %); best 0.001656s; worst 0.01412s; std dev. 0.005563 (taking best). -Reference operation time is 0.00165606 s (0.5072 Mflops) with 12 threads. -After merge step 1: tpop: 0.001656 s ~Mflops: 0.507 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.377x: 0.002281s -> 0.001656s, so taking this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.0007551s, ~1.407e-05s of computing time (of which 9.537e-07s sorting, 6.199e-06s analysis) -3 iterations (12 th.) took 0.01291s; avg 0.004302s ( +/- 74.22/141.23 %); best 0.001109s; worst 0.01038s; std dev. 0.004298 (taking best). -Reference operation time is 0.00110912 s (0.7574 Mflops) with 12 threads. -After merge step 2: tpop: 0.001109 s ~Mflops: 0.757 nsubm:10 otn:12 -Applying merge (16 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.493x: 0.001656s -> 0.001109s, so taking this instance. -Merge (10 -> 8 leaves) took w.c.t. of 1.407e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.01981s; avg 0.006603s ( +/- 56.62/ 84.90 %); best 0.002864s; worst 0.01221s; std dev. 0.004037 (taking best). -Reference operation time is 0.00286388 s (0.2933 Mflops) with 12 threads. -After merge step 3: tpop: 0.002864 s ~Mflops: 0.293 nsubm:8 otn:12 -Applying merge (10 -> 8 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.582x: 0.001109s -> 0.002864s. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.325e-08 +Starting autotuning (16 x 3.32475e-08 s stages, transA=N, nrhs=1, timer gran.=3.32475e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.005408s; avg 0.001803s ( +/- 22.34/ 26.15 %); best 0.0014s; worst 0.002274s; std dev. 0.0003601 (taking best). +Reference operation time is 0.00139999 s (0.6 Mflops) with 12 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: 0.0014 Mflops: 0.600) +Merge (22 -> 16 leaves) took w.c.t. of 0.0009639s, ~0.001157s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.00459s; avg 0.00153s ( +/- 37.39/ 34.05 %); best 0.000958s; worst 0.002051s; std dev. 0.0004476 (taking best). +Reference operation time is 0.000957966 s (0.8769 Mflops) with 12 threads. +After merge step 1: tpop: 0.000958 s ~Mflops: 0.877 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.461x: 0.0014s -> 0.000958s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.0003178s, ~9.06e-06s of computing time (of which 3.338e-06s sorting, 2.861e-06s analysis) +3 iterations (12 th.) took 0.005256s; avg 0.001752s ( +/- 26.60/ 16.33 %); best 0.001286s; worst 0.002038s; std dev. 0.0003323 (taking best). +Reference operation time is 0.00128603 s (0.6532 Mflops) with 12 threads. +After merge step 2: tpop: 0.001286 s ~Mflops: 0.653 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.342x: 0.000958s -> 0.001286s. 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 0.06274s (of which 0.001953s partitioning, 0s I/O); computing times: 0.001286s in par. loops, 4.768e-06s sorting, 1.717e-05s analyzing) -Total merge + benchmarking process took 0.06274s, equivalent to 56.6/27.5 new/old ops (0.02814s for 3 clones -- as 25.4/12.3 ops, or 8.5/4.1 ops per clone), SPEEDUP of 2.057x -Applying multi-merge (22 -> 10 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 2.057x (0.002281s -> 0.001109s), will amortize in 53.5 ops by saving 0.001172s per op. -In 1 tuning rounds (tot. 0.1s, 0.028s for constructor, 3 clones) obtained a SPEEDUP of 105.7% (2.057x) (from 0.3683 to 0.7574 Mflops). +A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.01544s (of which 0.001291s partitioning, 0s I/O); computing times: 0.001166s in par. loops, 5.245e-06s sorting, 7.868e-06s analyzing) +Total merge + benchmarking process took 0.01544s, equivalent to 16.1/11.0 new/old ops (0.009147s for 2 clones -- as 9.5/6.5 ops, or 4.8/3.3 ops per clone), SPEEDUP of 1.461x +Applying multi-merge (22 -> 16 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.461x (0.0014s -> 0.000958s), will amortize in 34.9 ops by saving 0.000442s per op. +In 1 tuning rounds (tot. 0.026s, 0.0091s for constructor, 2 clones) obtained a SPEEDUP of 46.1% (1.461x) (from 0.6 to 0.8769 Mflops). autotuner chose 12 threads -Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 14 subms, 10 lsubms, 3.1429 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.736e-08 -Starting autotuning (16 x 3.73602e-08 s stages, transA=N, nrhs=1, timer gran.=3.73602e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.01792s; avg 0.005972s ( +/- 40.61/ 30.61 %); best 0.003547s; worst 0.0078s; std dev. 0.001787 (taking best). -~ 12 threads: 0.003547s (0.24 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02638s; avg 0.008795s ( +/- 11.34/ 18.24 %); best 0.007797s; worst 0.0104s; std dev. 0.001146 (taking best). - 11 threads: 0.007797s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.01991s; avg 0.006638s ( +/- 22.07/ 22.18 %); best 0.005173s; worst 0.00811s; std dev. 0.001199 (taking best). - 10 threads: 0.005173s (0.16 Mflops) (2/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 2.2x; search took 0.064s. -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, 14 subms, 10 lsubms, 3.1429 bpnz (tpop: 0.003547 Mflops: 0.237) -Merge (10 -> 8 leaves) took w.c.t. of 2.098e-05s, ~6.914e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.02394s; avg 0.007981s ( +/- 49.94/ 47.39 %); best 0.003995s; worst 0.01176s; std dev. 0.003175 (taking best). -~ 12 threads: 0.003995s (0.21 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02398s; avg 0.007992s ( +/- 0.16/ 0.08 %); best 0.007979s; worst 0.007998s; std dev. 8.879e-06 (taking best). - 11 threads: 0.007979s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.0244s; avg 0.008133s ( +/- 43.35/ 50.01 %); best 0.004608s; worst 0.0122s; std dev. 0.003124 (taking best). - 10 threads: 0.004608s (0.18 Mflops) (2/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 2x; search took 0.072s. -After merge step 1: tpop: 0.003995 s ~Mflops: 0.210 nsubm:8 otn:12 -Applying merge (10 -> 8 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.126x: 0.003547s -> 0.003995s. -Merge (8 -> 6 leaves) took w.c.t. of 2.193e-05s, ~6.914e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.02057s; avg 0.006856s ( +/- 31.58/ 28.16 %); best 0.004691s; worst 0.008787s; std dev. 0.00168 (taking best). -~ 12 threads: 0.004691s (0.18 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.0236s; avg 0.007868s ( +/- 50.15/ 45.55 %); best 0.003922s; worst 0.01145s; std dev. 0.003085 (taking best). - 11 threads: 0.003922s (0.21 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 0.02796s; avg 0.00932s ( +/- 11.97/ 21.84 %); best 0.008204s; worst 0.01136s; std dev. 0.001442 (taking best). - 10 threads: 0.008204s (0.1 Mflops) (1/2 degradations so far) - -3 iterations (9 th.) took 0.02427s; avg 0.008091s ( +/- 45.20/ 40.45 %); best 0.004434s; worst 0.01136s; std dev. 0.002842 (taking best). - 9 threads: 0.004434s (0.19 Mflops) (2/2 degradations so far) - -Best threads choice is 11; starting threads were 12; max speed gap is 2.1x; search took 0.096s. -After merge step 2: tpop: 0.003922 s ~Mflops: 0.214 nsubm:6 otn:11 -Applying merge (8 -> 6 leaves, 11 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.106x: 0.003547s -> 0.003922s. -Merge (6 -> 3 leaves) took w.c.t. of 1.717e-05s, ~6.914e-06s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.03105s; avg 0.01035s ( +/- 31.46/ 52.52 %); best 0.007093s; worst 0.01578s; std dev. 0.003868 (taking best). -~ 12 threads: 0.007093s (0.12 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02398s; avg 0.007995s ( +/- 43.30/ 43.26 %); best 0.004533s; worst 0.01145s; std dev. 0.002825 (taking best). - 11 threads: 0.004533s (0.19 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 0.02398s; avg 0.007995s ( +/- 0.15/ 0.26 %); best 0.007983s; worst 0.008016s; std dev. 1.483e-05 (taking best). - 10 threads: 0.007983s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (9 th.) took 0.02481s; avg 0.008271s ( +/- 39.27/ 36.75 %); best 0.005023s; worst 0.01131s; std dev. 0.002571 (taking best). - 9 threads: 0.005023s (0.17 Mflops) (2/2 degradations so far) - -Best threads choice is 11; starting threads were 12; max speed gap is 1.8x; search took 0.1s. -After merge step 3: tpop: 0.004533 s ~Mflops: 0.185 nsubm:3 otn:11 -Applying merge (6 -> 3 leaves, 11 th.) yielded SLOWDOWN (3th of 3 tolerable) of 1.278x: 0.003547s -> 0.004533s. -Skipping further merge based tests after 3 definite performance degradations in a row (and last exceeding limit). -A total of 3 merge steps (of max 6) (10 -> 3 subms) took 0.273s (of which 6.7e-05s partitioning, 0s I/O); computing times: 2.074e-05s in par. loops, 3.815e-06s sorting, 1.216e-05s analyzing) -Total merge + benchmarking process took 0.273s, equivalent to 77.0/77.0 new/old ops (0.03118s for 1 clones -- as 8.8/8.8 ops, or 8.8/8.8 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.02398s; avg 0.007992s ( +/- 14.41/ 