Diff of the two buildlogs: -- --- b1/build.log 2024-06-07 08:28:16.083307546 +0000 +++ b2/build.log 2024-06-07 08:54:51.235387930 +0000 @@ -1,6 +1,6 @@ I: pbuilder: network access will be disabled during build -I: Current time: Thu Jun 6 20:15:57 -12 2024 -I: pbuilder-time-stamp: 1717748157 +I: Current time: Fri Jul 11 04:51:20 +14 2025 +I: pbuilder-time-stamp: 1752159080 I: Building the build Environment I: extracting base tarball [/var/cache/pbuilder/unstable-reproducible-base.tgz] I: copying local configuration @@ -27,51 +27,83 @@ dpkg-source: info: applying auto-gitignore I: Not using root during the build. I: Installing the build-deps -I: user script /srv/workspace/pbuilder/3725028/tmp/hooks/D02_print_environment starting +I: user script /srv/workspace/pbuilder/2972863/tmp/hooks/D01_modify_environment starting +debug: Running on infom02-amd64. +I: Changing host+domainname to test build reproducibility +I: Adding a custom variable just for the fun of it... +I: Changing /bin/sh to bash +'/bin/sh' -> '/bin/bash' +lrwxrwxrwx 1 root root 9 Jul 10 14:51 /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/2972863/tmp/hooks/D01_modify_environment finished +I: user script /srv/workspace/pbuilder/2972863/tmp/hooks/D02_print_environment starting I: set - BUILDDIR='/build/reproducible-path' - BUILDUSERGECOS='first user,first room,first work-phone,first home-phone,first other' - BUILDUSERNAME='pbuilder1' - BUILD_ARCH='amd64' - DEBIAN_FRONTEND='noninteractive' + 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]="21" [3]="1" [4]="release" [5]="x86_64-pc-linux-gnu") + BASH_VERSION='5.2.21(1)-release' + BUILDDIR=/build/reproducible-path + BUILDUSERGECOS='second user,second room,second work-phone,second home-phone,second other' + BUILDUSERNAME=pbuilder2 + BUILD_ARCH=amd64 + DEBIAN_FRONTEND=noninteractive DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=12 ' - DISTRIBUTION='unstable' - HOME='/root' - HOST_ARCH='amd64' + DIRSTACK=() + DISTRIBUTION=unstable + EUID=0 + FUNCNAME=([0]="Echo" [1]="main") + GROUPS=() + HOME=/root + HOSTNAME=i-capture-the-hostname + HOSTTYPE=x86_64 + HOST_ARCH=amd64 IFS=' ' - INVOCATION_ID='172602b4aacf42b7a48d0cc6a761f347' - 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='3725028' - PS1='# ' - PS2='> ' + INVOCATION_ID=4e116aa7ce274b2cbe69f0ffac72d3b9 + LANG=C + LANGUAGE=et_EE:et + LC_ALL=C + MACHTYPE=x86_64-pc-linux-gnu + MAIL=/var/mail/root + OPTERR=1 + OPTIND=1 + OSTYPE=linux-gnu + PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path + PBCURRENTCOMMANDLINEOPERATION=build + PBUILDER_OPERATION=build + PBUILDER_PKGDATADIR=/usr/share/pbuilder + PBUILDER_PKGLIBDIR=/usr/lib/pbuilder + PBUILDER_SYSCONFDIR=/etc + PIPESTATUS=([0]="0") + POSIXLY_CORRECT=y + PPID=2972863 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.p0t6z6kJ/pbuilderrc_dVwB --distribution unstable --hookdir /etc/pbuilder/first-build-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/unstable-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.p0t6z6kJ/b1 --logfile b1/build.log librsb_1.3.0.2+dfsg-6.1.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' + 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.p0t6z6kJ/pbuilderrc_Zsgt --distribution unstable --hookdir /etc/pbuilder/rebuild-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/unstable-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.p0t6z6kJ/b2 --logfile b2/build.log librsb_1.3.0.2+dfsg-6.1.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' I: uname -a - Linux infom01-amd64 6.1.0-21-cloud-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.1.90-1 (2024-05-03) x86_64 GNU/Linux + Linux i-capture-the-hostname 6.7.12+bpo-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.7.12-1~bpo12+1 (2024-05-06) x86_64 GNU/Linux I: ls -l /bin - lrwxrwxrwx 1 root root 7 Jun 6 07:42 /bin -> usr/bin -I: user script /srv/workspace/pbuilder/3725028/tmp/hooks/D02_print_environment finished + lrwxrwxrwx 1 root root 7 Jul 9 14:05 /bin -> usr/bin +I: user script /srv/workspace/pbuilder/2972863/tmp/hooks/D02_print_environment finished -> Attempting to satisfy build-dependencies -> Creating pbuilder-satisfydepends-dummy package Package: pbuilder-satisfydepends-dummy @@ -288,7 +320,7 @@ Get: 169 http://deb.debian.org/debian unstable/main amd64 libltdl-dev amd64 2.4.7-7+b1 [164 kB] Get: 170 http://deb.debian.org/debian unstable/main amd64 libhwloc-dev amd64 2.10.0-1+b1 [250 kB] Get: 171 http://deb.debian.org/debian unstable/main amd64 zlib1g-dev amd64 1:1.3.dfsg+really1.3.1-1 [919 kB] -Fetched 360 MB in 3s (111 MB/s) +Fetched 360 MB in 4s (99.3 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 ... 19716 files and directories currently installed.) @@ -852,8 +884,8 @@ Setting up tzdata (2024a-4) ... Current default time zone: 'Etc/UTC' -Local time is now: Fri Jun 7 08:17:59 UTC 2024. -Universal Time is now: Fri Jun 7 08:17:59 UTC 2024. +Local time is now: Thu Jul 10 14:53:52 UTC 2025. +Universal Time is now: Thu Jul 10 14:53:52 UTC 2025. Run 'dpkg-reconfigure tzdata' if you wish to change it. Setting up libfontenc1:amd64 (1:1.1.8-1) ... @@ -1020,7 +1052,11 @@ 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-6.1_source.changes +I: user script /srv/workspace/pbuilder/2972863/tmp/hooks/A99_set_merged_usr starting +Not re-configuring usrmerge for unstable +I: user script /srv/workspace/pbuilder/2972863/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-6.1_source.changes dpkg-buildpackage: info: source package librsb dpkg-buildpackage: info: source version 1.3.0.2+dfsg-6.1 dpkg-buildpackage: info: source distribution unstable @@ -1048,62 +1084,62 @@ cp: warning: behavior of -n is non-portable and may change in future; use --update=none instead cp: warning: behavior of -n is non-portable and may change in future; use --update=none instead 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'. @@ -1145,90 +1181,90 @@ 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' @@ -1411,7 +1447,7 @@ 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 @@ -1528,7 +1564,7 @@ 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 @@ -1550,7 +1586,7 @@ config.status: executing depfiles commands config.status: executing libtool commands === configuring in librsbpp (/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1672,7 +1708,7 @@ 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 @@ -1681,7 +1717,7 @@ config.status: executing libtool commands configure: Successfully created a Makefile. === configuring in rsblib (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1790,7 +1826,7 @@ 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 @@ -1800,7 +1836,7 @@ config.status: executing libtool commands configure: Created a Makefile. === configuring in rsbtest (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1911,7 +1947,7 @@ 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 @@ -1943,7 +1979,7 @@ ARFLAGS : cru M4 : m4 MAKE : gmake - BASH : /bin/bash + BASH : /bin/sh OCTAVE : false DOXYGEN : doxygen HELP2MAN : help2man @@ -1999,24 +2035,24 @@ 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 -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp.o rsbpp.cpp -/bin/bash ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_coo.lo rsbpp_coo.cpp -/bin/bash ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_csr.lo rsbpp_csr.cpp +/bin/sh ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_coo.lo rsbpp_coo.cpp +/bin/sh ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_csr.lo rsbpp_csr.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbtt.o rsbtt.cpp gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -c -o rsbct.o rsbct.c libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -fPIC -DPIC -o .libs/rsbpp_coo.o libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_csr.cpp -fPIC -DPIC -o .libs/rsbpp_csr.o libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -o rsbpp_coo.o >/dev/null 2>&1 libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_csr.cpp -o rsbpp_csr.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o librsbpp.la rsbpp_coo.lo rsbpp_csr.lo -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o librsbpp.la rsbpp_coo.lo rsbpp_csr.lo -lpthread -lstdc++fs libtool: link: ar cr .libs/librsbpp.a .libs/rsbpp_coo.o .libs/rsbpp_csr.o libtool: link: ranlib .libs/librsbpp.a libtool: link: ( cd ".libs" && rm -f "librsbpp.la" && ln -s "../librsbpp.la" "librsbpp.la" ) -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbpp rsbpp.o librsbpp.la -lpthread -lstdc++fs -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbtt rsbtt.o librsbpp.la -lpthread -lstdc++fs -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbct rsbct.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbpp rsbpp.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbtt rsbtt.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbct rsbct.o librsbpp.la -lpthread -lstdc++fs libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbct rsbct.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp -libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o 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 -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbtt rsbtt.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp +libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbpp rsbpp.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' @@ -2034,88 +2070,100 @@ gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsbench-rsb_libspblas_tests.o `test -f 'rsb_libspblas_tests.c' || echo './'`rsb_libspblas_tests.c g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -c -o rsb_dummy.o rsb_dummy.cpp gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o ch2icfb-ch2icfb.o `test -f 'ch2icfb.c' || echo './'`ch2icfb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_stropts.lo `test -f 'rsb_stropts.c' || echo './'`rsb_stropts.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_strmif.lo `test -f 'rsb_strmif.c' || echo './'`rsb_strmif.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_unroll.lo `test -f 'rsb_unroll.c' || echo './'`rsb_unroll.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_strmif.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_stropts.lo `test -f 'rsb_stropts.c' || echo './'`rsb_stropts.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_stropts.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_lb.lo `test -f 'rsb_krnl_lb.c' || echo './'`rsb_krnl_lb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_vb.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_strmif.lo `test -f 'rsb_strmif.c' || echo './'`rsb_strmif.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_unroll.lo `test -f 'rsb_unroll.c' || echo './'`rsb_unroll.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -o librsb_nounroll_la-rsb_stropts.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_strmif.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_lb.lo `test -f 'rsb_krnl_lb.c' || echo './'`rsb_krnl_lb.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_unroll.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_unroll.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_vb.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_lb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_lb.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -o librsb_nounroll_la-rsb_stropts.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_unroll.c -o librsb_nounroll_la-rsb_unroll.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_lb.c -o librsb_nounroll_la-rsb_krnl_lb.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_permute.lo `test -f 'rsb_permute.c' || echo './'`rsb_permute.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -o librsb_nounroll_la-rsb_strmif.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_bench.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_permute.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_permute.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_lb.c -o librsb_nounroll_la-rsb_krnl_lb.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_permute.lo `test -f 'rsb_permute.c' || echo './'`rsb_permute.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -o librsb_nounroll_la-rsb_strmif.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_l.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo `test -f 'rsb_krnl_bcss_spsv_u.c' || echo './'`rsb_krnl_bcss_spsv_u.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_permute.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_permute.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_l.c -o librsb_nounroll_la-rsb_krnl_bcss_l.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo `test -f 'rsb_krnl_bcss_spmv_u.c' || echo './'`rsb_krnl_bcss_spmv_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo `test -f 'rsb_krnl_bcss_misc_u.c' || echo './'`rsb_krnl_bcss_misc_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo `test -f 'rsb_krnl_bcss_spsv_u.c' || echo './'`rsb_krnl_bcss_spsv_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo `test -f 'rsb_krnl_bcss_spmv_u.c' || echo './'`rsb_krnl_bcss_spmv_u.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_u.c -o librsb_nounroll_la-rsb_krnl_bcss_u.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo `test -f 'rsb_krnl_bcoo_spmv_u.c' || echo './'`rsb_krnl_bcoo_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 -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss.lo `test -f 'rsb_krnl_bcss.c' || echo './'`rsb_krnl_bcss.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo `test -f 'rsb_krnl_bcss_misc_u.c' || echo './'`rsb_krnl_bcss_misc_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo `test -f 'rsb_krnl_bcoo_spmv_u.c' || echo './'`rsb_krnl_bcoo_spmv_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss.lo `test -f 'rsb_krnl_bcss.c' || echo './'`rsb_krnl_bcss.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spmv.lo `test -f 'rsb_spmv.c' || echo './'`rsb_spmv.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_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 -fcf-protection -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spmv.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -o librsb_nounroll_la-rsb_krnl_bcss.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -o librsb_nounroll_la-rsb_bench.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_ompio.lo `test -f 'rsb_ompio.c' || echo './'`rsb_ompio.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_merge.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_merge.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_ompio.lo `test -f 'rsb_ompio.c' || echo './'`rsb_ompio.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_ompio.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_ompio.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -o librsb_nounroll_la-rsb_bench.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_ompio.c -o librsb_nounroll_la-rsb_ompio.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_util.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spgemm_csr.lo `test -f 'rsb_spgemm_csr.c' || echo './'`rsb_spgemm_csr.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spgemm_csr.lo `test -f 'rsb_spgemm_csr.c' || echo './'`rsb_spgemm_csr.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_util.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm_csr.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spgemm_csr.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spsum_misc.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_prec.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_prec.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_is.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_prec.c -o librsb_nounroll_la-rsb_prec.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm_csr.c -o librsb_nounroll_la-rsb_spgemm_csr.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mio.lo `test -f 'rsb_mio.c' || echo './'`rsb_mio.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_op.lo `test -f 'rsb_op.c' || echo './'`rsb_op.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_prec.c -o librsb_nounroll_la-rsb_prec.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_is.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mio.lo `test -f 'rsb_mio.c' || echo './'`rsb_mio.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_op.lo `test -f 'rsb_op.c' || echo './'`rsb_op.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mio.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_bio.lo `test -f 'rsb_bio.c' || echo './'`rsb_bio.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_op.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_op.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_bio.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_op.c -o librsb_base_la-rsb_op.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_set.lo `test -f 'rsb_set.c' || echo './'`rsb_set.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_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 -fcf-protection -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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_get.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_get.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -o librsb_base_la-rsb_bio.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_mio.c -o librsb_base_la-rsb_mio.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_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 -fcf-protection -O3 -std=c99 -c rsb_set.c -o librsb_base_la-rsb_set.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_set.lo `test -f 'rsb_set.c' || echo './'`rsb_set.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo.lo `test -f 'rsb_coo.c' || echo './'`rsb_coo.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_set.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_set.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_set.c -o librsb_base_la-rsb_set.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_csr.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_get.c -o librsb_base_la-rsb_get.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_coo_check.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_check.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_idx.lo `test -f 'rsb_idx.c' || echo './'`rsb_idx.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_symm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_symm.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_coo_check.c -o librsb_base_la-rsb_coo_check.o >/dev/null 2>&1 rsb_test_matops.c: In function 'rsb__main_block_partitioned_spmv_sxsa': rsb_test_matops.c:214:41: warning: '%s' directive writing up to 2047 bytes into a region of size 1011 [-Wformat-overflow=] 214 | rsb__sprintf(dst,"%s%s_%s_%.0lf_%s%s" "%s%s%s" "%s%s" "%s",pp?pp:"",h,rsb__getenv_nnr("HOSTNAME"),rsb_time(),buf,ap?ap:"", @@ -2134,167 +2182,139 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 32 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_csr.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_get.c -o librsb_base_la-rsb_get.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_csr.c -o librsb_base_la-rsb_csr.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_symm.lo `test -f 'rsb_coo_symm.c' || echo './'`rsb_coo_symm.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -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 -fcf-protection -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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srt.lo `test -f 'rsb_srt.c' || echo './'`rsb_srt.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srt.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_idx.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_idx.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -o librsb_base_la-rsb_srt.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srtp.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srtp.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_idx.c -o librsb_base_la-rsb_idx.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_test_accuracy.lo `test -f 'rsb_test_accuracy.c' || echo './'`rsb_test_accuracy.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_clone.lo `test -f 'rsb_clone.c' || echo './'`rsb_clone.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_test_accuracy.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_test_accuracy.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -o librsb_base_la-rsb_srt.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_src.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_src.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_test_accuracy.lo `test -f 'rsb_test_accuracy.c' || echo './'`rsb_test_accuracy.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_clone.lo `test -f 'rsb_clone.c' || echo './'`rsb_clone.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec.lo `test -f 'rsb_rec.c' || echo './'`rsb_rec.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_clone.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_clone.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec.lo `test -f 'rsb_rec.c' || echo './'`rsb_rec.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_render.lo `test -f 'rsb_render.c' || echo './'`rsb_render.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_render.lo `test -f 'rsb_render.c' || echo './'`rsb_render.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_clone.c -o librsb_base_la-rsb_clone.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_render.c -o librsb_base_la-rsb_render.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_msort_up.lo `test -f 'rsb_msort_up.c' || echo './'`rsb_msort_up.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_eps.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_eps.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_msort_up.lo `test -f 'rsb_msort_up.c' || echo './'`rsb_msort_up.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec.c -o librsb_base_la-rsb_rec.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_msort_up.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_msort_up.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_sys.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_sys.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_msort_up.c -o librsb_base_la-rsb_msort_up.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_blas_stuff.lo `test -f 'rsb_blas_stuff.c' || echo './'`rsb_blas_stuff.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_blas_stuff.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_gen.lo `test -f 'rsb_gen.c' || echo './'`rsb_gen.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_blas_stuff.lo `test -f 'rsb_blas_stuff.c' || echo './'`rsb_blas_stuff.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_blas_stuff.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_gen.lo `test -f 'rsb_gen.c' || echo './'`rsb_gen.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_sys.c -o librsb_base_la-rsb_sys.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_gen.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_gen.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_perf.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_perf.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_rsb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rsb.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_err.lo `test -f 'rsb_err.c' || echo './'`rsb_err.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rsb.lo `test -f 'rsb_rsb.c' || echo './'`rsb_rsb.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_gen.c -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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_tune.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_perf.c -o librsb_base_la-rsb_perf.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_err.lo `test -f 'rsb_err.c' || echo './'`rsb_err.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_do.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_do.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rsb.c -o librsb_base_la-rsb_rsb.o >/dev/null 2>&1 -rsb_test_matops.c: In function 'rsb__main_block_partitioned_spsv_sxsx': -rsb_test_matops.c:214:41: warning: '%s' directive writing up to 2047 bytes into a region of size 1011 [-Wformat-overflow=] - 214 | rsb__sprintf(dst,"%s%s_%s_%.0lf_%s%s" "%s%s%s" "%s%s" "%s",pp?pp:"",h,rsb__getenv_nnr("HOSTNAME"),rsb_time(),buf,ap?ap:"", - | ^~ ~~~ -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/x86_64-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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -o librsb_nounroll_la-rsb_util.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_internals.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_internals.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_do.c -o librsb_base_la-rsb_do.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_do.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_do.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_tune.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_garbage.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -o librsb_base_la-rsb_garbage.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mmio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mmio.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -o librsb_base_la-rsb_garbage.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_do.c -o librsb_base_la-rsb_do.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_partition.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_partition.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mbw.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mbw.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mmio.c -o librsb_base_la-rsb_mmio.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -o librsb_base_la-rsb_tune.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_partition.c -o librsb_base_la-rsb_partition.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl.c -o librsb_nounroll_la-rsb_krnl.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_limiter.c -o librsb_base_la-rsb_limiter.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_fpb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_fpb.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -o librsb_base_la-rsb_tune.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_limiter.c -o librsb_base_la-rsb_limiter.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mbw.c -o librsb_base_la-rsb_mbw.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spgemm.lo `test -f 'rsb_spgemm.c' || echo './'`rsb_spgemm.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spgemm.lo `test -f 'rsb_spgemm.c' || echo './'`rsb_spgemm.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -o librsb_nounroll_la-rsb_util.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spgemm.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_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 -fcf-protection -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsum.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum.c -o librsb_base_la-rsb_spsum.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_swt.lo `test -f 'rsb_swt.c' || echo './'`rsb_swt.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_init.lo `test -f 'rsb_init.c' || echo './'`rsb_init.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsv.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_dump.lo `test -f 'rsb_dump.c' || echo './'`rsb_dump.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_swt.lo `test -f 'rsb_swt.c' || echo './'`rsb_swt.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_lock.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_lock.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -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 -fcf-protection -O3 -std=c99 -c rsb_init.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_init.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_dump.lo `test -f 'rsb_dump.c' || echo './'`rsb_dump.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_lock.c -o librsb_base_la-rsb_lock.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_swt.c -o librsb_base_la-rsb_swt.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_init.c -o librsb_base_la-rsb_init.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_init.c -o librsb_base_la-rsb_init.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_asm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_asm.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_user.lo `test -f 'rsb_user.c' || echo './'`rsb_user.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_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 -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo2rec.lo `test -f 'rsb_coo2rec.c' || echo './'`rsb_coo2rec.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo2rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo2rec.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl.c -o librsb_nounroll_la-rsb_krnl.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo2rec.lo `test -f 'rsb_coo2rec.c' || echo './'`rsb_coo2rec.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_user.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_user.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_asm.c -o librsb_base_la-rsb_asm.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2csr.lo `test -f 'rsb_rec2csr.c' || echo './'`rsb_rec2csr.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2coo.lo `test -f 'rsb_rec2coo.c' || echo './'`rsb_rec2coo.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2csr.lo `test -f 'rsb_rec2csr.c' || echo './'`rsb_rec2csr.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -c rsb_rec2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2coo.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2csr.o -/bin/bash ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 +/bin/sh ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_user.c -o librsb_base_la-rsb_user.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr2coo.o +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2csr.c -o librsb_base_la-rsb_rec2csr.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_user.c -o librsb_base_la-rsb_user.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2coo.c -o librsb_base_la-rsb_rec2coo.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.o >/dev/null 2>&1 -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.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 -fcf-protection -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 -fcf-protection -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -fPIC -DPIC -o .libs/rsb_libspblas_handle.o -gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.o rsb_blas_sparse.F90 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_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 -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o ch2icfb ch2icfb-ch2icfb.o -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -fPIC -DPIC -o .libs/rsb_libspblas.o -rsb_test_matops.c: In function 'rsb__main_block_partitioned_mat_stats': +gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.o rsb_blas_sparse.F90 +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o ch2icfb ch2icfb-ch2icfb.o -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +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_mat_stats' at rsb_test_matops.c:10768:4: + inlined from 'rsb__main_block_partitioned_spsv_sxsx' at rsb_test_matops.c:6327:4: /usr/include/x86_64-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, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -2302,35 +2322,51 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 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 -fcf-protection -O3 -std=c99 -c rsb_coo2rec.c -o librsb_base_la-rsb_coo2rec.o >/dev/null 2>&1 libtool: warning: '-version-info' is ignored for programs libtool: link: gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 if test -f ./rsb_types.h -a ! -f ./rsb_types.h ; then cp -pv ./rsb_types.h ./rsb_types.h ; fi # out-of-dir behaviour varies between installations -if test -f ch2icfb ; then if SED=/usr/bin/sed GREP=/usr/bin/grep /bin/bash ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi -/bin/bash ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.lo rsb.F90 -gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.o rsb.F90 +if test -f ch2icfb ; then if SED=/usr/bin/sed GREP=/usr/bin/grep /bin/sh ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi +/bin/sh ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.lo rsb.F90 libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -fPIC -o .libs/rsb.o libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -o rsb.o >/dev/null 2>&1 -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 +gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.o rsb.F90 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_base.la librsb_base_la-rsb_is.lo librsb_base_la-rsb_mio.lo librsb_base_la-rsb_op.lo librsb_base_la-rsb_bio.lo librsb_base_la-rsb_get.lo librsb_base_la-rsb_set.lo librsb_base_la-rsb_coo.lo librsb_base_la-rsb_csr.lo librsb_base_la-rsb_coo_check.lo librsb_base_la-rsb_coo_symm.lo librsb_base_la-rsb_idx.lo librsb_base_la-rsb_srt.lo librsb_base_la-rsb_srtp.lo librsb_base_la-rsb_src.lo librsb_base_la-rsb_test_accuracy.lo librsb_base_la-rsb_clone.lo librsb_base_la-rsb_rec.lo librsb_base_la-rsb_render.lo librsb_base_la-rsb_eps.lo librsb_base_la-rsb_msort_up.lo librsb_base_la-rsb_sys.lo librsb_base_la-rsb_blas_stuff.lo librsb_base_la-rsb_gen.lo librsb_base_la-rsb_perf.lo librsb_base_la-rsb_rsb.lo librsb_base_la-rsb_err.lo librsb_base_la-rsb_tune.lo librsb_base_la-rsb_do.lo librsb_base_la-rsb_internals.lo librsb_base_la-rsb_garbage.lo librsb_base_la-rsb_mmio.lo librsb_base_la-rsb_partition.lo librsb_base_la-rsb_mbw.lo librsb_base_la-rsb_limiter.lo librsb_base_la-rsb_fpb.lo librsb_base_la-rsb_spgemm.lo librsb_base_la-rsb_spsum.lo librsb_base_la-rsb_spsv.lo librsb_base_la-rsb_lock.lo librsb_base_la-rsb_swt.lo librsb_base_la-rsb_init.lo librsb_base_la-rsb_dump.lo librsb_base_la-rsb_cpmv.lo librsb_base_la-rsb_asm.lo librsb_base_la-rsb_user.lo librsb_base_la-rsb_coo2rec.lo librsb_base_la-rsb_rec2coo.lo librsb_base_la-rsb_rec2csr.lo librsb_base_la-rsb_csr2coo.lo rsb_blas_sparse.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -libtool: warning: '-version-info/-version-number' is ignored for convenience libraries -libtool: link: ar cr .libs/librsb_base.a .libs/librsb_base_la-rsb_is.o .libs/librsb_base_la-rsb_mio.o .libs/librsb_base_la-rsb_op.o .libs/librsb_base_la-rsb_bio.o .libs/librsb_base_la-rsb_get.o .libs/librsb_base_la-rsb_set.o .libs/librsb_base_la-rsb_coo.o .libs/librsb_base_la-rsb_csr.o .libs/librsb_base_la-rsb_coo_check.o .libs/librsb_base_la-rsb_coo_symm.o .libs/librsb_base_la-rsb_idx.o .libs/librsb_base_la-rsb_srt.o .libs/librsb_base_la-rsb_srtp.o .libs/librsb_base_la-rsb_src.o .libs/librsb_base_la-rsb_test_accuracy.o .libs/librsb_base_la-rsb_clone.o .libs/librsb_base_la-rsb_rec.o .libs/librsb_base_la-rsb_render.o .libs/librsb_base_la-rsb_eps.o .libs/librsb_base_la-rsb_msort_up.o .libs/librsb_base_la-rsb_sys.o .libs/librsb_base_la-rsb_blas_stuff.o .libs/librsb_base_la-rsb_gen.o .libs/librsb_base_la-rsb_perf.o .libs/librsb_base_la-rsb_rsb.o .libs/librsb_base_la-rsb_err.o .libs/librsb_base_la-rsb_tune.o .libs/librsb_base_la-rsb_do.o .libs/librsb_base_la-rsb_internals.o .libs/librsb_base_la-rsb_garbage.o .libs/librsb_base_la-rsb_mmio.o .libs/librsb_base_la-rsb_partition.o .libs/librsb_base_la-rsb_mbw.o .libs/librsb_base_la-rsb_limiter.o .libs/librsb_base_la-rsb_fpb.o .libs/librsb_base_la-rsb_spgemm.o .libs/librsb_base_la-rsb_spsum.o .libs/librsb_base_la-rsb_spsv.o .libs/librsb_base_la-rsb_lock.o .libs/librsb_base_la-rsb_swt.o .libs/librsb_base_la-rsb_init.o .libs/librsb_base_la-rsb_dump.o .libs/librsb_base_la-rsb_cpmv.o .libs/librsb_base_la-rsb_asm.o .libs/librsb_base_la-rsb_user.o .libs/librsb_base_la-rsb_coo2rec.o .libs/librsb_base_la-rsb_rec2coo.o .libs/librsb_base_la-rsb_rec2csr.o .libs/librsb_base_la-rsb_csr2coo.o .libs/rsb_blas_sparse.o -libtool: link: ranlib .libs/librsb_base.a -libtool: link: ( cd ".libs" && rm -f "librsb_base.la" && ln -s "../librsb_base.la" "librsb_base.la" ) -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_spblas.la rsb_libspblas_handle.lo rsb_libspblas.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_spblas.la rsb_libspblas_handle.lo rsb_libspblas.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_spblas.a .libs/rsb_libspblas_handle.o .libs/rsb_libspblas.o +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_base.la librsb_base_la-rsb_is.lo librsb_base_la-rsb_mio.lo librsb_base_la-rsb_op.lo librsb_base_la-rsb_bio.lo librsb_base_la-rsb_get.lo librsb_base_la-rsb_set.lo librsb_base_la-rsb_coo.lo librsb_base_la-rsb_csr.lo librsb_base_la-rsb_coo_check.lo librsb_base_la-rsb_coo_symm.lo librsb_base_la-rsb_idx.lo librsb_base_la-rsb_srt.lo librsb_base_la-rsb_srtp.lo librsb_base_la-rsb_src.lo librsb_base_la-rsb_test_accuracy.lo librsb_base_la-rsb_clone.lo librsb_base_la-rsb_rec.lo librsb_base_la-rsb_render.lo librsb_base_la-rsb_eps.lo librsb_base_la-rsb_msort_up.lo librsb_base_la-rsb_sys.lo librsb_base_la-rsb_blas_stuff.lo librsb_base_la-rsb_gen.lo librsb_base_la-rsb_perf.lo librsb_base_la-rsb_rsb.lo librsb_base_la-rsb_err.lo librsb_base_la-rsb_tune.lo librsb_base_la-rsb_do.lo librsb_base_la-rsb_internals.lo librsb_base_la-rsb_garbage.lo librsb_base_la-rsb_mmio.lo librsb_base_la-rsb_partition.lo librsb_base_la-rsb_mbw.lo librsb_base_la-rsb_limiter.lo librsb_base_la-rsb_fpb.lo librsb_base_la-rsb_spgemm.lo librsb_base_la-rsb_spsum.lo librsb_base_la-rsb_spsv.lo librsb_base_la-rsb_lock.lo librsb_base_la-rsb_swt.lo librsb_base_la-rsb_init.lo librsb_base_la-rsb_dump.lo librsb_base_la-rsb_cpmv.lo librsb_base_la-rsb_asm.lo librsb_base_la-rsb_user.lo librsb_base_la-rsb_coo2rec.lo librsb_base_la-rsb_rec2coo.lo librsb_base_la-rsb_rec2csr.lo librsb_base_la-rsb_csr2coo.lo rsb_blas_sparse.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: ranlib .libs/librsb_spblas.a libtool: link: ( cd ".libs" && rm -f "librsb_spblas.la" && ln -s "../librsb_spblas.la" "librsb_spblas.la" ) +libtool: warning: '-version-info/-version-number' is ignored for convenience libraries +libtool: link: ar cr .libs/librsb_base.a .libs/librsb_base_la-rsb_is.o .libs/librsb_base_la-rsb_mio.o .libs/librsb_base_la-rsb_op.o .libs/librsb_base_la-rsb_bio.o .libs/librsb_base_la-rsb_get.o .libs/librsb_base_la-rsb_set.o .libs/librsb_base_la-rsb_coo.o .libs/librsb_base_la-rsb_csr.o .libs/librsb_base_la-rsb_coo_check.o .libs/librsb_base_la-rsb_coo_symm.o .libs/librsb_base_la-rsb_idx.o .libs/librsb_base_la-rsb_srt.o .libs/librsb_base_la-rsb_srtp.o .libs/librsb_base_la-rsb_src.o .libs/librsb_base_la-rsb_test_accuracy.o .libs/librsb_base_la-rsb_clone.o .libs/librsb_base_la-rsb_rec.o .libs/librsb_base_la-rsb_render.o .libs/librsb_base_la-rsb_eps.o .libs/librsb_base_la-rsb_msort_up.o .libs/librsb_base_la-rsb_sys.o .libs/librsb_base_la-rsb_blas_stuff.o .libs/librsb_base_la-rsb_gen.o .libs/librsb_base_la-rsb_perf.o .libs/librsb_base_la-rsb_rsb.o .libs/librsb_base_la-rsb_err.o .libs/librsb_base_la-rsb_tune.o .libs/librsb_base_la-rsb_do.o .libs/librsb_base_la-rsb_internals.o .libs/librsb_base_la-rsb_garbage.o .libs/librsb_base_la-rsb_mmio.o .libs/librsb_base_la-rsb_partition.o .libs/librsb_base_la-rsb_mbw.o .libs/librsb_base_la-rsb_limiter.o .libs/librsb_base_la-rsb_fpb.o .libs/librsb_base_la-rsb_spgemm.o .libs/librsb_base_la-rsb_spsum.o .libs/librsb_base_la-rsb_spsv.o .libs/librsb_base_la-rsb_lock.o .libs/librsb_base_la-rsb_swt.o .libs/librsb_base_la-rsb_init.o .libs/librsb_base_la-rsb_dump.o .libs/librsb_base_la-rsb_cpmv.o .libs/librsb_base_la-rsb_asm.o .libs/librsb_base_la-rsb_user.o .libs/librsb_base_la-rsb_coo2rec.o .libs/librsb_base_la-rsb_rec2coo.o .libs/librsb_base_la-rsb_rec2csr.o .libs/librsb_base_la-rsb_csr2coo.o .libs/rsb_blas_sparse.o +libtool: link: ranlib .libs/librsb_base.a +libtool: link: ( cd ".libs" && rm -f "librsb_base.la" && ln -s "../librsb_base.la" "librsb_base.la" ) +rsb_test_matops.c: In function 'rsb__main_block_partitioned_mat_stats': +rsb_test_matops.c:214:41: warning: '%s' directive writing up to 2047 bytes into a region of size 1011 [-Wformat-overflow=] + 214 | rsb__sprintf(dst,"%s%s_%s_%.0lf_%s%s" "%s%s%s" "%s%s" "%s",pp?pp:"",h,rsb__getenv_nnr("HOSTNAME"),rsb_time(),buf,ap?ap:"", + | ^~ ~~~ +In function 'sprintf', + inlined from 'rsb__impcdstr' at rsb_test_matops.c:214:2, + inlined from 'rsb__main_block_partitioned_mat_stats' at rsb_test_matops.c:10768:4: +/usr/include/x86_64-linux-gnu/bits/stdio2.h:30:10: note: '__builtin___sprintf_chk' output 19 or more bytes (assuming 2070) into a destination of size 1025 + 30 | return __builtin___sprintf_chk (__s, __USE_FORTIFY_LEVEL - 1, + | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 31 | __glibc_objsize (__s), __fmt, + | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 32 | __va_arg_pack ()); + | ~~~~~~~~~~~~~~~~~ libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_nounroll.la librsb_nounroll_la-rsb_stropts.lo librsb_nounroll_la-rsb_strmif.lo librsb_nounroll_la-rsb_unroll.lo librsb_nounroll_la-rsb_krnl_vb.lo librsb_nounroll_la-rsb_krnl_lb.lo librsb_nounroll_la-rsb_krnl.lo librsb_nounroll_la-rsb_bench.lo librsb_nounroll_la-rsb_mergesort.lo librsb_nounroll_la-rsb_permute.lo librsb_nounroll_la-rsb_krnl_bcss_l.lo librsb_nounroll_la-rsb_krnl_bcss_u.lo librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss.lo librsb_nounroll_la-rsb_spmv.lo librsb_nounroll_la-rsb_merge.lo librsb_nounroll_la-rsb_ompio.lo librsb_nounroll_la-rsb_util.lo librsb_nounroll_la-rsb_spgemm_csr.lo librsb_nounroll_la-rsb_spsum_misc.lo librsb_nounroll_la-rsb_prec.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_nounroll.la librsb_nounroll_la-rsb_stropts.lo librsb_nounroll_la-rsb_strmif.lo librsb_nounroll_la-rsb_unroll.lo librsb_nounroll_la-rsb_krnl_vb.lo librsb_nounroll_la-rsb_krnl_lb.lo librsb_nounroll_la-rsb_krnl.lo librsb_nounroll_la-rsb_bench.lo librsb_nounroll_la-rsb_mergesort.lo librsb_nounroll_la-rsb_permute.lo librsb_nounroll_la-rsb_krnl_bcss_l.lo librsb_nounroll_la-rsb_krnl_bcss_u.lo librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss.lo librsb_nounroll_la-rsb_spmv.lo librsb_nounroll_la-rsb_merge.lo librsb_nounroll_la-rsb_ompio.lo librsb_nounroll_la-rsb_util.lo librsb_nounroll_la-rsb_spgemm_csr.lo librsb_nounroll_la-rsb_spsum_misc.lo librsb_nounroll_la-rsb_prec.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_nounroll.a .libs/librsb_nounroll_la-rsb_stropts.o .libs/librsb_nounroll_la-rsb_strmif.o .libs/librsb_nounroll_la-rsb_unroll.o .libs/librsb_nounroll_la-rsb_krnl_vb.o .libs/librsb_nounroll_la-rsb_krnl_lb.o .libs/librsb_nounroll_la-rsb_krnl.o .libs/librsb_nounroll_la-rsb_bench.o .libs/librsb_nounroll_la-rsb_mergesort.o .libs/librsb_nounroll_la-rsb_permute.o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss.o .libs/librsb_nounroll_la-rsb_spmv.o .libs/librsb_nounroll_la-rsb_merge.o .libs/librsb_nounroll_la-rsb_ompio.o .libs/librsb_nounroll_la-rsb_util.o .libs/librsb_nounroll_la-rsb_spgemm_csr.o .libs/librsb_nounroll_la-rsb_spsum_misc.o .libs/librsb_nounroll_la-rsb_prec.o libtool: link: ranlib .libs/librsb_nounroll.a libtool: link: ( cd ".libs" && rm -f "librsb_nounroll.la" && ln -s "../librsb_nounroll.la" "librsb_nounroll.la" ) -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/x86_64-linux-gnu rsb.lo librsb_nounroll.la librsb_base.la librsb_spblas.la /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/librsbpp.la -lstdc++ -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/x86_64-linux-gnu rsb.lo librsb_nounroll.la librsb_base.la librsb_spblas.la /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/librsbpp.la -lstdc++ -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: gcc -shared -fPIC -DPIC .libs/rsb.o -Wl,--whole-archive ./.libs/librsb_nounroll.a ./.libs/librsb_base.a ./.libs/librsb_spblas.a /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/.libs/librsbpp.a -Wl,--no-whole-archive -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lpthread -lstdc++fs -lstdc++ -lhwloc -lz -lgfortran -lm -lquadmath -g -O2 -fstack-protector-strong -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") @@ -2342,7 +2378,7 @@ libtool: link: ranlib .libs/librsb.a libtool: link: rm -fr .libs/librsb.lax libtool: link: ( cd ".libs" && rm -f "librsb.la" && ln -s "../librsb.la" "librsb.la" ) -/bin/bash ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -no-undefined -version-info 0:0:0 -Wl,-z,relro -o rsbench rsbench-rsbench.o rsbench-rsb_test_matops.o rsbench-rsb_mkl.o rsbench-rsb_genmm.o rsbench-rsb_mmls.o rsbench-rsb_pr.o rsbench-rsb_pcnt.o rsbench-rsb_failure_tests.o rsbench-rsb_libspblas_tests.o rsb_dummy.o librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -no-undefined -version-info 0:0:0 -Wl,-z,relro -o rsbench rsbench-rsbench.o rsbench-rsb_test_matops.o rsbench-rsb_mkl.o rsbench-rsb_genmm.o rsbench-rsb_mmls.o rsbench-rsb_pr.o rsbench-rsb_pcnt.o rsbench-rsb_failure_tests.o rsbench-rsb_libspblas_tests.o rsb_dummy.o librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info' is ignored for programs libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/rsbench rsbench-rsbench.o rsbench-rsb_test_matops.o rsbench-rsb_mkl.o rsbench-rsb_genmm.o rsbench-rsb_mmls.o rsbench-rsb_pr.o rsbench-rsb_pcnt.o rsbench-rsb_failure_tests.o rsbench-rsb_libspblas_tests.o rsb_dummy.o -fopenmp ./.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' @@ -2359,27 +2395,27 @@ gfortran -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -I.. -I.. -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o fortran.o fortran.F90 gfortran -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -I.. -I.. -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o fortran_rsb_fi.o fortran_rsb_fi.F90 g++ -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -c -o cplusplus.o cplusplus.cpp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o io-spblas io-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello hello.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o transpose transpose.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello-spblas hello-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o power power.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o backsolve backsolve.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran_rsb_fi fortran_rsb_fi.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o autotune autotune.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran fortran.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello hello.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o backsolve backsolve.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o io-spblas io-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o transpose transpose.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello-spblas hello-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o power power.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran_rsb_fi fortran_rsb_fi.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o autotune autotune.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran fortran.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/io-spblas io-spblas.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/power power.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/hello hello.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o snippets snippets.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/hello-spblas hello-spblas.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/backsolve backsolve.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/transpose transpose.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/backsolve backsolve.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/power power.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/fortran_rsb_fi fortran_rsb_fi.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/autotune autotune.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o snippets snippets.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/fortran fortran.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/snippets snippets.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o cplusplus cplusplus.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o cplusplus cplusplus.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/cplusplus cplusplus.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' Making all in scripts @@ -2399,9 +2435,9 @@ /usr/bin/mkdir -p man /usr/bin/mkdir -p man gmake makedox -SOURCE_DATE_EPOCH=1704114061 \ +SOURCE_DATE_EPOCH=1735642861 \ help2man --name="benchmark and test for librsb" --no-info ../rsbench | /usr/bin/sed 's/January //g' > man/rsbench.1 -SOURCE_DATE_EPOCH=1704114061 \ +SOURCE_DATE_EPOCH=1735642861 \ 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[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 ?" @@ -3113,13 +3149,13 @@ g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rgt-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rgt_ne-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rgt_rv-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp -/bin/bash ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' Making all in examples @@ -3134,25 +3170,25 @@ g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o mtx2bin.o mtx2bin.cpp g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o render.o render.cpp g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o span.o span.cpp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/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 -fcf-protection -Wl,-z,relro -o autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib/examples' gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' @@ -3162,7 +3198,7 @@ gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' g++ -DHAVE_CONFIG_H -I. -I/build/reproducible-path/librsb-1.3.0.2+dfsg -Wdate-time -D_FORTIFY_SOURCE=2 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rsbtest.o rsbtest.cpp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lstdc++fs -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lstdc++fs -lstdc++fs libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lstdc++fs -fopenmp gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' @@ -3238,7 +3274,7 @@ 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 @@ -3248,15 +3284,15 @@ 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 1717748722 +# beginning run at 1752160113 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx -qH -R -n1,4 -T z --verbose --nrhs 1,2 --by-rows # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -# average timer granularity: 6.12e-08 s -# Will write a final performance record to file rsbench_pr__1717748722_gcc-13.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1717748722_gcc-13.2-1,4th.rpr.tmp +# average timer granularity: 4.01e-08 s +# Will write a final performance record to file rsbench_pr__1752160113_gcc-13.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1752160113_gcc-13.2-1,4th.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 @@ -3295,61 +3331,61 @@ # 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: infom01-amd64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 1 (each --verbose occurrence counts +1) # This test will measure times in scanning arrays sized and aligned to fit in caches. # 3 cache levels detected Will fill struct with 50 samples... -# Memory benchmark took 6.955s +# Memory benchmark took 7.215s # 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 16777216 bytes, per-thread 1398101 bytes -# so far, program took 6.957s 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 7.217s 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, 80919 nnz/s ) (2.48 MB/s ) -#pre-sorting (6 elements) took 0.0151079 s -#weeding duplicates (to 6 elements) took 2.14577e-06 s (and check, 9.53674e-07 s ) +# file input of A.mtx took 0.00 s (6 nnz, 64528 nnz/s ) (1.98 MB/s ) +#pre-sorting (6 elements) took 0.0303359 s +#weeding duplicates (to 6 elements) took 2.86102e-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 0.076s): (3 x 3)[0x55cf12a332c0]{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 0.128s): (3 x 3)[0x55ab2564c300]{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 0.024s; avg 0.007999s ( +/- 0.06/ 0.08 %); best 0.007995s; worst 0.008006s; std dev. 4.856e-06 (taking best). -Reference operation time is 0.00799489 s (0.01201 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: 0.007995 Mflops: 0.012) -Merge (3 -> 1 leaves) took w.c.t. of 2.003e-05s, ~9.06e-06s of computing time (of which 1.192e-06s sorting, 3.099e-06s analysis) -3 iterations (1 th.) took 1.597e-05s; avg 5.325e-06s ( +/- 98.86/200.00 %); best 6.064e-08s; worst 1.597e-05s; std dev. 7.53e-06 (taking best). -Reference operation time is 6.06418e-08 s (1583 Mflops) with 1 threads. -After merge step 1: tpop: 6.064e-08 s ~Mflops: 1583.067 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 131838.018x: 0.007995s -> 6.064e-08s, so taking this instance. +3 iterations (1 th.) took 0.05199s; avg 0.01733s ( +/- 30.77/ 61.43 %); best 0.012s; worst 0.02797s; std dev. 0.007528 (taking best). +Reference operation time is 0.011997 s (0.008002 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: 0.012 Mflops: 0.008) +Merge (3 -> 1 leaves) took w.c.t. of 2.098e-05s, ~9.06e-06s of computing time (of which 0s sorting, 4.053e-06s analysis) +3 iterations (1 th.) took 2.003e-05s; avg 6.676e-06s ( +/- 99.43/200.00 %); best 3.805e-08s; worst 2.003e-05s; std dev. 9.441e-06 (taking best). +Reference operation time is 3.80516e-08 s (2523 Mflops) with 1 threads. +After merge step 1: tpop: 3.805e-08 s ~Mflops: 2522.890 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 315281.955x: 0.012s -> 3.805e-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 0.02399s (of which 2.313e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 1.192e-06s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02399s, equivalent to 395600.6/3.0 new/old ops (0.0479s for 2 clones -- as 789832.9/6.0 ops, or 394916.5/3.0 ops per clone), SPEEDUP of 131838.018x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 131838.018x (0.007995s -> 6.064e-08s), will amortize in 3.0 ops by saving 0.007995s per op. -In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 13183701.8% (1.318e+05x) (from 0.01201 to 1583 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.06s (of which 2.503e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 0s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.06s, equivalent to 1576804.5/5.0 new/old ops (0.1119s for 2 clones -- as 2940031.3/9.3 ops, or 1470015.7/4.7 ops per clone), SPEEDUP of 315281.955x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 315281.955x (0.012s -> 3.805e-08s), will amortize in 5.0 ops by saving 0.012s per op. +In 1 tuning rounds (tot. 0.16s, 0.11s for constructor, 2 clones) obtained a SPEEDUP of 31528095.5% (3.153e+05x) (from 0.008002 to 2523 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 0.0719929 s (7.995e-03 s -> 6.064e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.164007 s (1.200e-02 s -> 3.805e-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 0.475981 s and estimated a speedup of 1.000000 x (6.064e-08 s -> 6.064e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.999943 s and estimated a speedup of 1.000000 x (3.805e-08 s -> 3.805e-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 0.027542 0.031297 0.058839 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.058839 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.027542 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.031297 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.031897 0.047983 0.079880 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.079880 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.031897 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.047983 %: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 0.058839 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.079880 %: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 @@ -3364,47 +3400,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.069s): (3 x 3)[0x55cf12a37920]{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 0.116s): (3 x 3)[0x55ab25650960]{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 0.02398s; avg 0.007993s ( +/- 0.06/ 0.11 %); best 0.007988s; worst 0.008002s; std dev. 6.418e-06 (taking best). -Reference operation time is 0.00798798 s (0.01202 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: 0.007988 Mflops: 0.012) -Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (4 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 94.13/107.69 %); best 6.064e-08s; worst 2.146e-06s; std dev. 8.778e-07 (taking best). -Reference operation time is 6.06418e-08 s (1583 Mflops) with 4 threads. -After merge step 1: tpop: 6.064e-08 s ~Mflops: 1583.067 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 131724.002x: 0.007988s -> 6.064e-08s, so taking this instance. +3 iterations (4 th.) took 0.04865s; avg 0.01622s ( +/- 25.99/ 48.00 %); best 0.012s; worst 0.024s; std dev. 0.00551 (taking best). +Reference operation time is 0.012001 s (0.007999 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: 0.012 Mflops: 0.008) +Merge (3 -> 1 leaves) took w.c.t. of 1.192e-05s, ~4.053e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) +3 iterations (4 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 96.01/200.00 %); best 3.805e-08s; worst 2.861e-06s; std dev. 1.349e-06 (taking best). +Reference operation time is 3.80516e-08 s (2523 Mflops) with 4 threads. +After merge step 1: tpop: 3.805e-08 s ~Mflops: 2522.890 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 315388.471x: 0.012s -> 3.805e-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 0.02399s (of which 1.287e-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 0.02399s, equivalent to 395569.1/3.0 new/old ops (0.04793s for 2 clones -- as 790379.4/6.0 ops, or 395189.7/3.0 ops per clone), SPEEDUP of 131724.002x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 131724.002x (0.007988s -> 6.064e-08s), will amortize in 3.0 ops by saving 0.007988s per op. -In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 13172300.2% (1.317e+05x) (from 0.01202 to 1583 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.06334s (of which 1.383e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 0s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.06334s, equivalent to 1664686.7/5.3 new/old ops (0.1113s for 2 clones -- as 2924104.0/9.3 ops, or 1462052.0/4.6 ops per clone), SPEEDUP of 315388.471x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 315388.471x (0.012s -> 3.805e-08s), will amortize in 5.3 ops by saving 0.012s per op. +In 1 tuning rounds (tot. 0.16s, 0.11s for constructor, 2 clones) obtained a SPEEDUP of 31538747.1% (3.154e+05x) (from 0.007999 to 2523 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 0.07198 s (7.988e-03 s -> 6.064e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.159994 s (1.200e-02 s -> 3.805e-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 0.431825 s and estimated a speedup of 1.000000 x (6.064e-08 s -> 6.064e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.895971 s and estimated a speedup of 1.000000 x (3.805e-08 s -> 3.805e-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 0.024850 0.028010 0.052860 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.052860 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.024850 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.028010 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.043582 0.036004 0.079586 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.079586 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.043582 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.036004 %: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 0.052860 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.079586 %: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 1.11 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.11 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 1.11 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.12 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 1.11 1.12 1.11 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.73 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.33 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.73 1.33 1.00 #%: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 @@ -3413,56 +3449,56 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.0759411 1e+09 1e+09 +%operation:A.mtx 0.12789 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.0275421 0 0.031297 +%constructor:A.mtx 0 0.0318971 0 0.0479829 # 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 0.075s): (3 x 3)[0x55cf12a37920]{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 0.101s): (3 x 3)[0x55ab25650960]{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 0.024s; avg 0.007999s ( +/- 0.03/ 0.02 %); best 0.007997s; worst 0.008001s; std dev. 1.84e-06 (taking best). -Reference operation time is 0.0079968 s (0.02401 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: 0.007997 Mflops: 0.024) -Merge (3 -> 1 leaves) took w.c.t. of 1.097e-05s, ~4.053e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) -3 iterations (1 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 95.51/111.76 %); best 6.064e-08s; worst 2.861e-06s; std dev. 1.173e-06 (taking best). -Reference operation time is 6.06418e-08 s (3166 Mflops) with 1 threads. -After merge step 1: tpop: 6.064e-08 s ~Mflops: 3166.135 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 131869.471x: 0.007997s -> 6.064e-08s, so taking this instance. +3 iterations (1 th.) took 0.05202s; avg 0.01734s ( +/- 30.79/ 38.39 %); best 0.012s; worst 0.024s; std dev. 0.004985 (taking best). +Reference operation time is 0.012002 s (0.016 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: 0.012 Mflops: 0.016) +Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~2.861e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) +3 iterations (1 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 96.01/100.00 %); best 3.805e-08s; worst 1.907e-06s; std dev. 7.787e-07 (taking best). +Reference operation time is 3.80516e-08 s (5046 Mflops) with 1 threads. +After merge step 1: tpop: 3.805e-08 s ~Mflops: 5045.779 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 315413.534x: 0.012s -> 3.805e-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 0.02399s (of which 1.192e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 0s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02399s, equivalent to 395533.7/3.0 new/old ops (0.04793s for 2 clones -- as 790312.6/6.0 ops, or 395156.3/3.0 ops per clone), SPEEDUP of 131869.471x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 131869.471x (0.007997s -> 6.064e-08s), will amortize in 3.0 ops by saving 0.007997s per op. -In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 13186847.1% (1.319e+05x) (from 0.02401 to 3166 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.05197s (of which 1.192e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 0s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.05197s, equivalent to 1365695.5/4.3 new/old ops (0.1119s for 2 clones -- as 2940162.9/9.3 ops, or 1470081.5/4.7 ops per clone), SPEEDUP of 315413.534x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 315413.534x (0.012s -> 3.805e-08s), will amortize in 4.3 ops by saving 0.012s per op. +In 1 tuning rounds (tot. 0.16s, 0.11s for constructor, 2 clones) obtained a SPEEDUP of 31541253.4% (3.154e+05x) (from 0.016 to 5046 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 0.0719969 s (7.997e-03 s -> 6.064e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.163971 s (1.200e-02 s -> 3.805e-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 0.483758 s and estimated a speedup of 1.000000 x (6.064e-08 s -> 6.064e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.955999 s and estimated a speedup of 1.000000 x (3.805e-08 s -> 3.805e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000001 0.023304 0.027664 0.050968 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.050969 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.023304 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.027664 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 1 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 1 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.050968 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.032578 0.036591 0.069169 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.069169 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.032578 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.036591 +%: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 0.069169 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 1 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 %:RSB_SUBDIVISION_SCALING:A.mtx S N 1 3 3 6 1.00 %:RSB_SHUFFLE_SCALING:A.mtx S N 1 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 1 3 3 6 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 1 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 1 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 1 3 3 6 28 48 36 @@ -3471,47 +3507,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.071s): (3 x 3)[0x55cf12a37920]{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 0.144s): (3 x 3)[0x55ab25650960]{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 0.02809s; avg 0.009363s ( +/- 56.38/ 28.19 %); best 0.004084s; worst 0.012s; std dev. 0.003733 (taking best). -Reference operation time is 0.00408411 s (0.04701 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: 0.004084 Mflops: 0.047) -Merge (3 -> 1 leaves) took w.c.t. of 1.287e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (4 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 94.13/200.00 %); best 6.064e-08s; worst 3.099e-06s; std dev. 1.461e-06 (taking best). -Reference operation time is 6.06418e-08 s (3166 Mflops) with 4 threads. -After merge step 1: tpop: 6.064e-08 s ~Mflops: 3166.135 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 67348.142x: 0.004084s -> 6.064e-08s, so taking this instance. +3 iterations (4 th.) took 0.05199s; avg 0.01733s ( +/- 30.78/ 61.55 %); best 0.012s; worst 0.028s; std dev. 0.007543 (taking best). +Reference operation time is 0.011996 s (0.01601 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: 0.012 Mflops: 0.016) +Merge (3 -> 1 leaves) took w.c.t. of 1.287e-05s, ~5.007e-06s of computing time (of which 1.192e-06s sorting, 2.861e-06s analysis) +3 iterations (4 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 96.01/200.00 %); best 3.805e-08s; worst 2.861e-06s; std dev. 1.349e-06 (taking best). +Reference operation time is 3.80516e-08 s (5046 Mflops) with 4 threads. +After merge step 1: tpop: 3.805e-08 s ~Mflops: 5045.779 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 315256.892x: 0.012s -> 3.805e-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 0.03144s (of which 1.597e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.03144s, equivalent to 518502.1/7.7 new/old ops (0.06742s for 2 clones -- as 1111775.1/16.5 ops, or 555887.6/8.3 ops per clone), SPEEDUP of 67348.142x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 67348.142x (0.004084s -> 6.064e-08s), will amortize in 7.7 ops by saving 0.004084s per op. -In 1 tuning rounds (tot. 0.096s, 0.067s for constructor, 2 clones) obtained a SPEEDUP of 6734714.2% (6.735e+04x) (from 0.04701 to 3166 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.05199s (of which 1.478e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 1.192e-06s sorting, 2.861e-06s analyzing) +Total merge + benchmarking process took 0.05199s, equivalent to 1366403.5/4.3 new/old ops (0.1239s for 2 clones -- as 3256660.4/10.3 ops, or 1628330.2/5.2 ops per clone), SPEEDUP of 315256.892x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 315256.892x (0.012s -> 3.805e-08s), will amortize in 4.3 ops by saving 0.012s per op. +In 1 tuning rounds (tot. 0.18s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 31525589.2% (3.153e+05x) (from 0.01601 to 5046 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 0.095588 s (4.084e-03 s -> 6.064e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.175998 s (1.200e-02 s -> 3.805e-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 0.332711 s and estimated a speedup of 1.000000 x (6.064e-08 s -> 6.064e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.899961 s and estimated a speedup of 1.000000 x (3.805e-08 s -> 3.805e-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 0.026677 0.023980 0.050657 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.050657 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.026677 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.023980 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.047512 0.052001 0.099513 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.099513 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.047512 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.052001 %: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 inf -%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.050657 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.099513 %: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 0.87 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.15 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 inf 0.87 1.15 1.01 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.70 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.70 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.69 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.70 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.69 0.70 0.70 #%: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 @@ -3520,184 +3556,187 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.0752981 1e+09 1e+09 +%operation:A.mtx 0.101192 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 9.53674e-07 0.023304 0 0.0276639 +%constructor:A.mtx 0 0.032578 0 0.0365911 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 9.674s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.036s/0.000s . +# so far, program took 12.776s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.416s/0.000s . getrusage() stats: -ru_maxrss: 75 (maximum resident set size -- MB) -ru_stime : 0.264s (system CPU time used) -ru_utime : 36.35s (user CPU time used) +ru_maxrss: 81 (maximum resident set size -- MB) +ru_stime : 0.2727s (system CPU time used) +ru_utime : 27.93s (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 1583.07 7.995e-03 0.000e+00 6.064e-08 0.000e+00 7.199e-02 4.42e+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 1583.07 7.988e-03 0.000e+00 6.064e-08 0.000e+00 7.198e-02 4.42e+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 2522.89 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.640e-01 7.04e+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 2522.89 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.600e-01 7.04e+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. 13178001.0 % faster, avg. sp. ratio 131781.010x, max sp. ratio 131838.018x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1187076.9/1186970.7/1187183.0/2374153.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 9.0/ 9.0/ 18.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.0, min. 9.0, max. 9.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 31533421.3 % faster, avg. sp. ratio 315335.213x, max sp. ratio 315388.471x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4257390.4/4204661.7/4310119.0/8514780.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.5/ 13.3/ 13.7/ 27.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.5, min. 13.3, max. 13.7 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.628/ 3.628/ 3.628,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 8.839/ 4.419/ 4.419,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.782/ 5.782/ 5.782,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.086/ 7.043/ 7.043,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.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.583e+03, min 1.583e+03, max 1.583e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.201e-02, min 1.201e-02, max 1.202e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 6.064e-08s, min 6.064e-08s, max 6.064e-08s, tot 1.213e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.991e-03s, min 7.988e-03s, max 7.995e-03s, tot 1.598e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.083e+00 5.083e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.070e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.16 s, min 0.16 s, max 0.16 s, tot 0.32 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.16 s, min 0.16 s, max 0.16 s, tot 0.32 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.523e+03, min 2.523e+03, max 2.523e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 8.001e-03, min 7.999e-03, max 8.002e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.805e-08s, min 3.805e-08s, max 3.805e-08s, tot 7.610e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.200e-02s, min 1.200e-02s, max 1.200e-02s, tot 2.400e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.121e+00 1.121e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 6.888e+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 3166.13 7.997e-03 0.000e+00 6.064e-08 0.000e+00 7.200e-02 6.79e+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 3166.13 4.084e-03 0.000e+00 6.064e-08 0.000e+00 9.559e-02 6.79e+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 5045.78 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.640e-01 1.08e+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 5045.78 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.760e-01 1.08e+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. 9960780.7 % faster, avg. sp. ratio 99608.807x, max sp. ratio 131869.471x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1381761.4/1187249.9/1576272.9/2763522.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 16.2/ 9.0/ 23.4/ 32.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 16.2, min. 9.0, max. 23.4 ops) +#pr: (in succ. cases rsb autotuning gave avg. 31533421.3 % faster, avg. sp. ratio 315335.213x, max sp. ratio 315413.534x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4467208.6/4309172.9/4625244.4/8934417.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.2/ 13.7/ 14.7/ 28.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 14.2, min. 13.7, max. 14.7 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.211/ 5.211/ 5.211,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 13.588/ 6.794/ 6.794,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.305/ 8.305/ 8.305,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 21.655/ 10.827/ 10.827,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.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.166e+03, min 3.166e+03, max 3.166e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.551e-02, min 2.401e-02, max 4.701e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 6.064e-08s, min 6.064e-08s, max 6.064e-08s, tot 1.213e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.040e-03s, min 4.084e-03s, max 7.997e-03s, tot 1.208e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.539e+00 3.539e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.070e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.17 s, min 0.16 s, max 0.18 s, tot 0.34 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.17 s, min 0.16 s, max 0.18 s, tot 0.34 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 5.046e+03, min 5.046e+03, max 5.046e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.600e-02, min 1.600e-02, max 1.601e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.805e-08s, min 3.805e-08s, max 3.805e-08s, tot 7.610e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.200e-02s, min 1.200e-02s, max 1.200e-02s, tot 2.400e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.807e-01 7.807e-01 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds memory bandwidth --- is this a tiny matrix ? +#pr: in-cache to in-memory MEMSET bandwidth ratio: 6.888e+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 1583.07 7.995e-03 0.000e+00 6.064e-08 0.000e+00 7.199e-02 4.42e+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 3166.13 7.997e-03 0.000e+00 6.064e-08 0.000e+00 7.200e-02 6.79e+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 1583.07 7.988e-03 0.000e+00 6.064e-08 0.000e+00 7.198e-02 4.42e+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 3166.13 4.084e-03 0.000e+00 6.064e-08 0.000e+00 9.559e-02 6.79e+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 2522.89 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.640e-01 7.04e+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 5045.78 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.640e-01 1.08e+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 2522.89 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.600e-01 7.04e+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 5045.78 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.760e-01 1.08e+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. 11569390.9 % faster, avg. sp. ratio 115694.909x, max sp. ratio 131869.471x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1284419.1/1186970.7/1576272.9/5137676.4 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.6/ 9.0/ 23.4/ 50.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.6, min. 9.0, max. 23.4 ops) +#pr: (in succ. cases rsb autotuning gave avg. 31533421.3 % faster, avg. sp. ratio 315335.213x, max sp. ratio 315413.534x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4362299.5/4204661.7/4625244.4/17449198.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.8/ 13.3/ 14.7/ 55.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.8, min. 13.3, max. 14.7 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.419/ 3.628/ 5.211,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 22.427/ 4.419/ 6.794,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.043/ 5.782/ 8.305,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 35.741/ 7.043/ 10.827,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.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.31 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.31 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.375e+03, min 1.583e+03, max 3.166e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.376e-02, min 1.201e-02, max 4.701e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 6.064e-08s, min 6.064e-08s, max 6.064e-08s, tot 2.426e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.016e-03s, min 4.084e-03s, max 7.997e-03s, tot 2.806e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.539e+00 5.083e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.070e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.17 s, min 0.16 s, max 0.18 s, tot 0.66 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.17 s, min 0.16 s, max 0.18 s, tot 0.66 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.784e+03, min 2.523e+03, max 5.046e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.200e-02, min 7.999e-03, max 1.601e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.805e-08s, min 3.805e-08s, max 3.805e-08s, tot 1.522e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.200e-02s, min 1.200e-02s, max 1.200e-02s, tot 4.800e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.807e-01 1.121e+00 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds memory bandwidth --- is this a tiny matrix ? +#pr: in-cache to in-memory MEMSET bandwidth ratio: 6.888e+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 1583.07 7.995e-03 0.000e+00 6.064e-08 0.000e+00 7.199e-02 4.42e+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 1583.07 7.988e-03 0.000e+00 6.064e-08 0.000e+00 7.198e-02 4.42e+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 2522.89 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.640e-01 7.04e+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 2522.89 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.600e-01 7.04e+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. 13178001.0 % faster, avg. sp. ratio 131781.010x, max sp. ratio 131838.018x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1187076.9/1186970.7/1187183.0/2374153.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 9.0/ 9.0/ 18.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.0, min. 9.0, max. 9.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 31533421.3 % faster, avg. sp. ratio 315335.213x, max sp. ratio 315388.471x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4257390.4/4204661.7/4310119.0/8514780.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.5/ 13.3/ 13.7/ 27.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.5, min. 13.3, max. 13.7 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.628/ 3.628/ 3.628,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 8.839/ 4.419/ 4.419,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.782/ 5.782/ 5.782,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.086/ 7.043/ 7.043,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.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.583e+03, min 1.583e+03, max 1.583e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.201e-02, min 1.201e-02, max 1.202e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 6.064e-08s, min 6.064e-08s, max 6.064e-08s, tot 1.213e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.991e-03s, min 7.988e-03s, max 7.995e-03s, tot 1.598e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.083e+00 5.083e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.070e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.16 s, min 0.16 s, max 0.16 s, tot 0.32 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.16 s, min 0.16 s, max 0.16 s, tot 0.32 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.523e+03, min 2.523e+03, max 2.523e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 8.001e-03, min 7.999e-03, max 8.002e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.805e-08s, min 3.805e-08s, max 3.805e-08s, tot 7.610e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.200e-02s, min 1.200e-02s, max 1.200e-02s, tot 2.400e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.121e+00 1.121e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 6.888e+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 3166.13 7.997e-03 0.000e+00 6.064e-08 0.000e+00 7.200e-02 6.79e+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 3166.13 4.084e-03 0.000e+00 6.064e-08 0.000e+00 9.559e-02 6.79e+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 5045.78 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.640e-01 1.08e+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 5045.78 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.760e-01 1.08e+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. 