17.10 %); best 0.00684s; worst 0.009359s; std dev. 0.001039 (taking best). -~ 12 threads: 0.00684s (0.12 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02792s; avg 0.009308s ( +/- 45.89/ 23.81 %); best 0.005037s; worst 0.01152s; std dev. 0.003021 (taking best). - 11 threads: 0.005037s (0.17 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 0.03204s; avg 0.01068s ( +/- 21.37/ 14.39 %); best 0.008397s; worst 0.01222s; std dev. 0.001645 (taking best). - 10 threads: 0.008397s (0.1 Mflops) (1/2 degradations so far) - -3 iterations (9 th.) took 0.02001s; avg 0.00667s ( +/- 37.87/ 19.92 %); best 0.004144s; worst 0.007999s; std dev. 0.001787 (taking best). - 9 threads: 0.004144s (0.2 Mflops) (0/2 degradations so far) - -3 iterations (8 th.) took 0.03135s; avg 0.01045s ( +/- 21.70/ 12.05 %); best 0.008183s; worst 0.01171s; std dev. 0.001607 (taking best). - 8 threads: 0.008183s (0.1 Mflops) (1/2 degradations so far) - -3 iterations (7 th.) took 0.02443s; avg 0.008142s ( +/- 42.98/ 66.77 %); best 0.004642s; worst 0.01358s; std dev. 0.003897 (taking best). - 7 threads: 0.004642s (0.18 Mflops) (2/2 degradations so far) - -Best threads choice is 9; starting threads were 12; max speed gap is 2x; search took 0.16s. -Starting split (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 14 subms, 10 lsubms, 3.1429 bpnz (tpop: 0.004144 Mflops: 0.203) -Split (10 -> 25 leaves, 14 -> 34 subms) took 0.01494s (of which: 3.099e-06s analysis, -8.847e+09s mem.mgmt); compute time: 7.677e-05s overall, 1.907e-06s searches, 7.486e-05s shuffle, 6.175e-05s switch, 1.907e-06s quadrants. -3 iterations (12 th.) took 0.04074s; avg 0.01358s ( +/- 44.05/ 59.04 %); best 0.007597s; worst 0.0216s; std dev. 0.005894 (taking best). -~ 12 threads: 0.007597s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02419s; avg 0.008065s ( +/- 5.73/ 4.24 %); best 0.007603s; worst 0.008407s; std dev. 0.0003389 (taking best). - 11 threads: 0.007603s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.02356s; avg 0.007854s ( +/- 3.70/ 4.55 %); best 0.007564s; worst 0.008212s; std dev. 0.0002687 (taking best). - 10 threads: 0.007564s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (9 th.) took 0.02022s; avg 0.006739s ( +/- 37.20/ 18.71 %); best 0.004232s; worst 0.008s; std dev. 0.001773 (taking best). - 9 threads: 0.004232s (0.2 Mflops) (0/2 degradations so far) - -3 iterations (8 th.) took 0.02775s; avg 0.009251s ( +/- 16.04/ 22.92 %); best 0.007767s; worst 0.01137s; std dev. 0.001538 (taking best). - 8 threads: 0.007767s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (7 th.) took 0.02421s; avg 0.00807s ( +/- 1.09/ 1.89 %); best 0.007982s; worst 0.008222s; std dev. 0.000108 (taking best). - 7 threads: 0.007982s (0.11 Mflops) (2/2 degradations so far) - -Best threads choice is 9; starting threads were 12; max speed gap is 1.9x; search took 0.16s. -After split step 1: tpop: 0.004232 s ~Mflops: 0.198 nsubm:25 otn:9 -Applying split (10 -> 25 leaves, 9 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.021x: 0.004144s -> 0.004232s. -Split (25 -> 57 leaves, 34 -> 78 subms) took 0.01195s (of which: 5.96e-06s analysis, -2.123e+10s mem.mgmt); compute time: 2.122e-05s overall, 9.537e-07s searches, 2.027e-05s shuffle, 4.053e-06s switch, 1.192e-06s quadrants. -3 iterations (12 th.) took 0.02755s; avg 0.009182s ( +/- 56.11/ 30.20 %); best 0.00403s; worst 0.01196s; std dev. 0.003647 (taking best). -~ 12 threads: 0.00403s (0.21 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02443s; avg 0.008143s ( +/- 1.30/ 1.27 %); best 0.008037s; worst 0.008246s; std dev. 8.528e-05 (taking best). - 11 threads: 0.008037s (0.1 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.02377s; avg 0.007923s ( +/- 1.82/ 3.43 %); best 0.007779s; worst 0.008195s; std dev. 0.0001921 (taking best). - 10 threads: 0.007779s (0.11 Mflops) (2/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 2x; search took 0.076s. -After split step 2: tpop: 0.00403 s ~Mflops: 0.208 nsubm:57 otn:12 -Applying split (25 -> 57 leaves, 12 th.) yielded SPEEDUP of 1.028x: 0.004144s -> 0.00403s, so taking this instance. -Split (57 -> 137 leaves, 78 -> 186 subms) took 0.01593s (of which: 9.06e-06s analysis, -4.954e+10s mem.mgmt); compute time: 0.0003281s overall, 8.821e-06s searches, 0.0003192s shuffle, 0.000165s switch, 3.099e-05s quadrants. -3 iterations (12 th.) took 0.02395s; avg 0.007982s ( +/- 0.19/ 0.29 %); best 0.007967s; worst 0.008005s; std dev. 1.659e-05 (taking best). -~ 12 threads: 0.007967s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02399s; avg 0.007996s ( +/- 0.25/ 0.13 %); best 0.007976s; worst 0.008006s; std dev. 1.411e-05 (taking best). - 11 threads: 0.007976s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.028s; avg 0.009333s ( +/- 14.47/ 28.63 %); best 0.007983s; worst 0.01201s; std dev. 0.001889 (taking best). - 10 threads: 0.007983s (0.11 Mflops) (2/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 1x; search took 0.076s. -After split step 3: tpop: 0.007967 s ~Mflops: 0.105 nsubm:137 otn:12 -Applying split (57 -> 137 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.977x: 0.00403s -> 0.007967s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 split steps (of max 6) (10 -> 137 subms) took 0.3875s (of which 0.04302s partitioning, 0s I/O); computing times: 0.0004261s in par. loops, 1.168e-05s sorting, 1.812e-05s analyzing) -Total split + benchmarking process took 0.3875s, equivalent to 96.2/93.5 new/old ops (0.06331s for 2 clones -- as 15.7/15.3 ops, or 7.9/7.6 ops per clone), SPEEDUP of 1.028x -Applying multi-split (10 -> 57 leaves, 2 steps, 9 -> 12 th.sp.) yielded SPEEDUP of 1.028x (0.004144s -> 0.00403s), will amortize in 3400.5 ops by saving 0.000114s per op. -In 1 tuning rounds (tot. 0.95s, 0.094s for constructor, 3 clones) obtained a SPEEDUP of 2.8% (1.028x) (from 0.2027 to 0.2084 Mflops). +Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 22 subms, 16 lsubms, 3.4476 bpnz. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.325e-08 +Starting autotuning (16 x 3.32475e-08 s stages, transA=N, nrhs=1, timer gran.=3.32475e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.02149s; avg 0.007165s ( +/- 77.80/152.82 %); best 0.001591s; worst 0.01811s; std dev. 0.007743 (taking best). +~ 12 threads: 0.001591s (0.53 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.004225s; avg 0.001408s ( +/- 12.39/ 23.48 %); best 0.001234s; worst 0.001739s; std dev. 0.000234 (taking best). + 11 threads: 0.001234s (0.68 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 0.003719s; avg 0.00124s ( +/- 0.29/ 0.19 %); best 0.001236s; worst 0.001242s; std dev. 2.614e-06 (taking best). + 10 threads: 0.001236s (0.68 Mflops) (1/2 degradations so far) - +3 iterations (9 th.) took 0.003513s; avg 0.001171s ( +/- 11.70/ 6.32 %); best 0.001034s; worst 0.001245s; std dev. 9.698e-05 (taking best). + 9 threads: 0.001034s (0.81 Mflops) (0/2 degradations so far) - +3 iterations (8 th.) took 0.003299s; avg 0.0011s ( +/- 25.16/ 49.21 %); best 0.000823s; worst 0.001641s; std dev. 0.0003827 (taking best). + 8 threads: 0.000823s (1 Mflops) (0/2 degradations so far) - +3 iterations (7 th.) took 0.004112s; avg 0.001371s ( +/- 39.45/ 20.39 %); best 0.0008299s; worst 0.00165s; std dev. 0.0003824 (taking best). + 7 threads: 0.0008299s (1 Mflops) (1/2 degradations so far) - +3 iterations (6 th.) took 0.003708s; avg 0.001236s ( +/- 33.51/ 48.71 %); best 0.0008218s; worst 0.001838s; std dev. 0.0004356 (taking best). + 6 threads: 0.0008218s (1 Mflops) (0/2 degradations so far) - +3 iterations (5 th.) took 0.003289s; avg 0.001096s ( +/- 24.93/ 49.23 %); best 0.000823s; worst 0.001636s; std dev. 0.0003816 (taking best). + 5 threads: 0.000823s (1 Mflops) (1/2 degradations so far) - +3 iterations (4 th.) took 0.004101s; avg 0.001367s ( +/- 39.58/ 19.98 %); best 0.0008259s; worst 0.00164s; std dev. 0.0003826 (taking best). + 4 threads: 0.0008259s (1 Mflops) (2/2 degradations so far) - +Best threads choice is 6; starting threads were 12; max speed gap is 1.9x; search took 0.052s. +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, 22 subms, 16 lsubms, 3.4476 bpnz (tpop: 0.0008218 Mflops: 1.022) +Merge (16 -> 10 leaves) took w.c.t. of 0.0003159s, ~1.216e-05s of computing time (of which 2.146e-06s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.004538s; avg 0.001513s ( +/- 31.97/ 36.05 %); best 0.001029s; worst 0.002058s; std dev. 0.0004224 (taking best). +~ 12 threads: 0.001029s (0.82 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.003919s; avg 0.001306s ( +/- 20.62/ 10.62 %); best 0.001037s; worst 0.001445s; std dev. 0.0001905 (taking best). + 11 threads: 0.001037s (0.81 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.00374s; avg 0.001247s ( +/- 33.18/ 17.19 %); best 0.000833s; worst 0.001461s; std dev. 0.0002926 (taking best). + 10 