9960780.7 % faster, avg. sp. ratio 99608.807x, max sp. ratio 131869.471x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1381761.4/1187249.9/1576272.9/2763522.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 16.2/ 9.0/ 23.4/ 32.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 16.2, min. 9.0, max. 23.4 ops) +#pr: (in succ. cases rsb autotuning gave avg. 31533421.3 % faster, avg. sp. ratio 315335.213x, max sp. ratio 315413.534x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4467208.6/4309172.9/4625244.4/8934417.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.2/ 13.7/ 14.7/ 28.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 14.2, min. 13.7, max. 14.7 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.211/ 5.211/ 5.211,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 13.588/ 6.794/ 6.794,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.305/ 8.305/ 8.305,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 21.655/ 10.827/ 10.827,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.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.166e+03, min 3.166e+03, max 3.166e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.551e-02, min 2.401e-02, max 4.701e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 6.064e-08s, min 6.064e-08s, max 6.064e-08s, tot 1.213e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.040e-03s, min 4.084e-03s, max 7.997e-03s, tot 1.208e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.539e+00 3.539e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.070e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.17 s, min 0.16 s, max 0.18 s, tot 0.34 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.17 s, min 0.16 s, max 0.18 s, tot 0.34 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 5.046e+03, min 5.046e+03, max 5.046e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.600e-02, min 1.600e-02, max 1.601e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.805e-08s, min 3.805e-08s, max 3.805e-08s, tot 7.610e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.200e-02s, min 1.200e-02s, max 1.200e-02s, tot 2.400e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.807e-01 7.807e-01 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds memory bandwidth --- is this a tiny matrix ? +#pr: in-cache to in-memory MEMSET bandwidth ratio: 6.888e+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. @@ -3708,44 +3747,45 @@ #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 1583.07 7.995e-03 0.000e+00 6.064e-08 0.000e+00 7.199e-02 4.42e+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 3166.13 7.997e-03 0.000e+00 6.064e-08 0.000e+00 7.200e-02 6.79e+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 1583.07 7.988e-03 0.000e+00 6.064e-08 0.000e+00 7.198e-02 4.42e+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 3166.13 4.084e-03 0.000e+00 6.064e-08 0.000e+00 9.559e-02 6.79e+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 2522.89 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.640e-01 7.04e+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 5045.78 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.640e-01 1.08e+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 2522.89 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.600e-01 7.04e+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 5045.78 1.200e-02 0.000e+00 3.805e-08 0.000e+00 1.760e-01 1.08e+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. 11569390.9 % faster, avg. sp. ratio 115694.909x, max sp. ratio 131869.471x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1284419.1/1186970.7/1576272.9/5137676.4 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.6/ 9.0/ 23.4/ 50.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.6, min. 9.0, max. 23.4 ops) +#pr: (in succ. cases rsb autotuning gave avg. 31533421.3 % faster, avg. sp. ratio 315335.213x, max sp. ratio 315413.534x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4362299.5/4204661.7/4625244.4/17449198.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.8/ 13.3/ 14.7/ 55.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.8, min. 13.3, max. 14.7 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.419/ 3.628/ 5.211,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 22.427/ 4.419/ 6.794,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.043/ 5.782/ 8.305,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 35.741/ 7.043/ 10.827,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.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.31 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.31 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.375e+03, min 1.583e+03, max 3.166e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.376e-02, min 1.201e-02, max 4.701e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 6.064e-08s, min 6.064e-08s, max 6.064e-08s, tot 2.426e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.016e-03s, min 4.084e-03s, max 7.997e-03s, tot 2.806e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.539e+00 5.083e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.070e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.17 s, min 0.16 s, max 0.18 s, tot 0.66 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.17 s, min 0.16 s, max 0.18 s, tot 0.66 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.784e+03, min 2.523e+03, max 5.046e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.200e-02, min 7.999e-03, max 1.601e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.805e-08s, min 3.805e-08s, max 3.805e-08s, tot 1.522e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.200e-02s, min 1.200e-02s, max 1.200e-02s, tot 4.800e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.807e-01 1.121e+00 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds memory bandwidth --- is this a tiny matrix ? +#pr: in-cache to in-memory MEMSET bandwidth ratio: 6.888e+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 2.30 s. +#pr: Record collection took 4.48 s. #pr: Record comprises 50 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4298 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4352 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1717748722_gcc-13.2-1,4th.rpr -# Removing the temporary record file rsbench_pr__1717748722_gcc-13.2-1,4th.rpr.tmp. -# terminating run at 1717748732 (after 9.7s of w.c.t.) +#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1752160113_gcc-13.2-1,4th.rpr +# Removing the temporary record file rsbench_pr__1752160113_gcc-13.2-1,4th.rpr.tmp. +# terminating run at 1752160126 (after 12.8s 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. @@ -4021,10 +4061,10 @@ L2 size: 524288 L3 size: 16777216 sysconf() : 4096 bytes per pagesize -sysconf() : 6156131 physical pages -sysconf() : 25215512576 bytes (24047 MB) of physical memory -sysconf() : 4545241 available (free) physical pages -sysconf() : 18617307136 available (free) physical memory +sysconf() : 6154304 physical pages +sysconf() : 25208029184 bytes (24040 MB) of physical memory +sysconf() : 3349991 available (free) physical pages +sysconf() : 13721563136 available (free) physical memory sysconf() , processors : 12 sysconf() , processors online : 12 sysconf() : level 1 cache size 32768 @@ -4055,35 +4095,35 @@ 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 : 4.90427e-08 s +timing granularity : 3.80039e-08 s CFLAGS : -g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 CXXFLAGS : -g -O2 -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp CC : gcc memhinfo : L3:16/64/16M,L2:8/64/512K,L1:8/64/32K -detected free memory : 18617307136 -detected total memory : 25215512576 -for array sized 16777216 elems, took 0.00584483 s for linear search and 0 s for binary search for element 16777215, in 17 tries, for a total of 0.103740 s (ignore this:570425310) -for array sized 16777216 elems, took 0.00288987 s for linear search and 0 s for binary search for element 8388607, in 34 tries, for a total of 0.100965 s (ignore this:1140850586) -for array sized 16777216 elems, took 0.00138497 s for linear search and 0 s for binary search for element 4194303, in 71 tries, for a total of 0.100642 s (ignore this:1736441612) -for array sized 16777216 elems, took 0.000690937 s for linear search and 0 s for binary search for element 2097151, in 142 tries, for a total of 0.100560 s (ignore this:-1962934800) -for array sized 16777216 elems, took 0.000344038 s for linear search and 0 s for binary search for element 1048575, in 285 tries, for a total of 0.100311 s (ignore this:-1365247050) -for array sized 16777216 elems, took 0.000170946 s for linear search and 0 s for binary search for element 524287, in 570 tries, for a total of 0.100119 s (ignore this:-767559870) -for array sized 16777216 elems, took 8.4877e-05 s for linear search and 0 s for binary search for element 262143, in 1138 tries, for a total of 0.100062 s (ignore this:-170922402) -for array sized 16777216 elems, took 4.19617e-05 s for linear search and 0 s for binary search for element 131071, in 2277 tries, for a total of 0.100018 s (ignore this:425974932) -for array sized 16777216 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 65535, in 4428 tries, for a total of 0.100014 s (ignore this:1006352892) -for array sized 16777216 elems, took 9.77516e-06 s for linear search and 0 s for binary search for element 32767, in 8937 tries, for a total of 0.100004 s (ignore this:1592030250) -for array sized 16777216 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 16383, in 18154 tries, for a total of 0.100004 s (ignore this:-2108103082) -for array sized 16777216 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 8191, in 35269 tries, for a total of 0.100002 s (ignore this:-1530326324) -for array sized 16777216 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 4095, in 69096 tries, for a total of 0.100002 s (ignore this:-964430084) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 2047, in 127591 tries, for a total of 0.100001 s (ignore this:-442072530) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 222365 tries, for a total of 0.100001 s (ignore this:12886260) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 511, in 364066 tries, for a total of 0.100001 s (ignore this:384961712) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 255, in 525481 tries, for a total of 0.100000 s (ignore this:652957022) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 127, in 679529 tries, for a total of 0.100000 s (ignore this:825557388) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 63, in 791004 tries, for a total of 0.100001 s (ignore this:925223892) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 31, in 926602 tries, for a total of 0.100001 s (ignore this:982673216) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 15, in 934234 tries, for a total of 0.100000 s (ignore this:1010700236) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 7, in 941422 tries, for a total of 0.100000 s (ignore this:1023880144) +detected free memory : 13721563136 +detected total memory : 25208029184 +for array sized 16777216 elems, took 0.00986314 s for linear search and 0 s for binary search for element 16777215, in 10 tries, for a total of 0.136273 s (ignore this:335544300) +for array sized 16777216 elems, took 0.00285506 s for linear search and 0 s for binary search for element 8388607, in 15 tries, for a total of 0.106509 s (ignore this:587202510) +for array sized 16777216 elems, took 0.00139713 s for linear search and 0 s for binary search for element 4194303, in 69 tries, for a total of 0.100260 s (ignore this:1166016324) +for array sized 16777216 elems, took 0.000690937 s for linear search and 0 s for binary search for element 2097151, in 138 tries, for a total of 0.100401 s (ignore this:1744830000) +for array sized 16777216 elems, took 0.000344992 s for linear search and 0 s for binary search for element 1048575, in 244 tries, for a total of 0.100061 s (ignore this:-2038432696) +for array sized 16777216 elems, took 0.000170946 s for linear search and 0 s for binary search for element 524287, in 233 tries, for a total of 0.100130 s (ignore this:-1794114954) +for array sized 16777216 elems, took 8.4877e-05 s for linear search and 0 s for binary search for element 262143, in 471 tries, for a total of 0.100067 s (ignore this:-1547176248) +for array sized 16777216 elems, took 4.19617e-05 s for linear search and 0 s for binary search for element 131071, in 946 tries, for a total of 0.100086 s (ignore this:-1299189916) +for array sized 16777216 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 65535, in 2027 tries, for a total of 0.106500 s (ignore this:-1033511026) +for array sized 16777216 elems, took 9.77516e-06 s for linear search and 0 s for binary search for element 32767, in 4267 tries, for a total of 0.107634 s (ignore this:-753877448) +for array sized 16777216 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 16383, in 8598 tries, for a total of 0.107190 s (ignore this:-472155380) +for array sized 16777216 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 8191, in 15333 tries, for a total of 0.100002 s (ignore this:-220970174) +for array sized 16777216 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 4095, in 28852 tries, for a total of 0.100001 s (ignore this:15327706) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 2047, in 43812 tries, for a total of 0.103043 s (ignore this:194694034) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 79163 tries, for a total of 0.102584 s (ignore this:356661532) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 511, in 124977 tries, for a total of 0.102863 s (ignore this:484388026) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 255, in 307211 tries, for a total of 0.100000 s (ignore this:641065636) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 127, in 491428 tries, for a total of 0.100001 s (ignore this:765888348) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 63, in 558695 tries, for a total of 0.100755 s (ignore this:836283918) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 31, in 681658 tries, for a total of 0.101203 s (ignore this:878546714) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 15, in 352768 tries, for a total of 0.102716 s (ignore this:889129754) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 7, in 823711 tries, for a total of 0.100000 s (ignore this:900661708) + ./rsbench -C /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench version: 1.3.0 format switches:br @@ -4130,17 +4170,17 @@ 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 1717748735 +# beginning run at 1752160129 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx --verbose --nrhs 1,4 --by-rows # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 # User did not specify threads; assuming 1. Environment provides max 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: 5.11e-08 s -# Will write a final performance record to file rsbench_pr__1717748735_gcc-13.2.rpr and periodic checkpoints to rsbench_pr__1717748735_gcc-13.2.rpr.tmp +# average timer granularity: 3.8e-08 s +# Will write a final performance record to file rsbench_pr__1752160129_gcc-13.2.rpr and periodic checkpoints to rsbench_pr__1752160129_gcc-13.2.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 @@ -4179,61 +4219,61 @@ # 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: infom01-amd64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 1 (each --verbose occurrence counts +1) # This test will measure times in scanning arrays sized and aligned to fit in caches. # 3 cache levels detected Will fill struct with 50 samples... -# Memory benchmark took 6.953s +# Memory benchmark took 7.953s # 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 16777216 bytes, per-thread 1398101 bytes -# so far, program took 6.955s 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 7.959s 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, 75801 nnz/s ) (2.32 MB/s ) -#pre-sorting (6 elements) took 0.014236 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, 55067 nnz/s ) (1.69 MB/s ) +#pre-sorting (6 elements) took 0.0137959 s +#weeding duplicates (to 6 elements) took 9.53674e-07 s (and check, 2.14577e-06 s ) # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.084s): (3 x 3)[0x55d6ada6ba90]{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 0.052s): (3 x 3)[0x558794c14a90]{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 0.02274s; avg 0.007581s ( +/- 11.04/ 5.54 %); best 0.006744s; worst 0.008001s; std dev. 0.0005917 (taking best). -Reference operation time is 0.00674415 s (0.003559 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: 0.006744 Mflops: 0.004) -Merge (3 -> 1 leaves) took w.c.t. of 1.812e-05s, ~8.106e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 1.097e-05s; avg 3.656e-06s ( +/- 98.59/200.00 %); best 5.145e-08s; worst 1.097e-05s; std dev. 5.17e-06 (taking best). -Reference operation time is 5.14507e-08 s (466.5 Mflops) with 12 threads. -After merge step 1: tpop: 5.145e-08 s ~Mflops: 466.466 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 131079.703x: 0.006744s -> 5.145e-08s, so taking this instance. +3 iterations (12 th.) took 0.02401s; avg 0.008002s ( +/- 0.09/ 0.12 %); best 0.007995s; worst 0.008012s; std dev. 6.993e-06 (taking best). +Reference operation time is 0.00799513 s (0.003002 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: 0.007995 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 2.789e-05s, ~1.121e-05s of computing time (of which 9.537e-07s sorting, 5.96e-06s analysis) +3 iterations (12 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 96.58/186.36 %); best 2.394e-07s; worst 2.003e-05s; std dev. 9.224e-06 (taking best). +Reference operation time is 2.39408e-07 s (100.2 Mflops) with 12 threads. +After merge step 1: tpop: 2.394e-07 s ~Mflops: 100.247 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 33395.409x: 0.007995s -> 2.394e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04483s (of which 2.003e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 0s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.04483s, equivalent to 871302.1/6.6 new/old ops (0.06875s for 2 clones -- as 1336177.0/10.2 ops, or 668088.5/5.1 ops per clone), SPEEDUP of 131079.703x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 131079.703x (0.006744s -> 5.145e-08s), will amortize in 6.6 ops by saving 0.006744s per op. -In 1 tuning rounds (tot. 0.092s, 0.069s for constructor, 2 clones) obtained a SPEEDUP of 13107870.3% (1.311e+05x) (from 0.003559 to 466.5 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02398s (of which 3.099e-05s partitioning, 0s I/O); computing times: 1.121e-05s in par. loops, 9.537e-07s sorting, 5.96e-06s analyzing) +Total merge + benchmarking process took 0.02398s, equivalent to 100167.3/3.0 new/old ops (0.04783s for 2 clones -- as 199801.8/6.0 ops, or 99900.9/3.0 ops per clone), SPEEDUP of 33395.409x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 33395.409x (0.007995s -> 2.394e-07s), will amortize in 3.0 ops by saving 0.007995s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 3339440.9% (3.34e+04x) (from 0.003002 to 100.2 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 0.091583 s (6.744e-03 s -> 5.145e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0719881 s (7.995e-03 s -> 2.394e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.268598 s and estimated a speedup of 1.000000 x (5.145e-08 s -> 5.145e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.419966 s and estimated a speedup of 1.000000 x (2.394e-07 s -> 2.394e-07 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 0.043713 0.024216 0.067929 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.067929 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.043713 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.024216 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.019644 0.015997 0.035641 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.035641 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.019644 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.015997 %: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 0.067929 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.035641 %: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 @@ -4248,50 +4288,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0839279 1e+09 1e+09 +%operation:A.mtx 0.051657 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.0437129 0 0.0242162 +%constructor:A.mtx 0 0.019644 0 0.0159969 # 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 0.000s): (3 x 3)[0x55d6ada6ba90]{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 0.050s): (3 x 3)[0x558794c14a90]{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 3.314e-05s; avg 1.105e-05s ( +/- 46.04/ 89.93 %); best 5.96e-06s; worst 2.098e-05s; std dev. 7.025e-06 (taking best). -Reference operation time is 5.96046e-06 s (16.11 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: 5.96e-06 Mflops: 16.106) -Merge (3 -> 1 leaves) took w.c.t. of 4.053e-06s, ~1.907e-06s of computing time (of which 0s sorting, 9.537e-07s analysis) -3 iterations (12 th.) took 8.106e-06s; avg 2.702e-06s ( +/- 98.10/200.00 %); best 5.145e-08s; worst 8.106e-06s; std dev. 3.821e-06 (taking best). -Reference operation time is 5.14507e-08 s (1866 Mflops) with 12 threads. -After merge step 1: tpop: 5.145e-08 s ~Mflops: 1865.863 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 115.848x: 5.96e-06s -> 5.145e-08s, so taking this instance. +3 iterations (12 th.) took 0.02399s; avg 0.007995s ( +/- 0.27/ 0.37 %); best 0.007974s; worst 0.008025s; std dev. 2.174e-05 (taking best). +Reference operation time is 0.00797391 s (0.01204 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: 0.007974 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 1.192e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) +3 iterations (12 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 96.58/186.36 %); best 2.394e-07s; worst 2.003e-05s; std dev. 9.224e-06 (taking best). +Reference operation time is 2.39408e-07 s (401 Mflops) with 12 threads. +After merge step 1: tpop: 2.394e-07 s ~Mflops: 400.989 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 33306.777x: 0.007974s -> 2.394e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 3.195e-05s (of which 5.96e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 0s sorting, 9.537e-07s analyzing) -Total merge + benchmarking process took 3.195e-05s, equivalent to 620.9/5.4 new/old ops (2.599e-05s for 2 clones -- as 505.1/4.4 ops, or 252.5/2.2 ops per clone), SPEEDUP of 115.848x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 115.848x (5.96e-06s -> 5.145e-08s), will amortize in 5.4 ops by saving 5.909e-06s per op. -In 1 tuning rounds (tot. 9.2e-05s, 2.6e-05s for constructor, 2 clones) obtained a SPEEDUP of 11484.8% (115.8x) (from 16.11 to 1866 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02399s (of which 1.597e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 2.861e-06s analyzing) +Total merge + benchmarking process took 0.02399s, equivalent to 100213.1/3.0 new/old ops (0.04791s for 2 clones -- as 200122.5/6.0 ops, or 100061.2/3.0 ops per clone), SPEEDUP of 33306.777x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 33306.777x (0.007974s -> 2.394e-07s), will amortize in 3.0 ops by saving 0.007974s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 3330577.7% (3.331e+04x) (from 0.01204 to 401 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 0.000100136 s (5.960e-06 s -> 5.145e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0720019 s (7.974e-03 s -> 2.394e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.000274897 s and estimated a speedup of 1.000000 x (5.145e-08 s -> 5.145e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.459979 s and estimated a speedup of 1.000000 x (2.394e-07 s -> 2.394e-07 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 0.000019 0.000013 0.000032 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000032 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000019 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000013 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.017873 0.016004 0.033877 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.033877 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.017873 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.016004 %: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 0.000032 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.033877 %: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 @@ -4306,59 +4346,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 4.60148e-05 1e+09 1e+09 +%operation:A.mtx 0.04989 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 1.88351e-05 0 1.3113e-05 +%constructor:A.mtx 0 0.017873 0 0.0160041 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 7.528s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.361s/0.000s . +# so far, program took 9.252s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.024s/0.000s . getrusage() stats: -ru_maxrss: 73 (maximum resident set size -- MB) -ru_stime : 0.1597s (system CPU time used) -ru_utime : 13.13s (user CPU time used) +ru_maxrss: 81 (maximum resident set size -- MB) +ru_stime : 0.3305s (system CPU time used) +ru_utime : 18.93s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). # Cache block size total 16777216 bytes, per-thread 1398101 bytes -# so far, program took 7.528s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.361s/0.000s . +# so far, program took 9.252s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.024s/0.000s . # 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 0.000s): (3 x 3)[0x55d6ada6ba90]{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 0.057s): (3 x 3)[0x558794c14a90]{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 3.982e-05s; avg 1.327e-05s ( +/- 55.09/110.18 %); best 5.96e-06s; worst 2.789e-05s; std dev. 1.034e-05 (taking best). -Reference operation time is 5.96046e-06 s (4.027 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: 5.96e-06 Mflops: 4.027) -Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~1.907e-06s of computing time (of which 9.537e-07s sorting, 1.192e-06s analysis) -3 iterations (12 th.) took 5.96e-06s; avg 1.987e-06s ( +/- 97.41/200.00 %); best 5.145e-08s; worst 5.96e-06s; std dev. 2.81e-06 (taking best). -Reference operation time is 5.14507e-08 s (466.5 Mflops) with 12 threads. -After merge step 1: tpop: 5.145e-08 s ~Mflops: 466.466 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 115.848x: 5.96e-06s -> 5.145e-08s, so taking this instance. +3 iterations (12 th.) took 0.024s; avg 0.008001s ( +/- 0.26/ 0.27 %); best 0.007981s; worst 0.008023s; std dev. 1.725e-05 (taking best). +Reference operation time is 0.00798082 s (0.003007 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: 0.007981 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 1.097e-05s, ~3.815e-06s of computing time (of which 0s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 1.216e-05s; avg 4.053e-06s ( +/- 94.09/200.00 %); best 2.394e-07s; worst 1.216e-05s; std dev. 5.732e-06 (taking best). +Reference operation time is 2.39408e-07 s (100.2 Mflops) with 12 threads. +After merge step 1: tpop: 2.394e-07 s ~Mflops: 100.247 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 33335.657x: 0.007981s -> 2.394e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 2.909e-05s (of which 7.153e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 9.537e-07s sorting, 1.192e-06s analyzing) -Total merge + benchmarking process took 2.909e-05s, equivalent to 565.3/4.9 new/old ops (2.384e-05s for 2 clones -- as 463.4/4.0 ops, or 231.7/2.0 ops per clone), SPEEDUP of 115.848x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 115.848x (5.96e-06s -> 5.145e-08s), will amortize in 4.9 ops by saving 5.909e-06s per op. -In 1 tuning rounds (tot. 9.8e-05s, 2.4e-05s for constructor, 2 clones) obtained a SPEEDUP of 11484.8% (115.8x) (from 4.027 to 466.5 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02799s (of which 1.192e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 0s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.02799s, equivalent to 116917.8/3.5 new/old ops (0.05592s for 2 clones -- as 233588.6/7.0 ops, or 116794.3/3.5 ops per clone), SPEEDUP of 33335.657x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 33335.657x (0.007981s -> 2.394e-07s), will amortize in 3.5 ops by saving 0.007981s per op. +In 1 tuning rounds (tot. 0.08s, 0.056s for constructor, 2 clones) obtained a SPEEDUP of 3333465.7% (3.334e+04x) (from 0.003007 to 100.2 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 0.000104904 s (5.960e-06 s -> 5.145e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0801952 s (7.981e-03 s -> 2.394e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.000244856 s and estimated a speedup of 1.000000 x (5.145e-08 s -> 5.145e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.399773 s and estimated a speedup of 1.000000 x (2.394e-07 s -> 2.394e-07 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 0.000018 0.000011 0.000029 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000029 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000018 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000011 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.021156 0.015992 0.037148 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.037148 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.021156 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.015992 %: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 0.000029 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.037148 %: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 @@ -4373,50 +4413,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 4.3869e-05 1e+09 1e+09 +%operation:A.mtx 0.057143 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 1.81198e-05 0 1.09673e-05 +%constructor:A.mtx 0 0.0211561 0 0.0159919 # 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 0.000s): (3 x 3)[0x55d6ada6be20]{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 0.056s): (3 x 3)[0x558794c14a90]{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 2.789e-05s; avg 9.298e-06s ( +/- 35.90/ 71.79 %); best 5.96e-06s; worst 1.597e-05s; std dev. 4.72e-06 (taking best). -Reference operation time is 5.96046e-06 s (16.11 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: 5.96e-06 Mflops: 16.106) -Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~3.099e-06s of computing time (of which 0s sorting, 0s analysis) -3 iterations (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 95.02/107.69 %); best 5.145e-08s; worst 2.146e-06s; std dev. 8.778e-07 (taking best). -Reference operation time is 5.14507e-08 s (1866 Mflops) with 12 threads. -After merge step 1: tpop: 5.145e-08 s ~Mflops: 1865.863 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 115.848x: 5.96e-06s -> 5.145e-08s, so taking this instance. +3 iterations (12 th.) took 0.028s; avg 0.009333s ( +/- 14.26/ 28.37 %); best 0.008002s; worst 0.01198s; std dev. 0.001872 (taking best). +Reference operation time is 0.00800204 s (0.012 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: 0.008002 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 1.216e-05s, ~4.053e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 82.28/200.00 %); best 2.394e-07s; worst 4.053e-06s; std dev. 1.911e-06 (taking best). +Reference operation time is 2.39408e-07 s (401 Mflops) with 12 threads. +After merge step 1: tpop: 2.394e-07 s ~Mflops: 400.989 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 33424.289x: 0.008002s -> 2.394e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 4.101e-05s (of which 6.914e-06s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 4.101e-05s, equivalent to 797.0/6.9 new/old ops (2.48e-05s for 2 clones -- as 481.9/4.2 ops, or 241.0/2.1 ops per clone), SPEEDUP of 115.848x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 115.848x (5.96e-06s -> 5.145e-08s), will amortize in 6.9 ops by saving 5.909e-06s per op. -In 1 tuning rounds (tot. 9.6e-05s, 2.5e-05s for constructor, 2 clones) obtained a SPEEDUP of 11484.8% (115.8x) (from 16.11 to 1866 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02813s (of which 1.407e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 0s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.02813s, equivalent to 117490.4/3.5 new/old ops (0.05595s for 2 clones -- as 233689.2/7.0 ops, or 116844.6/3.5 ops per clone), SPEEDUP of 33424.289x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 33424.289x (0.008002s -> 2.394e-07s), will amortize in 3.5 ops by saving 0.008002s per op. +In 1 tuning rounds (tot. 0.084s, 0.056s for constructor, 2 clones) obtained a SPEEDUP of 3342328.9% (3.342e+04x) (from 0.012 to 401 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 0.000103951 s (5.960e-06 s -> 5.145e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0841489 s (8.002e-03 s -> 2.394e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.000241995 s and estimated a speedup of 1.000000 x (5.145e-08 s -> 5.145e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.391824 s and estimated a speedup of 1.000000 x (2.394e-07 s -> 2.394e-07 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 0.000020 0.000012 0.000032 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000032 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000020 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000012 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.023591 0.016017 0.039608 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.039608 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.023591 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.016017 %: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 0.000032 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.039608 %: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 @@ -4431,59 +4471,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 4.69685e-05 1e+09 1e+09 +%operation:A.mtx 0.0555861 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 2.00272e-05 0 1.19209e-05 +%constructor:A.mtx 0 0.023591 0 0.016017 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 7.648s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.361s/0.000s . +# so far, program took 10.510s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.980s/0.000s . getrusage() stats: -ru_maxrss: 73 (maximum resident set size -- MB) -ru_stime : 0.2196s (system CPU time used) -ru_utime : 14.44s (user CPU time used) +ru_maxrss: 81 (maximum resident set size -- MB) +ru_stime : 0.4145s (system CPU time used) +ru_utime : 28.65s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was S). # Cache block size total 16777216 bytes, per-thread 1398101 bytes -# so far, program took 7.648s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.361s/0.000s . +# so far, program took 10.510s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.980s/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 0.000s): (3 x 3)[0x55d6ada6ee80]{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 0.063s): (3 x 3)[0x558794c17ea0]{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 4.411e-05s; avg 1.47e-05s ( +/- 52.97/104.32 %); best 6.914e-06s; worst 3.004e-05s; std dev. 1.085e-05 (taking best). -Reference operation time is 6.91414e-06 s (13.88 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: 6.914e-06 Mflops: 13.885) -Merge (3 -> 1 leaves) took w.c.t. of 4.053e-06s, ~1.907e-06s of computing time (of which 0s sorting, 0s analysis) -3 iterations (12 th.) took 1.097e-05s; avg 3.656e-06s ( +/- 98.59/173.91 %); best 5.145e-08s; worst 1.001e-05s; std dev. 4.512e-06 (taking best). -Reference operation time is 5.14507e-08 s (1866 Mflops) with 12 threads. -After merge step 1: tpop: 5.145e-08 s ~Mflops: 1865.863 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 134.384x: 6.914e-06s -> 5.145e-08s, so taking this instance. +3 iterations (12 th.) took 0.02399s; avg 0.007997s ( +/- 0.05/ 0.04 %); best 0.007993s; worst 0.008s; std dev. 2.997e-06 (taking best). +Reference operation time is 0.00799298 s (0.01201 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: 0.007993 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 1.216e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 96.58/200.00 %); best 2.394e-07s; worst 2.098e-05s; std dev. 9.89e-06 (taking best). +Reference operation time is 2.39408e-07 s (401 Mflops) with 12 threads. +After merge step 1: tpop: 2.394e-07 s ~Mflops: 400.989 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 33386.446x: 0.007993s -> 2.394e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 3.695e-05s (of which 6.914e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 3.695e-05s, equivalent to 718.3/5.3 new/old ops (2.503e-05s for 2 clones -- as 486.6/3.6 ops, or 243.3/1.8 ops per clone), SPEEDUP of 134.384x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 134.384x (6.914e-06s -> 5.145e-08s), will amortize in 5.4 ops by saving 6.863e-06s per op. -In 1 tuning rounds (tot. 0.00011s, 2.5e-05s for constructor, 2 clones) obtained a SPEEDUP of 13338.4% (134.4x) (from 13.88 to 1866 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03599s (of which 1.502e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.03599s, equivalent to 150333.1/4.5 new/old ops (0.05968s for 2 clones -- as 249268.5/7.5 ops, or 124634.3/3.7 ops per clone), SPEEDUP of 33386.446x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 33386.446x (0.007993s -> 2.394e-07s), will amortize in 4.5 ops by saving 0.007993s per op. +In 1 tuning rounds (tot. 0.084s, 0.06s for constructor, 2 clones) obtained a SPEEDUP of 3338544.6% (3.339e+04x) (from 0.01201 to 401 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 0.00011611 s (6.914e-06 s -> 5.145e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.083761 s (7.993e-03 s -> 2.394e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.000359058 s and estimated a speedup of 1.000000 x (5.145e-08 s -> 5.145e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.443797 s and estimated a speedup of 1.000000 x (2.394e-07 s -> 2.394e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.73205078 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000017 0.000013 0.000030 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000030 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000017 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000013 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.023308 0.019909 0.043217 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.043217 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.023308 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.019909 %: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 0.000030 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.043217 %: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 @@ -4498,50 +4538,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 4.50611e-05 1e+09 1e+09 +%operation:A.mtx 0.063344 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 1.69277e-05 0 1.3113e-05 +%constructor:A.mtx 0 0.0233078 0 0.0199089 # 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 0.000s): (3 x 3)[0x55d6ada6ee80]{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 0.059s): (3 x 3)[0x558794c17ea0]{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 0.004144s; avg 0.001381s ( +/- 99.14/191.25 %); best 1.192e-05s; worst 0.004023s; std dev. 0.001868 (taking best). -Reference operation time is 1.19209e-05 s (32.21 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: 1.192e-05 Mflops: 32.212) -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 2.861e-06s; avg 9.537e-07s ( +/- 94.61/100.00 %); best 5.145e-08s; worst 1.907e-06s; std dev. 7.787e-07 (taking best). -Reference operation time is 5.14507e-08 s (7463 Mflops) with 12 threads. -After merge step 1: tpop: 5.145e-08 s ~Mflops: 7463.451 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 231.696x: 1.192e-05s -> 5.145e-08s, so taking this instance. +3 iterations (12 th.) took 0.024s; avg 0.008s ( +/- 0.11/ 0.14 %); best 0.007992s; worst 0.008011s; std dev. 8.051e-06 (taking best). +Reference operation time is 0.00799179 s (0.04805 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: 0.007992 Mflops: 0.048) +Merge (3 -> 1 leaves) took w.c.t. of 1.097e-05s, ~3.815e-06s of computing time (of which 0s sorting, 2.861e-06s analysis) +3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 82.28/129.41 %); best 2.394e-07s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 2.39408e-07 s (1604 Mflops) with 12 threads. +After merge step 1: tpop: 2.394e-07 s ~Mflops: 1603.956 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 33381.467x: 0.007992s -> 2.394e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 2.813e-05s (of which 7.153e-06s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 0s sorting, 9.537e-07s analyzing) -Total merge + benchmarking process took 2.813e-05s, equivalent to 546.8/2.4 new/old ops (2.503e-05s for 2 clones -- as 486.6/2.1 ops, or 243.3/1.1 ops per clone), SPEEDUP of 231.696x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 231.696x (1.192e-05s -> 5.145e-08s), will amortize in 2.4 ops by saving 1.187e-05s per op. -In 1 tuning rounds (tot. 0.0042s, 2.5e-05s for constructor, 2 clones) obtained a SPEEDUP of 23069.6% (231.7x) (from 32.21 to 7463 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02399s (of which 1.287e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 0s sorting, 