threads: 0.000833s (1 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 0.003308s; avg 0.001103s ( +/- 24.36/ 48.55 %); best 0.000834s; worst 0.001638s; std dev. 0.0003785 (taking best). + 9 threads: 0.000834s (1 Mflops) (1/2 degradations so far) - +3 iterations (8 th.) took 0.004328s; avg 0.001443s ( +/- 41.56/ 27.90 %); best 0.000843s; worst 0.001845s; std dev. 0.0004322 (taking best). + 8 threads: 0.000843s (1 Mflops) (2/2 degradations so far) - +Best threads choice is 10; starting threads were 12; max speed gap is 1.2x; search took 0.02s. +After merge step 1: tpop: 0.000833 s ~Mflops: 1.008 nsubm:10 otn:10 +Applying merge (16 -> 10 leaves, 10 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98655x): 0.0008218s -> 0.000833s, so IGNORING this instance. +Merge (10 -> 8 leaves) took w.c.t. of 1.502e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.003335s; avg 0.001112s ( +/- 24.96/ 47.25 %); best 0.0008342s; worst 0.001637s; std dev. 0.0003717 (taking best). +~ 12 threads: 0.0008342s (1 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.004115s; avg 0.001372s ( +/- 39.41/ 19.85 %); best 0.0008311s; worst 0.001644s; std dev. 0.0003822 (taking best). + 11 threads: 0.0008311s (1 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 0.003504s; avg 0.001168s ( +/- 28.52/ 40.07 %); best 0.0008349s; worst 0.001636s; std dev. 0.0003407 (taking best). + 10 threads: 0.0008349s (1 Mflops) (1/2 degradations so far) - +3 iterations (9 th.) took 0.003355s; avg 0.001118s ( +/- 25.68/ 46.55 %); best 0.0008311s; worst 0.001639s; std dev. 0.0003687 (taking best). + 9 threads: 0.0008311s (1 Mflops) (0/2 degradations so far) - +3 iterations (8 th.) took 0.004108s; avg 0.001369s ( +/- 39.16/ 19.69 %); best 0.000833s; worst 0.001639s; std dev. 0.0003792 (taking best). + 8 threads: 0.000833s (1 Mflops) (1/2 degradations so far) - +3 iterations (7 th.) took 0.003303s; avg 0.001101s ( +/- 24.62/ 48.86 %); best 0.0008299s; worst 0.001639s; std dev. 0.0003804 (taking best). + 7 threads: 0.0008299s (1 Mflops) (0/2 degradations so far) - +3 iterations (6 th.) took 0.003758s; avg 0.001253s ( +/- 29.18/ 30.76 %); best 0.0008872s; worst 0.001638s; std dev. 0.0003068 (taking best). + 6 threads: 0.0008872s (0.95 Mflops) (1/2 degradations so far) - +3 iterations (5 th.) took 0.004107s; avg 0.001369s ( +/- 39.08/ 19.64 %); best 0.000834s; worst 0.001638s; std dev. 0.0003783 (taking best). + 5 threads: 0.000834s (1 Mflops) (2/2 degradations so far) - +Best threads choice is 7; starting threads were 12; max speed gap is 1.1x; search took 0.03s. +After merge step 2: tpop: 0.0008299 s ~Mflops: 1.012 nsubm:8 otn:7 +Applying merge (10 -> 8 leaves, 7 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=0.99023x): 0.0008218s -> 0.0008299s, so IGNORING this instance. +Merge (8 -> 6 leaves) took w.c.t. of 1.192e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.003305s; avg 0.001102s ( +/- 24.75/ 49.42 %); best 0.000829s; worst 0.001646s; std dev. 0.0003849 (taking best). +~ 12 threads: 0.000829s (1 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.004166s; avg 0.001389s ( +/- 40.16/ 22.21 %); best 0.0008309s; worst 0.001697s; std dev. 0.0003951 (taking best). + 11 threads: 0.0008309s (1 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.003321s; avg 0.001107s ( +/- 25.74/ 49.96 %); best 0.0008221s; worst 0.00166s; std dev. 0.0003911 (taking best). + 10 threads: 0.0008221s (1 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 0.004111s; avg 0.00137s ( +/- 39.43/ 19.97 %); best 0.0008299s; worst 0.001644s; std dev. 0.0003821 (taking best). + 9 threads: 0.0008299s (1 Mflops) (1/2 degradations so far) - +3 iterations (8 th.) took 0.003299s; avg 0.0011s ( +/- 24.42/ 48.67 %); best 0.0008311s; worst 0.001635s; std dev. 0.0003784 (taking best). + 8 threads: 0.0008311s (1 Mflops) (2/2 degradations so far) - +Best threads choice is 10; starting threads were 12; max speed gap is 1x; search took 0.018s. +After merge step 3: tpop: 0.0008221 s ~Mflops: 1.022 nsubm:6 otn:10 +Applying merge (8 -> 6 leaves, 10 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=0.99971x): 0.0008218s -> 0.0008221s, so IGNORING this instance. +Merge (6 -> 3 leaves) took w.c.t. of 9.06e-06s, ~4.053e-06s of computing time (of which 2.146e-06s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 0.004318s; avg 0.001439s ( +/- 42.21/ 28.13 %); best 0.0008318s; worst 0.001844s; std dev. 0.0004374 (taking best). +~ 12 threads: 0.0008318s (1 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.003299s; avg 0.0011s ( +/- 24.79/ 48.78 %); best 0.0008271s; worst 0.001636s; std dev. 0.0003793 (taking best). + 11 threads: 0.0008271s (1 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 0.004108s; avg 0.001369s ( +/- 39.30/ 19.69 %); best 0.0008311s; worst 0.001639s; std dev. 0.0003806 (taking best). + 10 threads: 0.0008311s (1 Mflops) (1/2 degradations so far) - +3 iterations (9 th.) took 0.003318s; avg 0.001106s ( +/- 24.96/ 47.84 %); best 0.0008299s; worst 0.001635s; std dev. 0.0003743 (taking best). + 9 threads: 0.0008299s (1 Mflops) (2/2 degradations so far) - +Best threads choice is 11; starting threads were 12; max speed gap is 1x; search took 0.015s. +After merge step 4: tpop: 0.0008271 s ~Mflops: 1.016 nsubm:3 otn:11 +Applying merge (6 -> 3 leaves, 11 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=0.99366x): 0.0008218s -> 0.0008271s, so IGNORING this instance. +Merge (3 -> 1 leaves) took w.c.t. of 1.407e-05s, ~5.96e-06s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.77/ 50.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +~ 12 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.77/ 50.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 11 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.54/200.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 10 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 91.63/200.00 %); best 3.325e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). + 9 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.54/200.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 8 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (7 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.54/200.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 7 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (6 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.54/200.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 6 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (5 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.54/200.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 5 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (4 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.77/ 50.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 4 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (3 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.54/200.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 3 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (2 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.54/200.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 2 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +3 iterations (1 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.54/200.00 %); best 3.325e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 1 threads: 3.325e-08s (2.5e+04 Mflops) (0/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 1x; search took 4.4e-05s. +After merge step 5: tpop: 3.325e-08 s ~Mflops: 25265.080 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 24718.537x: 0.0008218s -> 3.325e-08s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 5 merge steps (of max 6) (16 -> 1 subms) took 0.08729s (of which 0.000572s partitioning, 0s I/O); computing times: 3.123e-05s in par. loops, 8.106e-06s sorting, 1.717e-05s analyzing) +Total merge + benchmarking process took 0.08729s, equivalent to 2625399.8/106.2 new/old ops (0.007315s for 2 clones -- as 220014.3/8.9 ops, or 110007.2/4.5 ops per clone), SPEEDUP of 24718.537x +Applying multi-merge (16 -> 1 leaves, 5 steps, 6 -> 12 th.sp.) yielded SPEEDUP of 24718.537x (0.0008218s -> 3.325e-08s), will amortize in 106.2 ops by saving 0.0008218s per op. +In 1 tuning rounds (tot. 0.14s, 0.0073s for constructor, 2 clones) obtained a SPEEDUP of 2471753.7% (2.472e+04x) (from 1.022 to 2.527e+04 Mflops). check results are ok Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 3.103e-02 s (100.00 %) - analyzed arrays in 1.199e-02 s (38.65 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 1.172e-02 s (37.78 %) - shuffled partitions in 7.290e-03 s (23.50 %) - memory allocations took 1.192e-05 s (0.04 %) - leafs setup took 5.007e-06 s (0.02 %) - halfword conversion took 9.537e-07 s (0.00 %) -Built (6 x 6)[0xaaaaed5a6fc0]{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 3.977e-03 s (100.00 %) + analyzed arrays in 1.853e-03 s (46.59 %) + cleaned-up arrays in 9.537e-07 s (0.02 %) + deduplicated arrays in 9.537e-07 s (0.02 %) + sorted arrays in 1.276e-03 s (32.09 %) + shuffled partitions in 8.402e-04 s (21.13 %) + memory allocations took 1.907e-06 s (0.05 %) + leafs setup took 9.537e-07 s (0.02 %) + halfword conversion took 1.907e-06 s (0.05 %) +Built (6 x 6)[0xaaaab82d8f10]{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 0.1872E-03 s +Repeated USMV took 0.2189E-03 s A single USMM took 0.5960E-05 s -USMM-to-USMV speed ratio is is 31.40 x +USMM-to-USMV speed ratio is is 36.72 x Call auto-tuning routine.. Repeat measurement. -Tuned USMM took 0.2146E-05 s -Tuned-to-untuned speed ratio is is 2.778 x +Tuned USMM took 0.5007E-05 s +Tuned-to-untuned speed ratio is is 1.190 x FAILED: 0 PASSED: 2 /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran_rsb_fi @@ -8857,259 +8896,235 @@ 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 7.713e-02 s (100.00 %) - analyzed arrays in 2.349e-02 s (30.45 %) - cleaned-up arrays in 5.007e-06 s (0.01 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 2.140e-02 s (27.75 %) - shuffled partitions in 1.624e-02 s (21.05 %) - memory allocations took 1.621e-05 s (0.02 %) - leafs setup took 8.106e-06 s (0.01 %) - halfword conversion took 1.597e-02 s (20.70 %) -Built (6 x 6)[0xaaaadef32a20]{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 1.409e-02 s (100.00 %) + analyzed arrays in 4.488e-03 s (31.84 %) + cleaned-up arrays in 5.960e-06 s (0.04 %) + deduplicated arrays in 1.907e-06 s (0.01 %) + sorted arrays in 2.674e-03 s (18.97 %) + shuffled partitions in 3.466e-03 s (24.59 %) + memory allocations took 1.192e-05 s (0.08 %) + leafs setup took 5.007e-06 s (0.04 %) + halfword conversion took 3.426e-03 s (24.31 %) +Built (6 x 6)[0xaaaad8d61a20]{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)[0xaaaadef36aa0]{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)[0xaaaad8d65aa0]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.02664s; avg 0.00888s ( +/- 41.17/ 74.80 %); best 0.005224s; worst 0.01552s; std dev. 0.004705 (taking best). -Reference operation time is 0.00522399 s (0.02757 Mflops) with 12 threads. -After 0.026694s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.005579s; avg 0.00186s ( +/- 20.96/ 18.09 %); best 0.00147s; worst 0.002196s; std dev. 0.0002989 (taking best). +Reference operation time is 0.00146985 s (0.09797 Mflops) with 12 threads. +After 0.005623s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.026s; avg 0.008665s ( +/- 53.68/ 33.55 %); best 0.004014s; worst 0.01157s; std dev. 0.003323 (taking best). -Reference operation time is 0.00401402 s (0.03587 Mflops) with 12 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: 0.004014 Mflops: 0.036) -Merge (22 -> 16 leaves) took w.c.t. of 0.008339s, ~0.004116s of computing time (of which 1.907e-06s sorting, 5.96e-06s analysis) -3 iterations (12 th.) took 0.03586s; avg 0.01195s ( +/- 34.36/ 64.24 %); best 0.007846s; worst 0.01963s; std dev. 0.005435 (taking best). -Reference operation time is 0.00784588 s (0.01835 Mflops) with 12 threads. -After merge step 1: tpop: 0.007846 s ~Mflops: 0.018 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.955x: 0.004014s -> 0.007846s. -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 0.04423s (of which 0.008351s partitioning, 0s I/O); computing times: 0.004116s in par. loops, 1.907e-06s sorting, 5.96e-06s analyzing) -Total merge + benchmarking process took 0.04423s, equivalent to 11.0/11.0 new/old ops (0.02644s for 1 clones -- as 6.6/6.6 ops, or 6.6/6.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.02734s; avg 0.009112s ( +/- 14.43/ 26.73 %); best 0.007797s; worst 0.01155s; std dev. 0.001724 (taking best). -Reference operation time is 0.007797 s (0.01847 Mflops) with 12 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 D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.007797 Mflops: 0.018) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.008387s (of which: 4.053e-06s analysis, -3.539e+09s mem.mgmt); compute time: 0.0001168s overall, 9.537e-07s searches, 0.0001159s shuffle, 7.987e-05s switch, 0s quadrants. -3 iterations (12 th.) took 0.03153s; avg 0.01051s ( +/- 23.90/ 13.62 %); best 0.007998s; worst 0.01194s; std dev. 0.001782 (taking best). -Reference operation time is 0.00799799 s (0.018 Mflops) with 12 threads. -After split step 1: tpop: 0.007998 s ~Mflops: 0.018 nsubm:28 otn:12 -Applying split (22 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.026x: 0.007797s -> 0.007998s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01192s (of which: 5.96e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.02433s; avg 0.008109s ( +/- 50.56/ 47.61 %); best 0.004009s; worst 0.01197s; std dev. 0.003254 (taking best). -Reference operation time is 0.00400901 s (0.03592 Mflops) with 12 threads. -After split step 2: tpop: 0.004009 s ~Mflops: 0.036 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.945x: 0.007797s -> 0.004009s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01601s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.02021s; avg 0.006736s ( +/- 41.39/ 29.12 %); best 0.003948s; worst 0.008698s; std dev. 0.002025 (taking best). -Reference operation time is 0.00394797 s (0.03647 Mflops) with 12 threads. -After split step 3: tpop: 0.003948 s ~Mflops: 0.036 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.015x: 0.004009s -> 0.003948s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.008158s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.02343s; avg 0.007809s ( +/- 4.35/ 5.54 %); best 0.007469s; worst 0.008241s; std dev. 0.0003218 (taking best). -Reference operation time is 0.00746918 s (0.01928 Mflops) with 12 threads. -After split step 4: tpop: 0.007469 s ~Mflops: 0.019 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.892x: 0.003948s -> 0.007469s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 4 split steps (of max 6) (22 -> 28 subms) took 0.1921s (of which 0.04469s partitioning, 0s I/O); computing times: 0.0001168s in par. loops, 9.537e-07s sorting, 1.907e-05s analyzing) -Total split + benchmarking process took 0.1921s, equivalent to 48.7/24.6 new/old ops (0.07198s for 3 clones -- as 18.2/9.2 ops, or 6.1/3.1 ops per clone), SPEEDUP of 1.975x -Applying multi-split (22 -> 28 leaves, 3 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.975x (0.007797s -> 0.003948s), will amortize in 49.9 ops by saving 0.003849s per op. -In 1 tuning rounds (tot. 0.34s, 0.098s for constructor, 4 clones) obtained a SPEEDUP of 97.5% (1.975x) (from 0.01847 to 0.03647 Mflops). -After 0.340594s, global autotuning declared speedup of 1.97494 x, when using threads count of 12 and a new matrix: -(6 x 6)[0xaaaadef53050]{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: 28, symflags:'' +3 iterations (12 th.) took 0.004328s; avg 0.001443s ( +/- 0.46/ 0.30 %); best 0.001436s; worst 0.001447s; std dev. 4.784e-06 (taking best). +Reference operation time is 0.001436 s (0.1003 Mflops) with 12 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: 0.001436 Mflops: 0.100) +Merge (22 -> 16 leaves) took w.c.t. of 0.001812s, ~0.001466s of computing time (of which 2.146e-06s sorting, 2.861e-06s analysis) +3 iterations (12 th.) took 0.005696s; avg 0.001899s ( +/- 16.57/ 15.12 %); best 0.001584s; worst 0.002186s; std dev. 0.0002464 (taking best). +Reference operation time is 0.00158405 s (0.09091 Mflops) with 12 threads. +After merge step 1: tpop: 0.001584 s ~Mflops: 0.091 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.103x: 0.001436s -> 0.001584s. +Merge (16 -> 10 leaves) took w.c.t. of 0.0001819s, ~1.311e-05s of computing time (of which 3.099e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.005374s; avg 0.001791s ( +/- 12.52/ 16.50 %); best 0.001567s; worst 0.002087s; std dev. 0.0002181 (taking best). +Reference operation time is 0.00156713 s (0.09189 Mflops) with 12 threads. +After merge step 2: tpop: 0.001567 s ~Mflops: 0.092 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.091x: 0.001436s -> 0.001567s. +Merge (10 -> 7 leaves) took w.c.t. of 1.383e-05s, ~4.053e-06s of computing time (of which 1.192e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.003934s; avg 0.001311s ( +/- 28.31/ 28.95 %); best 0.0009401s; worst 0.001691s; std dev. 0.0003066 (taking best). +Reference operation time is 0.000940084 s (0.1532 Mflops) with 12 threads. +After merge step 3: tpop: 0.0009401 s ~Mflops: 0.153 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded SPEEDUP of 1.528x: 0.001436s -> 0.0009401s, so taking this instance. +Merge (7 -> 4 leaves) took w.c.t. of 1.097e-05s, ~1.907e-06s of computing time (of which 0s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 0.004095s; avg 0.001365s ( +/- 32.61/ 33.12 %); best 0.0009198s; worst 