2.861e-06s analyzing) +Total merge + benchmarking process took 0.02399s, equivalent to 100185.2/3.0 new/old ops (0.04793s for 2 clones -- as 200186.2/6.0 ops, or 100093.1/3.0 ops per clone), SPEEDUP of 33381.467x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 33381.467x (0.007992s -> 2.394e-07s), will amortize in 3.0 ops by saving 0.007992s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 3338046.7% (3.338e+04x) (from 0.04805 to 1604 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 0.0042088 s (1.192e-05 s -> 5.145e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0719938 s (7.992e-03 s -> 2.394e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.000303984 s and estimated a speedup of 1.000000 x (5.145e-08 s -> 5.145e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.524002 s and estimated a speedup of 1.000000 x (2.394e-07 s -> 2.394e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.73205078 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000017 0.000011 0.000028 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000028 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000017 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000011 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.027008 0.015995 0.043003 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.043003 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.027008 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.015995 %: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 0.000028 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.043003 %: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 @@ -4556,59 +4596,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 4.29153e-05 1e+09 1e+09 +%operation:A.mtx 0.0590069 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 1.69277e-05 0 1.09673e-05 +%constructor:A.mtx 0 0.0270078 0 0.0159948 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 7.770s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.366s/0.000s . +# so far, program took 11.974s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.103s/0.000s . getrusage() stats: -ru_maxrss: 73 (maximum resident set size -- MB) -ru_stime : 0.2795s (system CPU time used) -ru_utime : 15.8s (user CPU time used) +ru_maxrss: 81 (maximum resident set size -- MB) +ru_stime : 0.4929s (system CPU time used) +ru_utime : 40.29s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was C). # Cache block size total 16777216 bytes, per-thread 1398101 bytes -# so far, program took 7.771s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.366s/0.000s . +# so far, program took 11.974s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.103s/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 0.055s): (3 x 3)[0x55d6ada6ee80]{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 0.115s): (3 x 3)[0x558794c17ea0]{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 0.048s; avg 0.016s ( +/- 0.02/ 0.03 %); best 0.016s; worst 0.016s; std dev. 3.44e-06 (taking best). -Reference operation time is 0.0159962 s (0.006001 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: 0.016 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 9.06e-06s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (12 th.) took 1.502e-05s; avg 5.007e-06s ( +/- 98.97/180.95 %); best 5.145e-08s; worst 1.407e-05s; std dev. 6.418e-06 (taking best). -Reference operation time is 5.14507e-08 s (1866 Mflops) with 12 threads. -After merge step 1: tpop: 5.145e-08 s ~Mflops: 1865.863 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 310903.614x: 0.016s -> 5.145e-08s, so taking this instance. +3 iterations (12 th.) took 0.048s; avg 0.016s ( +/- 25.00/ 49.90 %); best 0.012s; worst 0.02398s; std dev. 0.005645 (taking best). +Reference operation time is 0.0119991 s (0.008001 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: 0.012 Mflops: 0.008) +Merge (3 -> 1 leaves) took w.c.t. of 1.311e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 2.599e-05s; avg 8.663e-06s ( +/- 97.24/200.00 %); best 2.394e-07s; worst 2.599e-05s; std dev. 1.225e-05 (taking best). +Reference operation time is 2.39408e-07 s (401 Mflops) with 12 threads. +After merge step 1: tpop: 2.394e-07 s ~Mflops: 400.989 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 50120.002x: 0.012s -> 2.394e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.048s (of which 1.097e-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 0.048s, equivalent to 932873.0/3.0 new/old ops (0.09595s for 2 clones -- as 1864870.3/6.0 ops, or 932435.1/3.0 ops per clone), SPEEDUP of 310903.614x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 310903.614x (0.016s -> 5.145e-08s), will amortize in 3.0 ops by saving 0.016s per op. -In 1 tuning rounds (tot. 0.14s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 31090261.4% (3.109e+05x) (from 0.006001 to 1866 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.048s (of which 1.407e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.048s, equivalent to 200502.9/4.0 new/old ops (0.09592s for 2 clones -- as 400642.3/8.0 ops, or 200321.2/4.0 ops per clone), SPEEDUP of 50120.002x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 50120.002x (0.012s -> 2.394e-07s), will amortize in 4.0 ops by saving 0.012s per op. +In 1 tuning rounds (tot. 0.14s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 5011900.2% (5.012e+04x) (from 0.008001 to 401 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 0.144017 s (1.600e-02 s -> 5.145e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.144007 s (1.200e-02 s -> 2.394e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.232277 s and estimated a speedup of 1.000000 x (5.145e-08 s -> 5.145e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.77997 s and estimated a speedup of 1.000000 x (2.394e-07 s -> 2.394e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.018697 0.015993 0.034690 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.034690 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.018697 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.015993 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.039793 0.039567 0.079360 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.079360 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.039793 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.039567 %: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 0.034690 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.079360 %: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 @@ -4623,50 +4663,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0546989 1e+09 1e+09 +%operation:A.mtx 0.115361 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.018697 0 0.0159931 +%constructor:A.mtx 0 0.039793 0 0.039567 # 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 0.103s): (3 x 3)[0x55d6ada6ee80]{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 0.112s): (3 x 3)[0x558794c17ea0]{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 0.048s; avg 0.016s ( +/- 0.03/ 0.04 %); best 0.01599s; worst 0.01601s; std dev. 5.081e-06 (taking best). -Reference operation time is 0.0159941 s (0.02401 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: 0.01599 Mflops: 0.024) -Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~3.815e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) -3 iterations (12 th.) took 3.815e-06s; avg 1.272e-06s ( +/- 95.95/125.00 %); best 5.145e-08s; worst 2.861e-06s; std dev. 1.189e-06 (taking best). -Reference operation time is 5.14507e-08 s (7463 Mflops) with 12 threads. -After merge step 1: tpop: 5.145e-08 s ~Mflops: 7463.451 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 310861.909x: 0.01599s -> 5.145e-08s, so taking this instance. +3 iterations (12 th.) took 0.05599s; avg 0.01866s ( +/- 14.29/ 28.56 %); best 0.016s; worst 0.02399s; std dev. 0.003769 (taking best). +Reference operation time is 0.0159972 s (0.024 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: 0.016 Mflops: 0.024) +Merge (3 -> 1 leaves) took w.c.t. of 1.597e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 5.96e-06s; avg 1.987e-06s ( +/- 87.95/152.00 %); best 2.394e-07s; worst 5.007e-06s; std dev. 2.171e-06 (taking best). +Reference operation time is 2.39408e-07 s (1604 Mflops) with 12 threads. +After merge step 1: tpop: 2.394e-07 s ~Mflops: 1603.956 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 66819.698x: 0.016s -> 2.394e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.04799s (of which 1.192e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 0s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.04799s, equivalent to 932757.2/3.0 new/old ops (0.09593s for 2 clones -- as 1864559.8/6.0 ops, or 932279.9/3.0 ops per clone), SPEEDUP of 310861.909x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 310861.909x (0.01599s -> 5.145e-08s), will amortize in 3.0 ops by saving 0.01599s per op. -In 1 tuning rounds (tot. 0.14s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 31086090.9% (3.109e+05x) (from 0.02401 to 7463 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.05596s (of which 1.693e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 9.537e-07s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.05596s, equivalent to 233763.9/3.5 new/old ops (0.1119s for 2 clones -- as 467437.1/7.0 ops, or 233718.6/3.5 ops per clone), SPEEDUP of 66819.698x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 66819.698x (0.016s -> 2.394e-07s), will amortize in 3.5 ops by saving 0.016s per op. +In 1 tuning rounds (tot. 0.17s, 0.11s for constructor, 2 clones) obtained a SPEEDUP of 6681869.8% (6.682e+04x) (from 0.024 to 1604 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 0.144 s (1.599e-02 s -> 5.145e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.167985 s (1.600e-02 s -> 2.394e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.443955 s and estimated a speedup of 1.000000 x (5.145e-08 s -> 5.145e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.819789 s and estimated a speedup of 1.000000 x (2.394e-07 s -> 2.394e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.038542 0.031998 0.070540 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.070540 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.038542 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.031998 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.047747 0.039993 0.087740 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.087740 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.047747 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.039993 %: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 0.070540 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.087740 %: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 @@ -4681,332 +4721,332 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.102545 1e+09 1e+09 +%operation:A.mtx 0.111761 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.038542 0 0.0319979 +%constructor:A.mtx 0 0.0477469 0 0.0399928 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 9.050s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.330s/0.000s . +# so far, program took 14.369s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.015s/0.000s . getrusage() stats: -ru_maxrss: 73 (maximum resident set size -- MB) -ru_stime : 0.3384s (system CPU time used) -ru_utime : 29.83s (user CPU time used) +ru_maxrss: 81 (maximum resident set size -- MB) +ru_stime : 0.554s (system CPU time used) +ru_utime : 51.93s (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 1 466.47 6.744e-03 0.000e+00 5.145e-08 0.000e+00 9.158e-02 2.88e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.001e-04 7.07e+00 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 1 100.25 7.995e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 6.18e-01 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 1 400.99 7.974e-03 0.000e+00 2.394e-07 0.000e+00 7.200e-02 1.52e+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. 6559677.6 % faster, avg. sp. ratio 65597.776x, max sp. ratio 131079.703x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 890980.1/1946.2/1780013.9/1781960.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 15.2/ 13.6/ 16.8/ 30.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 15.3, min. 13.6, max. 16.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3335009.3 % faster, avg. sp. ratio 33351.093x, max sp. ratio 33395.409x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 300721.0/300692.1/300749.9/601442.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 9.0/ 9.0/ 18.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.0, min. 9.0, max. 9.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 16/ 16/ 16) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 48/ 48/ 48) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.809/ 2.410/ 5.209,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.951/ 2.877/ 7.075,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.819/ 0.518/ 1.119,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.139/ 0.618/ 1.520,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.: 0.05 s, min 0.00 s, max 0.09 s, tot 0.09 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.00 s, max 0.09 s, tot 0.09 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.166e+03, min 4.665e+02, max 1.866e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 8.055e+00, min 3.559e-03, max 1.611e+01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 1.029e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 3.375e-03s, min 5.960e-06s, max 6.744e-03s, tot 6.750e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.523e+00 7.613e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.506e+02, min 1.002e+02, max 4.010e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.521e-03, min 3.002e-03, max 1.204e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 4.788e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.985e-03s, min 7.974e-03s, max 7.995e-03s, tot 1.597e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.431e+01 3.093e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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 1 466.47 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.049e-04 1.71e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.040e-04 3.81e+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 1 100.25 7.981e-03 0.000e+00 2.394e-07 0.000e+00 8.020e-02 3.68e-01 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 1 400.99 8.002e-03 0.000e+00 2.394e-07 0.000e+00 8.415e-02 8.19e-01 1.54e+00 1 9.60e-05 #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 11484.8 % faster, avg. sp. ratio 115.848x, max sp. ratio 115.848x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2029.7/2020.4/2038.9/4059.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 17.5/ 17.4/ 17.6/ 35.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 17.7, min. 17.6, max. 17.8 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3337897.3 % faster, avg. sp. ratio 33379.973x, max sp. ratio 33424.289x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 343230.1/334972.9/351487.3/686460.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.3/ 10.0/ 10.5/ 20.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.3, min. 10.0, max. 10.5 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 8/ 8/ 8) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 24/ 24/ 24) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.177/ 1.477/ 2.877,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.520/ 1.710/ 3.809,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.468/ 0.317/ 0.618,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.186/ 0.368/ 0.819,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.354/ 1.542/ 3.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.166e+03, min 4.665e+02, max 1.866e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.007e+01, min 4.027e+00, max 1.611e+01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 1.029e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.960e-06s, min 5.960e-06s, max 5.960e-06s, tot 1.192e-05s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.379e+00 1.242e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.08 s, max 0.08 s, tot 0.16 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.08 s, max 0.08 s, tot 0.16 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.506e+02, min 1.002e+02, max 4.010e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.502e-03, min 3.007e-03, max 1.200e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 4.788e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.991e-03s, min 7.981e-03s, max 8.002e-03s, tot 1.598e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.592e+01 5.047e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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 1865.86 6.914e-06 0.000e+00 5.145e-08 0.000e+00 1.161e-04 2.88e+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 7463.45 1.192e-05 0.000e+00 5.145e-08 0.000e+00 4.209e-03 7.07e+00 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 1 400.99 7.993e-03 0.000e+00 2.394e-07 0.000e+00 8.376e-02 6.18e-01 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 1603.96 7.992e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 1.52e+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. 18204.0 % faster, avg. sp. ratio 183.040x, max sp. ratio 231.696x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 42029.7/2256.7/81802.6/84059.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 184.9/ 16.8/353.1/369.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 185.8, min. 16.9, max. 354.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3338295.7 % faster, avg. sp. ratio 33383.957x, max sp. ratio 33386.446x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 325291.5/300716.0/349867.1/650583.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.7/ 9.0/ 10.5/ 19.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.7, min. 9.0, max. 10.5 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 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 3.809/ 2.410/ 5.209,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.951/ 2.877/ 7.075,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.819/ 0.518/ 1.119,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.139/ 0.618/ 1.520,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 0.995/ 0.698/ 1.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.665e+03, min 1.866e+03, max 7.463e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.305e+01, min 1.388e+01, max 3.221e+01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 1.029e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 9.418e-06s, min 6.914e-06s, max 1.192e-05s, tot 1.884e-05s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.523e+00 7.613e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.08 s, tot 0.16 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.08 s, tot 0.16 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.002e+03, min 4.010e+02, max 1.604e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.003e-02, min 1.201e-02, max 4.805e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 4.788e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.992e-03s, min 7.992e-03s, max 7.993e-03s, tot 1.598e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.431e+01 3.093e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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 1865.86 1.600e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 5.21e+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 7463.45 1.599e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 1.36e+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 1 400.99 1.200e-02 0.000e+00 2.394e-07 0.000e+00 1.440e-01 1.12e+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 1603.96 1.600e-02 0.000e+00 2.394e-07 0.000e+00 1.680e-01 2.92e+00 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. 31088176.2 % faster, avg. sp. ratio 310882.762x, max sp. ratio 310903.614x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2798957.4/2798790.5/2799124.2/5597914.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 9.0/ 9.0/ 18.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.0, min. 9.0, max. 9.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 5846885.0 % faster, avg. sp. ratio 58469.850x, max sp. ratio 66819.698x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 651590.4/601512.7/701668.1/1303180.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.3/ 10.5/ 12.0/ 22.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.3, min. 10.5, max. 12.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 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 7.075/ 4.276/ 9.874,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.814/ 5.209/ 13.605,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.520/ 0.919/ 2.122,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 4.043/ 1.119/ 2.924,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.807/ 1.323/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.14 s, min 0.14 s, max 0.14 s, tot 0.29 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.14 s, max 0.14 s, tot 0.29 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.665e+03, min 1.866e+03, max 7.463e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.501e-02, min 6.001e-03, max 2.401e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 1.029e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.600e-02s, min 1.599e-02s, max 1.600e-02s, tot 3.199e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.858e+00 4.291e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.16 s, min 0.14 s, max 0.17 s, tot 0.31 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.16 s, min 0.14 s, max 0.17 s, tot 0.31 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.002e+03, min 4.010e+02, max 1.604e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.600e-02, min 8.001e-03, max 2.400e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 4.788e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.400e-02s, min 1.200e-02s, max 1.600e-02s, tot 2.800e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.551e+00 1.744e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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 1 466.47 6.744e-03 0.000e+00 5.145e-08 0.000e+00 9.158e-02 2.88e+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 1 466.47 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.049e-04 1.71e+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 1865.86 6.914e-06 0.000e+00 5.145e-08 0.000e+00 1.161e-04 2.88e+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 1865.86 1.600e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 5.21e+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 1 100.25 7.995e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 6.18e-01 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 1 100.25 7.981e-03 0.000e+00 2.394e-07 0.000e+00 8.020e-02 3.68e-01 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 1 400.99 7.993e-03 0.000e+00 2.394e-07 0.000e+00 8.376e-02 6.18e-01 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 1 400.99 1.200e-02 0.000e+00 2.394e-07 0.000e+00 1.440e-01 1.12e+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. 11055738.7 % faster, avg. sp. ratio 110558.387x, max sp. ratio 310903.614x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1145858.4/2038.9/2799124.2/4583433.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.2/ 9.0/ 17.6/ 57.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.3, min. 9.0, max. 17.8 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3755837.9 % faster, avg. sp. ratio 37559.379x, max sp. ratio 50120.002x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 396761.2/300692.1/601512.7/1587044.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.4/ 9.0/ 12.0/ 41.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.4, min. 9.0, max. 12.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.643/ 1.477/ 4.276,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.672/ 1.710/ 5.209,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.568/ 0.317/ 0.919,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.723/ 0.368/ 1.119,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.: 0.06 s, min 0.00 s, max 0.14 s, tot 0.24 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.00 s, max 0.14 s, tot 0.24 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.166e+03, min 4.665e+02, max 1.866e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.480e+00, min 3.559e-03, max 1.388e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 2.058e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.688e-03s, min 5.960e-06s, max 1.600e-02s, tot 2.275e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.291e+00 1.242e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.09 s, min 0.07 s, max 0.14 s, tot 0.38 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.09 s, min 0.07 s, max 0.14 s, tot 0.38 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.506e+02, min 1.002e+02, max 4.010e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.505e-03, min 3.002e-03, max 1.201e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 9.576e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.992e-03s, min 7.981e-03s, max 1.200e-02s, tot 3.597e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.744e+01 5.047e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.001e-04 7.07e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.040e-04 3.81e+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 7463.45 1.192e-05 0.000e+00 5.145e-08 0.000e+00 4.209e-03 7.07e+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 7463.45 1.599e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 1.36e+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 1 400.99 7.974e-03 0.000e+00 2.394e-07 0.000e+00 7.200e-02 1.52e+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 1 400.99 8.002e-03 0.000e+00 2.394e-07 0.000e+00 8.415e-02 8.19e-01 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 1603.96 7.992e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 1.52e+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 1603.96 1.600e-02 0.000e+00 2.394e-07 0.000e+00 1.680e-01 2.92e+00 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. 7783032.5 % faster, avg. sp. ratio 77831.325x, max sp. ratio 310861.909x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 721139.9/1946.2/2798790.5/2884559.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 99.1/ 9.0/353.1/396.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 99.5, min. 9.0, max. 354.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4173205.8 % faster, avg. sp. ratio 41733.058x, max sp. ratio 66819.698x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 413655.3/300716.0/701668.1/1654621.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.8/ 9.0/ 10.5/ 39.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.8, min. 9.0, max. 10.5 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.792/ 2.877/ 9.874,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 31.564/ 3.809/ 13.605,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.245/ 0.618/ 2.122,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 6.783/ 0.819/ 2.924,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.589/ 0.698/ 2.792) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.00 s, max 0.14 s, tot 0.15 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.00 s, max 0.14 s, tot 0.15 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.665e+03, min 1.866e+03, max 7.463e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.611e+01, min 2.401e-02, max 3.221e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 2.058e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.004e-03s, min 5.960e-06s, max 1.599e-02s, tot 1.602e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.858e+00 6.379e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.10 s, min 0.07 s, max 0.17 s, tot 0.40 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.10 s, min 0.07 s, max 0.17 s, tot 0.40 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.002e+03, min 4.010e+02, max 1.604e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.402e-02, min 1.200e-02, max 4.805e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 9.576e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.991e-03s, min 7.974e-03s, max 1.600e-02s, tot 3.996e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.551e+00 2.592e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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 1 466.47 6.744e-03 0.000e+00 5.145e-08 0.000e+00 9.158e-02 2.88e+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 1 466.47 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.049e-04 1.71e+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 1865.86 6.914e-06 0.000e+00 5.145e-08 0.000e+00 1.161e-04 2.88e+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 1865.86 1.600e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 5.21e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.001e-04 7.07e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.040e-04 3.81e+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 7463.45 1.192e-05 0.000e+00 5.145e-08 0.000e+00 4.209e-03 7.07e+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 7463.45 1.599e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 1.36e+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 1 100.25 7.995e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 6.18e-01 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 1 100.25 7.981e-03 0.000e+00 2.394e-07 0.000e+00 8.020e-02 3.68e-01 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 1 400.99 7.993e-03 0.000e+00 2.394e-07 0.000e+00 8.376e-02 6.18e-01 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 1 400.99 1.200e-02 0.000e+00 2.394e-07 0.000e+00 1.440e-01 1.12e+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 1 400.99 7.974e-03 0.000e+00 2.394e-07 0.000e+00 7.200e-02 1.52e+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 1 400.99 8.002e-03 0.000e+00 2.394e-07 0.000e+00 8.415e-02 8.19e-01 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 1603.96 7.992e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 1.52e+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 1603.96 1.600e-02 0.000e+00 2.394e-07 0.000e+00 1.680e-01 2.92e+00 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. 9419385.6 % faster, avg. sp. ratio 94194.856x, max sp. ratio 310903.614x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 933499.2/1946.2/2799124.2/7467993.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 56.7/ 9.0/353.1/453.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 56.9, min. 9.0, max. 354.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3964521.8 % faster, avg. sp. ratio 39646.218x, max sp. ratio 66819.698x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 405208.3/300692.1/701668.1/3241666.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.1/ 9.0/ 12.0/ 80.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.1, min. 9.0, max. 12.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.218/ 1.477/ 9.874,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.236/ 1.710/ 13.605,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.906/ 0.317/ 2.122,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.507/ 0.368/ 2.924,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.: 0.05 s, min 0.00 s, max 0.14 s, tot 0.38 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.00 s, max 0.14 s, tot 0.38 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.915e+03, min 4.665e+02, max 7.463e+03 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.030e+01, min 3.559e-03, max 3.221e+01 (8 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 4.116e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.846e-03s, min 5.960e-06s, max 1.600e-02s, tot 3.877e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.858e+00 1.242e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.10 s, min 0.07 s, max 0.17 s, tot 0.78 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.10 s, min 0.07 s, max 0.17 s, tot 0.78 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.265e+02, min 1.002e+02, max 1.604e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.526e-02, min 3.002e-03, max 4.805e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 1.915e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.492e-03s, min 7.974e-03s, max 1.600e-02s, tot 7.593e-02s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.551e+00 5.047e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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 1 466.47 6.744e-03 0.000e+00 5.145e-08 0.000e+00 9.158e-02 2.88e+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 1 466.47 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.049e-04 1.71e+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 1865.86 6.914e-06 0.000e+00 5.145e-08 0.000e+00 1.161e-04 2.88e+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 1865.86 1.600e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 5.21e+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 1 100.25 7.995e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 6.18e-01 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 1 100.25 7.981e-03 0.000e+00 2.394e-07 0.000e+00 8.020e-02 3.68e-01 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 1 400.99 7.993e-03 0.000e+00 2.394e-07 0.000e+00 8.376e-02 6.18e-01 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 1 400.99 1.200e-02 0.000e+00 2.394e-07 0.000e+00 1.440e-01 1.12e+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. 11055738.7 % faster, avg. sp. ratio 110558.387x, max sp. ratio 310903.614x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1145858.4/2038.9/2799124.2/4583433.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.2/ 9.0/ 17.6/ 57.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.3, min. 9.0, max. 17.8 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3755837.9 % faster, avg. sp. ratio 37559.379x, max sp. ratio 50120.002x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 396761.2/300692.1/601512.7/1587044.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.4/ 9.0/ 12.0/ 41.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.4, min. 9.0, max. 12.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.643/ 1.477/ 4.276,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.672/ 1.710/ 5.209,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.568/ 0.317/ 0.919,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.723/ 0.368/ 1.119,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.: 0.06 s, min 0.00 s, max 0.14 s, tot 0.24 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.00 s, max 0.14 s, tot 0.24 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.166e+03, min 4.665e+02, max 1.866e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.480e+00, min 3.559e-03, max 1.388e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 2.058e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.688e-03s, min 5.960e-06s, max 1.600e-02s, tot 2.275e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.291e+00 1.242e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.09 s, min 0.07 s, max 0.14 s, tot 0.38 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.09 s, min 0.07 s, max 0.14 s, tot 0.38 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.506e+02, min 1.002e+02, max 4.010e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.505e-03, min 3.002e-03, max 1.201e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 9.576e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.992e-03s, min 7.981e-03s, max 1.200e-02s, tot 3.597e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.744e+01 5.047e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.001e-04 7.07e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.040e-04 3.81e+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 7463.45 1.192e-05 0.000e+00 5.145e-08 0.000e+00 4.209e-03 7.07e+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 7463.45 1.599e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 1.36e+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 1 400.99 7.974e-03 0.000e+00 2.394e-07 0.000e+00 7.200e-02 1.52e+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 1 400.99 8.002e-03 0.000e+00 2.394e-07 0.000e+00 8.415e-02 8.19e-01 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 1603.96 7.992e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 1.52e+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 1603.96 1.600e-02 0.000e+00 2.394e-07 0.000e+00 1.680e-01 2.92e+00 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. 7783032.5 % faster, avg. sp. ratio 77831.325x, max sp. ratio 310861.909x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 721139.9/1946.2/2798790.5/2884559.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 99.1/ 9.0/353.1/396.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 99.5, min. 9.0, max. 354.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4173205.8 % faster, avg. sp. ratio 41733.058x, max sp. ratio 66819.698x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 413655.3/300716.0/701668.1/1654621.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.8/ 9.0/ 10.5/ 39.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.8, min. 9.0, max. 10.5 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.792/ 2.877/ 9.874,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 31.564/ 3.809/ 13.605,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.245/ 0.618/ 2.122,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 6.783/ 0.819/ 2.924,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.589/ 0.698/ 2.792) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.04 s, min 0.00 s, max 0.14 s, tot 0.15 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.04 s, min 0.00 s, max 0.14 s, tot 0.15 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.665e+03, min 1.866e+03, max 7.463e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.611e+01, min 2.401e-02, max 3.221e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 2.058e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.004e-03s, min 5.960e-06s, max 1.599e-02s, tot 1.602e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.858e+00 6.379e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.10 s, min 0.07 s, max 0.17 s, tot 0.40 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.10 s, min 0.07 s, max 0.17 s, tot 0.40 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.002e+03, min 4.010e+02, max 1.604e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.402e-02, min 1.200e-02, max 4.805e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 9.576e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.991e-03s, min 7.974e-03s, max 1.600e-02s, tot 3.996e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.551e+00 2.592e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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. @@ -5017,65 +5057,65 @@ #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 1 466.47 6.744e-03 0.000e+00 5.145e-08 0.000e+00 9.158e-02 2.88e+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 1 466.47 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.049e-04 1.71e+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 1865.86 6.914e-06 0.000e+00 5.145e-08 0.000e+00 1.161e-04 2.88e+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 1865.86 1.600e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 5.21e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.001e-04 7.07e+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 1865.86 5.960e-06 0.000e+00 5.145e-08 0.000e+00 1.040e-04 3.81e+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 7463.45 1.192e-05 0.000e+00 5.145e-08 0.000e+00 4.209e-03 7.07e+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 7463.45 1.599e-02 0.000e+00 5.145e-08 0.000e+00 1.440e-01 1.36e+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 1 100.25 7.995e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 6.18e-01 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 1 100.25 7.981e-03 0.000e+00 2.394e-07 0.000e+00 8.020e-02 3.68e-01 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 1 400.99 7.993e-03 0.000e+00 2.394e-07 0.000e+00 8.376e-02 6.18e-01 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 1 400.99 1.200e-02 0.000e+00 2.394e-07 0.000e+00 1.440e-01 1.12e+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 1 400.99 7.974e-03 0.000e+00 2.394e-07 0.000e+00 7.200e-02 1.52e+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 1 400.99 8.002e-03 0.000e+00 2.394e-07 0.000e+00 8.415e-02 8.19e-01 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 1603.96 7.992e-03 0.000e+00 2.394e-07 0.000e+00 7.199e-02 1.52e+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 1603.96 1.600e-02 0.000e+00 2.394e-07 0.000e+00 1.680e-01 2.92e+00 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. 9419385.6 % faster, avg. sp. ratio 94194.856x, max sp. ratio 310903.614x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 933499.2/1946.2/2799124.2/7467993.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 56.7/ 9.0/353.1/453.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 56.9, min. 9.0, max. 354.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3964521.8 % faster, avg. sp. ratio 39646.218x, max sp. ratio 66819.698x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 405208.3/300692.1/701668.1/3241666.