0.001817s; std dev. 0.0003663 (taking best). +Reference operation time is 0.000919819 s (0.1566 Mflops) with 12 threads. +After merge step 4: tpop: 0.0009198 s ~Mflops: 0.157 nsubm:4 otn:12 +Applying merge (7 -> 4 leaves, 12 th.) yielded SPEEDUP of 1.022x: 0.0009401s -> 0.0009198s, so taking this instance. +Merge (4 -> 1 leaves) took w.c.t. of 1.192e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 95.93/200.00 %); best 3.885e-08s; worst 2.861e-06s; std dev. 1.349e-06 (taking best). +Reference operation time is 3.88503e-08 s (3707 Mflops) with 12 threads. +After merge step 5: tpop: 3.885e-08 s ~Mflops: 3706.534 nsubm:1 otn:12 +Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 23675.974x: 0.0009198s -> 3.885e-08s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 5 merge steps (of max 6) (22 -> 1 subms) took 0.03469s (of which 0.002048s partitioning, 0s I/O); computing times: 0.001489s in par. loops, 7.391e-06s sorting, 1.574e-05s analyzing) +Total merge + benchmarking process took 0.03469s, equivalent to 892961.0/24.2 new/old ops (0.01721s for 4 clones -- as 442945.7/12.0 ops, or 110736.4/3.0 ops per clone), SPEEDUP of 36962.258x +Applying multi-merge (22 -> 1 leaves, 5 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 36962.258x (0.001436s -> 3.885e-08s), will amortize in 24.2 ops by saving 0.001436s per op. +In 1 tuning rounds (tot. 0.043s, 0.017s for constructor, 4 clones) obtained a SPEEDUP of 3696125.8% (3.696e+04x) (from 0.1003 to 3707 Mflops). +After 0.043226s, global autotuning declared speedup of 36962.3 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaad8d67e70]{D} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' Considering S clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 4.826e-02 s (100.00 %) - analyzed arrays in 1.688e-02 s (34.97 %) - cleaned-up arrays in 0.000e+00 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) + converted COO to RSB in 9.095e-03 s (100.00 %) + analyzed arrays in 3.416e-03 s (37.56 %) + cleaned-up arrays in 1.192e-06 s (0.01 %) + deduplicated arrays in 9.537e-07 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.589e-02 s (32.93 %) - memory allocations took 4.768e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 1.548e-02 s (32.07 %) -Built (6 x 6)[0xaaaadef36aa0]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' + shuffled partitions in 3.578e-03 s (39.34 %) + memory allocations took 9.537e-07 s (0.01 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 2.096e-03 s (23.05 %) +Built (6 x 6)[0xaaaad8d67e70]{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)[0xaaaadef36aa0]{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)[0xaaaad8d67e70]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.02419s; avg 0.008064s ( +/- 42.16/ 45.94 %); best 0.004664s; worst 0.01177s; std dev. 0.002908 (taking best). -Reference operation time is 0.00466418 s (0.03087 Mflops) with 12 threads. -After 0.024225s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.004222s; avg 0.001407s ( +/- 3.92/ 2.17 %); best 0.001352s; worst 0.001438s; std dev. 3.913e-05 (taking best). +Reference operation time is 0.00135207 s (0.1065 Mflops) with 12 threads. +After 0.004236s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.02082s; avg 0.006939s ( +/- 12.26/ 15.48 %); best 0.006088s; worst 0.008013s; std dev. 0.0008016 (taking best). -Reference operation time is 0.00608802 s (0.02365 Mflops) with 12 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: 0.006088 Mflops: 0.024) -Merge (16 -> 10 leaves) took w.c.t. of 0.003334s, ~1.001e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.03538s; avg 0.01179s ( +/- 34.03/ 66.14 %); best 0.007781s; worst 0.01959s; std dev. 0.005517 (taking best). -Reference operation time is 0.00778103 s (0.01851 Mflops) with 12 threads. -After merge step 1: tpop: 0.007781 s ~Mflops: 0.019 nsubm:10 otn:12 -Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.278x: 0.006088s -> 0.007781s. -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) (16 -> 10 subms) took 0.03874s (of which 0.003343s partitioning, 0s I/O); computing times: 1.001e-05s in par. loops, 1.907e-06s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.03874s, equivalent to 6.4/6.4 new/old ops (0.02771s for 1 clones -- as 4.6/4.6 ops, or 4.6/4.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.02355s; avg 0.007851s ( +/- 46.42/ 50.22 %); best 0.004207s; worst 0.01179s; std dev. 0.003105 (taking best). -Reference operation time is 0.0042069 s (0.03423 Mflops) with 12 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, 4.8889 bpnz (tpop: 0.004207 Mflops: 0.034) -Split (16 -> 28 leaves, 21 -> 37 subms) took 0.0158s (of which: 3.099e-06s analysis, -7.078e+09s mem.mgmt); compute time: 2.861e-05s overall, 2.146e-06s searches, 2.646e-05s shuffle, 1.287e-05s switch, 1.907e-06s quadrants. -3 iterations (12 th.) took 0.03197s; avg 0.01066s ( +/- 44.61/ 87.42 %); best 0.005903s; worst 0.01997s; std dev. 0.006587 (taking best). -Reference operation time is 0.00590277 s (0.0244 Mflops) with 12 threads. -After split step 1: tpop: 0.005903 s ~Mflops: 0.024 nsubm:28 otn:12 -Applying split (16 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.403x: 0.004207s -> 0.005903s. -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 -> 28 subms) took 0.04782s (of which 0.01582s partitioning, 0s I/O); computing times: 2.861e-05s in par. loops, 2.146e-06s sorting, 3.099e-06s analyzing) -Total split + benchmarking process took 0.04782s, equivalent to 11.4/11.4 new/old ops (0.02062s 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. 0.18s, 0.048s for constructor, 2 clones) obtained NO speedup (best stays 0.03423 Mflops). -After 0.179343s, global autotuning found old matrix optimal, with declared speedup 1 x when using 12 threads +3 iterations (12 th.) took 0.003769s; avg 0.001256s ( +/- 29.96/ 32.36 %); best 0.00088s; worst 0.001663s; std dev. 0.0003204 (taking best). +Reference operation time is 0.000880003 s (0.1636 Mflops) with 12 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: 0.00088 Mflops: 0.164) +Merge (16 -> 10 leaves) took w.c.t. of 0.0006752s, ~1.097e-05s of computing time (of which 2.146e-06s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 0.01863s; avg 0.006211s ( +/- 83.26/156.85 %); best 0.00104s; worst 0.01595s; std dev. 0.006893 (taking best). +Reference operation time is 0.00103998 s (0.1385 Mflops) with 12 threads. +After merge step 1: tpop: 0.00104 s ~Mflops: 0.138 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.182x: 0.00088s -> 0.00104s. +Merge (10 -> 7 leaves) took w.c.t. of 1.311e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.003699s; avg 0.001233s ( +/- 31.55/ 32.92 %); best 0.000844s; worst 0.001639s; std dev. 0.0003247 (taking best). +Reference operation time is 0.000844002 s (0.1706 Mflops) with 12 threads. +After merge step 2: tpop: 0.000844 s ~Mflops: 0.171 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded SPEEDUP of 1.043x: 0.00088s -> 0.000844s, so taking this instance. +Merge (7 -> 4 leaves) took w.c.t. of 7.868e-06s, ~4.053e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 0.003327s; avg 0.001109s ( +/- 25.34/ 48.68 %); best 0.000828s; worst 0.001649s; std dev. 0.0003818 (taking best). +Reference operation time is 0.000828028 s (0.1739 Mflops) with 12 threads. +After merge step 3: tpop: 0.000828 s ~Mflops: 0.174 nsubm:4 otn:12 +Applying merge (7 -> 4 leaves, 12 th.) yielded SPEEDUP of 1.019x: 0.000844s -> 0.000828s, so taking this instance. +Merge (4 -> 1 leaves) took w.c.t. of 5.96e-06s, ~2.146e-06s of computing time (of which 1.192e-06s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 90.22/200.00 %); best 3.885e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). +Reference operation time is 3.88503e-08 s (3707 Mflops) with 12 threads. +After merge step 4: tpop: 3.885e-08 s ~Mflops: 3706.534 nsubm:1 otn:12 +Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 21313.286x: 0.000828s -> 3.885e-08s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 4 merge steps (of max 6) (16 -> 1 subms) took 0.03824s (of which 0.0009198s partitioning, 0s I/O); computing times: 2.217e-05s in par. loops, 4.292e-06s sorting, 8.821e-06s analyzing) +Total merge + benchmarking process took 0.03824s, equivalent to 984265.1/43.5 new/old ops (0.015s for 4 clones -- as 385989.6/17.0 ops, or 96497.4/4.3 ops per clone), SPEEDUP of 22651.120x +Applying multi-merge (16 -> 1 leaves, 4 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 22651.120x (0.00088s -> 3.885e-08s), will amortize in 43.5 ops by saving 0.00088s per op. +In 1 tuning rounds (tot. 0.045s, 0.015s for constructor, 4 clones) obtained a SPEEDUP of 2265012.0% (2.265e+04x) (from 0.1636 to 3707 Mflops). +After 0.045416s, global autotuning declared speedup of 22651.1 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaad8d671a0]{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 4.826e-02 s (100.00 %) - analyzed arrays in 2.065e-02 s (42.78 %) - cleaned-up arrays in 1.192e-06 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) + converted COO to RSB in 8.303e-03 s (100.00 %) + analyzed arrays in 3.290e-03 s (39.62 %) + cleaned-up arrays in 0.000e+00 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.846e-02 s (38.25 %) - memory allocations took 6.676e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 9.144e-03 s (18.95 %) -Built (6 x 6)[0xaaaadef3d2d0]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' + shuffled partitions in 2.500e-03 s (30.11 %) + memory allocations took 9.060e-06 s (0.11 %) + leafs setup took 9.537e-07 s (0.01 %) + halfword conversion took 2.501e-03 s (30.12 %) +Built (6 x 6)[0xaaaad8d6b4d0]{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)[0xaaaadef3d2d0]{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)[0xaaaad8d6b4d0]{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 (12 th.) took 0.01182s; avg 0.00394s ( +/- 17.38/ 24.53 %); best 0.003255s; worst 0.004906s; std dev. 0.0007029 (taking best). -Reference operation time is 0.00325489 s (0.177 Mflops) with 12 threads. -After 0.011835s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.003653s; avg 0.001218s ( +/- 28.79/ 35.00 %); best 0.0008671s; worst 0.001644s; std dev. 0.0003216 (taking best). +Reference operation time is 0.000867128 s (0.6643 Mflops) with 12 threads. +After 0.003669s, 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 (12 th.) took 0.006129s; avg 0.002043s ( +/- 39.55/ 19.78 %); best 0.001235s; worst 0.002447s; std dev. 0.0005713 (taking best). -Reference operation time is 0.00123501 s (0.4664 Mflops) with 12 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: 0.001235 Mflops: 0.466) -Merge (22 -> 16 leaves) took w.c.t. of 0.0007951s, ~8.106e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 0.01253s; avg 0.004177s ( +/- 65.21/ 81.54 %); best 0.001453s; worst 0.007582s; std dev. 0.002548 (taking best). -Reference operation time is 0.00145292 s (0.3964 Mflops) with 12 threads. -After merge step 1: tpop: 0.001453 s ~Mflops: 0.396 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.176x: 0.001235s -> 0.001453s. -Merge (16 -> 10 leaves) took w.c.t. of 0.002338s, ~6.914e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.01499s; avg 0.004996s ( +/- 51.08/ 25.79 %); best 0.002444s; worst 0.006284s; std dev. 0.001804 (taking best). -Reference operation time is 0.00244403 s (0.2357 Mflops) with 12 threads. -After merge step 2: tpop: 0.002444 s ~Mflops: 0.236 nsubm:10 otn:12 -Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.979x: 0.001235s -> 0.002444s. -Skipping further merge based tests after 2 definite performance degradations in a row (and last exceeding limit). -A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.0307s (of which 0.003143s partitioning, 0s I/O); computing times: 1.502e-05s in par. loops, 1.907e-06s sorting, 7.153e-06s analyzing) -Total merge + benchmarking process took 0.0307s, equivalent to 24.9/24.9 new/old ops (0.006293s for 1 clones -- as 5.1/5.1 ops, or 5.1/5.1 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.005942s; avg 0.001981s ( +/- 6.56/ 3.30 %); best 0.001851s; worst 0.002046s; std dev. 9.182e-05 (taking best). -Reference operation time is 0.00185084 s (0.3112 Mflops) with 12 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: 0.001851 Mflops: 0.311) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.00305s (of which: 3.099e-06s analysis, -3.539e+09s mem.mgmt); compute time: 1.001e-05s overall, 9.537e-07s searches, 9.06e-06s shuffle, 4.053e-06s switch, 0s quadrants. -3 iterations (12 th.) took 0.006299s; avg 0.0021s ( +/- 40.42/ 33.16 %); best 0.001251s; worst 0.002796s; std dev. 0.0006399 (taking best). -Reference operation time is 0.00125098 s (0.4604 Mflops) with 12 threads. -After split step 1: tpop: 0.001251 s ~Mflops: 0.460 nsubm:28 otn:12 -Applying split (22 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.480x: 0.001851s -> 0.001251s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001873s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.003936s; avg 0.001312s ( +/- 36.51/ 41.00 %); best 0.000833s; worst 0.00185s; std dev. 0.0004172 (taking best). +3 iterations (12 th.) took 0.004749s; avg 0.001583s ( +/- 9.42/ 7.13 %); best 0.001434s; worst 0.001696s; std dev. 0.00011 (taking best). +Reference operation time is 0.00143385 s (0.4017 Mflops) with 12 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: 0.001434 Mflops: 0.402) +Merge (22 -> 16 leaves) took w.c.t. of 0.0001099s, ~8.106e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.00479s; avg 0.001597s ( +/- 22.22/ 19.87 %); best 0.001242s; worst 0.001914s; std dev. 0.0002757 (taking best). +Reference operation time is 0.00124192 s (0.4638 Mflops) with 12 threads. +After merge step 1: tpop: 0.001242 s ~Mflops: 0.464 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.155x: 0.001434s -> 0.001242s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.0002441s, ~7.153e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 0.004181s; avg 0.001394s ( +/- 25.81/ 22.26 %); best 0.001034s; worst 0.001704s; std dev. 0.0002757 (taking best). +Reference operation time is 0.00103402 s (0.557 Mflops) with 12 threads. +After merge step 2: tpop: 0.001034 s ~Mflops: 0.557 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.201x: 0.001242s -> 0.001034s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 1.407e-05s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.003703s; avg 0.001234s ( +/- 32.61/ 16.52 %); best 0.0008318s; worst 0.001438s; std dev. 0.0002846 (taking best). +Reference operation time is 0.000831842 s (0.6924 Mflops) with 12 threads. +After merge step 3: tpop: 0.0008318 s ~Mflops: 0.692 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded SPEEDUP of 1.243x: 0.001034s -> 0.0008318s, so taking this instance. +Merge (7 -> 4 leaves) took w.c.t. of 5.96e-06s, ~2.146e-06s of computing time (of which 0s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 0.004355s; avg 0.001452s ( +/- 42.61/ 30.00 %); best 0.000833s; worst 0.001887s; std dev. 0.0004494 (taking best). Reference operation time is 0.000833035 s (0.6914 Mflops) with 12 threads. -After split step 2: tpop: 0.000833 s ~Mflops: 0.691 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.502x: 0.001251s -> 0.000833s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001857s (of which: 2.146e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.004204s; avg 0.001401s ( +/- 35.86/ 18.40 %); best 0.0008988s; worst 0.001659s; std dev. 0.0003554 (taking best). -Reference operation time is 0.000898838 s (0.6408 Mflops) with 12 threads. -After split step 3: tpop: 0.0008988 s ~Mflops: 0.641 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.079x: 0.000833s -> 0.0008988s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001888s (of which: 2.146e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.005813s; avg 0.001938s ( +/- 23.77/ 14.83 %); best 0.001477s; worst 0.002225s; std dev. 0.000329 (taking best). -Reference operation time is 0.001477 s (0.39 Mflops) with 12 threads. -After split step 4: tpop: 0.001477 s ~Mflops: 0.390 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.773x: 0.000833s -> 0.001477s. -Skipping further split based tests after 2 definite performance degradations in a row (and last exceeding limit). -A total of 4 split steps (of max 6) (22 -> 28 subms) took 0.03672s (of which 0.008745s partitioning, 0s I/O); computing times: 1.001e-05s in par. loops, 9.537e-07s sorting, 1.144e-05s analyzing) -Total split + benchmarking process took 0.03672s, equivalent to 44.1/19.8 new/old ops (0.0164s for 3 clones -- as 19.7/8.9 ops, or 6.6/3.0 ops per clone), SPEEDUP of 2.222x -Applying multi-split (22 -> 28 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 2.222x (0.001851s -> 0.000833s), will amortize in 36.1 ops by saving 0.001018s per op. -In 1 tuning rounds (tot. 0.095s, 0.023s for constructor, 4 clones) obtained a SPEEDUP of 122.2% (2.222x) (from 0.3112 to 0.6914 Mflops). -After 0.094594s, global autotuning declared speedup of 2.22181 x, when using threads count of 12 and a new matrix: -(6 x 6)[0xaaaadef49340]{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:'' +After merge step 4: tpop: 0.000833 s ~Mflops: 0.691 nsubm:4 otn:12 +Applying merge (7 -> 4 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99857x): 0.0008318s -> 0.000833s, so IGNORING this instance. +Merge (4 -> 1 leaves) took w.c.t. of 5.96e-06s, ~1.907e-06s of computing time (of which 0s sorting, 0s analysis) +3 iterations (12 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 94.57/ 66.67 %); best 3.885e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). +Reference