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.1/ 9.0/ 12.0/ 80.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.1, min. 9.0, max. 12.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.218/ 1.477/ 9.874,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.236/ 1.710/ 13.605,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.906/ 0.317/ 2.122,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.507/ 0.368/ 2.924,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.: 0.05 s, min 0.00 s, max 0.14 s, tot 0.38 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.00 s, max 0.14 s, tot 0.38 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.915e+03, min 4.665e+02, max 7.463e+03 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.030e+01, min 3.559e-03, max 3.221e+01 (8 samples) -#pr: best tun. rsb operation time was: on avg. 5.145e-08s, min 5.145e-08s, max 5.145e-08s, tot 4.116e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.846e-03s, min 5.960e-06s, max 1.600e-02s, tot 3.877e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.858e+00 1.242e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.952e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.10 s, min 0.07 s, max 0.17 s, tot 0.78 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.10 s, min 0.07 s, max 0.17 s, tot 0.78 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.265e+02, min 1.002e+02, max 1.604e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.526e-02, min 3.002e-03, max 4.805e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 2.394e-07s, min 2.394e-07s, max 2.394e-07s, tot 1.915e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.492e-03s, min 7.974e-03s, max 1.600e-02s, tot 7.593e-02s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.551e+00 5.047e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.990e+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 1.57 s. +#pr: Record collection took 5.45 s. #pr: Record comprises 50 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4298 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4352 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1717748735_gcc-13.2.rpr -# Removing the temporary record file rsbench_pr__1717748735_gcc-13.2.rpr.tmp. -# terminating run at 1717748744 (after 9.0s 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__1752160129_gcc-13.2.rpr +# Removing the temporary record file rsbench_pr__1752160129_gcc-13.2.rpr.tmp. +# terminating run at 1752160143 (after 14.4s of w.c.t.) +srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/sh ./scripts/doc-tests.sh + set -o pipefail + test x/build/reproducible-path/librsb-1.3.0.2+dfsg = x -+ cat /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/autotune.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/backsolve.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/hello-spblas.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/hello.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/io-spblas.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/power.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/snippets.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/transpose.c + grep '^.\{71,\}' ++ 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 + true + cat /build/reproducible-path/librsb-1.3.0.2+dfsg/README + grep '^[^ ].\{80,\}' + true -++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h ++ wc -l +++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h + test 63 -ge 61 ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h ++ wc -c + test 2014 -ge 1966 -++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h ++ wc -l +++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h + test 182 -ge 157 ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h ++ wc -c @@ -5113,7 +5153,7 @@ 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 @@ -5123,15 +5163,15 @@ 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 1717748744 +# beginning run at 1752160144 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench --lower 100 --as-symmetric --types : -n 1 --notranspose --compare-competitors --verbose --verbose --write-performance-record=test.rpr # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -# average timer granularity: 4.73e-08 s +# average timer granularity: 3.81e-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 @@ -5170,7 +5210,7 @@ # 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: infom01-amd64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 2 (each --verbose occurrence counts +1) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 1398101 bytes @@ -5190,29 +5230,29 @@ # This test will measure times in scanning arrays sized and aligned to fit in caches. # 3 cache levels detected Will fill struct with 50 samples... -# Memory benchmark took 6.893s +# Memory benchmark took 7.167s # 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 16777216 bytes, per-thread 1398101 bytes -# so far, program took 6.895s 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 7.173s 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 1.044e-01 s (100.00 %) - analyzed arrays in 2.434e-02 s (23.31 %) - cleaned-up arrays in 6.199e-06 s (0.01 %) - deduplicated arrays in 6.914e-06 s (0.01 %) + converted COO to RSB in 6.356e-02 s (100.00 %) + analyzed arrays in 1.154e-02 s (18.16 %) + cleaned-up arrays in 1.001e-05 s (0.02 %) + deduplicated arrays in 1.192e-05 s (0.02 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.954e-02 s (57.00 %) - memory allocations took 3.815e-06 s (0.00 %) - leafs setup took 9.060e-06 s (0.01 %) - halfword conversion took 2.053e-02 s (19.66 %) -Built (100 x 100)[0x55ac7db922d0]{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 0.104s): (100 x 100)[0x55ac7db922d0]{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 3.598e-02 s (56.60 %) + memory allocations took 1.812e-05 s (0.03 %) + leafs setup took 6.914e-06 s (0.01 %) + halfword conversion took 1.599e-02 s (25.16 %) +Built (100 x 100)[0x55b7c7a2d300]{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 0.064s): (100 x 100)[0x55b7c7a2d300]{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. @@ -5263,10 +5303,10 @@ # 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 0.02397s; avg 0.007989s ( +/- 0.27/ 0.14 %); best 0.007967s; worst 0.008s; std dev. 1.518e-05 (taking best). -Reference operation time is 0.00796723 s (2.535 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: 0.007967 Mflops: 2.535) -Merge (3 -> 1 leaves) took w.c.t. of 5.412e-05s, ~3.791e-05s of computing time (of which 1.192e-05s sorting, 6.199e-06s analysis) +3 iterations (1 th.) took 0.03196s; avg 0.01065s ( +/- 25.02/ 49.97 %); best 0.007988s; worst 0.01598s; std dev. 0.003765 (taking best). +Reference operation time is 0.00798798 s (2.529 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: 0.007988 Mflops: 2.529) +Merge (3 -> 1 leaves) took w.c.t. of 4.005e-05s, ~2.813e-05s of computing time (of which 9.06e-06s sorting, 4.053e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5297,7 +5337,7 @@ # 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 2.003e-05s; avg 6.676e-06s ( +/- 10.71/ 7.14 %); best 5.96e-06s; worst 7.153e-06s; std dev. 5.15e-07 (taking best). +3 iterations (1 th.) took 1.907e-05s; avg 6.358e-06s ( +/- 6.25/ 8.75 %); best 5.96e-06s; worst 6.914e-06s; std dev. 4.052e-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 16777216 bytes, per-thread 16777216 bytes @@ -5315,15 +5355,15 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success 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 1336.680x: 0.007967s -> 5.96e-06s, so taking this instance. +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1340.160x: 0.007988s -> 5.96e-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 0.07204s (of which 5.794e-05s partitioning, 0.04804s I/O); computing times: 3.791e-05s in par. loops, 1.192e-05s sorting, 6.199e-06s analyzing) -Total merge + benchmarking process took 0.07204s, equivalent to 12086.2/9.0 new/old ops (0.04776s for 2 clones -- as 8012.2/6.0 ops, or 4006.1/3.0 ops per clone), SPEEDUP of 1336.680x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1336.680x (0.007967s -> 5.96e-06s), will amortize in 9.0 ops by saving 0.007961s per op. -In 1 tuning rounds (tot. 0.12s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 133568.0% (1337x) (from 2.535 to 3389 Mflops). Employed 0.048s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.07606s (of which 4.292e-05s partitioning, 0.04804s I/O); computing times: 2.813e-05s in par. loops, 9.06e-06s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.07606s, equivalent to 12759.9/9.5 new/old ops (0.05167s for 2 clones -- as 8668.0/6.5 ops, or 4334.0/3.2 ops per clone), SPEEDUP of 1340.160x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1340.160x (0.007988s -> 5.96e-06s), will amortize in 9.5 ops by saving 0.007982s per op. +In 1 tuning rounds (tot. 0.13s, 0.052s for constructor, 2 clones) obtained a SPEEDUP of 133916.0% (1340x) (from 2.529 to 3389 Mflops). Employed 0.048s 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 0.168017 s (7.967e-03 s -> 5.960e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.180021 s (7.988e-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 D, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 @@ -5389,20 +5429,20 @@ # 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 2.599e-05s; avg 8.663e-06s ( +/- 31.19/ 62.39 %); best 5.96e-06s; worst 1.407e-05s; std dev. 3.821e-06 (taking best). -Reference operation time is 5.96046e-06 s (3389 Mflops) with 1 threads. +3 iterations (1 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 28.41/ 56.82 %); best 5.007e-06s; worst 1.097e-05s; std dev. 2.81e-06 (taking best). +Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.782e-02 s (100.00 %) - analyzed arrays in 1.180e-02 s (42.41 %) - cleaned-up arrays in 5.960e-06 s (0.02 %) - deduplicated arrays in 6.914e-06 s (0.02 %) + converted COO to RSB in 3.568e-02 s (100.00 %) + analyzed arrays in 1.566e-02 s (43.90 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.007e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.599e-02 s (57.49 %) - memory allocations took 3.099e-06 s (0.01 %) - leafs setup took 1.907e-06 s (0.01 %) - halfword conversion took 8.106e-06 s (0.03 %) -Built (100 x 100)[0x55ac7db9caa0]{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 1.999e-02 s (56.04 %) + memory allocations took 1.907e-06 s (0.01 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 5.007e-06 s (0.01 %) +Built (100 x 100)[0x55b7c7a37ad0]{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 16777216 bytes, per-thread 16777216 bytes @@ -5436,16 +5476,16 @@ # 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 4.395e-02 s (100.00 %) - analyzed arrays in 1.194e-02 s (27.17 %) - cleaned-up arrays in 6.199e-06 s (0.01 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 5.597e-02 s (100.00 %) + analyzed arrays in 1.599e-02 s (28.57 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (36.40 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 1.599e-02 s (36.38 %) -Built (100 x 100)[0x55ac7db92620]{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' + shuffled partitions in 1.995e-02 s (35.65 %) + memory allocations took 2.146e-06 s (0.00 %) + leafs setup took 2.146e-06 s (0.00 %) + halfword conversion took 2.001e-02 s (35.75 %) +Built (100 x 100)[0x55b7c7a2d650]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5491,9 +5531,9 @@ # 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 0.02395s; avg 0.007984s ( +/- 0.46/ 0.30 %); best 0.007947s; worst 0.008008s; std dev. 2.657e-05 (taking best). -Reference operation time is 0.00794697 s (2.542 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, 0.00794697 s/0 threads (speedup 0.00075003 x), same?n. +3 iterations (1 th.) took 0.02767s; avg 0.009224s ( +/- 14.30/ 27.53 %); best 0.007905s; worst 0.01176s; std dev. 0.001796 (taking best). +Reference operation time is 0.00790501 s (2.555 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00790501 s/0 threads (speedup 0.00063337 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 16777216 bytes, per-thread 16777216 bytes @@ -5527,16 +5567,16 @@ # 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 5.192e-02 s (100.00 %) - analyzed arrays in 1.990e-02 s (38.34 %) - cleaned-up arrays in 7.153e-06 s (0.01 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 5.219e-02 s (100.00 %) + analyzed arrays in 2.015e-02 s (38.61 %) + cleaned-up arrays in 4.053e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (30.81 %) - memory allocations took 4.053e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 1.599e-02 s (30.80 %) -Built (100 x 100)[0x55ac7db93010]{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 1.602e-02 s (30.69 %) + memory allocations took 4.768e-06 s (0.01 %) + leafs setup took 2.146e-06 s (0.00 %) + halfword conversion took 1.600e-02 s (30.66 %) +Built (100 x 100)[0x55b7c7a2e040]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5582,9 +5622,9 @@ # 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 0.02395s; avg 0.007982s ( +/- 0.48/ 0.39 %); best 0.007944s; worst 0.008013s; std dev. 2.866e-05 (taking best). -Reference operation time is 0.00794387 s (2.543 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, 0.00794387 s/0 threads (speedup 0.000750323 x), same?n. +3 iterations (1 th.) took 0.02372s; avg 0.007907s ( +/- 2.13/ 1.65 %); best 0.007739s; worst 0.008037s; std dev. 0.0001247 (taking best). +Reference operation time is 0.00773883 s (2.61 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.00773883 s/0 threads (speedup 0.00064697 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 16777216 bytes, per-thread 16777216 bytes @@ -5618,16 +5658,16 @@ # 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 5.193e-02 s (100.00 %) - analyzed arrays in 1.990e-02 s (38.32 %) - cleaned-up arrays in 1.311e-05 s (0.03 %) - deduplicated arrays in 1.502e-05 s (0.03 %) + converted COO to RSB in 5.596e-02 s (100.00 %) + analyzed arrays in 2.393e-02 s (42.76 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.601e-02 s (30.83 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 9.060e-06 s (0.02 %) - halfword conversion took 1.598e-02 s (30.77 %) -Built (100 x 100)[0x55ac7db9cbc0]{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: 23, symflags:'LS' + shuffled partitions in 1.602e-02 s (28.62 %) + memory allocations took 4.053e-06 s (0.01 %) + leafs setup took 5.007e-06 s (0.01 %) + halfword conversion took 1.599e-02 s (28.58 %) +Built (100 x 100)[0x55b7c7a37bf0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5673,10 +5713,10 @@ # 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 0.02392s; avg 0.007973s ( +/- 0.62/ 0.32 %); best 0.007923s; worst 0.007998s; std dev. 3.518e-05 (taking best). -Reference operation time is 0.00792289 s (2.55 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 1, 23 leaves, 2.295 bytes/nz, 0.00792289 s/0 threads (speedup 0.00075231 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 32 subms, 23 lsubms, 2.2947 bpnz +3 iterations (1 th.) took 0.0317s; avg 0.01057s ( +/- 24.31/ 13.49 %); best 0.007998s; worst 0.01199s; std dev. 0.00182 (taking best). +Reference operation time is 0.00799799 s (2.526 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.00799799 s/0 threads (speedup 0.000626006 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 30 subms, 22 lsubms, 2.2947 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5709,16 +5749,16 @@ # 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 7.160e-02 s (100.00 %) - analyzed arrays in 1.992e-02 s (27.82 %) - cleaned-up arrays in 5.960e-06 s (0.01 %) - deduplicated arrays in 8.106e-06 s (0.01 %) + converted COO to RSB in 5.994e-02 s (100.00 %) + analyzed arrays in 2.790e-02 s (46.55 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.000e-02 s (27.94 %) - memory allocations took 9.060e-06 s (0.01 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 3.165e-02 s (44.20 %) -Built (100 x 100)[0x55ac7dbc3860]{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 1.600e-02 s (26.69 %) + memory allocations took 5.007e-06 s (0.01 %) + leafs setup took 5.007e-06 s (0.01 %) + halfword conversion took 1.602e-02 s (26.72 %) +Built (100 x 100)[0x55b7c7a5e860]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5764,9 +5804,9 @@ # 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 0.04427s; avg 0.01476s ( +/- 14.43/ 7.41 %); best 0.01263s; worst 0.01585s; std dev. 0.001506 (taking best). -Reference operation time is 0.0126281 s (1.6 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.0126281 s/0 threads (speedup 0.000472001 x), same?n. +3 iterations (1 th.) took 0.02766s; avg 0.00922s ( +/- 16.46/ 30.02 %); best 0.007703s; worst 0.01199s; std dev. 0.00196 (taking best). +Reference operation time is 0.00770283 s (2.622 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00770283 s/0 threads (speedup 0.000649994 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 16777216 bytes, per-thread 16777216 bytes @@ -5800,16 +5840,16 @@ # 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 5.194e-02 s (100.00 %) - analyzed arrays in 1.991e-02 s (38.33 %) - cleaned-up arrays in 7.153e-06 s (0.01 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 5.993e-02 s (100.00 %) + analyzed arrays in 2.389e-02 s (39.86 %) + cleaned-up arrays in 9.060e-06 s (0.02 %) + deduplicated arrays in 1.097e-05 s (0.02 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.601e-02 s (30.82 %) - memory allocations took 1.311e-05 s (0.03 %) + shuffled partitions in 2.001e-02 s (33.40 %) + memory allocations took 9.775e-06 s (0.02 %) leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.598e-02 s (30.78 %) -Built (100 x 100)[0x55ac7dbc3860]{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' + halfword conversion took 1.599e-02 s (26.68 %) +Built (100 x 100)[0x55b7c7a5e860]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5855,11 +5895,11 @@ # 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 0.02396s; avg 0.007985s ( +/- 0.39/ 0.26 %); best 0.007954s; worst 0.008006s; std dev. 2.248e-05 (taking best). -Reference operation time is 0.00795412 s (2.54 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00795412 s/0 threads (speedup 0.000749356 x), same?n. +3 iterations (1 th.) took 0.02378s; avg 0.007926s ( +/- 1.89/ 1.07 %); best 0.007776s; worst 0.00801s; std dev. 0.0001061 (taking best). +Reference operation time is 0.00777602 s (2.598 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00777602 s/0 threads (speedup 0.000643876 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: 3389 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 4034.52 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5875,23 +5915,23 @@ # 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 0.43992 s (eq. to 7e+04/ 7e+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 ! +Last tuner inner round (1 of 1) took 0.455945 s (eq. to 9e+04/ 9e+04 old/new op.times), gained local/global speedup 1 x (5.00679e-06 : 5.00679e-06) / 1 x (5.00679e-06 : 5.00679e-06). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.44s, 0.3s for constructor, 0 clones) obtained NO speedup (best stays 3389 Mflops). -Second run of RSB Autotuner took 0.439957 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) +In 1 tuning rounds (tot. 0.46s, 0.32s for constructor, 0 clones) obtained NO speedup (best stays 4035 Mflops). +Second run of RSB Autotuner took 0.455982 s and estimated a speedup of 1.000000 x (5.007e-06 s -> 5.007e-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 0.024344 0.059537 0.083881 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.083881 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.024344 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.059537 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.011542 0.035979 0.047521 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.047521 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.011542 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.035979 %: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 0.083881 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.047521 %: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 @@ -5906,34 +5946,34 @@ %: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 0.104444 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.0635641 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.024344 0 0.0595369 -# so far, program took 7.709s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.608s/0.000s . +%constructor:lower-100x100-5050nz 0 0.0115421 0 0.035979 +# so far, program took 7.959s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.636s/0.000s . getrusage() stats: -ru_maxrss: 75 (maximum resident set size -- MB) -ru_stime : 0.1922s (system CPU time used) -ru_utime : 15.56s (user CPU time used) +ru_maxrss: 81 (maximum resident set size -- MB) +ru_stime : 0.2755s (system CPU time used) +ru_utime : 12.19s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). # Cache block size total 16777216 bytes, per-thread 16777216 bytes -# so far, program took 7.709s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.608s/0.000s . +# so far, program took 7.959s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.636s/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 1.186e-01 s (100.00 %) - analyzed arrays in 2.259e-02 s (19.04 %) - cleaned-up arrays in 6.199e-06 s (0.01 %) - deduplicated arrays in 7.868e-06 s (0.01 %) + converted COO to RSB in 6.243e-02 s (100.00 %) + analyzed arrays in 1.040e-02 s (16.66 %) + cleaned-up arrays in 8.106e-06 s (0.01 %) + deduplicated arrays in 2.384e-05 s (0.04 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.399e-02 s (53.96 %) - memory allocations took 4.768e-06 s (0.00 %) + shuffled partitions in 3.598e-02 s (57.64 %) + memory allocations took 4.053e-06 s (0.01 %) leafs setup took 3.099e-06 s (0.00 %) - halfword conversion took 3.199e-02 s (26.98 %) -Built (100 x 100)[0x55ac7db9cbc0]{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 0.119s): (100 x 100)[0x55ac7db9cbc0]{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 1.600e-02 s (25.63 %) +Built (100 x 100)[0x55b7c7a37bf0]{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 0.062s): (100 x 100)[0x55b7c7a37bf0]{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. @@ -5984,10 +6024,10 @@ # 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 0.02398s; avg 0.007994s ( +/- 0.16/ 0.20 %); best 0.007981s; worst 0.00801s; std dev. 1.205e-05 (taking best). -Reference operation time is 0.00798106 s (2.531 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: 0.007981 Mflops: 2.531) -Merge (3 -> 1 leaves) took w.c.t. of 4.196e-05s, ~3.099e-05s of computing time (of which 9.06e-06s sorting, 4.053e-06s analysis) +3 iterations (1 th.) took 0.024s; avg 0.007999s ( +/- 0.15/ 0.17 %); best 0.007987s; worst 0.008013s; std dev. 1.065e-05 (taking best). +Reference operation time is 0.00798702 s (2.529 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: 0.007987 Mflops: 2.529) +Merge (3 -> 1 leaves) took w.c.t. of 4.387e-05s, ~3.695e-05s of computing time (of which 1.597e-05s sorting, 1.907e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6018,7 +6058,7 @@ # 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 1.979e-05s; avg 6.596e-06s ( +/- 9.64/ 19.28 %); best 5.96e-06s; worst 7.868e-06s; std dev. 8.991e-07 (taking best). +3 iterations (1 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 14.77/ 15.91 %); best 5.96e-06s; worst 8.106e-06s; std dev. 8.778e-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 16777216 bytes, per-thread 16777216 bytes @@ -6036,15 +6076,15 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success 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 1339.000x: 0.007981s -> 5.96e-06s, so taking this instance. +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1340.000x: 0.007987s -> 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 0.07205s (of which 4.387e-05s partitioning, 0.04805s I/O); computing times: 3.099e-05s in par. loops, 9.06e-06s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.07205s, equivalent to 12088.5/9.0 new/old ops (0.06831s for 2 clones -- as 11460.8/8.6 ops, or 5730.4/4.3 ops per clone), SPEEDUP of 1339.000x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1339.000x (0.007981s -> 5.96e-06s), will amortize in 9.0 ops by saving 0.007975s per op. -In 1 tuning rounds (tot. 0.14s, 0.068s for constructor, 2 clones) obtained a SPEEDUP of 133800.0% (1339x) (from 2.531 to 3389 Mflops). Employed 0.092s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.07203s (of which 4.697e-05s partitioning, 0.04802s I/O); computing times: 3.695e-05s in par. loops, 1.597e-05s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.07203s, equivalent to 12085.0/9.0 new/old ops (0.0477s for 2 clones -- as 8002.4/6.0 ops, or 4001.2/3.0 ops per clone), SPEEDUP of 1340.000x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1340.000x (0.007987s -> 5.96e-06s), will amortize in 9.0 ops by saving 0.007981s per op. +In 1 tuning rounds (tot. 0.12s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 133900.0% (1340x) (from 2.529 to 3389 Mflops). Employed 0.056s 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 0.232038 s (7.981e-03 s -> 5.960e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.176031 s (7.987e-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 @@ -6110,20 +6150,20 @@ # 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 2.503e-05s; avg 8.345e-06s ( +/- 28.57/ 42.86 %); best 5.96e-06s; worst 1.192e-05s; std dev. 2.575e-06 (taking best). +3 iterations (1 th.) took 2.289e-05s; avg 7.629e-06s ( +/- 21.88/ 31.25 %); best 5.96e-06s; worst 1.001e-05s; std dev. 1.73e-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 5.102e-05 s (100.00 %) - analyzed arrays in 1.717e-05 s (33.64 %) - cleaned-up arrays in 6.199e-06 s (12.15 %) - deduplicated arrays in 6.914e-06 s (13.55 %) + converted COO to RSB in 2.764e-02 s (100.00 %) + analyzed arrays in 1.163e-02 s (42.06 %) + cleaned-up arrays in 6.199e-06 s (0.02 %) + deduplicated arrays in 6.914e-06 s (0.03 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.287e-05 s (25.23 %) - memory allocations took 2.861e-06 s (5.61 %) - leafs setup took 1.192e-06 s (2.34 %) - halfword conversion took 2.861e-06 s (5.61 %) -Built (100 x 100)[0x55ac7db9caa0]{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 1.600e-02 s (57.86 %) + memory allocations took 3.815e-06 s (0.01 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 3.099e-06 s (0.01 %) +Built (100 x 100)[0x55b7c7a37ad0]{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 16777216 bytes, per-thread 16777216 bytes @@ -6157,16 +6197,16 @@ # 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 4.005e-05 s (100.00 %) - analyzed arrays in 1.502e-05 s (37.50 %) - cleaned-up arrays in 5.007e-06 s (12.50 %) - deduplicated arrays in 7.868e-06 s (19.64 %) + converted COO to RSB in 1.998e-02 s (100.00 %) + analyzed arrays in 1.196e-02 s (59.85 %) + cleaned-up arrays in 5.007e-06 s (0.03 %) + deduplicated arrays in 6.914e-06 s (0.03 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.199e-06 s (15.48 %) - memory allocations took 9.537e-07 s (2.38 %) - leafs setup took 9.537e-07 s (2.38 %) - halfword conversion took 2.861e-06 s (7.14 %) -Built (100 x 100)[0x55ac7db93010]{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 8.005e-03 s (40.06 %) + memory allocations took 1.907e-06 s (0.01 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 4.053e-06 s (0.02 %) +Built (100 x 100)[0x55b7c7a2e040]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6212,7 +6252,7 @@ # 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 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). +3 iterations (1 th.) took 2.193e-05s; avg 7.312e-06s ( +/- 18.48/ 36.96 %); best 5.96e-06s; worst 1.001e-05s; std dev. 1.911e-06 (taking best). Reference operation time is 5.96046e-06 s (3389 Mflops) with 1 threads. 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 @@ -6248,16 +6288,16 @@ # 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 1.092e-04 s (100.00 %) - analyzed arrays in 4.101e-05 s (37.55 %) - cleaned-up arrays in 5.960e-06 s (5.46 %) - deduplicated arrays in 6.914e-06 s (6.33 %) + converted COO to RSB in 5.181e-02 s (100.00 %) + analyzed arrays in 1.977e-02 s (38.16 %) + cleaned-up arrays in 5.960e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.505e-05 s (32.10 %) - memory allocations took 2.146e-06 s (1.97 %) - leafs setup took 9.537e-07 s (0.87 %) - halfword conversion took 1.717e-05 s (15.72 %) -Built (100 x 100)[0x55ac7db93010]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 6, symflags:'LS' + shuffled partitions in 1.602e-02 s (30.91 %) + memory allocations took 2.146e-06 s (0.00 %) + leafs setup took 2.146e-06 s (0.00 %) + halfword conversion took 1.601e-02 s (30.90 %) +Built (100 x 100)[0x55b7c7a2e040]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 6, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6303,9 +6343,9 @@ # 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 4.101e-05s; avg 1.367e-05s ( +/- 19.77/ 16.86 %); best 1.097e-05s; worst 1.597e-05s; std dev. 2.063e-06 (taking best). -Reference operation time is 1.09673e-05 s (1842 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 0.5, 6 leaves, 2.163 bytes/nz, 1.09673e-05 s/0 threads (speedup 0.543478 x), same?n. +3 iterations (1 th.) took 0.0238s; avg 0.007934s ( +/- 1.08/ 0.76 %); best 0.007848s; worst 0.007994s; std dev. 6.222e-05 (taking best). +Reference operation time is 0.00784802 s (2.574 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 0.5, 6 leaves, 2.163 bytes/nz, 0.00784802 s/0 threads (speedup 0.000759486 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 8 subms, 6 lsubms, 2.1632 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -6339,16 +6379,16 @@ # 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 1.409e-04 s (100.00 %) - analyzed arrays in 6.485e-05 s (46.02 %) - cleaned-up arrays in 5.007e-06 s (3.55 %) - deduplicated arrays in 7.153e-06 s (5.08 %) - sorted arrays in 9.537e-07 s (0.68 %) - shuffled partitions in 4.482e-05 s (31.81 %) - memory allocations took 2.146e-06 s (1.52 %) - leafs setup took 2.146e-06 s (1.52 %) - halfword conversion took 1.383e-05 s (9.81 %) -Built (100 x 100)[0x55ac7db9cbc0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 16, symflags:'LS' + converted COO to RSB in 5.997e-02 s (100.00 %) + analyzed arrays in 1.997e-02 s (33.30 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 6.914e-06 s (0.01 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 1.600e-02 s (26.68 %) + memory allocations took 3.099e-06 s (0.01 %) + leafs setup took 1.907e-06 s (0.00 %) + halfword conversion took 2.398e-02 s (39.99 %) +Built (100 x 100)[0x55b7c7a37bf0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 16, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6394,9 +6434,9 @@ # 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 4.578e-05s; avg 1.526e-05s ( +/- 9.38/ 17.19 %); best 1.383e-05s; worst 1.788e-05s; std dev. 1.857e-06 (taking best). -Reference operation time is 1.38283e-05 s (1461 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 1, 16 leaves, 2.25 bytes/nz, 1.38283e-05 s/0 threads (speedup 0.431034 x), same?n. +3 iterations (1 th.) took 0.02782s; avg 0.009274s ( +/- 15.64/ 29.47 %); best 0.007824s; worst 0.01201s; std dev. 0.001934 (taking best). +Reference operation time is 0.00782394 s (2.582 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 1, 16 leaves, 2.25 bytes/nz, 0.00782394 s/0 threads (speedup 0.000761824 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 22 subms, 16 lsubms, 2.2503 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -6430,16 +6470,16 @@ # 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 2.229e-04 s (100.00 %) - analyzed arrays in 8.893e-05 s (39.89 %) - cleaned-up arrays in 5.007e-06 s (2.25 %) - deduplicated arrays in 7.153e-06 s (3.21 %) + converted COO to RSB in 6.396e-02 s (100.00 %) + analyzed arrays in 3.193e-02 s (49.93 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.001e-04 s (44.92 %) - memory allocations took 3.815e-06 s (1.71 %) - leafs setup took 2.861e-06 s (1.28 %) - halfword conversion took 1.502e-05 s (6.74 %) -Built (100 x 100)[0x55ac7db9cbc0]{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 1.601e-02 s (25.03 %) + memory allocations took 5.007e-06 s (0.01 %) + leafs setup took 4.053e-06 s (0.01 %) + halfword conversion took 1.600e-02 s (25.01 %) +Built (100 x 100)[0x55b7c7a37bf0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6485,9 +6525,9 @@ # 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 5.507e-05s; avg 1.836e-05s ( +/- 12.99/ 19.48 %); best 1.597e-05s; worst 2.193e-05s; std dev. 2.575e-06 (taking best). -Reference operation time is 1.5974e-05 s (1265 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 1.5974e-05 s/0 threads (speedup 0.373134 x), same?n. +3 iterations (1 th.) took 0.03182s; avg 0.01061s ( +/- 26.24/ 13.75 %); best 0.007823s; worst 0.01206s; std dev. 0.001969 (taking best). +Reference operation time is 0.00782299 s (2.582 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00782299 s/0 threads (speedup 0.000761916 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 16777216 bytes, per-thread 16777216 bytes @@ -6521,16 +6561,16 @@ # 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 2.100e-04 s (100.00 %) - analyzed arrays in 8.011e-05 s (38.14 %) - cleaned-up arrays in 5.960e-06 s (2.84 %) - deduplicated arrays in 6.914e-06 s (3.29 %) + converted COO to RSB in 4.796e-02 s (100.00 %) + analyzed arrays in 1.596e-02 s (33.28 %) + cleaned-up arrays in 4.768e-06 s (0.01 %) + deduplicated arrays in 6.199e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.513e-05 s (45.29 %) - memory allocations took 5.007e-06 s (2.38 %) - leafs setup took 1.907e-06 s (0.91 %) - halfword conversion took 1.502e-05 s (7.15 %) -Built (100 x 100)[0x55ac7dbafca0]{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 1.599e-02 s (33.34 %) + memory allocations took 5.960e-06 s (0.01 %) + leafs setup took 3.099e-06 s (0.01 %) + halfword conversion took 1.599e-02 s (33.34 %) +Built (100 x 100)[0x55b7c7a4aca0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6576,9 +6616,9 @@ # 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 5.507e-05s; avg 1.836e-05s ( +/- 12.99/ 19.48 %); best 1.597e-05s; worst 2.193e-05s; std dev. 2.575e-06 (taking best). -Reference operation time is 1.5974e-05 s (1265 Mflops) with 1 threads. -Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 1.5974e-05 s/0 threads (speedup 0.373134 x), same?n. +3 iterations (1 th.) took 0.0238s; avg 0.007934s ( +/- 1.65/ 0.86 %); best 0.007803s; worst 0.008002s; std dev. 9.269e-05 (taking best). +Reference operation time is 0.00780296 s (2.589 Mflops) with 1 threads. +Challenging best inner round reference (5.96046e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00780296 s/0 threads (speedup 0.000763872 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 1: 3389 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing @@ -6596,23 +6636,23 @@ # 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 0.00129819 s (eq. to 2e+02/ 2e+02 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 ! +Last tuner inner round (1 of 1) took 0.379929 s (eq. to 6e+04/ 6e+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. 