operation time is 3.88503e-08 s (1.483e+04 Mflops) with 12 threads. +After merge step 5: tpop: 3.885e-08 s ~Mflops: 14826.137 nsubm:1 otn:12 +Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 21411.476x: 0.0008318s -> 3.885e-08s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 5 merge steps (of max 6) (22 -> 1 subms) took 0.03197s (of which 0.0003917s partitioning, 0s I/O); computing times: 2.217e-05s in par. loops, 2.861e-06s sorting, 9.298e-06s analyzing) +Total merge + benchmarking process took 0.03197s, equivalent to 823000.9/22.3 new/old ops (0.01842s for 5 clones -- as 474231.4/12.8 ops, or 94846.3/2.6 ops per clone), SPEEDUP of 36907.027x +Applying multi-merge (22 -> 1 leaves, 5 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 36907.027x (0.001434s -> 3.885e-08s), will amortize in 22.3 ops by saving 0.001434s per op. +In 1 tuning rounds (tot. 0.041s, 0.018s for constructor, 5 clones) obtained a SPEEDUP of 3690602.7% (3.691e+04x) (from 0.4017 to 1.483e+04 Mflops). +After 0.040881s, global autotuning declared speedup of 36907 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaad8d6a340]{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 8.341e-03 s (100.00 %) - analyzed arrays in 3.784e-03 s (45.37 %) - cleaned-up arrays in 0.000e+00 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.01 %) + converted COO to RSB in 8.367e-03 s (100.00 %) + analyzed arrays in 2.665e-03 s (31.85 %) + cleaned-up arrays in 1.192e-06 s (0.01 %) + deduplicated arrays in 0.000e+00 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.875e-03 s (22.48 %) - memory allocations took 5.007e-06 s (0.06 %) - leafs setup took 9.537e-07 s (0.01 %) - halfword conversion took 2.674e-03 s (32.06 %) -Built (6 x 6)[0xaaaadef3d2d0]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' + shuffled partitions in 3.230e-03 s (38.60 %) + memory allocations took 5.722e-06 s (0.07 %) + leafs setup took 3.099e-06 s (0.04 %) + halfword conversion took 2.462e-03 s (29.42 %) +Built (6 x 6)[0xaaaad8d6a340]{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)[0xaaaadef3d2d0]{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)[0xaaaad8d6a340]{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 (12 th.) took 0.004096s; avg 0.001365s ( +/- 21.26/ 22.83 %); best 0.001075s; worst 0.001677s; std dev. 0.0002462 (taking best). -Reference operation time is 0.00107503 s (0.5358 Mflops) with 12 threads. -After 0.004113s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.003637s; avg 0.001212s ( +/- 26.67/ 38.56 %); best 0.0008891s; worst 0.00168s; std dev. 0.0003386 (taking best). +Reference operation time is 0.000889063 s (0.6479 Mflops) with 12 threads. +After 0.003655s, 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 (12 th.) took 0.00415s; avg 0.001383s ( +/- 39.99/ 20.14 %); best 0.0008302s; worst 0.001662s; std dev. 0.0003912 (taking best). -Reference operation time is 0.000830173 s (0.6938 Mflops) with 12 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: 0.0008302 Mflops: 0.694) -Merge (28 -> 22 leaves) took w.c.t. of 0.0002949s, ~8.106e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 0.02116s; avg 0.007054s ( +/- 45.29/ 23.08 %); best 0.003859s; worst 0.008682s; std dev. 0.002259 (taking best). -Reference operation time is 0.00385904 s (0.1493 Mflops) with 12 threads. -After merge step 1: tpop: 0.003859 s ~Mflops: 0.149 nsubm:22 otn:12 -Applying merge (28 -> 22 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 4.648x: 0.0008302s -> 0.003859s. +3 iterations (12 th.) took 0.004122s; avg 0.001374s ( +/- 38.64/ 28.39 %); best 0.000843s; worst 0.001764s; std dev. 0.000389 (taking best). +Reference operation time is 0.000843048 s (0.6832 Mflops) with 12 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: 0.000843 Mflops: 0.683) +Merge (28 -> 22 leaves) took w.c.t. of 0.0009749s, ~6.914e-06s of computing time (of which 0s sorting, 3.815e-06s analysis) +3 iterations (12 th.) took 0.005708s; avg 0.001903s ( +/- 21.75/ 18.20 %); best 0.001489s; worst 0.002249s; std dev. 0.0003139 (taking best). +Reference operation time is 0.00148892 s (0.3869 Mflops) with 12 threads. +After merge step 1: tpop: 0.001489 s ~Mflops: 0.387 nsubm:22 otn:12 +Applying merge (28 -> 22 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.766x: 0.000843s -> 0.001489s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (28 -> 22 subms) took 0.02148s (of which 0.000298s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02148s, equivalent to 25.9/25.9 new/old ops (0.003702s for 1 clones -- as 4.5/4.5 ops, or 4.5/4.5 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (28 -> 22 subms) took 0.006705s (of which 0.0009789s partitioning, 0s I/O); computing times: 6.914e-06s in par. loops, 0s sorting, 3.815e-06s analyzing) +Total merge + benchmarking process took 0.006705s, equivalent to 8.0/8.0 new/old ops (0.003669s for 1 clones -- as 4.4/4.4 ops, or 4.4/4.4 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.006369s; avg 0.002123s ( +/- 3.67/ 7.16 %); best 0.002045s; worst 0.002275s; std dev. 0.0001075 (taking best). -Reference operation time is 0.00204515 s (0.2816 Mflops) with 12 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.002045 Mflops: 0.282) -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.003114s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.006174s; avg 0.002058s ( +/- 0.44/ 0.73 %); best 0.002049s; worst 0.002073s; std dev. 1.07e-05 (taking best). -Reference operation time is 0.00204897 s (0.2811 Mflops) with 12 threads. -After split step 1: tpop: 0.002049 s ~Mflops: 0.281 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99814x): 0.002045s -> 0.002049s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.003179s (of which: 1.907e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.005549s; avg 0.00185s ( +/- 33.18/ 21.81 %); best 0.001236s; worst 0.002253s; std dev. 0.000441 (taking best). -Reference operation time is 0.00123596 s (0.466 Mflops) with 12 threads. -After split step 2: tpop: 0.001236 s ~Mflops: 0.466 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.655x: 0.002045s -> 0.001236s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001658s (of which: 2.861e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.004981s; avg 0.00166s ( +/- 49.41/ 60.70 %); best 0.0008399s; worst 0.002668s; std dev. 0.000758 (taking best). -Reference operation time is 0.000839949 s (0.6858 Mflops) with 12 threads. -After split step 3: tpop: 0.0008399 s ~Mflops: 0.686 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.471x: 0.001236s -> 0.0008399s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001469s (of which: 2.861e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.004561s; avg 0.00152s ( +/- 29.68/ 20.96 %); best 0.001069s; worst 0.001839s; std dev. 0.000328 (taking best). -Reference operation time is 0.00106907 s (0.5388 Mflops) with 12 threads. -After split step 4: tpop: 0.001069 s ~Mflops: 0.539 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.273x: 0.0008399s -> 0.001069s. +3 iterations (12 th.) took 0.005771s; avg 0.001924s ( +/- 14.12/ 27.36 %); best 0.001652s; worst 0.00245s; std dev. 0.0003722 (taking best). +Reference operation time is 0.001652 s (0.3487 Mflops) with 12 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.001652 Mflops: 0.349) +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001483s (of which: 3.815e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.00397s; avg 0.001323s ( +/- 20.89/ 39.20 %); best 0.001047s; worst 0.001842s; std dev. 0.0003671 (taking best). +Reference operation time is 0.0010469 s (0.5502 Mflops) with 12 threads. +After split step 1: tpop: 0.001047 s ~Mflops: 0.550 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.578x: 0.001652s -> 0.001047s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001656s (of which: 2.146e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.004867s; avg 0.001622s ( +/- 10.87/ 8.91 %); best 0.001446s; worst 0.001767s; std dev. 0.0001329 (taking best). +Reference operation time is 0.00144601 s (0.3983 Mflops) with 12 threads. +After split step 2: tpop: 0.001446 s ~Mflops: 0.398 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.381x: 0.001047s -> 0.001446s. Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 4 split steps (of max 6) (28 -> 28 subms) took 0.04157s (of which 0.009467s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.168e-05s analyzing) -Total split + benchmarking process took 0.04157s, equivalent to 49.5/20.3 new/old ops (0.02078s for 3 clones -- as 24.7/10.2 ops, or 8.2/3.4 ops per clone), SPEEDUP of 2.435x -Applying multi-split (28 -> 28 leaves, 3 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 2.435x (0.002045s -> 0.0008399s), will amortize in 34.5 ops by saving 0.001205s per op. -In 1 tuning rounds (tot. 0.087s, 0.024s for constructor, 4 clones) obtained a SPEEDUP of 143.5% (2.435x) (from 0.2816 to 0.6858 Mflops). -After 0.087436s, global autotuning declared speedup of 2.43486 x, when using threads count of 12 and a new matrix: -(6 x 6)[0xaaaadef4cec0]{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:'' +A total of 2 split steps (of max 6) (28 -> 28 subms) took 0.01661s (of which 0.003423s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 5.96e-06s analyzing) +Total split + benchmarking process took 0.01661s, equivalent to 15.9/10.1 new/old ops (0.008623s for 2 clones -- as 8.2/5.2 ops, or 4.1/2.6 ops per clone), SPEEDUP of 1.578x +Applying multi-split (28 -> 28 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.578x (0.001652s -> 0.001047s), will amortize in 27.5 ops by saving 0.0006051s per op. +In 1 tuning rounds (tot. 0.041s, 0.012s for constructor, 3 clones) obtained a SPEEDUP of 57.8% (1.578x) (from 0.3487 to 0.5502 Mflops). +After 0.041231s, global autotuning declared speedup of 1.578 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaad8d71270]{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:'' 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' @@ -9240,9 +9255,9 @@ 4 0 DIFF PRINT TEST END Beginning large binary search test. -Detected 63089258496 bytes of memory, comprehensive of 34448744448 of free memory. +Detected 63089266688 bytes of memory, comprehensive of 18263695360 of free memory. On this system, maximal array of coordinates can have 2147483137 elements and occupy 8589932548 bytes. -Will perform the test using less memory (17592186036287 MB) than on the maximal coordinate indices array (18446744065186371584) allows. +Will perform the test using less memory (17592186041095 MB) than on the maximal coordinate indices array (18446744070227453952) allows. Skipping test: too little memory. Skipping large binary search test. BASIC SPARSE BLAS TEST: BEGIN @@ -9251,7 +9266,7 @@ got RSB_IO_WANT_IS_INITIALIZED_MARKER: 1 INIT INTERFACE TEST: END (SUCCESS) DEVEL PRINT TEST: BEGIN -(4 x 4)[0xaaaad29083a0]{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)[0xaaaaaef713a0]{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 | @@ -9260,8 +9275,8 @@ RSB_FLAG_ASSEMBLED_IN_COO_ARRAYS | RSB_FLAG_OWN_PARTITIONING_ARRAYS | RSB_FLAG_SORT_INPUT -(2 x 2)[0xaaaad29084b0]{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)[0xaaaad29085c0]{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)[0xaaaaaef714b0]{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)[0xaaaaaef715c0]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' #R 4 x 4, 4 nnz (16 bytes), 16 index space for bytes, 544 bytes for 2 structs (2 of which are on the diagonal) (1e+02% of nnz are on the diagonal) #N at 0 0, 4 x 4, 4 nnz ( 25%) #T at 0 0, 2 x 2, 2 nnz ( 50%) @@ -9269,9 +9284,9 @@ ( 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)[0xaaaad29084b0]{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)[0xaaaad29085c0]{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)[0xaaaad29083a0]{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)[0xaaaaaef714b0]{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)[0xaaaaaef715c0]{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)[0xaaaaaef713a0]{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 | @@ -9289,8 +9304,8 @@ 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 30.004950 s, max allowed was 30.000000. - PASSED:13074 +Terminating testing earlier due to user timeout request: test took 30.001114 s, max allowed was 30.000000. + PASSED:14384 FAILED:0 ADVANCED SPARSE BLAS TEST: END (SUCCESS) gmake qtests -C librsbpp @@ -9299,10 +9314,10 @@ 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 -++ wc -l ++ grep Z-sort +++ wc -l + test 54 = 54 ++ ./rsbpp Td G.mtx ++ grep Z-sort @@ -9354,25 +9369,25 @@ ++ grep spmm- ++ wc -l + test 9 = 9 +++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1sFvtN,T -++ grep spmm- ++ wc -l + test 3 = 3 -++ grep spmm- ++ OMP_NUM_THREADS=1 +++ grep spmm- ++ ./rsbpp C1000m100M100I1r1vtN,TsF ++ wc -l + test 2 = 2 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r0vtN,TsF -++ wc -l ++ grep spmm- +++ wc -l + test 0 = 0 ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 -++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF ++ grep Recursing +++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF ++ wc -l + test 4 = 4 ++ OMP_NUM_THREADS=2 @@ -9382,10 +9397,10 @@ ++ wc -l + test 4 = 4 ++ OMP_NUM_THREADS=1 -++ RSB_NUM_THREADS=1 -++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF ++ grep Recursing ++ wc -l +++ RSB_NUM_THREADS=1 +++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF + test 208 = 208 ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 @@ -9438,7 +9453,7 @@ 0 0 0 0 before tuning for SPMV: -(3 x 3)[0xaaaae43d54c0]{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)[0xaaaaed9c9b10]{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 @@ -9527,18 +9542,18 @@ BEGIN Rsb_Matrix_test_multimatrix_ms_mnrhs BEGIN -(3 x 3)[0xaaaae4408c50]{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)[0xaaaaed9fa9a0]{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 1.01211: +(3 x 3)[0xaaaaed9fdec0]{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)[0xaaaaed9fa9a0]{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)[0xaaaae4408c50]{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)[0xaaaae43e27e0]{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 1.14773: -(3 x 3)[0xaaaae43fd2d0]{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)[0xaaaae4408c50]{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)[0xaaaae4408c50]{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)[0xaaaae43e27e0]{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 1.04545: -(3 x 3)[0xaaaae4409470]{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)[0xaaaaed9fa9a0]{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)[0xaaaaed9dd2e0]{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 1.00491: +(3 x 3)[0xaaaaed9fcb90]{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)[0xaaaaed9fa9a0]{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 1.31606: +(3 x 3)[0xaaaaeda00eb0]{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 ! @@ -9555,10 +9570,10 @@ ./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 codethink03-arm64 +running on i-capture-the-hostname Built without the MKL. ( ! ./rsbtest --unrecognized-option-triggers-abort ) -running on codethink03-arm64 +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 ) @@ -9567,7 +9582,7 @@ ( ! ./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 codethink03-arm64 +running on i-capture-the-hostname Will not invoke autotuning routine. Benchmark will sample for at most 0.01 s Built without render support! @@ -9619,7 +9634,7 @@ 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/aarch64-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/aarch64-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/aarch64-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/aarch64-linux-gnu/librsb.so.0.0.0 libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-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/aarch64-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; }; }) @@ -9629,7 +9644,7 @@ libtool: install: ranlib /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-linux-gnu/librsb.a libtool: warning: remember to run 'libtool --finish /usr/lib/aarch64-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/aarch64-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' @@ -9764,11 +9779,11 @@ dh_gencontrol dh_md5sums dh_builddeb -dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-7_arm64.deb'. +dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-7_arm64.deb'. dpkg-deb: building package 'librsb0t64' in '../librsb0t64_1.3.0.2+dfsg-7_arm64.deb'. dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-7_arm64.deb'. -dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-7_arm64.deb'. dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-7_arm64.deb'. +dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-7_arm64.deb'. dpkg-deb: building package 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-7_all.deb'. dpkg-genbuildinfo --build=binary -O../librsb_1.3.0.2+dfsg-7_arm64.buildinfo dpkg-genchanges --build=binary -O../librsb_1.3.0.2+dfsg-7_arm64.changes @@ -9778,12 +9793,14 @@ 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/259719/tmp/hooks/B01_cleanup starting +I: user script /srv/workspace/pbuilder/259719/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/3814367 and its subdirectories -I: Current time: Sun Jan 25 20:09:31 -12 2026 -I: pbuilder-time-stamp: 1769414971 +I: removing directory /srv/workspace/pbuilder/259719 and its subdirectories +I: Current time: Mon Jan 26 22:26:52 +14 2026 +I: pbuilder-time-stamp: 1769416012