0.0013s, 0.00093s for constructor, 0 clones) obtained NO speedup (best stays 3389 Mflops). -Second run of RSB Autotuner took 0.001333 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) +In 1 tuning rounds (tot. 0.38s, 0.27s for constructor, 0 clones) obtained NO speedup (best stays 3389 Mflops). +Second run of RSB Autotuner took 0.379961 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 0.022586 0.063990 0.086576 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.086576 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.022586 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.063990 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.010402 0.035982 0.046384 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.046384 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.010402 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.035982 %: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 0.086576 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.046384 %: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 +6667,34 @@ %: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 0.118593 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.0624259 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0225859 0 0.0639901 -# so far, program took 8.165s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.841s/0.000s . +%constructor:lower-100x100-5050nz 0 0.010402 0 0.0359819 +# so far, program took 8.660s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.192s/0.000s . getrusage() stats: -ru_maxrss: 75 (maximum resident set size -- MB) -ru_stime : 0.2407s (system CPU time used) -ru_utime : 20.45s (user CPU time used) +ru_maxrss: 81 (maximum resident set size -- MB) +ru_stime : 0.2993s (system CPU time used) +ru_utime : 18.07s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was D). # Cache block size total 16777216 bytes, per-thread 16777216 bytes -# so far, program took 8.165s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.841s/0.000s . +# so far, program took 8.660s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.192s/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 1.145e-01 s (100.00 %) - analyzed arrays in 1.896e-02 s (16.57 %) - cleaned-up arrays in 6.914e-06 s (0.01 %) - deduplicated arrays in 7.153e-06 s (0.01 %) + converted COO to RSB in 6.125e-02 s (100.00 %) + analyzed arrays in 9.227e-03 s (15.07 %) + cleaned-up arrays in 9.060e-06 s (0.01 %) + deduplicated arrays in 1.192e-05 s (0.02 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.366e-02 s (55.61 %) - memory allocations took 4.053e-06 s (0.00 %) - leafs setup took 3.815e-06 s (0.00 %) - halfword conversion took 3.182e-02 s (27.80 %) -Built (100 x 100)[0x55ac7db9cbc0]{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 0.114s): (100 x 100)[0x55ac7db9cbc0]{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 3.600e-02 s (58.77 %) + memory allocations took 3.815e-06 s (0.01 %) + leafs setup took 1.907e-06 s (0.00 %) + halfword conversion took 1.600e-02 s (26.12 %) +Built (100 x 100)[0x55b7c7a37bf0]{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 0.061s): (100 x 100)[0x55b7c7a37bf0]{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 +6745,10 @@ # 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 0.02399s; avg 0.007997s ( +/- 0.41/ 0.48 %); best 0.007964s; worst 0.008035s; std dev. 2.921e-05 (taking best). -Reference operation time is 0.0079639 s (10.15 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: 0.007964 Mflops: 10.146) -Merge (3 -> 1 leaves) took w.c.t. of 4.101e-05s, ~3.195e-05s of computing time (of which 1.192e-05s sorting, 1.907e-06s analysis) +3 iterations (1 th.) took 0.02399s; avg 0.007995s ( +/- 0.18/ 0.14 %); best 0.007981s; worst 0.008006s; std dev. 1.064e-05 (taking best). +Reference operation time is 0.00798082 s (10.12 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: 0.007981 Mflops: 10.124) +Merge (3 -> 1 leaves) took w.c.t. of 3.6e-05s, ~2.789e-05s of computing time (of which 1.001e-05s sorting, 2.861e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6739,8 +6779,8 @@ # 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 5.412e-05s; avg 1.804e-05s ( +/- 0.88/ 0.44 %); best 1.788e-05s; worst 1.812e-05s; std dev. 1.124e-07 (taking best). -Reference operation time is 1.78814e-05 s (4519 Mflops) with 1 threads. +3 iterations (1 th.) took 6.318e-05s; avg 2.106e-05s ( +/- 9.43/ 8.68 %); best 1.907e-05s; worst 2.289e-05s; std dev. 1.561e-06 (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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6756,16 +6796,16 @@ # 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: 1.788e-05 s ~Mflops: 4518.664 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 445.373x: 0.007964s -> 1.788e-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 418.425x: 0.007981s -> 1.907e-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 0.07202s (of which 4.506e-05s partitioning, 0.04803s I/O); computing times: 3.195e-05s in par. loops, 1.192e-05s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.07202s, equivalent to 4027.6/9.0 new/old ops (0.04779s for 2 clones -- as 2672.8/6.0 ops, or 1336.4/3.0 ops per clone), SPEEDUP of 445.373x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 445.373x (0.007964s -> 1.788e-05s), will amortize in 9.1 ops by saving 0.007946s per op. -In 1 tuning rounds (tot. 0.12s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 44437.3% (445.4x) (from 10.15 to 4519 Mflops). Employed 0.053s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.08382s (of which 3.791e-05s partitioning, 0.05213s I/O); computing times: 2.789e-05s in par. loops, 1.001e-05s sorting, 2.861e-06s analyzing) +Total merge + benchmarking process took 0.08382s, equivalent to 4394.5/10.5 new/old ops (0.06345s for 2 clones -- as 3326.8/8.0 ops, or 1663.4/4.0 ops per clone), SPEEDUP of 418.425x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 418.425x (0.007981s -> 1.907e-05s), will amortize in 10.5 ops by saving 0.007962s per op. +In 1 tuning rounds (tot. 0.14s, 0.063s for constructor, 2 clones) obtained a SPEEDUP of 41742.5% (418.4x) (from 10.12 to 4236 Mflops). Employed 0.06s 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 0.172515 s (7.964e-03 s -> 1.788e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.200024 s (7.981e-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 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 +6871,20 @@ # 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 6.509e-05s; avg 2.17e-05s ( +/- 17.58/ 34.07 %); best 1.788e-05s; worst 2.909e-05s; std dev. 5.227e-06 (taking best). -Reference operation time is 1.78814e-05 s (4519 Mflops) with 1 threads. +3 iterations (1 th.) took 4.697e-05s; avg 1.566e-05s ( +/- 17.77/ 21.83 %); best 1.287e-05s; worst 1.907e-05s; std dev. 2.57e-06 (taking best). +Reference operation time is 1.28746e-05 s (6276 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.778e-02 s (100.00 %) - analyzed arrays in 1.176e-02 s (42.34 %) - cleaned-up arrays in 5.960e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.03 %) + converted COO to RSB in 3.164e-02 s (100.00 %) + analyzed arrays in 1.561e-02 s (49.36 %) + cleaned-up arrays in 4.768e-06 s (0.02 %) + deduplicated arrays in 7.153e-06 s (0.02 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (57.58 %) + shuffled partitions in 1.600e-02 s (50.58 %) memory allocations took 2.146e-06 s (0.01 %) leafs setup took 2.146e-06 s (0.01 %) halfword conversion took 2.861e-06 s (0.01 %) -Built (100 x 100)[0x55ac7db9caa0]{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' +Built (100 x 100)[0x55b7c7a37ad0]{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 16777216 bytes, per-thread 16777216 bytes @@ -6878,16 +6918,16 @@ # 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 4.394e-02 s (100.00 %) - analyzed arrays in 1.193e-02 s (27.16 %) - cleaned-up arrays in 1.097e-05 s (0.02 %) - deduplicated arrays in 1.311e-05 s (0.03 %) + converted COO to RSB in 5.176e-02 s (100.00 %) + analyzed arrays in 1.576e-02 s (30.45 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.599e-02 s (36.38 %) - memory allocations took 4.053e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 1.599e-02 s (36.40 %) -Built (100 x 100)[0x55ac7db93220]{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 1.599e-02 s (30.89 %) + memory allocations took 2.861e-06 s (0.01 %) + leafs setup took 1.907e-06 s (0.00 %) + halfword conversion took 1.999e-02 s (38.62 %) +Built (100 x 100)[0x55b7c7a2e040]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6933,9 +6973,9 @@ # 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 0.02398s; avg 0.007994s ( +/- 0.17/ 0.32 %); best 0.00798s; worst 0.00802s; std dev. 1.834e-05 (taking best). -Reference operation time is 0.00798011 s (10.13 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00798011 s/0 threads (speedup 0.00224075 x), same?n. +3 iterations (1 th.) took 0.03244s; avg 0.01081s ( +/- 27.67/ 47.73 %); best 0.007821s; worst 0.01597s; std dev. 0.003665 (taking best). +Reference operation time is 0.00782108 s (10.33 Mflops) with 1 threads. +Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00782108 s/0 threads (speedup 0.00164614 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 16777216 bytes, per-thread 16777216 bytes @@ -6969,16 +7009,16 @@ # 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 4.796e-02 s (100.00 %) - analyzed arrays in 1.993e-02 s (41.56 %) - cleaned-up arrays in 5.960e-06 s (0.01 %) - deduplicated arrays in 8.106e-06 s (0.02 %) + converted COO to RSB in 5.121e-02 s (100.00 %) + analyzed arrays in 2.321e-02 s (45.32 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.603e-02 s (33.43 %) - memory allocations took 1.907e-06 s (0.00 %) - leafs setup took 1.907e-06 s (0.00 %) - halfword conversion took 1.198e-02 s (24.97 %) -Built (100 x 100)[0x55ac7db9cbc0]{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 1.201e-02 s (23.45 %) + memory allocations took 4.053e-06 s (0.01 %) + leafs setup took 3.099e-06 s (0.01 %) + halfword conversion took 1.598e-02 s (31.19 %) +Built (100 x 100)[0x55b7c7a2e040]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7024,9 +7064,9 @@ # 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 9.298e-05s; avg 3.099e-05s ( +/- 10.00/ 13.08 %); best 2.789e-05s; worst 3.505e-05s; std dev. 2.997e-06 (taking best). -Reference operation time is 2.7895e-05 s (2897 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 2.7895e-05 s/0 threads (speedup 0.641026 x), same?n. +3 iterations (1 th.) took 0.024s; avg 0.008s ( +/- 0.31/ 0.30 %); best 0.007975s; worst 0.008024s; std dev. 2.005e-05 (taking best). +Reference operation time is 0.00797486 s (10.13 Mflops) with 1 threads. +Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.00797486 s/0 threads (speedup 0.0016144 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 16777216 bytes, per-thread 16777216 bytes @@ -7060,16 +7100,16 @@ # 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 1.411e-04 s (100.00 %) - analyzed arrays in 5.698e-05 s (40.37 %) - cleaned-up arrays in 5.960e-06 s (4.22 %) - deduplicated arrays in 6.914e-06 s (4.90 %) + converted COO to RSB in 5.576e-02 s (100.00 %) + analyzed arrays in 2.375e-02 s (42.59 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.412e-05 s (38.34 %) - memory allocations took 3.099e-06 s (2.20 %) - leafs setup took 2.861e-06 s (2.03 %) - halfword conversion took 1.121e-05 s (7.94 %) -Built (100 x 100)[0x55ac7db9cbc0]{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: 23, symflags:'LS' + shuffled partitions in 1.601e-02 s (28.71 %) + memory allocations took 3.099e-06 s (0.01 %) + leafs setup took 3.099e-06 s (0.01 %) + halfword conversion took 1.599e-02 s (28.67 %) +Built (100 x 100)[0x55b7c7a37bf0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7115,10 +7155,10 @@ # 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 9.489e-05s; avg 3.163e-05s ( +/- 5.03/ 10.05 %); best 3.004e-05s; worst 3.481e-05s; std dev. 2.248e-06 (taking best). -Reference operation time is 3.00407e-05 s (2690 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 1, 23 leaves, 2.295 bytes/nz, 3.00407e-05 s/0 threads (speedup 0.595238 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 32 subms, 23 lsubms, 2.2947 bpnz +3 iterations (1 th.) took 0.02799s; avg 0.009328s ( +/- 14.47/ 28.54 %); best 0.007978s; worst 0.01199s; std dev. 0.001883 (taking best). +Reference operation time is 0.0079782 s (10.13 Mflops) with 1 threads. +Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.0079782 s/0 threads (speedup 0.00161372 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 30 subms, 22 lsubms, 2.2947 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7151,16 +7191,16 @@ # 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 1.729e-04 s (100.00 %) - analyzed arrays in 7.105e-05 s (41.10 %) - cleaned-up arrays in 5.960e-06 s (3.45 %) - deduplicated arrays in 7.153e-06 s (4.14 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.296e-05 s (42.21 %) - memory allocations took 2.861e-06 s (1.66 %) - leafs setup took 1.907e-06 s (1.10 %) - halfword conversion took 1.097e-05 s (6.34 %) -Built (100 x 100)[0x55ac7dbc3860]{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' + converted COO to RSB in 6.375e-02 s (100.00 %) + analyzed arrays in 1.972e-02 s (30.94 %) + cleaned-up arrays in 4.053e-06 s (0.01 %) + deduplicated arrays in 6.199e-06 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 2.800e-02 s (43.93 %) + memory allocations took 4.053e-06 s (0.01 %) + leafs setup took 4.053e-06 s (0.01 %) + halfword conversion took 1.600e-02 s (25.10 %) +Built (100 x 100)[0x55b7c7a5e860]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7206,9 +7246,9 @@ # 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 0.000103s; avg 3.433e-05s ( +/- 4.17/ 7.64 %); best 3.29e-05s; worst 3.695e-05s; std dev. 1.857e-06 (taking best). -Reference operation time is 3.29018e-05 s (2456 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 3.29018e-05 s/0 threads (speedup 0.543478 x), same?n. +3 iterations (1 th.) took 0.02396s; avg 0.007988s ( +/- 0.31/ 0.20 %); best 0.007964s; worst 0.008004s; std dev. 1.748e-05 (taking best). +Reference operation time is 0.0079639 s (10.15 Mflops) with 1 threads. +Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.0079639 s/0 threads (speedup 0.00161662 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 16777216 bytes, per-thread 16777216 bytes @@ -7242,16 +7282,16 @@ # 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 1.729e-04 s (100.00 %) - analyzed arrays in 6.509e-05 s (37.66 %) - cleaned-up arrays in 5.007e-06 s (2.90 %) - deduplicated arrays in 7.868e-06 s (4.55 %) + converted COO to RSB in 5.969e-02 s (100.00 %) + analyzed arrays in 2.768e-02 s (46.37 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.606e-05 s (44.00 %) - memory allocations took 5.960e-06 s (3.45 %) - leafs setup took 1.907e-06 s (1.10 %) - halfword conversion took 1.097e-05 s (6.34 %) -Built (100 x 100)[0x55ac7dbc3860]{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 1.600e-02 s (26.81 %) + memory allocations took 7.868e-06 s (0.01 %) + leafs setup took 3.815e-06 s (0.01 %) + halfword conversion took 1.599e-02 s (26.78 %) +Built (100 x 100)[0x55b7c7a5e860]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7297,11 +7337,11 @@ # 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 0.0001042s; avg 3.473e-05s ( +/- 5.26/ 9.84 %); best 3.29e-05s; worst 3.815e-05s; std dev. 2.418e-06 (taking best). -Reference operation time is 3.29018e-05 s (2456 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 3.29018e-05 s/0 threads (speedup 0.543478 x), same?n. +3 iterations (1 th.) took 0.02399s; avg 0.007996s ( +/- 0.24/ 0.12 %); best 0.007977s; worst 0.008006s; std dev. 1.366e-05 (taking best). +Reference operation time is 0.00797701 s (10.13 Mflops) with 1 threads. +Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00797701 s/0 threads (speedup 0.00161396 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: 4518.66 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 6275.92 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7317,23 +7357,23 @@ # 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 0.14501 s (eq. to 8e+03/ 8e+03 old/new op.times), gained local/global speedup 1 x (1.78814e-05 : 1.78814e-05) / 1 x (1.78814e-05 : 1.78814e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.447748 s (eq. to 3e+04/ 3e+04 old/new op.times), gained local/global speedup 1 x (1.28746e-05 : 1.28746e-05) / 1 x (1.28746e-05 : 1.28746e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.15s, 0.12s for constructor, 0 clones) obtained NO speedup (best stays 4519 Mflops). -Second run of RSB Autotuner took 0.145054 s and estimated a speedup of 1.000000 x (1.788e-05 s -> 1.788e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.45s, 0.31s for constructor, 0 clones) obtained NO speedup (best stays 6276 Mflops). +Second run of RSB Autotuner took 0.448232 s and estimated a speedup of 1.000000 x (1.287e-05 s -> 1.287e-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 0.018961 0.063658 0.082619 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.082619 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.018961 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.063658 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.009227 0.035995 0.045222 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.045222 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.009227 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.035995 %: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 0.082619 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.045222 %: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 +7388,34 @@ %: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 0.114463 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.0612459 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.018961 0 0.063658 -# so far, program took 8.665s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.159s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00922704 0 0.035995 +# so far, program took 9.446s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.840s/0.000s . getrusage() stats: -ru_maxrss: 75 (maximum resident set size -- MB) -ru_stime : 0.2766s (system CPU time used) -ru_utime : 25.94s (user CPU time used) +ru_maxrss: 81 (maximum resident set size -- MB) +ru_stime : 0.3505s (system CPU time used) +ru_utime : 24.97s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was D). # Cache block size total 16777216 bytes, per-thread 16777216 bytes -# so far, program took 8.665s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.159s/0.000s . +# so far, program took 9.446s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.840s/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 1.049e-04 s (100.00 %) - analyzed arrays in 2.098e-05 s (20.00 %) - cleaned-up arrays in 6.199e-06 s (5.91 %) - deduplicated arrays in 7.868e-06 s (7.50 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.507e-05 s (52.50 %) - memory allocations took 2.861e-06 s (2.73 %) - leafs setup took 9.537e-07 s (0.91 %) - halfword conversion took 1.001e-05 s (9.55 %) -Built (100 x 100)[0x55ac7db9cbc0]{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 0.000s): (100 x 100)[0x55ac7db9cbc0]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + converted COO to RSB in 6.684e-02 s (100.00 %) + analyzed arrays in 1.084e-02 s (16.21 %) + cleaned-up arrays in 4.053e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 3.999e-02 s (59.84 %) + memory allocations took 2.861e-06 s (0.00 %) + leafs setup took 5.007e-06 s (0.01 %) + halfword conversion took 1.599e-02 s (23.92 %) +Built (100 x 100)[0x55b7c7a37bf0]{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 0.067s): (100 x 100)[0x55b7c7a37bf0]{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 +7466,10 @@ # 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 0.000103s; avg 3.433e-05s ( +/- 18.75/ 36.81 %); best 2.789e-05s; worst 4.697e-05s; std dev. 8.936e-06 (taking best). -Reference operation time is 2.7895e-05 s (2897 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: 2.789e-05 Mflops: 2896.579) -Merge (3 -> 1 leaves) took w.c.t. of 3.719e-05s, ~3.386e-05s of computing time (of which 1.597e-05s sorting, 1.192e-06s analysis) +3 iterations (1 th.) took 0.024s; avg 0.007999s ( +/- 0.12/ 0.08 %); best 0.007989s; worst 0.008005s; std dev. 6.99e-06 (taking best). +Reference operation time is 0.00798893 s (10.11 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: 0.007989 Mflops: 10.114) +Merge (3 -> 1 leaves) took w.c.t. of 4.196e-05s, ~3.481e-05s of computing time (of which 1.812e-05s sorting, 2.861e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7460,8 +7500,8 @@ # 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 5.293e-05s; avg 1.764e-05s ( +/- 2.70/ 1.35 %); best 1.717e-05s; worst 1.788e-05s; std dev. 3.372e-07 (taking best). -Reference operation time is 1.71661e-05 s (4707 Mflops) with 1 threads. +3 iterations (1 th.) took 4.315e-05s; avg 1.438e-05s ( +/- 2.21/ 4.42 %); best 1.407e-05s; worst 1.502e-05s; std dev. 4.496e-07 (taking best). +Reference operation time is 1.40667e-05 s (5744 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7477,16 +7517,16 @@ # 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: 1.717e-05 s ~Mflops: 4706.941 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1.625x: 2.789e-05s -> 1.717e-05s, so taking this instance. +After merge step 1: tpop: 1.407e-05 s ~Mflops: 5744.064 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 567.932x: 0.007989s -> 1.407e-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 0.004678s (of which 3.91e-05s partitioning, 0.004555s I/O); computing times: 3.386e-05s in par. loops, 1.597e-05s sorting, 1.192e-06s analyzing) -Total merge + benchmarking process took 0.004678s, equivalent to 272.5/167.7 new/old ops (4.125e-05s for 2 clones -- as 2.4/1.5 ops, or 1.2/0.7 ops per clone), SPEEDUP of 1.625x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1.625x (2.789e-05s -> 1.717e-05s), will amortize in 436.0 ops by saving 1.073e-05s per op. -In 1 tuning rounds (tot. 0.0048s, 4.1e-05s for constructor, 2 clones) obtained a SPEEDUP of 62.5% (1.625x) (from 2897 to 4707 Mflops). Employed 0.0018s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.07205s (of which 4.482e-05s partitioning, 0.04806s I/O); computing times: 3.481e-05s in par. loops, 1.812e-05s sorting, 2.861e-06s analyzing) +Total merge + benchmarking process took 0.07205s, equivalent to 5121.7/9.0 new/old ops (0.04758s for 2 clones -- as 3382.2/6.0 ops, or 1691.1/3.0 ops per clone), SPEEDUP of 567.932x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 567.932x (0.007989s -> 1.407e-05s), will amortize in 9.0 ops by saving 0.007975s per op. +In 1 tuning rounds (tot. 0.12s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 56693.2% (567.9x) (from 10.11 to 5744 Mflops). Employed 0.048s 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 0.00671601 s (2.789e-05 s -> 1.717e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.168042 s (7.989e-03 s -> 1.407e-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 +7592,20 @@ # 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 5.603e-05s; avg 1.868e-05s ( +/- 4.26/ 7.23 %); best 1.788e-05s; worst 2.003e-05s; std dev. 9.603e-07 (taking best). -Reference operation time is 1.78814e-05 s (4519 Mflops) with 1 threads. +3 iterations (1 th.) took 8.297e-05s; avg 2.766e-05s ( +/- 6.03/ 12.07 %); best 2.599e-05s; worst 3.099e-05s; std dev. 2.36e-06 (taking best). +Reference operation time is 2.59876e-05 s (3109 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 3.815e-05 s (100.00 %) - analyzed arrays in 1.001e-05 s (26.25 %) - cleaned-up arrays in 5.007e-06 s (13.12 %) - deduplicated arrays in 1.001e-05 s (26.25 %) + converted COO to RSB in 3.541e-02 s (100.00 %) + analyzed arrays in 1.152e-02 s (32.53 %) + cleaned-up arrays in 8.821e-06 s (0.02 %) + deduplicated arrays in 1.097e-05 s (0.03 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.106e-06 s (21.25 %) - memory allocations took 1.907e-06 s (5.00 %) - leafs setup took 0.000e+00 s (0.00 %) - halfword conversion took 3.099e-06 s (8.12 %) -Built (100 x 100)[0x55ac7db9caa0]{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 2.386e-02 s (67.38 %) + memory allocations took 3.338e-06 s (0.01 %) + leafs setup took 3.099e-06 s (0.01 %) + halfword conversion took 4.053e-06 s (0.01 %) +Built (100 x 100)[0x55b7c7a37ad0]{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 16777216 bytes, per-thread 16777216 bytes @@ -7599,16 +7639,16 @@ # 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 1.070e-04 s (100.00 %) - analyzed arrays in 3.600e-05 s (33.63 %) - cleaned-up arrays in 5.960e-06 s (5.57 %) - deduplicated arrays in 7.153e-06 s (6.68 %) + converted COO to RSB in 6.001e-02 s (100.00 %) + analyzed arrays in 2.799e-02 s (46.64 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 7.153e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.506e-05 s (42.09 %) - memory allocations took 9.537e-07 s (0.89 %) - leafs setup took 9.537e-07 s (0.89 %) - halfword conversion took 1.097e-05 s (10.24 %) -Built (100 x 100)[0x55ac7db9cbc0]{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 1.601e-02 s (26.67 %) + memory allocations took 3.099e-06 s (0.01 %) + leafs setup took 1.907e-06 s (0.00 %) + halfword conversion took 1.600e-02 s (26.66 %) +Built (100 x 100)[0x55b7c7a37bf0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7654,9 +7694,9 @@ # 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 8.011e-05s; avg 2.67e-05s ( +/- 2.68/ 5.36 %); best 2.599e-05s; worst 2.813e-05s; std dev. 1.012e-06 (taking best). -Reference operation time is 2.59876e-05 s (3109 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 2.59876e-05 s/0 threads (speedup 0.688073 x), same?n. +3 iterations (1 th.) took 0.02374s; avg 0.007915s ( +/- 2.26/ 1.24 %); best 0.007736s; worst 0.008013s; std dev. 0.0001266 (taking best). +Reference operation time is 0.00773597 s (10.44 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, 0.00773597 s/0 threads (speedup 0.00335932 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 16777216 bytes, per-thread 16777216 bytes @@ -7690,16 +7730,16 @@ # 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 1.299e-04 s (100.00 %) - analyzed arrays in 5.102e-05 s (39.27 %) - cleaned-up arrays in 6.199e-06 s (4.77 %) - deduplicated arrays in 6.914e-06 s (5.32 %) + converted COO to RSB in 5.193e-02 s (100.00 %) + analyzed arrays in 1.992e-02 s (38.36 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 6.914e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.293e-05 s (40.73 %) - memory allocations took 9.537e-07 s (0.73 %) - leafs setup took 9.537e-07 s (0.73 %) - halfword conversion took 1.097e-05 s (8.44 %) -Built (100 x 100)[0x55ac7db9cbc0]{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 1.601e-02 s (30.83 %) + memory allocations took 2.861e-06 s (0.01 %) + leafs setup took 2.861e-06 s (0.01 %) + halfword conversion took 1.598e-02 s (30.78 %) +Built (100 x 100)[0x55b7c7a37bf0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7745,9 +7785,9 @@ # 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 9.298e-05s; avg 3.099e-05s ( +/- 6.15/ 10.00 %); best 2.909e-05s; worst 3.409e-05s; std dev. 2.211e-06 (taking best). -Reference operation time is 2.90871e-05 s (2778 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 2.90871e-05 s/0 threads (speedup 0.614754 x), same?n. +3 iterations (1 th.) took 0.02376s; avg 0.007921s ( +/- 1.93/ 1.02 %); best 0.007768s; worst 0.008002s; std dev. 0.0001083 (taking best). +Reference operation time is 0.00776792 s (10.4 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, 0.00776792 s/0 threads (speedup 0.00334551 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 16777216 bytes, per-thread 16777216 bytes @@ -7781,16 +7821,16 @@ # 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 1.662e-04 s (100.00 %) - analyzed arrays in 6.080e-05 s (36.59 %) - cleaned-up arrays in 5.007e-06 s (3.01 %) - deduplicated arrays in 6.914e-06 s (4.16 %) + converted COO to RSB in 5.194e-02 s (100.00 %) + analyzed arrays in 1.993e-02 s (38.37 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.606e-05 s (45.77 %) - memory allocations took 4.292e-06 s (2.58 %) - leafs setup took 2.146e-06 s (1.29 %) - halfword conversion took 1.097e-05 s (6.60 %) -Built (100 x 100)[0x55ac7db9cbc0]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 34, symflags:'LS' + shuffled partitions in 1.599e-02 s (30.78 %) + memory allocations took 4.053e-06 s (0.01 %) + leafs setup took 2.146e-06 s (0.00 %) + halfword conversion took 1.600e-02 s (30.81 %) +Built (100 x 100)[0x55b7c7a37bf0]{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: 33, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7836,10 +7876,10 @@ # 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 0.000103s; avg 3.433e-05s ( +/- 4.17/ 7.64 %); best 3.29e-05s; worst 3.695e-05s; std dev. 1.857e-06 (taking best). -Reference operation time is 3.29018e-05 s (2456 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 1, 34 leaves, 2.372 bytes/nz, 3.29018e-05 s/0 threads (speedup 0.543478 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 47 subms, 34 lsubms, 2.3723 bpnz +3 iterations (1 th.) took 0.02777s; avg 0.009258s ( +/- 16.04/ 29.52 %); best 0.007773s; worst 0.01199s; std dev. 0.001935 (taking best). +Reference operation time is 0.00777292 s (10.4 Mflops) with 1 threads. +Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 1, 33 leaves, 2.361 bytes/nz, 0.00777292 s/0 threads (speedup 0.00334335 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 46 subms, 33 lsubms, 2.3612 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7872,16 +7912,16 @@ # 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 1.709e-04 s (100.00 %) - analyzed arrays in 5.889e-05 s (34.45 %) - cleaned-up arrays in 6.199e-06 s (3.63 %) - deduplicated arrays in 6.914e-06 s (4.04 %) + converted COO to RSB in 6.396e-02 s (100.00 %) + analyzed arrays in 1.592e-02 s (24.89 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 6.199e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.011e-05 s (46.86 %) - memory allocations took 3.815e-06 s (2.23 %) - leafs setup took 3.099e-06 s (1.81 %) - halfword conversion took 1.192e-05 s (6.97 %) -Built (100 x 100)[0x55ac7dbeafb0]{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 2.801e-02 s (43.79 %) + memory allocations took 5.007e-06 s (0.01 %) + leafs setup took 5.960e-06 s (0.01 %) + halfword conversion took 2.001e-02 s (31.29 %) +Built (100 x 100)[0x55b7c7a85fb0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7927,9 +7967,9 @@ # 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 0.0001049s; avg 3.497e-05s ( +/- 5.91/ 8.41 %); best 3.29e-05s; worst 3.791e-05s; std dev. 2.135e-06 (taking best). -Reference operation time is 3.29018e-05 s (2456 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 3.29018e-05 s/0 threads (speedup 0.543478 x), same?n. +3 iterations (1 th.) took 0.03189s; avg 0.01063s ( +/- 24.89/ 13.31 %); best 0.007985s; worst 0.01205s; std dev. 0.001873 (taking best). +Reference operation time is 0.00798512 s (10.12 Mflops) with 1 threads. +Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00798512 s/0 threads (speedup 0.00325451 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 16777216 bytes, per-thread 16777216 bytes @@ -7963,16 +8003,16 @@ # 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 1.760e-04 s (100.00 %) - analyzed arrays in 6.199e-05 s (35.23 %) - cleaned-up arrays in 5.007e-06 s (2.85 %) - deduplicated arrays in 6.914e-06 s (3.93 %) + converted COO to RSB in 6.390e-02 s (100.00 %) + analyzed arrays in 2.389e-02 s (37.38 %) + cleaned-up arrays in 5.007e-06 s (0.01 %) + deduplicated arrays in 6.199e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.082e-05 s (45.93 %) - memory allocations took 7.153e-06 s (4.07 %) - leafs setup took 2.146e-06 s (1.22 %) - halfword conversion took 1.192e-05 s (6.78 %) -Built (100 x 100)[0x55ac7dbeafb0]{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 2.401e-02 s (37.58 %) + memory allocations took 7.868e-06 s (0.01 %) + leafs setup took 5.960e-06 s (0.01 %) + halfword conversion took 1.598e-02 s (25.00 %) +Built (100 x 100)[0x55b7c7a85fb0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -8018,11 +8058,11 @@ # 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 0.0001051s; avg 3.505e-05s ( +/- 5.44/ 8.84 %); best 3.314e-05s; worst 3.815e-05s; std dev. 2.211e-06 (taking best). -Reference operation time is 3.31402e-05 s (2438 Mflops) with 1 threads. -Challenging best inner round reference (1.78814e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 3.31402e-05 s/0 threads (speedup 0.539568 x), same?n. +3 iterations (1 th.) took 0.02775s; avg 0.009251s ( +/- 13.57/ 27.09 %); best 0.007996s; worst 0.01176s; std dev. 0.001772 (taking best). +Reference operation time is 0.00799608 s (10.1 Mflops) with 1 threads. +Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00799608 s/0 threads (speedup 0.00325004 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: 4518.66 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 3109.17 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -8038,29 +8078,29 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.0017662 s (eq. to 1e+02/ 1e+02 old/new op.times), gained local/global speedup 1 x (1.78814e-05 : 1.78814e-05) / 1 x (1.78814e-05 : 1.78814e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.463904 s (eq. to 2e+04/ 2e+04 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 ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.0018s, 0.0011s for constructor, 0 clones) obtained NO speedup (best stays 4519 Mflops). -Second run of RSB Autotuner took 0.00178504 s and estimated a speedup of 1.000000 x (1.788e-05 s -> 1.788e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.46s, 0.33s for constructor, 0 clones) obtained NO speedup (best stays 3109 Mflops). +Second run of RSB Autotuner took 0.463937 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) #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 0.000021 0.000055 0.000076 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000076 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000021 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000055 -%: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 0.000076 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000001 0.010836 0.039993 0.050829 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.050830 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.010836 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.039993 +%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 +%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.050829 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -8069,68 +8109,68 @@ %: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 0.000104904 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.0668371 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 2.09808e-05 0 5.50747e-05 -# so far, program took 8.751s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.167s/0.000s . +%constructor:lower-100x100-5050nz 9.53674e-07 0.0108359 0 0.039993 +# so far, program took 10.223s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.472s/0.000s . getrusage() stats: -ru_maxrss: 75 (maximum resident set size -- MB) -ru_stime : 0.3086s (system CPU time used) -ru_utime : 26.87s (user CPU time used) +ru_maxrss: 81 (maximum resident set size -- MB) +ru_stime : 0.3783s (system CPU time used) +ru_utime : 31.88s (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 3389.00 7.967e-03 0.000e+00 5.960e-06 0.000e+00 1.680e-01 8.94e+00 2.60e+00 1 2.02e-02 -pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 3389.00 7.981e-03 0.000e+00 5.960e-06 0.000e+00 2.320e-01 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 4518.66 7.964e-03 0.000e+00 1.788e-05 0.000e+00 1.725e-01 2.98e+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 4706.94 2.789e-05 0.000e+00 1.717e-05 0.000e+00 6.716e-03 5.60e+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 3389.00 7.988e-03 0.000e+00 5.960e-06 0.000e+00 1.800e-01 8.94e+00 2.60e+00 1 2.02e-02 +pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 3389.00 7.987e-03 0.000e+00 5.960e-06 0.000e+00 1.760e-01 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 4236.25 7.981e-03 0.000e+00 1.907e-05 0.000e+00 2.000e-01 2.79e+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 5744.06 7.989e-03 0.000e+00 1.407e-05 0.000e+00 1.680e-01 6.83e+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. 77967.0 % faster, avg. sp. ratio 780.670x, max sp. ratio 1339.000x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 19289.3/391.2/38929.5/77157.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 78.1/ 21.1/240.8/312.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 174.5, min. 21.1, max. 626.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 91562.9 % faster, avg. sp. ratio 916.629x, max sp. ratio 1340.160x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 20542.2/10487.0/30202.5/82168.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 22.7/ 21.0/ 25.1/ 90.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 22.7, min. 21.1, max. 25.1 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 5.634/ 2.936/ 8.809,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 22.875/ 2.981/ 8.943,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.891/ 2.753/ 8.809,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 23.922/ 2.795/ 8.943,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.: 0.14 s, min 0.01 s, max 0.23 s, tot 0.58 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.01 s, max 0.23 s, tot 0.58 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.001e+03, min 3.389e+03, max 4.707e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 7.279e+02, min 2.531e+00, max 2.897e+03 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.174e-05s, min 5.960e-06s, max 1.788e-05s, tot 4.697e-05s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.985e-03s, min 2.789e-05s, max 7.981e-03s, tot 2.394e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.264e+00 6.792e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.359e+00 -#pr: Record collection took 1.78 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.18 s, min 0.17 s, max 0.20 s, tot 0.72 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.18 s, min 0.17 s, max 0.20 s, tot 0.72 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.190e+03, min 3.389e+03, max 5.744e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.324e+00, min 2.529e+00, max 1.012e+01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 1.127e-05s, min 5.960e-06s, max 1.907e-05s, tot 4.506e-05s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.986e-03s, min 7.981e-03s, max 7.989e-03s, tot 3.194e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.014e+00 6.444e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 5.419e+00 +#pr: Record collection took 2.51 s. #pr: Record comprises 50 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 99 environment variables in 4344 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 99 environment variables in 4398 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 1717748753 (after 8.7s of w.c.t.) +# terminating run at 1752160154 (after 10.2s 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 85634 Jun 6 20:25 test-tuning-lower-100x100-5050nz--D-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jun 6 20:25 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85634 Jun 6 20:25 test-tuning-lower-100x100-5050nz--S-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jun 6 20:25 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85634 Jun 6 20:25 test-tuning-lower-100x100-5050nz--C-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84555 Jun 6 20:25 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85635 Jun 6 20:25 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84557 Jun 6 20:25 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85643 Jul 11 05:09 test-tuning-lower-100x100-5050nz--D-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Jul 11 05:09 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85643 Jul 11 05:09 test-tuning-lower-100x100-5050nz--S-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Jul 11 05:09 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Jul 11 05:09 test-tuning-lower-100x100-5050nz--C-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84565 Jul 11 05:09 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85643 Jul 11 05:09 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84565 Jul 11 05:09 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 4098 Jun 6 20:25 test.txt +-rw-r--r-- 1 pbuilder2 pbuilder2 4100 Jul 11 05:09 test.txt + RSB_PR_WLTC=2 + RSB_PR_SR=0 + rsbench --read-performance-record test.rpr @@ -8140,29 +8180,29 @@ /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 +8217,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x557ece92b4a0]{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)[0x564295ea14a0]{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 +8232,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x563cc37424a0]{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)[0x560ae2ba34a0]{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 +8296,51 @@ Done. Building a matrix with 5 nnz, 5 x 5 Duplicates check: 5 - 0 = 5 - converted COO to RSB in 7.468e-02 s (100.00 %) - analyzed arrays in 3.568e-02 s (47.78 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 1.192e-06 s (0.00 %) - sorted arrays in 6.989e-03 s (9.36 %) - shuffled partitions in 1.600e-02 s (21.43 %) - memory allocations took 7.153e-06 s (0.01 %) + converted COO to RSB in 7.067e-02 s (100.00 %) + analyzed arrays in 2.000e-02 s (28.30 %) + cleaned-up arrays in 0.000e+00 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) + sorted arrays in 6.660e-03 s (9.42 %) + shuffled partitions in 2.402e-02 s (33.98 %) + memory allocations took 7.391e-06 s (0.01 %) leafs setup took 3.099e-06 s (0.00 %) - halfword conversion took 1.599e-02 s (21.42 %) -Built (5 x 5)[0x563cc3744820]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' + halfword conversion took 1.998e-02 s (28.28 %) +Built (5 x 5)[0x560ae2ba5820]{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)[0x563cc3744820]{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)[0x560ae2ba5820]{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 0.132441s. +Before auto-tuning, 100 multiplications took 0.983955s. 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.=4.915e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 2.503e-05s; avg 8.345e-06s ( +/- 28.57/ 57.14 %); best 5.96e-06s; worst 1.311e-05s; std dev. 3.372e-06 (taking best). -Reference operation time is 5.96046e-06 s (3.355 Mflops) with 12 threads. -3 iterations (12 th.) took 1.693e-05s; avg 5.643e-06s ( +/- 11.27/ 5.63 %); best 5.007e-06s; worst 5.96e-06s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.00679e-06 s (3.995 Mflops) with 12 threads. -After 0.000095s, autotuning routine did not find a better threads count configuration. -(5 x 5)[0x563cc3744820]{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 0.000535s -- effective speedup of 247.548 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.17488e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.02396s; avg 0.007986s ( +/- 0.38/ 0.30 %); best 0.007955s; worst 0.00801s; std dev. 2.283e-05 (taking best). +Reference operation time is 0.00795507 s (0.002514 Mflops) with 12 threads. +3 iterations (12 th.) took 0.02797s; avg 0.009323s ( +/- 14.50/ 28.68 %); best 0.007971s; worst 0.012s; std dev. 0.001891 (taking best). +Reference operation time is 0.00797105 s (0.002509 Mflops) with 12 threads. +After 0.051999s, autotuning routine did not find a better threads count configuration. +(5 x 5)[0x560ae2ba5820]{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 0.863980s -- effective speedup of 1.13886 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.=4.915e-08), 12 suggested as starting thread count. -3 iterations (12 th.) took 1.788e-05s; avg 5.96e-06s ( +/- 16.00/ 32.00 %); best 5.007e-06s; worst 7.868e-06s; std dev. 1.349e-06 (taking best). -Reference operation time is 5.00679e-06 s (3.995 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: 5.007e-06 Mflops: 3.995) -Merge (2 -> 1 leaves) took w.c.t. of 1.407e-05s, ~2.861e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 84.54/200.00 %); best 4.915e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 4.915e-08 s (406.9 Mflops) with 12 threads. -After merge step 1: tpop: 4.915e-08 s ~Mflops: 406.918 nsubm:1 otn:12 -Applying merge (2 -> 1 leaves, 12 th.) yielded SPEEDUP of 101.868x: 5.007e-06s -> 4.915e-08s, so taking this instance. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.17488e-08), 12 suggested as starting thread count. +3 iterations (12 th.) took 0.024s; avg 0.008001s ( +/- 0.05/ 0.10 %); best 0.007997s; worst 0.008009s; std dev. 5.409e-06 (taking best). +Reference operation time is 0.00799704 s (0.002501 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: 0.007997 Mflops: 0.003) +Merge (2 -> 1 leaves) took w.c.t. of 1.907e-05s, ~3.815e-06s of computing time (of which 0s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 96.90/200.00 %); best 5.175e-08s; worst 5.007e-06s; std dev. 2.36e-06 (taking best). +Reference operation time is 5.17488e-08 s (386.5 Mflops) with 12 threads. +After merge step 1: tpop: 5.175e-08 s ~Mflops: 386.483 nsubm:1 otn:12 +Applying merge (2 -> 1 leaves, 12 th.) yielded SPEEDUP of 154535.821x: 0.007997s -> 5.175e-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 5.984e-05s (of which 3.695e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 0s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 5.984e-05s, equivalent to 1217.6/12.0 new/old ops (4.101e-05s for 2 clones -- as 834.3/8.2 ops, or 417.2/4.1 ops per clone), SPEEDUP of 101.868x -Applying multi-merge (2 -> 1 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 101.868x (5.007e-06s -> 4.915e-08s), will amortize in 12.1 ops by saving 4.958e-06s per op. -In 1 tuning rounds (tot. 0.00012s, 4.1e-05s for constructor, 2 clones) obtained a SPEEDUP of 10086.8% (101.9x) (from 3.995 to 406.9 Mflops). -After 0.000126s, autotuning routine declared speedup of 101.868 x, when using threads count of 12. -(5 x 5)[0x563cc3747de0]{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 0.000013s -- further speedup of 41.5556 x +A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.024s (of which 0.000319s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 0s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.024s, equivalent to 463741.1/3.0 new/old ops (0.04762s for 2 clones -- as 920138.2/6.0 ops, or 460069.1/3.0 ops per clone), SPEEDUP of 154535.821x +Applying multi-merge (2 -> 1 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 154535.821x (0.007997s -> 5.175e-08s), will amortize in 3.0 ops by saving 0.007997s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 15453482.1% (1.545e+05x) (from 0.002501 to 386.5 Mflops). +After 0.072011s, autotuning routine declared speedup of 154536 x, when using threads count of 12. +(5 x 5)[0x560ae2ba8de0]{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 0.000015s -- further speedup of 57520.6 x 0/2 0 0 -> 0 1/2 1 0 -> 5 0/2 0 3 -> 0 @@ -8311,7 +8351,7 @@ Correctly initialized the library. Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0x563cc3744820]{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)[0x560ae2ba5820]{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 @@ -8462,83 +8502,75 @@ 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 1.810e-01 s (100.00 %) - analyzed arrays in 3.586e-02 s (19.81 %) - cleaned-up arrays in 7.010e-05 s (0.04 %) - deduplicated arrays in 8.512e-05 s (0.05 %) - sorted arrays in 6.152e-02 s (33.98 %) - shuffled partitions in 5.170e-02 s (28.56 %) - memory allocations took 1.979e-05 s (0.01 %) - leafs setup took 8.106e-06 s (0.00 %) - halfword conversion took 3.176e-02 s (17.54 %) -Built (500 x 500)[0x55eb7054f2d0]{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: 22, symflags:'' + converted COO to RSB in 1.251e-01 s (100.00 %) + analyzed arrays in 1.577e-02 s (12.60 %) + cleaned-up arrays in 6.485e-05 s (0.05 %) + deduplicated arrays in 6.986e-05 s (0.06 %) + sorted arrays in 6.116e-02 s (48.90 %) + shuffled partitions in 3.201e-02 s (25.59 %) + memory allocations took 3.219e-05 s (0.03 %) + leafs setup took 6.914e-06 s (0.01 %) + halfword conversion took 1.598e-02 s (12.77 %) +Built (500 x 500)[0x556d1f9d12d0]{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: 22, symflags:'' Allocated matrix of 62500 nonzeroes: -(500 x 500)[0x55eb7054f2d0]{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: 22, symflags:'' +(500 x 500)[0x556d1f9d12d0]{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: 22, symflags:'' -Before auto-tuning, 100 multiplications took 0.740296s. +Before auto-tuning, 100 multiplications took 0.847774s. 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, 31 subms, 22 lsubms, 2.0733 bpnz. +Will use autotuning routine to sample matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 31 subms, 22 lsubms, 2.0694 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.=4.8852e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.02392s; avg 0.007974s ( +/- 0.54/ 0.28 %); best 0.007931s; worst 0.007996s; std dev. 3.041e-05 (taking best). -Reference operation time is 0.00793099 s (31.52 Mflops) with 12 threads. -3 iterations (12 th.) took 0.02398s; avg 0.007994s ( +/- 0.10/ 0.07 %); best 0.007986s; worst 0.008s; std dev. 5.96e-06 (taking best). -Reference operation time is 0.00798607 s (31.3 Mflops) with 12 threads. -After 0.047980s, autotuning routine did not find a better threads count configuration. -(500 x 500)[0x55eb7054f2d0]{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: 22, symflags:'' -After threads auto-tuning, 100 multiplications took 0.144580s -- effective speedup of 5.12032 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.12481e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.02794s; avg 0.009314s ( +/- 14.15/ 28.26 %); best 0.007996s; worst 0.01195s; std dev. 0.001861 (taking best). +Reference operation time is 0.00799608 s (31.27 Mflops) with 12 threads. +3 iterations (12 th.) took 0.03219s; avg 0.01073s ( +/- 22.48/ 11.54 %); best 0.008317s; worst 0.01197s; std dev. 0.001706 (taking best). +Reference operation time is 0.00831699 s (30.06 Mflops) with 12 threads. +After 0.060196s, autotuning routine did not find a better threads count configuration. +(500 x 500)[0x556d1f9d12d0]{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: 22, symflags:'' +After threads auto-tuning, 100 multiplications took 0.847793s -- effective speedup of 0.999978 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, 31 subms, 22 lsubms, 2.0733 bpnz. +Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 31 subms, 22 lsubms, 2.0694 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.=4.8852e-08), 12 suggested as starting thread count. -3 iterations (12 th.) took 0.0003381s; avg 0.0001127s ( +/- 8.60/ 5.57 %); best 0.000103s; worst 0.000119s; std dev. 6.955e-06 (taking best). -Reference operation time is 0.000102997 s (2427 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, 31 subms, 22 lsubms, 2.0733 bpnz (tpop: 0.000103 Mflops: 2427.259) -Merge (22 -> 16 leaves) took w.c.t. of 0.000622s, ~0.0006468s of computing time (of which 3.004e-05s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.04194s; avg 0.01398s ( +/- 14.22/ 12.04 %); best 0.01199s; worst 0.01566s; std dev. 0.001514 (taking best). -Reference operation time is 0.0119929 s (20.85 Mflops) with 12 threads. -After merge step 1: tpop: 0.01199 s ~Mflops: 20.846 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 116.440x: 0.000103s -> 0.01199s. -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 0.04258s (of which 0.0006249s partitioning, 0s I/O); computing times: 0.0006468s in par. loops, 3.004e-05s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.04258s, equivalent to 413.4/413.4 new/old ops (0.0001271s for 1 clones -- as 1.2/1.2 ops, or 1.2/1.2 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 0.03607s; avg 0.01202s ( +/- 0.23/ 0.45 %); best 0.012s; worst 0.01208s; std dev. 3.866e-05 (taking best). -Reference operation time is 0.011997 s (20.84 Mflops) with 12 threads. -Starting split (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 31 subms, 22 lsubms, 2.0733 bpnz (tpop: 0.012 Mflops: 20.839) -Split (22 -> 55 leaves, 31 -> 75 subms) took 0.01595s (of which: 4.768e-06s analysis, -1.89e+10s mem.mgmt); compute time: 0.03782s overall, 0.0003386s searches, 0.03748s shuffle, 0.02113s switch, 0.003785s quadrants. -3 iterations (12 th.) took 0.03592s; avg 0.01197s ( +/- 0.41/ 0.21 %); best 0.01192s; worst 0.012s; std dev. 3.462e-05 (taking best). -Reference operation time is 0.011924 s (20.97 Mflops) with 12 threads. -After split step 1: tpop: 0.01192 s ~Mflops: 20.966 nsubm:55 otn:12 -Applying split (22 -> 55 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00612x): 0.012s -> 0.01192s, so IGNORING this instance. -Split (55 -> 136 leaves, 75 -> 183 subms) took 0.01996s (of which: 8.106e-06s analysis, -4.638e+10s mem.mgmt); compute time: 0.001441s overall, 0.0002174s searches, 0.001223s shuffle, 0.0003803s switch, 6.366e-05s quadrants. -3 iterations (12 th.) took 0.03991s; avg 0.0133s ( +/- 9.80/ 17.92 %); best 0.012s; worst 0.01569s; std dev. 0.001689 (taking best). -Reference operation time is 0.0120001 s (20.83 Mflops) with 12 threads. -After split step 2: tpop: 0.012 s ~Mflops: 20.833 nsubm:136 otn:12 -Applying split (55 -> 136 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=0.99974x): 0.012s -> 0.012s, so IGNORING this instance. -Split (136 -> 340 leaves, 183 -> 455 subms) took 0.02393s (of which: 1.884e-05s analysis, -1.168e+11s mem.mgmt); compute time: 0.002257s overall, 0.0002725s searches, 0.001984s shuffle, 0.0006359s switch, 0.0003197s quadrants. -3 iterations (12 th.) took 0.04366s; avg 0.01455s ( +/- 17.04/ 10.24 %); best 0.01207s; worst 0.01604s; std dev. 0.001765 (taking best). -Reference operation time is 0.0120749 s (20.7 Mflops) with 12 threads. -After split step 3: tpop: 0.01207 s ~Mflops: 20.704 nsubm:340 otn:12 -Applying split (136 -> 340 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=0.99354x): 0.012s -> 0.01207s, so IGNORING this instance. -Split (340 -> 850 leaves, 455 -> 1135 subms) took 0.01194s (of which: 2.599e-05s analysis, -2.92e+11s mem.mgmt); compute time: 0.005257s overall, 0.0003204s searches, 0.004937s shuffle, 0.001034s switch, 0.00127s quadrants. -3 iterations (12 th.) took 0.03581s; avg 0.01194s ( +/- 1.04/ 0.69 %); best 0.01181s; worst 0.01202s; std dev. 8.94e-05 (taking best). -Reference operation time is 0.0118132 s (21.16 Mflops) with 12 threads. -After split step 4: tpop: 0.01181 s ~Mflops: 21.163 nsubm:850 otn:12 -Applying split (340 -> 850 leaves, 12 th.) yielded SPEEDUP of 1.016x: 0.012s -> 0.01181s, so taking this instance. -Split (850 -> 2125 leaves, 1135 -> 2835 subms) took 0.02338s (of which: 5.698e-05s analysis, -7.3e+11s mem.mgmt); compute time: 0.0195s overall, 0.0002871s searches, 0.01921s shuffle, 0.004583s switch, 0.004714s quadrants. -3 iterations (12 th.) took 0.05976s; avg 0.01992s ( +/- 0.75/ 0.41 %); best 0.01977s; worst 0.02s; std dev. 0.0001057 (taking best). -Reference operation time is 0.0197721 s (12.64 Mflops) with 12 threads. -After split step 5: tpop: 0.01977 s ~Mflops: 12.644 nsubm:2125 otn:12 -Applying split (850 -> 2125 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.674x: 0.01181s -> 0.01977s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 5 split steps (of max 6) (22 -> 2125 subms) took 0.348s (of which 0.09684s partitioning, 0s I/O); computing times: 0.06627s in par. loops, 0.001436s sorting, 0.0001147s analyzing) -Total split + benchmarking process took 0.348s, equivalent to 29.5/29.0 new/old ops (0.07223s for 2 clones -- as 6.1/6.0 ops, or 3.1/3.0 ops per clone), SPEEDUP of 1.016x -Applying multi-split (22 -> 850 leaves, 4 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 1.016x (0.012s -> 0.01181s), will amortize in 1893.1 ops by saving 0.0001838s per op. -In 1 tuning rounds (tot. 0.46s, 0.072s for constructor, 3 clones) obtained a SPEEDUP of 1.6% (1.016x) (from 20.84 to 21.16 Mflops). -After 0.463771s, autotuning routine declared speedup of 1.01556 x, when using threads count of 12. -(500 x 500)[0x55eb7068b740]{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: 850, symflags:'' -After threads auto-tuning, 100 multiplications took 0.851624s -- further speedup of 0.16977 x +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.12481e-08), 12 suggested as starting thread count. +3 iterations (12 th.) took 0.02442s; avg 0.00814s ( +/- 1.92/ 3.46 %); best 0.007984s; worst 0.008422s; std dev. 0.0001997 (taking best). +Reference operation time is 0.00798392 s (31.31 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, 31 subms, 22 lsubms, 2.0694 bpnz (tpop: 0.007984 Mflops: 31.313) +Merge (22 -> 16 leaves) took w.c.t. of 0.003901s, ~0.0004323s of computing time (of which 4.911e-05s sorting, 7.868e-06s analysis) +3 iterations (12 th.) took 0.02363s; avg 0.007878s ( +/- 1.21/ 1.55 %); best 0.007782s; worst 0.008s; std dev. 9.092e-05 (taking best). +Reference operation time is 0.00778198 s (32.13 Mflops) with 12 threads. +After merge step 1: tpop: 0.007782 s ~Mflops: 32.125 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.026x: 0.007984s -> 0.007782s, so taking this instance. +Merge (16 -> 13 leaves) took w.c.t. of 7.391e-05s, ~5.794e-05s of computing time (of which 2.718e-05s sorting, 6.199e-06s analysis) +3 iterations (12 th.) took 0.02389s; avg 0.007965s ( +/- 0.79/ 0.47 %); best 0.007902s; worst 0.008002s; std dev. 4.45e-05 (taking best). +Reference operation time is 0.00790215 s (31.64 Mflops) with 12 threads. +After merge step 2: tpop: 0.007902 s ~Mflops: 31.637 nsubm:13 otn:12 +Applying merge (16 -> 13 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98479x): 0.007782s -> 0.007902s, so IGNORING this instance. +Merge (13 -> 10 leaves) took w.c.t. of 0.000231s, ~0.0002141s of computing time (of which 0.0001261s sorting, 5.96e-06s analysis) +3 iterations (12 th.) took 0.0235s; avg 0.007833s ( +/- 4.39/ 2.23 %); best 0.007489s; worst 0.008008s; std dev. 0.0002431 (taking best). +Reference operation time is 0.0074892 s (33.38 Mflops) with 12 threads. +After merge step 3: tpop: 0.007489 s ~Mflops: 33.381 nsubm:10 otn:12 +Applying merge (13 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.039x: 0.007782s -> 0.007489s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 0.0001299s, ~0.000114s of computing time (of which 5.198e-05s sorting, 7.153e-06s analysis) +3 iterations (12 th.) took 0.02385s; avg 0.007949s ( +/- 1.35/ 0.78 %); best 0.007842s; worst 0.008011s; std dev. 7.596e-05 (taking best). +Reference operation time is 0.00784206 s (31.88 Mflops) with 12 threads. +After merge step 4: tpop: 0.007842 s ~Mflops: 31.879 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.047x: 0.007489s -> 0.007842s. +Merge (7 -> 4 leaves) took w.c.t. of 0.000103s, ~9.489e-05s of computing time (of which 4.601e-05s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.02386s; avg 0.007955s ( +/- 1.08/ 0.71 %); best 0.007869s; worst 0.008012s; std dev. 6.184e-05 (taking best). +Reference operation time is 0.00786901 s (31.77 Mflops) with 12 threads. +After merge step 5: tpop: 0.007869 s ~Mflops: 31.770 nsubm:4 otn:12 +Applying merge (7 -> 4 leaves, 12 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.051x: 0.007489s -> 0.007869s. +Merge (4 -> 3 leaves) took w.c.t. of 0.0001302s, ~0.000123s of computing time (of which 0s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 0.03187s; avg 0.01062s ( +/- 25.97/ 13.08 %); best 0.007865s; worst 0.01201s; std dev. 0.001951 (taking best). +Reference operation time is 0.00786495 s (31.79 Mflops) with 12 threads. +After merge step 6: tpop: 0.007865 s ~Mflops: 31.787 nsubm:3 otn:12 +Applying merge (4 -> 3 leaves, 12 th.) yielded SLOWDOWN (3th of 3 tolerable) of 1.050x: 0.007489s -> 0.007865s. +A total of 6 merge steps (of max 6) (22 -> 3 subms) took 0.2036s (of which 0.004852s partitioning, 0s I/O); computing times: 0.001036s in par. loops, 0.0003004s sorting, 3.242e-05s analyzing) +Total merge + benchmarking process took 0.2036s, equivalent to 27.2/25.5 new/old ops (0.07197s for 3 clones -- as 9.6/9.0 ops, or 3.2/3.0 ops per clone), SPEEDUP of 1.066x +Applying multi-merge (22 -> 10 leaves, 3 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 1.066x (0.007984s -> 0.007489s), will amortize in 411.5 ops by saving 0.0004947s per op. +In 1 tuning rounds (tot. 0.25s, 0.072s for constructor, 3 clones) obtained a SPEEDUP of 6.6% (1.066x) (from 31.31 to 33.38 Mflops). +After 0.252288s, autotuning routine declared speedup of 1.06606 x, when using threads count of 12. +(500 x 500)[0x556d1face070]{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: 10, symflags:'' +After threads auto-tuning, 100 multiplications took 0.185752s -- further speedup of 4.56411 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! @@ -8546,19 +8578,19 @@ Correctly initialized the library. Building a matrix with 7 nnz, 6 x 6 Duplicates check: 1 - 0 = 1 - converted COO to RSB in 4.389e-02 s (100.00 %) - analyzed arrays in 3.182e-02 s (72.49 %) + converted COO to RSB in 4.470e-02 s (100.00 %) + analyzed arrays in 3.277e-02 s (73.30 %) cleaned-up arrays in 4.053e-06 s (0.01 %) - deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 1.907e-06 s (0.00 %) - shuffled partitions in 1.205e-02 s (27.45 %) - memory allocations took 1.001e-05 s (0.02 %) - leafs setup took 1.907e-06 s (0.00 %) + deduplicated arrays in 1.192e-06 s (0.00 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 1.191e-02 s (26.64 %) + memory allocations took 1.287e-05 s (0.03 %) + leafs setup took 3.099e-06 s (0.01 %) halfword conversion took 5.960e-06 s (0.01 %) -Built (6 x 6)[0x56044472a4d0]{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' +Built (6 x 6)[0x5564b73284d0]{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)[0x56044472a4d0]{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)[0x5564b73284d0]{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 @@ -8584,55 +8616,55 @@ 1 1 Will autotune matrix: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.716e-08 -3 iterations (12 th.) took 1.693e-05s; avg 5.643e-06s ( +/- 99.34/183.10 %); best 3.716e-08s; worst 1.597e-05s; std dev. 7.316e-06 (taking best). -Reference operation time is 3.71575e-08 s (53.82 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: 3.716e-08 Mflops: 53.825) +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.805e-08 +3 iterations (12 th.) took 1.502e-05s; avg 5.007e-06s ( +/- 99.24/176.19 %); best 3.805e-08s; worst 1.383e-05s; std dev. 6.257e-06 (taking best). +Reference operation time is 3.80516e-08 s (52.56 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: 3.805e-08 Mflops: 52.560) 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 9.537e-07s; avg 3.179e-07s ( +/- 88.31/200.00 %); best 3.716e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After merge step 1: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying merge (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.03/200.00 %); best 3.805e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 3.80516e-08 s (52.56 Mflops) with 12 threads. +After merge step 1: tpop: 3.805e-08 s ~Mflops: 52.560 nsubm:1 otn:12 +Applying merge (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.805e-08s -> 3.805e-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 8.106e-06s (of which 2.146e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 8.106e-06s, equivalent to 218.2/218.2 new/old ops (0.03993s for 1 clones -- as 1074693.6/1074693.6 ops, or 1074693.6/1074693.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (1 -> 1 subms) took 7.868e-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 7.868e-06s, equivalent to 206.8/206.8 new/old ops (0.02402s for 1 clones -- as 631328.3/631328.3 ops, or 631328.3/631328.3 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 1.907e-06s; avg 6.358e-07s ( +/- 94.16/200.00 %); best 3.716e-08s; worst 1.907e-06s; std dev. 8.991e-07 (taking best). -Reference operation time is 3.71575e-08 s (53.82 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: 3.716e-08 Mflops: 53.825) -Split (1 -> 1 leaves, 1 -> 1 subms) took 1.192e-05s (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 9.537e-07s; avg 3.179e-07s ( +/- 88.31/200.00 %); best 3.716e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 1: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-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 3.716e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 2: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. -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 3.716e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 3: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 0s (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 3.716e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 4: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 0s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 90.65/200.00 %); best 3.716e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 5: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. +3 iterations (12 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.01/200.00 %); best 3.805e-08s; worst 1.907e-06s; std dev. 8.991e-07 (taking best). +Reference operation time is 3.80516e-08 s (52.56 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: 3.805e-08 Mflops: 52.560) +Split (1 -> 1 leaves, 1 -> 1 subms) took 1.311e-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 0s; avg 0s ( +/- -inf/ -nan %); best 3.805e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 3.80516e-08 s (52.56 Mflops) with 12 threads. +After split step 1: tpop: 3.805e-08 s ~Mflops: 52.560 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.805e-08s -> 3.805e-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 1.192e-06s; avg 3.974e-07s ( +/- 90.65/200.00 %); best 3.716e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 6: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. -A total of 6 split steps (of max 6) (1 -> 1 subms) took 6.39e-05s (of which 4.315e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 3.099e-06s analyzing) -Total split + benchmarking process took 6.39e-05s, equivalent to 1719.6/1719.6 new/old ops (0.03589s for 1 clones -- as 965992.9/965992.9 ops, or 965992.9/965992.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.076s, 0.076s for constructor, 2 clones) obtained NO speedup (best stays 53.82 Mflops). +3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ -nan %); best 3.805e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 3.80516e-08 s (52.56 Mflops) with 12 threads. +After split step 2: tpop: 3.805e-08 s ~Mflops: 52.560 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 3.805e-08s -> 3.805e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 1.907e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.03/200.00 %); best 3.805e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 3.80516e-08 s (52.56 Mflops) with 12 threads. +After split step 3: tpop: 3.805e-08 s ~Mflops: 52.560 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 3.805e-08s -> 3.805e-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 0s; avg 0s ( +/- -inf/ -nan %); best 3.805e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 3.80516e-08 s (52.56 Mflops) with 12 threads. +After split step 4: tpop: 3.805e-08 s ~Mflops: 52.560 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 3.805e-08s -> 3.805e-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 3.805e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 3.80516e-08 s (52.56 Mflops) with 12 threads. +After split step 5: tpop: 3.805e-08 s ~Mflops: 52.560 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 3.805e-08s -> 3.805e-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 3.805e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 3.80516e-08 s (52.56 Mflops) with 12 threads. +After split step 6: tpop: 3.805e-08 s ~Mflops: 52.560 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 3.805e-08s -> 3.805e-08s, so IGNORING this instance. +A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.000139s (of which 3.624e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.907e-06s analyzing) +Total split + benchmarking process took 0.000139s, equivalent to 3652.9/3652.9 new/old ops (0.02396s for 1 clones -- as 629799.5/629799.5 ops, or 629799.5/629799.5 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.048s, 0.048s for constructor, 2 clones) obtained NO speedup (best stays 52.56 Mflops). Backsolving we should get a unitary vector: %%MatrixMarket matrix array real general @@ -8667,151 +8699,180 @@ /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 8.743e-02 s (100.00 %) - analyzed arrays in 2.398e-02 s (27.43 %) - cleaned-up arrays in 1.907e-06 s (0.00 %) - deduplicated arrays in 1.907e-06 s (0.00 %) - sorted arrays in 1.184e-02 s (13.54 %) - shuffled partitions in 2.400e-02 s (27.45 %) - memory allocations took 2.098e-05 s (0.02 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 2.758e-02 s (31.54 %) -Built (20 x 20)[0x55a94db019f0]{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:3.765e-08 -Starting autotuning (16 x 3.76463e-08 s stages, transA=N, nrhs=1, timer gran.=3.76463e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.024s; avg 0.007998s ( +/- 0.03/ 0.05 %); best 0.007996s; worst 0.008002s; std dev. 2.614e-06 (taking best). -Reference operation time is 0.00799608 s (0.1051 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: 0.007996 Mflops: 0.105) -Merge (22 -> 16 leaves) took w.c.t. of 0.004281s, ~0.0003009s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.03571s; avg 0.0119s ( +/- 32.79/ 34.43 %); best 0.008s; worst 0.016s; std dev. 0.00327 (taking best). -Reference operation time is 0.0079999 s (0.105 Mflops) with 12 threads. -After merge step 1: tpop: 0.008 s ~Mflops: 0.105 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99952x): 0.007996s -> 0.008s, so IGNORING this instance. -Merge (16 -> 13 leaves) took w.c.t. of 2.098e-05s, ~5.96e-06s of computing time (of which 1.192e-06s sorting, 6.914e-06s analysis) -3 iterations (12 th.) took 0.03951s; avg 0.01317s ( +/- 9.27/ 18.11 %); best 0.01195s; worst 0.01555s; std dev. 0.001686 (taking best). -Reference operation time is 0.0119481 s (0.0703 Mflops) with 12 threads. -After merge step 2: tpop: 0.01195 s ~Mflops: 0.070 nsubm:13 otn:12 -Applying merge (16 -> 13 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.494x: 0.007996s -> 0.01195s. -Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 2 merge steps (of max 6) (22 -> 13 subms) took 0.07956s (of which 0.004309s partitioning, 0s I/O); computing times: 0.0003068s in par. loops, 2.146e-06s sorting, 1.097e-05s analyzing) -Total merge + benchmarking process took 0.07956s, equivalent to 9.9/9.9 new/old ops (0.02836s for 1 clones -- as 3.5/3.5 ops, or 3.5/3.5 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 0.03991s; avg 0.0133s ( +/- 9.84/ 18.52 %); best 0.01199s; worst 0.01577s; std dev. 0.001743 (taking best). -Reference operation time is 0.0119941 s (0.07003 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: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.01199 Mflops: 0.070) -Split (22 -> 51 leaves, 30 -> 70 subms) took 0.004604s (of which: 4.053e-06s analysis, -1.89e+10s mem.mgmt); compute time: 0.003033s overall, 8.821e-06s searches, 0.003024s shuffle, 0.002331s switch, 0.0001442s quadrants. -3 iterations (12 th.) took 0.03155s; avg 0.01052s ( +/- 23.93/ 14.09 %); best 0.008001s; worst 0.012s; std dev. 0.001789 (taking best). -Reference operation time is 0.00800109 s (0.105 Mflops) with 12 threads. -After split step 1: tpop: 0.008001 s ~Mflops: 0.105 nsubm:51 otn:12 -Applying split (22 -> 51 leaves, 12 th.) yielded SPEEDUP of 1.499x: 0.01199s -> 0.008001s, so taking this instance. -Split (51 -> 122 leaves, 70 -> 166 subms) took 0.01198s (of which: 6.199e-06s analysis, -4.294e+10s mem.mgmt); compute time: 0.0007749s overall, 7.868e-06s searches, 0.000767s shuffle, 0.0004089s switch, 0.0001032s quadrants. -3 iterations (12 th.) took 0.02396s; avg 0.007986s ( +/- 0.34/ 0.20 %); best 0.007959s; worst 0.008002s; std dev. 1.927e-05 (taking best). -Reference operation time is 0.00795889 s (0.1055 Mflops) with 12 threads. -After split step 2: tpop: 0.007959 s ~Mflops: 0.106 nsubm:122 otn:12 -Applying split (51 -> 122 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00530x): 0.008001s -> 0.007959s, so IGNORING this instance. -Split (122 -> 146 leaves, 166 -> 198 subms) took 0.01188s (of which: 1.192e-05s analysis, -1.374e+10s mem.mgmt); compute time: 0.0001552s overall, 3.815e-06s searches, 0.0001514s shuffle, 6.938e-05s switch, 2.718e-05s quadrants. -3 iterations (12 th.) took 0.02397s; avg 0.007991s ( +/- 0.18/ 0.10 %); best 0.007976s; worst 0.007999s; std dev. 1.048e-05 (taking best). + converted COO to RSB in 7.924e-02 s (100.00 %) + analyzed arrays in 2.797e-02 s (35.30 %) + cleaned-up arrays in 2.861e-06 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) + sorted arrays in 1.922e-02 s (24.25 %) + shuffled partitions in 1.600e-02 s (20.20 %) + memory allocations took 4.125e-05 s (0.05 %) + leafs setup took 5.960e-06 s (0.01 %) + halfword conversion took 1.599e-02 s (20.18 %) +Built (20 x 20)[0x55dae54729f0]{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: 23, symflags:'LS' +Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 32 subms, 23 lsubms, 3.7524 bpnz. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:4.874e-08 +Starting autotuning (16 x 4.87447e-08 s stages, transA=N, nrhs=1, timer gran.=4.87447e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.024s; avg 0.008001s ( +/- 0.15/ 0.16 %); best 0.007989s; worst 0.008014s; std dev. 1.022e-05 (taking best). +Reference operation time is 0.00798893 s (0.1051 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, 32 subms, 23 lsubms, 3.7524 bpnz (tpop: 0.007989 Mflops: 0.105) +Merge (23 -> 19 leaves) took w.c.t. of 0.0003669s, ~0.0003502s of computing time (of which 9.537e-07s sorting, 6.914e-06s analysis) +3 iterations (12 th.) took 0.0236s; avg 0.007866s ( +/- 3.39/ 1.73 %); best 0.007599s; worst 0.008002s; std dev. 0.0001887 (taking best). +Reference operation time is 0.00759888 s (0.1105 Mflops) with 12 threads. +After merge step 1: tpop: 0.007599 s ~Mflops: 0.111 nsubm:19 otn:12 +Applying merge (23 -> 19 leaves, 12 th.) yielded SPEEDUP of 1.051x: 0.007989s -> 0.007599s, so taking this instance. +Merge (19 -> 13 leaves) took w.c.t. of 0.004101s, ~3.6e-05s of computing time (of which 5.96e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.02392s; avg 0.007973s ( +/- 0.63/ 0.72 %); best 0.007922s; worst 0.00803s; std dev. 4.425e-05 (taking best). +Reference operation time is 0.00792217 s (0.106 Mflops) with 12 threads. +After merge step 2: tpop: 0.007922 s ~Mflops: 0.106 nsubm:13 otn:12 +Applying merge (19 -> 13 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.043x: 0.007599s -> 0.007922s. +Merge (13 -> 10 leaves) took w.c.t. of 1.383e-05s, ~5.007e-06s of computing time (of which 0s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.02394s; avg 0.00798s ( +/- 0.48/ 0.24 %); best 0.007941s; worst 0.007999s; std dev. 2.731e-05 (taking best). +Reference operation time is 0.00794101 s (0.1058 Mflops) with 12 threads. +After merge step 3: tpop: 0.007941 s ~Mflops: 0.106 nsubm:10 otn:12 +Applying merge (13 -> 10 leaves, 12 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.045x: 0.007599s -> 0.007941s. +Merge (10 -> 8 leaves) took w.c.t. of 1.097e-05s, ~5.007e-06s of computing time (of which 1.192e-06s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.02397s; avg 0.007991s ( +/- 0.19/ 0.11 %); best 0.007976s; worst 0.008s; std dev. 1.081e-05 (taking best). Reference operation time is 0.00797582 s (0.1053 Mflops) with 12 threads. -After split step 3: tpop: 0.007976 s ~Mflops: 0.105 nsubm:146 otn:12 -Applying split (122 -> 146 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00317x): 0.008001s -> 0.007976s, so IGNORING this instance. -Split (146 -> 146 leaves, 198 -> 198 subms) took 0.0119s (of which: 1.884e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.02397s; avg 0.007992s ( +/- 0.15/ 0.19 %); best 0.00798s; worst 0.008007s; std dev. 1.139e-05 (taking best). -Reference operation time is 0.00797987 s (0.1053 Mflops) with 12 threads. -After split step 4: tpop: 0.00798 s ~Mflops: 0.105 nsubm:146 otn:12 -Applying split (146 -> 146 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00266x): 0.008001s -> 0.00798s, so IGNORING this instance. -Split (146 -> 146 leaves, 198 -> 198 subms) took 0.01199s (of which: 1.192e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.02398s; avg 0.007993s ( +/- 0.20/ 0.11 %); best 0.007977s; worst 0.008001s; std dev. 1.108e-05 (taking best). -Reference operation time is 0.00797701 s (0.1053 Mflops) with 12 threads. -After split step 5: tpop: 0.007977 s ~Mflops: 0.105 nsubm:146 otn:12 -Applying split (146 -> 146 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00302x): 0.008001s -> 0.007977s, so IGNORING this instance. -Split (146 -> 146 leaves, 198 -> 198 subms) took 0.01199s (of which: 1.001e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.02398s; avg 0.007994s ( +/- 0.16/ 0.09 %); best 0.007981s; worst 0.008001s; std dev. 9.285e-06 (taking best). -Reference operation time is 0.00798082 s (0.1053 Mflops) with 12 threads. -After split step 6: tpop: 0.007981 s ~Mflops: 0.105 nsubm:146 otn:12 -Applying split (146 -> 146 leaves, 12 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00254x): 0.008001s -> 0.007981s, so IGNORING this instance. -A total of 6 split steps (of max 6) (22 -> 146 subms) took 0.2402s (of which 0.06476s partitioning, 0s I/O); computing times: 0.003963s in par. loops, 2.05e-05s sorting, 6.294e-05s analyzing) -Total split + benchmarking process took 0.2402s, equivalent to 30.0/20.0 new/old ops (0.06026s for 2 clones -- as 7.5/5.0 ops, or 3.8/2.5 ops per clone), SPEEDUP of 1.499x -Applying multi-split (22 -> 51 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.499x (0.01199s -> 0.008001s), will amortize in 60.2 ops by saving 0.003993s per op. -In 1 tuning rounds (tot. 0.45s, 0.089s for constructor, 3 clones) obtained a SPEEDUP of 49.9% (1.499x) (from 0.07003 to 0.105 Mflops). +After merge step 4: tpop: 0.007976 s ~Mflops: 0.105 nsubm:8 otn:12 +Applying merge (10 -> 8 leaves, 12 th.) yielded SLOWDOWN (3th of 3 tolerable) of 1.050x: 0.007599s -> 0.007976s. +Merge (8 -> 6 leaves) took w.c.t. of 1.097e-05s, ~4.053e-06s of computing time (of which 1.192e-06s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.02398s; avg 0.007992s ( +/- 0.07/ 0.09 %); best 0.007986s; worst 0.007999s; std dev. 5.315e-06 (taking best). +Reference operation time is 0.00798607 s (0.1052 Mflops) with 12 threads. +After merge step 5: tpop: 0.007986 s ~Mflops: 0.105 nsubm:6 otn:12 +Applying merge (8 -> 6 leaves, 12 th.) yielded SLOWDOWN (4th of 3 tolerable) of 1.051x: 0.007599s -> 0.007986s. +Skipping further merge based tests after 4 definite performance degradations in a row. +A total of 5 merge steps (of max 6) (23 -> 6 subms) took 0.1482s (of which 0.004521s partitioning, 0s I/O); computing times: 0.0004003s in par. loops, 9.298e-06s sorting, 2.217e-05s analyzing) +Total merge + benchmarking process took 0.1482s, equivalent to 19.5/18.6 new/old ops (0.04794s for 2 clones -- as 6.3/6.0 ops, or 3.2/3.0 ops per clone), SPEEDUP of 1.051x +Applying multi-merge (23 -> 19 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.051x (0.007989s -> 0.007599s), will amortize in 380.0 ops by saving 0.0003901s per op. +In 1 tuning rounds (tot. 0.2s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 5.1% (1.051x) (from 0.1051 to 0.1105 Mflops). autotuner chose 12 threads -Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 70 subms, 51 lsubms, 4.4571 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.765e-08 -Starting autotuning (16 x 3.76463e-08 s stages, transA=N, nrhs=1, timer gran.=3.76463e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.03601s; avg 0.012s ( +/- 33.32/ 33.32 %); best 0.008003s; worst 0.016s; std dev. 0.003266 (taking best). -~ 12 threads: 0.008003s (0.1 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.03998s; avg 0.01333s ( +/- 10.00/ 19.96 %); best 0.012s; worst 0.01599s; std dev. 0.001881 (taking best). - 11 threads: 0.012s (0.07 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.03985s; avg 0.01328s ( +/- 10.88/ 17.82 %); best 0.01184s; worst 0.01565s; std dev. 0.001687 (taking best). - 10 threads: 0.01184s (0.071 Mflops) (2/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 1.5x; search took 0.12s. -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, 70 subms, 51 lsubms, 4.4571 bpnz (tpop: 0.008003 Mflops: 0.105) -Merge (51 -> 36 leaves) took w.c.t. of 0.007709s, ~6.104e-05s of computing time (of which 5.007e-06s sorting, 7.153e-06s analysis) -3 iterations (12 th.) took 0.03639s; avg 0.01213s ( +/- 1.10/ 2.13 %); best 0.012s; worst 0.01239s; std dev. 0.0001826 (taking best). -~ 12 threads: 0.012s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.036s; avg 0.012s ( +/- 0.05/ 0.08 %); best 0.012s; worst 0.01201s; std dev. 6.955e-06 (taking best). - 11 threads: 0.012s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 0.03599s; avg 0.012s ( +/- 0.10/ 0.09 %); best 0.01199s; worst 0.01201s; std dev. 9e-06 (taking best). - 10 threads: 0.01199s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (9 th.) took 0.03594s; avg 0.01198s ( +/- 0.32/ 0.18 %); best 0.01194s; worst 0.012s; std dev. 2.727e-05 (taking best). - 9 threads: 0.01194s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (8 th.) took 0.03692s; avg 0.01231s ( +/- 26.46/ 26.43 %); best 0.009051s; worst 0.01556s; std dev. 0.002657 (taking best). - 8 threads: 0.009051s (0.093 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 0.0005281s; avg 0.000176s ( +/- 24.42/ 34.09 %); best 0.000133s; worst 0.000236s; std dev. 4.373e-05 (taking best). - 7 threads: 0.000133s (6.3 Mflops) (0/2 degradations so far) - -3 iterations (6 th.) took 0.0005841s; avg 0.0001947s ( +/- 29.10/ 39.22 %); best 0.000138s; worst 0.0002711s; std dev. 5.607e-05 (taking best). - 6 threads: 0.000138s (6.1 Mflops) (1/2 degradations so far) - -3 iterations (5 th.) took 0.0006411s; avg 0.0002137s ( +/- 14.32/ 22.16 %); best 0.0001831s; worst 0.0002611s; std dev. 3.397e-05 (taking best). - 5 threads: 0.0001831s (4.6 Mflops) (2/2 degradations so far) - -Best threads choice is 7; starting threads were 12; max speed gap is 90x; search took 0.18s. -After merge step 1: tpop: 0.000133 s ~Mflops: 6.314 nsubm:36 otn:7 -Applying merge (51 -> 36 leaves, 7 th.) yielded SPEEDUP of 60.156x: 0.008003s -> 0.000133s, so taking this instance. -Merge (36 -> 25 leaves) took w.c.t. of 5.412e-05s, ~6.628e-05s of computing time (of which 4.292e-06s sorting, 5.96e-06s analysis) -3 iterations (12 th.) took 0.04117s; avg 0.01372s ( +/- 12.62/ 16.00 %); best 0.01199s; worst 0.01592s; std dev. 0.001637 (taking best). -~ 12 threads: 0.01199s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.03606s; avg 0.01202s ( +/- 33.47/ 31.08 %); best 0.007998s; worst 0.01576s; std dev. 0.003174 (taking best). - 11 threads: 0.007998s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 0.024s; avg 0.007999s ( +/- 0.06/ 0.04 %); best 0.007994s; worst 0.008002s; std dev. 3.46e-06 (taking best). - 10 threads: 0.007994s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (9 th.) took 0.024s; avg 0.007999s ( +/- 0.13/ 0.16 %); best 0.007989s; worst 0.008012s; std dev. 9.668e-06 (taking best). - 9 threads: 0.007989s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (8 th.) took 0.02397s; avg 0.00799s ( +/- 0.21/ 0.12 %); best 0.007973s; worst 0.008s; std dev. 1.208e-05 (taking best). - 8 threads: 0.007973s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 0.024s; avg 0.007999s ( +/- 0.03/ 0.04 %); best 0.007996s; worst 0.008002s; std dev. 2.57e-06 (taking best). - 7 threads: 0.007996s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (6 th.) took 0.02398s; avg 0.007995s ( +/- 0.02/ 0.04 %); best 0.007993s; worst 0.007998s; std dev. 2.171e-06 (taking best). - 6 threads: 0.007993s (0.11 Mflops) (2/2 degradations so far) - -Best threads choice is 8; starting threads were 12; max speed gap is 1.5x; search took 0.2s. -After merge step 2: tpop: 0.007973 s ~Mflops: 0.105 nsubm:25 otn:8 -Applying merge (36 -> 25 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 59.930x: 0.000133s -> 0.007973s. -Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 2 merge steps (of max 6) (51 -> 25 subms) took 0.3881s (of which 0.007773s partitioning, 0s I/O); computing times: 0.0001273s in par. loops, 9.298e-06s sorting, 1.311e-05s analyzing) -Total merge + benchmarking process took 0.3881s, equivalent to 2917.5/48.5 new/old ops (0.02401s for 2 clones -- as 180.5/3.0 ops, or 90.2/1.5 ops per clone), SPEEDUP of 60.156x -Applying multi-merge (51 -> 36 leaves, 1 steps, 12 -> 7 th.sp.) yielded SPEEDUP of 60.156x (0.008003s -> 0.000133s), will amortize in 49.3 ops by saving 0.00787s per op. -In 1 tuning rounds (tot. 0.53s, 0.024s for constructor, 2 clones) obtained a SPEEDUP of 5915.6% (60.16x) (from 0.105 to 6.314 Mflops). +Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 26 subms, 19 lsubms, 3.6000 bpnz. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:4.874e-08 +Starting autotuning (16 x 4.87447e-08 s stages, transA=N, nrhs=1, timer gran.=4.87447e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.032s; avg 0.01067s ( +/- 25.11/ 50.12 %); best 0.007988s; worst 0.01601s; std dev. 0.003781 (taking best). +~ 12 threads: 0.007988s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.02399s; avg 0.007995s ( +/- 0.26/ 0.14 %); best 0.007975s; worst 0.008007s; std dev. 1.448e-05 (taking best). + 11 threads: 0.007975s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 0.02397s; avg 0.007991s ( +/- 0.11/ 0.12 %); best 0.007982s; worst 0.008001s; std dev. 7.714e-06 (taking best). + 10 threads: 0.007982s (0.11 Mflops) (1/2 degradations so far) - +3 iterations (9 th.) took 0.02399s; avg 0.007996s ( +/- 0.21/ 0.41 %); best 0.007979s; worst 0.008029s; std dev. 2.333e-05 (taking best). + 9 threads: 0.007979s (0.11 Mflops) (2/2 degradations so far) - +Best threads choice is 11; starting threads were 12; max speed gap is 1x; search took 0.1s. +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, 26 subms, 19 lsubms, 3.6000 bpnz (tpop: 0.007975 Mflops: 0.105) +Merge (19 -> 13 leaves) took w.c.t. of 0.004018s, ~2.408e-05s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.02395s; avg 0.007985s ( +/- 0.07/ 0.05 %); best 0.007979s; worst 0.007989s; std dev. 4.211e-06 (taking best). +~ 12 threads: 0.007979s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.02399s; avg 0.007995s ( +/- 0.09/ 0.06 %); best 0.007988s; worst 0.008s; std dev. 5.159e-06 (taking best). + 11 threads: 0.007988s (0.11 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.024s; avg 0.008s ( +/- 0.12/ 0.21 %); best 0.007991s; worst 0.008017s; std dev. 1.183e-05 (taking best). + 10 threads: 0.007991s (0.11 Mflops) (2/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 1x; search took 0.072s. +After merge step 1: tpop: 0.007979 s ~Mflops: 0.105 nsubm:13 otn:12 +Applying merge (19 -> 13 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99949x): 0.007975s -> 0.007979s, so IGNORING this instance. +Merge (13 -> 10 leaves) took w.c.t. of 2.003e-05s, ~7.153e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.02398s; avg 0.007994s ( +/- 0.53/ 0.48 %); best 0.007951s; worst 0.008032s; std dev. 3.323e-05 (taking best). +~ 12 threads: 0.007951s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.03597s; avg 0.01199s ( +/- 0.24/ 0.15 %); best 0.01196s; worst 0.01201s; std dev. 2.054e-05 (taking best). + 11 threads: 0.01196s (0.07 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.02398s; avg 0.007993s ( +/- 0.21/ 0.20 %); best 0.007976s; worst 0.008009s; std dev. 1.343e-05 (taking best). + 10 threads: 0.007976s (0.11 Mflops) (2/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 1.5x; search took 0.084s. +After merge step 2: tpop: 0.007951 s ~Mflops: 0.106 nsubm:10 otn:12 +Applying merge (13 -> 10 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00300x): 0.007975s -> 0.007951s, so IGNORING this instance. +Merge (10 -> 8 leaves) took w.c.t. of 2.003e-05s, ~6.914e-06s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.02396s; avg 0.007985s ( +/- 0.37/ 0.23 %); best 0.007956s; worst 0.008004s; std dev. 2.098e-05 (taking best). +~ 12 threads: 0.007956s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.02398s; avg 0.007994s ( +/- 0.07/ 0.04 %); best 0.007988s; worst 0.007997s; std dev. 4.019e-06 (taking best). + 11 threads: 0.007988s (0.11 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.0238s; avg 0.007932s ( +/- 1.76/ 0.93 %); best 0.007792s; worst 0.008006s; std dev. 9.901e-05 (taking best). + 10 threads: 0.007792s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 0.024s; avg 0.007999s ( +/- 0.46/ 0.42 %); best 0.007962s; worst 0.008032s; std dev. 2.87e-05 (taking best). + 9 threads: 0.007962s (0.11 Mflops) (1/2 degradations so far) - +3 iterations (8 th.) took 0.02398s; avg 0.007994s ( +/- 0.03/ 0.03 %); best 0.007992s; worst 0.007997s; std dev. 2.063e-06 (taking best). + 8 threads: 0.007992s (0.11 Mflops) (2/2 degradations so far) - +Best threads choice is 10; starting threads were 12; max speed gap is 1x; search took 0.12s. +After merge step 3: tpop: 0.007792 s ~Mflops: 0.108 nsubm:8 otn:10 +Applying merge (10 -> 8 leaves, 10 th.) yielded SPEEDUP of 1.023x: 0.007975s -> 0.007792s, so taking this instance. +Merge (8 -> 6 leaves) took w.c.t. of 2.003e-05s, ~6.914e-06s of computing time (of which 2.146e-06s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.02397s; avg 0.00799s ( +/- 0.38/ 0.29 %); best 0.007959s; worst 0.008013s; std dev. 2.252e-05 (taking best). +~ 12 threads: 0.007959s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.02399s; avg 0.007995s ( +/- 0.17/ 0.12 %); best 0.007982s; worst 0.008005s; std dev. 9.774e-06 (taking best). + 11 threads: 0.007982s (0.11 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.02399s; avg 0.007998s ( +/- 0.72/ 0.71 %); best 0.00794s; worst 0.008055s; std dev. 4.692e-05 (taking best). + 10 threads: 0.00794s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 0.02398s; avg 0.007994s ( +/- 0.04/ 0.02 %); best 0.007991s; worst 0.007996s; std dev. 2.306e-06 (taking best). + 9 threads: 0.007991s (0.11 Mflops) (1/2 degradations so far) - +3 iterations (8 th.) took 0.02407s; avg 0.008022s ( +/- 0.35/ 0.66 %); best 0.007994s; worst 0.008075s; std dev. 3.729e-05 (taking best). + 8 threads: 0.007994s (0.11 Mflops) (2/2 degradations so far) - +Best threads choice is 10; starting threads were 12; max speed gap is 1x; search took 0.12s. +After merge step 4: tpop: 0.00794 s ~Mflops: 0.106 nsubm:6 otn:10 +Applying merge (8 -> 6 leaves, 10 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98135x): 0.007792s -> 0.00794s, so IGNORING this instance. +Merge (6 -> 3 leaves) took w.c.t. of 1.812e-05s, ~6.914e-06s of computing time (of which 1.192e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.0239s; avg 0.007965s ( +/- 0.99/ 0.61 %); best 0.007886s; worst 0.008014s; std dev. 5.629e-05 (taking best). +~ 12 threads: 0.007886s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.02398s; avg 0.007993s ( +/- 0.12/ 0.19 %); best 0.007983s; worst 0.008008s; std dev. 1.097e-05 (taking best). + 11 threads: 0.007983s (0.11 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.02414s; avg 0.008047s ( +/- 0.55/ 1.07 %); best 0.008003s; worst 0.008133s; std dev. 6.081e-05 (taking best). + 10 threads: 0.008003s (0.1 Mflops) (2/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 1x; search took 0.072s. +After merge step 5: tpop: 0.007886 s ~Mflops: 0.107 nsubm:3 otn:12 +Applying merge (6 -> 3 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=0.98806x): 0.007792s -> 0.007886s, so IGNORING this instance. +Merge (3 -> 1 leaves) took w.c.t. of 2.003e-05s, ~8.821e-06s of computing time (of which 9.537e-07s sorting, 3.815e-06s analysis) +3 iterations (12 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 92.33/ 50.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +~ 12 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 84.67/200.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 11 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 92.33/ 50.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 10 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 84.67/200.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 9 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 84.67/200.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 8 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (7 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 92.33/ 50.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 7 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (6 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 84.67/200.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 6 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (5 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 92.33/ 50.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 5 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (4 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 84.67/200.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 4 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (3 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 84.67/200.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 3 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (2 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 84.67/200.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 2 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +3 iterations (1 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 84.67/200.00 %); best 4.874e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 1 threads: 4.874e-08s (1.7e+04 Mflops) (0/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 1x; search took 0.00021s. +After merge step 6: tpop: 4.874e-08 s ~Mflops: 17232.650 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 159853.265x: 0.007792s -> 4.874e-08s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 6 merge steps (of max 6) (19 -> 1 subms) took 0.52s (of which 0.004131s partitioning, 0s I/O); computing times: 6.08e-05s in par. loops, 9.537e-06s sorting, 2.789e-05s analyzing) +Total merge + benchmarking process took 0.52s, equivalent to 10667649.8/65.2 new/old ops (0.07158s for 3 clones -- as 1468544.9/9.0 ops, or 489515.0/3.0 ops per clone), SPEEDUP of 163604.793x +Applying multi-merge (19 -> 1 leaves, 6 steps, 11 -> 12 th.sp.) yielded SPEEDUP of 163604.793x (0.007975s -> 4.874e-08s), will amortize in 65.2 ops by saving 0.007975s per op. +In 1 tuning rounds (tot. 0.65s, 0.072s for constructor, 3 clones) obtained a SPEEDUP of 16360379.3% (1.636e+05x) (from 0.1053 to 1.723e+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 2.781e-02 s (100.00 %) - analyzed arrays in 1.201e-02 s (43.18 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) + converted COO to RSB in 3.548e-02 s (100.00 %) + analyzed arrays in 1.986e-02 s (55.97 %) + cleaned-up arrays in 1.192e-06 s (0.00 %) deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 7.814e-03 s (28.10 %) - shuffled partitions in 7.977e-03 s (28.68 %) - memory allocations took 6.676e-06 s (0.02 %) - leafs setup took 2.146e-06 s (0.01 %) - halfword conversion took 9.537e-07 s (0.00 %) -Built (6 x 6)[0x55a94db05ab0]{Z} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x20440b4 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'UL' + sorted arrays in 7.470e-03 s (21.05 %) + shuffled partitions in 8.141e-03 s (22.95 %) + memory allocations took 3.099e-06 s (0.01 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 4.053e-06 s (0.01 %) +Built (6 x 6)[0x55dae5474e30]{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 0.2408E-04 s -A single USMM took 0.1001E-04 s -USMM-to-USMV speed ratio is is 2.405 x +Repeated USMV took 0.2909E-04 s +A single USMM took 0.1907E-04 s +USMM-to-USMV speed ratio is is 1.525 x Call auto-tuning routine.. Repeat measurement. -Tuned USMM took 0.3099E-05 s -Tuned-to-untuned speed ratio is is 3.231 x +Tuned USMM took 0.3815E-05 s +Tuned-to-untuned speed ratio is is 5.000 x FAILED: 0 PASSED: 2 /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran_rsb_fi @@ -8860,285 +8921,228 @@ 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 9.021e-02 s (100.00 %) - analyzed arrays in 2.786e-02 s (30.89 %) - cleaned-up arrays in 2.861e-06 s (0.00 %) + converted COO to RSB in 6.836e-02 s (100.00 %) + analyzed arrays in 1.580e-02 s (23.11 %) + cleaned-up arrays in 5.960e-06 s (0.01 %) deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 1.436e-02 s (15.92 %) - shuffled partitions in 2.399e-02 s (26.59 %) - memory allocations took 7.153e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.00 %) - halfword conversion took 2.398e-02 s (26.58 %) -Built (6 x 6)[0x557a0f3eda20]{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:'' + sorted arrays in 2.053e-02 s (30.04 %) + shuffled partitions in 1.600e-02 s (23.41 %) + memory allocations took 1.597e-05 s (0.02 %) + leafs setup took 6.199e-06 s (0.01 %) + halfword conversion took 1.599e-02 s (23.39 %) +Built (6 x 6)[0x55b13778ba20]{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)[0x557a0f3f1aa0]{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)[0x55b13778faa0]{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 0.036s; avg 0.012s ( +/- 33.34/ 29.81 %); best 0.007999s; worst 0.01558s; std dev. 0.003108 (taking best). -Reference operation time is 0.00799894 s (0.018 Mflops) with 12 threads. -After 0.036039s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.02394s; avg 0.007981s ( +/- 0.48/ 0.26 %); best 0.007943s; worst 0.008002s; std dev. 2.697e-05 (taking best). +Reference operation time is 0.00794291 s (0.01813 Mflops) with 12 threads. +After 0.023988s, 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 0.036s; avg 0.012s ( +/- 31.06/ 31.10 %); best 0.008273s; worst 0.01573s; std dev. 0.003045 (taking best). -Reference operation time is 0.00827312 s (0.01741 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: 0.008273 Mflops: 0.017) -Merge (22 -> 16 leaves) took w.c.t. of 0.004312s, ~0.0003281s of computing time (of which 2.146e-06s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.03963s; avg 0.01321s ( +/- 11.66/ 18.60 %); best 0.01167s; worst 0.01567s; std dev. 0.001756 (taking best). -Reference operation time is 0.0116699 s (0.01234 Mflops) with 12 threads. -After merge step 1: tpop: 0.01167 s ~Mflops: 0.012 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.411x: 0.008273s -> 0.01167s. -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 0.04396s (of which 0.004317s partitioning, 0s I/O); computing times: 0.0003281s in par. loops, 2.146e-06s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.04396s, equivalent to 5.3/5.3 new/old ops (0.03641s 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 0.04373s; avg 0.01458s ( +/- 17.67/ 9.76 %); best 0.012s; worst 0.016s; std dev. 0.001825 (taking best). -Reference operation time is 0.012002 s (0.012 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: 0.012 Mflops: 0.012) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.01205s (of which: 3.815e-06s analysis, -3.435e+09s mem.mgmt); compute time: 0.0001199s overall, 2.146e-06s searches, 0.0001178s shuffle, 5.698e-05s switch, 1.907e-06s quadrants. -3 iterations (12 th.) took 0.04007s; avg 0.01336s ( +/- 9.43/ 18.71 %); best 0.0121s; worst 0.01586s; std dev. 0.001767 (taking best). -Reference operation time is 0.0120969 s (0.0119 Mflops) with 12 threads. -After split step 1: tpop: 0.0121 s ~Mflops: 0.012 nsubm:28 otn:12 -Applying split (22 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99216x): 0.012s -> 0.0121s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.02758s (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 0.04005s; avg 0.01335s ( +/- 10.28/ 17.19 %); best 0.01198s; worst 0.01565s; std dev. 0.001633 (taking best). -Reference operation time is 0.0119779 s (0.01202 Mflops) with 12 threads. -After split step 2: tpop: 0.01198 s ~Mflops: 0.012 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00201x): 0.012s -> 0.01198s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01217s (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 0.03611s; avg 0.01204s ( +/- 0.55/ 0.54 %); best 0.01197s; worst 0.0121s; std dev. 5.353e-05 (taking best). -Reference operation time is 0.011972 s (0.01203 Mflops) with 12 threads. -After split step 3: tpop: 0.01197 s ~Mflops: 0.012 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00251x): 0.012s -> 0.01197s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01987s (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 0.03612s; avg 0.01204s ( +/- 1.29/ 0.70 %); best 0.01188s; worst 0.01212s; std dev. 0.0001098 (taking best). -Reference operation time is 0.0118849 s (0.01212 Mflops) with 12 threads. -After split step 4: tpop: 0.01188 s ~Mflops: 0.012 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00985x): 0.012s -> 0.01188s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01971s (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 0.03626s; avg 0.01209s ( +/- 0.75/ 1.42 %); best 0.012s; worst 0.01226s; std dev. 0.0001215 (taking best). -Reference operation time is 0.011996 s (0.012 Mflops) with 12 threads. -After split step 5: tpop: 0.012 s ~Mflops: 0.012 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00050x): 0.012s -> 0.012s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.02769s (of which: 3.099e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.03228s; avg 0.01076s ( +/- 25.26/ 13.72 %); best 0.008042s; worst 0.01224s; std dev. 0.001924 (taking best). -Reference operation time is 0.00804186 s (0.01791 Mflops) with 12 threads. -After split step 6: tpop: 0.008042 s ~Mflops: 0.018 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.492x: 0.012s -> 0.008042s, so taking this instance. -A total of 6 split steps (of max 6) (22 -> 28 subms) took 0.3842s (of which 0.1193s partitioning, 0s I/O); computing times: 0.0001199s in par. loops, 2.146e-06s sorting, 2.17e-05s analyzing) -Total split + benchmarking process took 0.3842s, equivalent to 47.8/32.0 new/old ops (0.08798s for 2 clones -- as 10.9/7.3 ops, or 5.5/3.7 ops per clone), SPEEDUP of 1.492x -Applying multi-split (22 -> 28 leaves, 6 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.492x (0.012s -> 0.008042s), will amortize in 97.0 ops by saving 0.00396s per op. -In 1 tuning rounds (tot. 0.59s, 0.12s for constructor, 3 clones) obtained a SPEEDUP of 49.2% (1.492x) (from 0.012 to 0.01791 Mflops). -After 0.588406s, global autotuning declared speedup of 1.49244 x, when using threads count of 12 and a new matrix: -(6 x 6)[0x557a0f402530]{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 0.032s; avg 0.01067s ( +/- 25.01/ 50.00 %); best 0.007999s; worst 0.016s; std dev. 0.003771 (taking best). +Reference operation time is 0.00799894 s (0.018 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: 0.007999 Mflops: 0.018) +Merge (22 -> 16 leaves) took w.c.t. of 0.00101s, ~0.001001s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.03501s; avg 0.01167s ( +/- 31.46/ 28.30 %); best 0.007999s; worst 0.01497s; std dev. 0.002859 (taking best). +Reference operation time is 0.00799894 s (0.018 Mflops) with 12 threads. +After merge step 1: tpop: 0.007999 s ~Mflops: 0.018 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 0.007999s -> 0.007999s, so IGNORING this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.007972s, ~2.003e-05s of computing time (of which 2.146e-06s sorting, 3.815e-06s analysis) +3 iterations (12 th.) took 0.02398s; avg 0.007994s ( +/- 0.39/ 0.30 %); best 0.007963s; worst 0.008018s; std dev. 2.303e-05 (taking best). +Reference operation time is 0.00796294 s (0.01808 Mflops) with 12 threads. +After merge step 2: tpop: 0.007963 s ~Mflops: 0.018 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00452x): 0.007999s -> 0.007963s, so IGNORING this instance. +Merge (10 -> 7 leaves) took w.c.t. of 1.192e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.02396s; avg 0.007988s ( +/- 0.32/ 0.16 %); best 0.007963s; worst 0.008001s; std dev. 1.793e-05 (taking best). +Reference operation time is 0.00796294 s (0.01808 Mflops) with 12 threads. +After merge step 3: tpop: 0.007963 s ~Mflops: 0.018 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00452x): 0.007999s -> 0.007963s, so IGNORING this instance. +Merge (7 -> 4 leaves) took w.c.t. of 1.884e-05s, ~5.96e-06s of computing time (of which 1.192e-06s sorting, 6.914e-06s analysis) +3 iterations (12 th.) took 0.02395s; avg 0.007984s ( +/- 0.13/ 0.09 %); best 0.007973s; worst 0.007991s; std dev. 7.622e-06 (taking best). +Reference operation time is 0.00797319 s (0.01806 Mflops) with 12 threads. +After merge step 4: tpop: 0.007973 s ~Mflops: 0.018 nsubm:4 otn:12 +Applying merge (7 -> 4 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00323x): 0.007999s -> 0.007973s, so IGNORING this instance. +Merge (4 -> 1 leaves) took w.c.t. of 1.478e-05s, ~5.96e-06s of computing time (of which 9.537e-07s sorting, 3.815e-06s analysis) +3 iterations (12 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 97.05/142.86 %); best 4.93e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). +Reference operation time is 4.9305e-08 s (2921 Mflops) with 12 threads. +After merge step 5: tpop: 4.93e-08 s ~Mflops: 2920.599 nsubm:1 otn:12 +Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 162234.043x: 0.007999s -> 4.93e-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 0.14s (of which 0.00905s partitioning, 0s I/O); computing times: 0.001037s in par. loops, 7.391e-06s sorting, 2.265e-05s analyzing) +Total merge + benchmarking process took 0.14s, equivalent to 2839410.1/17.5 new/old ops (0.0479s for 2 clones -- as 971586.1/6.0 ops, or 485793.0/3.0 ops per clone), SPEEDUP of 162234.043x +Applying multi-merge (22 -> 1 leaves, 5 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 162234.043x (0.007999s -> 4.93e-08s), will amortize in 17.5 ops by saving 0.007999s per op. +In 1 tuning rounds (tot. 0.2s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 16223304.3% (1.622e+05x) (from 0.018 to 2921 Mflops). +After 0.196022s, global autotuning declared speedup of 162234 x, when using threads count of 12 and a new matrix: +(6 x 6)[0x55b137791e70]{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 5.596e-02 s (100.00 %) - analyzed arrays in 2.395e-02 s (42.80 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) + converted COO to RSB in 5.241e-02 s (100.00 %) + analyzed arrays in 1.996e-02 s (38.08 %) + cleaned-up arrays in 0.000e+00 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (28.60 %) - memory allocations took 5.007e-06 s (0.01 %) - leafs setup took 2.146e-06 s (0.00 %) - halfword conversion took 1.600e-02 s (28.59 %) -Built (6 x 6)[0x557a0f3f1aa0]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' + shuffled partitions in 1.600e-02 s (30.53 %) + memory allocations took 4.292e-06 s (0.01 %) + leafs setup took 2.861e-06 s (0.01 %) + halfword conversion took 1.644e-02 s (31.37 %) +Built (6 x 6)[0x55b137791e70]{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)[0x557a0f3f1aa0]{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)[0x55b137791e70]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.5000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.02396s; avg 0.007986s ( +/- 0.40/ 0.24 %); best 0.007954s; worst 0.008005s; std dev. 2.284e-05 (taking best). -Reference operation time is 0.00795388 s (0.0181 Mflops) with 12 threads. -After 0.023976s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.0275s; avg 0.009167s ( +/- 18.23/ 30.75 %); best 0.007496s; worst 0.01199s; std dev. 0.002005 (taking best). +Reference operation time is 0.00749612 s (0.01921 Mflops) with 12 threads. +After 0.027532s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.5000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.02401s; avg 0.008003s ( +/- 0.07/ 0.07 %); best 0.007998s; worst 0.008009s; std dev. 4.483e-06 (taking best). -Reference operation time is 0.00799799 s (0.018 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, 4.5000 bpnz (tpop: 0.007998 Mflops: 0.018) -Merge (16 -> 13 leaves) took w.c.t. of 1.216e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (12 th.) took 0.02397s; avg 0.007989s ( +/- 0.31/ 0.29 %); best 0.007964s; worst 0.008012s; std dev. 1.949e-05 (taking best). -Reference operation time is 0.00796413 s (0.01808 Mflops) with 12 threads. -After merge step 1: tpop: 0.007964 s ~Mflops: 0.018 nsubm:13 otn:12 -Applying merge (16 -> 13 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00425x): 0.007998s -> 0.007964s, so IGNORING this instance. -Merge (13 -> 10 leaves) took w.c.t. of 1.311e-05s, ~4.053e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 0.02401s; avg 0.008003s ( +/- 0.42/ 0.42 %); best 0.007969s; worst 0.008037s; std dev. 2.764e-05 (taking best). -Reference operation time is 0.00796914 s (0.01807 Mflops) with 12 threads. -After merge step 2: tpop: 0.007969 s ~Mflops: 0.018 nsubm:10 otn:12 -Applying merge (13 -> 10 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00362x): 0.007998s -> 0.007969s, so IGNORING this instance. -Merge (10 -> 7 leaves) took w.c.t. of 9.06e-06s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (12 th.) took 0.02394s; avg 0.00798s ( +/- 0.39/ 0.27 %); best 0.007949s; worst 0.008002s; std dev. 2.264e-05 (taking best). -Reference operation time is 0.00794911 s (0.01812 Mflops) with 12 threads. -After merge step 3: tpop: 0.007949 s ~Mflops: 0.018 nsubm:7 otn:12 -Applying merge (10 -> 7 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00615x): 0.007998s -> 0.007949s, so IGNORING this instance. -Merge (7 -> 4 leaves) took w.c.t. of 7.868e-06s, ~3.099e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) -3 iterations (12 th.) took 0.02398s; avg 0.007993s ( +/- 0.09/ 0.11 %); best 0.007986s; worst 0.008002s; std dev. 6.591e-06 (taking best). +3 iterations (12 th.) took 0.024s; avg 0.008s ( +/- 0.07/ 0.04 %); best 0.007994s; worst 0.008003s; std dev. 4.065e-06 (taking best). +Reference operation time is 0.00799394 s (0.01801 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, 4.5000 bpnz (tpop: 0.007994 Mflops: 0.018) +Merge (16 -> 13 leaves) took w.c.t. of 1.502e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.02396s; avg 0.007985s ( +/- 0.39/ 0.21 %); best 0.007954s; worst 0.008002s; std dev. 2.19e-05 (taking best). +Reference operation time is 0.00795412 s (0.0181 Mflops) with 12 threads. +After merge step 1: tpop: 0.007954 s ~Mflops: 0.018 nsubm:13 otn:12 +Applying merge (16 -> 13 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00501x): 0.007994s -> 0.007954s, so IGNORING this instance. +Merge (13 -> 10 leaves) took w.c.t. of 1.812e-05s, ~5.96e-06s of computing time (of which 0s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.02386s; avg 0.007954s ( +/- 1.28/ 0.67 %); best 0.007852s; worst 0.008007s; std dev. 7.19e-05 (taking best). +Reference operation time is 0.00785208 s (0.01834 Mflops) with 12 threads. +After merge step 2: tpop: 0.007852 s ~Mflops: 0.018 nsubm:10 otn:12 +Applying merge (13 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.018x: 0.007994s -> 0.007852s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 1.287e-05s, ~4.053e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.02402s; avg 0.008008s ( +/- 0.28/ 0.50 %); best 0.007986s; worst 0.008048s; std dev. 2.817e-05 (taking best). Reference operation time is 0.00798607 s (0.01803 Mflops) with 12 threads. -After merge step 4: tpop: 0.007986 s ~Mflops: 0.018 nsubm:4 otn:12 -Applying merge (7 -> 4 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00149x): 0.007998s -> 0.007986s, so IGNORING this instance. -Merge (4 -> 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 9.537e-07s; avg 3.179e-07s ( +/- 85.48/200.00 %); best 4.615e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 4.61459e-08 s (3121 Mflops) with 12 threads. -After merge step 5: tpop: 4.615e-08 s ~Mflops: 3120.536 nsubm:1 otn:12 -Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 173319.556x: 0.007998s -> 4.615e-08s, so taking this instance. +After merge step 3: tpop: 0.007986 s ~Mflops: 0.018 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98322x): 0.007852s -> 0.007986s, so IGNORING this instance. +Merge (7 -> 4 leaves) took w.c.t. of 1.121e-05s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 0.02393s; avg 0.007978s ( +/- 0.53/ 0.37 %); best 0.007935s; worst 0.008007s; std dev. 3.08e-05 (taking best). +Reference operation time is 0.00793505 s (0.01815 Mflops) with 12 threads. +After merge step 4: tpop: 0.007935 s ~Mflops: 0.018 nsubm:4 otn:12 +Applying merge (7 -> 4 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=0.98954x): 0.007852s -> 0.007935s, so IGNORING this instance. +Merge (4 -> 1 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 2.861e-06s; avg 9.537e-07s ( +/- 94.83/100.00 %); best 4.93e-08s; worst 1.907e-06s; std dev. 7.787e-07 (taking best). +Reference operation time is 4.9305e-08 s (2921 Mflops) with 12 threads. +After merge step 5: tpop: 4.93e-08 s ~Mflops: 2920.599 nsubm:1 otn:12 +Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 159255.319x: 0.007852s -> 4.93e-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 0.12s (of which 7.296e-05s partitioning, 0s I/O); computing times: 1.717e-05s in par. loops, 2.861e-06s sorting, 9.775e-06s analyzing) -Total merge + benchmarking process took 0.12s, equivalent to 2600191.2/15.0 new/old ops (0.04795s for 2 clones -- as 1039095.8/6.0 ops, or 519547.9/3.0 ops per clone), SPEEDUP of 173319.556x -Applying multi-merge (16 -> 1 leaves, 5 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 173319.556x (0.007998s -> 4.615e-08s), will amortize in 15.0 ops by saving 0.007998s per op. -In 1 tuning rounds (tot. 0.17s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 17331855.6% (1.733e+05x) (from 0.018 to 3121 Mflops). -After 0.168013s, global autotuning declared speedup of 173320 x, when using threads count of 12 and a new matrix: -(6 x 6)[0x557a0f3f3e70]{S} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' +A total of 5 merge steps (of max 6) (16 -> 1 subms) took 0.144s (of which 8.392e-05s partitioning, 0s I/O); computing times: 2.217e-05s in par. loops, 2.861e-06s sorting, 1.812e-05s analyzing) +Total merge + benchmarking process took 0.144s, equivalent to 2920130.6/18.0 new/old ops (0.0719s for 3 clones -- as 1458370.4/9.0 ops, or 486123.5/3.0 ops per clone), SPEEDUP of 162132.495x +Applying multi-merge (16 -> 1 leaves, 5 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 162132.495x (0.007994s -> 4.93e-08s), will amortize in 18.0 ops by saving 0.007994s per op. +In 1 tuning rounds (tot. 0.19s, 0.072s for constructor, 3 clones) obtained a SPEEDUP of 16213149.5% (1.621e+05x) (from 0.01801 to 2921 Mflops). +After 0.192007s, global autotuning declared speedup of 162132 x, when using threads count of 12 and a new matrix: +(6 x 6)[0x55b137795ab0]{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 5.196e-02 s (100.00 %) - analyzed arrays in 1.996e-02 s (38.41 %) + converted COO to RSB in 4.795e-02 s (100.00 %) + analyzed arrays in 1.591e-02 s (33.19 %) cleaned-up arrays in 9.537e-07 s (0.00 %) deduplicated arrays in 0.000e+00 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (30.78 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.600e-02 s (30.78 %) -Built (6 x 6)[0x557a0f3f6a80]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' + shuffled partitions in 1.601e-02 s (33.39 %) + memory allocations took 2.122e-05 s (0.04 %) + leafs setup took 5.007e-06 s (0.01 %) + halfword conversion took 1.599e-02 s (33.35 %) +Built (6 x 6)[0x55b137795ab0]{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)[0x557a0f3f6a80]{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)[0x55b137795ab0]{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. +Will use autotuning routine to sample matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.2778 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.02396s; avg 0.007985s ( +/- 0.27/ 0.15 %); best 0.007964s; worst 0.007997s; std dev. 1.503e-05 (taking best). -Reference operation time is 0.00796413 s (0.07232 Mflops) with 12 threads. -After 0.023984s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.02395s; avg 0.007983s ( +/- 0.70/ 0.56 %); best 0.007927s; worst 0.008027s; std dev. 4.155e-05 (taking best). +Reference operation time is 0.00792718 s (0.07266 Mflops) with 12 threads. +After 0.024000s, 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. +Will autotune matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.2778 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.024s; avg 0.008001s ( +/- 0.04/ 0.08 %); best 0.007997s; worst 0.008007s; std dev. 4.401e-06 (taking best). -Reference operation time is 0.00799704 s (0.07203 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: 0.007997 Mflops: 0.072) -Merge (22 -> 16 leaves) took w.c.t. of 0.004143s, ~1.216e-05s of computing time (of which 0s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.03585s; avg 0.01195s ( +/- 0.97/ 0.50 %); best 0.01184s; worst 0.01201s; std dev. 8.173e-05 (taking best). -Reference operation time is 0.0118351 s (0.04867 Mflops) with 12 threads. -After merge step 1: tpop: 0.01184 s ~Mflops: 0.049 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.480x: 0.007997s -> 0.01184s. -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 0.04001s (of which 0.004147s partitioning, 0s I/O); computing times: 1.216e-05s in par. loops, 0s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.04001s, equivalent to 5.0/5.0 new/old ops (0.02397s for 1 clones -- as 3.0/3.0 ops, or 3.0/3.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.03198s; avg 0.01066s ( +/- 25.28/ 50.38 %); best 0.007965s; worst 0.01603s; std dev. 0.003798 (taking best). -Reference operation time is 0.00796509 s (0.07232 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: 0.007965 Mflops: 0.072) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.008017s (of which: 4.053e-06s analysis, -3.435e+09s mem.mgmt); compute time: 0.0001111s overall, 2.146e-06s searches, 0.000109s shuffle, 5.198e-05s switch, 3.815e-06s quadrants. -3 iterations (12 th.) took 0.03197s; avg 0.01066s ( +/- 24.90/ 12.59 %); best 0.008004s; worst 0.012s; std dev. 0.001876 (taking best). -Reference operation time is 0.00800395 s (0.07196 Mflops) with 12 threads. -After split step 1: tpop: 0.008004 s ~Mflops: 0.072 nsubm:28 otn:12 -Applying split (22 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99514x): 0.007965s -> 0.008004s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01199s (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 0.02399s; avg 0.007997s ( +/- 0.08/ 0.12 %); best 0.007991s; worst 0.008007s; std dev. 6.955e-06 (taking best). -Reference operation time is 0.00799108 s (0.07208 Mflops) with 12 threads. -After split step 2: tpop: 0.007991 s ~Mflops: 0.072 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=0.99675x): 0.007965s -> 0.007991s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01199s (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 0.02399s; avg 0.007998s ( +/- 0.05/ 0.07 %); best 0.007994s; worst 0.008004s; std dev. 4.305e-06 (taking best). -Reference operation time is 0.00799394 s (0.07205 Mflops) with 12 threads. -After split step 3: tpop: 0.007994 s ~Mflops: 0.072 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=0.99639x): 0.007965s -> 0.007994s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01199s (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 0.02798s; avg 0.009328s ( +/- 14.43/ 28.72 %); best 0.007982s; worst 0.01201s; std dev. 0.001894 (taking best). -Reference operation time is 0.00798178 s (0.07216 Mflops) with 12 threads. -After split step 4: tpop: 0.007982 s ~Mflops: 0.072 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=0.99791x): 0.007965s -> 0.007982s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01988s (of which: 3.099e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.04784s; avg 0.01595s ( +/- 24.69/ 48.83 %); best 0.01201s; worst 0.02373s; std dev. 0.005506 (taking best). -Reference operation time is 0.0120099 s (0.04796 Mflops) with 12 threads. -After split step 5: tpop: 0.01201 s ~Mflops: 0.048 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.508x: 0.007965s -> 0.01201s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 5 split steps (of max 6) (22 -> 28 subms) took 0.2198s (of which 0.06392s partitioning, 0s I/O); computing times: 0.0001111s in par. loops, 2.146e-06s sorting, 1.478e-05s analyzing) -Total split + benchmarking process took 0.2198s, equivalent to 27.6/27.6 new/old ops (0.03994s for 1 clones -- as 5.0/5.0 ops, or 5.0/5.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.38s, 0.064s for constructor, 2 clones) obtained NO speedup (best stays 0.07232 Mflops). -After 0.379787s, global autotuning found old matrix optimal, with declared speedup 1 x when using 12 threads +3 iterations (12 th.) took 0.02404s; avg 0.008013s ( +/- 0.32/ 0.44 %); best 0.007987s; worst 0.008048s; std dev. 2.573e-05 (taking best). +Reference operation time is 0.00798702 s (0.07212 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, 4.2778 bpnz (tpop: 0.007987 Mflops: 0.072) +Merge (22 -> 19 leaves) took w.c.t. of 1.311e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.02394s; avg 0.007979s ( +/- 0.57/ 0.32 %); best 0.007933s; worst 0.008004s; std dev. 3.227e-05 (taking best). +Reference operation time is 0.00793314 s (0.07261 Mflops) with 12 threads. +After merge step 1: tpop: 0.007933 s ~Mflops: 0.073 nsubm:19 otn:12 +Applying merge (22 -> 19 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00679x): 0.007987s -> 0.007933s, so IGNORING this instance. +Merge (19 -> 16 leaves) took w.c.t. of 9.775e-06s, ~1.907e-06s of computing time (of which 0s sorting, 3.815e-06s analysis) +3 iterations (12 th.) took 0.03197s; avg 0.01066s ( +/- 30.89/ 50.06 %); best 0.007365s; worst 0.01599s; std dev. 0.003807 (taking best). +Reference operation time is 0.00736499 s (0.07821 Mflops) with 12 threads. +After merge step 2: tpop: 0.007365 s ~Mflops: 0.078 nsubm:16 otn:12 +Applying merge (19 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.084x: 0.007987s -> 0.007365s, so taking this instance. +Merge (16 -> 13 leaves) took w.c.t. of 1.383e-05s, ~4.053e-06s of computing time (of which 1.192e-06s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.024s; avg 0.007999s ( +/- 0.25/ 0.21 %); best 0.007979s; worst 0.008016s; std dev. 1.525e-05 (taking best). +Reference operation time is 0.00797892 s (0.07219 Mflops) with 12 threads. +After merge step 3: tpop: 0.007979 s ~Mflops: 0.072 nsubm:13 otn:12 +Applying merge (16 -> 13 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.083x: 0.007365s -> 0.007979s. +Merge (13 -> 10 leaves) took w.c.t. of 1.097e-05s, ~4.053e-06s of computing time (of which 0s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 0.03592s; avg 0.01197s ( +/- 0.23/ 0.18 %); best 0.01195s; worst 0.01199s; std dev. 2.027e-05 (taking best). +Reference operation time is 0.011945 s (0.04822 Mflops) with 12 threads. +After merge step 4: tpop: 0.01195 s ~Mflops: 0.048 nsubm:10 otn:12 +Applying merge (13 -> 10 leaves, 12 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.622x: 0.007365s -> 0.01195s. +Skipping further merge based tests after 2 definite performance degradations in a row (and last exceeding limit). +A total of 4 merge steps (of max 6) (22 -> 10 subms) took 0.1479s (of which 5.507e-05s partitioning, 0s I/O); computing times: 1.407e-05s in par. loops, 2.146e-06s sorting, 1.311e-05s analyzing) +Total merge + benchmarking process took 0.1479s, equivalent to 20.1/18.5 new/old ops (0.05594s for 2 clones -- as 7.6/7.0 ops, or 3.8/3.5 ops per clone), SPEEDUP of 1.084x +Applying multi-merge (22 -> 16 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.084x (0.007987s -> 0.007365s), will amortize in 237.8 ops by saving 0.000622s per op. +In 1 tuning rounds (tot. 0.2s, 0.056s for constructor, 2 clones) obtained a SPEEDUP of 8.4% (1.084x) (from 0.07212 to 0.07821 Mflops). +After 0.195989s, global autotuning declared speedup of 1.08446 x, when using threads count of 12 and a new matrix: +(6 x 6)[0x55b13778faa0]{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: 16, symflags:'' Considering Z clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 8.416e-02 s (100.00 %) - analyzed arrays in 2.817e-02 s (33.47 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) + converted COO to RSB in 4.825e-02 s (100.00 %) + analyzed arrays in 1.594e-02 s (33.03 %) + cleaned-up arrays in 1.192e-06 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.150e-02 s (37.43 %) - memory allocations took 6.914e-06 s (0.01 %) - leafs setup took 2.861e-06 s (0.00 %) - halfword conversion took 2.448e-02 s (29.08 %) -Built (6 x 6)[0x557a0f3f6a80]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' + shuffled partitions in 1.601e-02 s (33.19 %) + memory allocations took 3.815e-06 s (0.01 %) + leafs setup took 4.053e-06 s (0.01 %) + halfword conversion took 1.628e-02 s (33.75 %) +Built (6 x 6)[0x55b137795ab0]{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)[0x557a0f3f6a80]{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)[0x55b137795ab0]{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 0.03597s; avg 0.01199s ( +/- 0.20/ 0.11 %); best 0.01197s; worst 0.012s; std dev. 1.72e-05 (taking best). -Reference operation time is 0.011966 s (0.04814 Mflops) with 12 threads. -After 0.035991s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.02889s; avg 0.009631s ( +/- 20.46/ 16.52 %); best 0.00766s; worst 0.01122s; std dev. 0.001479 (taking best). +Reference operation time is 0.00766015 s (0.07519 Mflops) with 12 threads. +After 0.028922s, 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 0.01679s; avg 0.005596s ( +/- 97.52/184.59 %); best 0.000139s; worst 0.01593s; std dev. 0.007309 (taking best). -Reference operation time is 0.000138998 s (4.144 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: 0.000139 Mflops: 4.144) -Merge (28 -> 22 leaves) took w.c.t. of 1.478e-05s, ~8.106e-06s of computing time (of which 2.146e-06s sorting, 2.861e-06s analysis) -3 iterations (12 th.) took 0.03924s; avg 0.01308s ( +/- 13.72/ 21.53 %); best 0.01129s; worst 0.0159s; std dev. 0.002016 (taking best). -Reference operation time is 0.0112851 s (0.05104 Mflops) with 12 threads. -After merge step 1: tpop: 0.01129 s ~Mflops: 0.051 nsubm:22 otn:12 -Applying merge (28 -> 22 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 81.189x: 0.000139s -> 0.01129s. +3 iterations (12 th.) took 0.02797s; avg 0.009323s ( +/- 14.22/ 28.42 %); best 0.007997s; worst 0.01197s; std dev. 0.001873 (taking best). +Reference operation time is 0.00799704 s (0.07203 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: 0.007997 Mflops: 0.072) +Merge (28 -> 22 leaves) took w.c.t. of 0.000119s, ~1.287e-05s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.03205s; avg 0.01068s ( +/- 30.17/ 49.68 %); best 0.00746s; worst 0.01599s; std dev. 0.003781 (taking best). +Reference operation time is 0.00746012 s (0.07721 Mflops) with 12 threads. +After merge step 1: tpop: 0.00746 s ~Mflops: 0.077 nsubm:22 otn:12 +Applying merge (28 -> 22 leaves, 12 th.) yielded SPEEDUP of 1.072x: 0.007997s -> 0.00746s, so taking this instance. +Merge (22 -> 16 leaves) took w.c.t. of 0.004191s, ~5.627e-05s of computing time (of which 3.815e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.02386s; avg 0.007954s ( +/- 19.54/ 17.56 %); best 0.0064s; worst 0.00935s; std dev. 0.00121 (taking best). +Reference operation time is 0.00639987 s (0.09 Mflops) with 12 threads. +After merge step 2: tpop: 0.0064 s ~Mflops: 0.090 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.166x: 0.00746s -> 0.0064s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.004138s, ~2.694e-05s of computing time (of which 8.106e-06s sorting, 3.815e-06s analysis) +3 iterations (12 th.) took 0.04782s; avg 0.01594s ( +/- 0.71/ 0.39 %); best 0.01583s; worst 0.016s; std dev. 8.055e-05 (taking best). +Reference operation time is 0.0158269 s (0.03639 Mflops) with 12 threads. +After merge step 3: tpop: 0.01583 s ~Mflops: 0.036 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.473x: 0.0064s -> 0.01583s. 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 0.03927s (of which 1.597e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 2.146e-06s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.03927s, equivalent to 282.5/282.5 new/old ops (0.04786s for 1 clones -- as 344.3/344.3 ops, or 344.3/344.3 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 0.03999s; avg 0.01333s ( +/- 9.99/ 18.93 %); best 0.012s; worst 0.01585s; std dev. 0.001785 (taking best). -Reference operation time is 0.0119989 s (0.048 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: 0.012 Mflops: 0.048) -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.02002s (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 0.03603s; avg 0.01201s ( +/- 1.06/ 0.57 %); best 0.01188s; worst 0.01208s; std dev. 9.027e-05 (taking best). -Reference operation time is 0.0118811 s (0.04848 Mflops) with 12 threads. -After split step 1: tpop: 0.01188 s ~Mflops: 0.048 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00991x): 0.012s -> 0.01188s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01999s (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 0.03605s; avg 0.01202s ( +/- 0.16/ 0.28 %); best 0.012s; worst 0.01205s; std dev. 2.352e-05 (taking best). -Reference operation time is 0.0119979 s (0.04801 Mflops) with 12 threads. -After split step 2: tpop: 0.012 s ~Mflops: 0.048 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00008x): 0.012s -> 0.012s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01988s (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 0.04351s; avg 0.0145s ( +/- 16.52/ 8.33 %); best 0.01211s; worst 0.01571s; std dev. 0.001694 (taking best). -Reference operation time is 0.0121071 s (0.04758 Mflops) with 12 threads. -After split step 3: tpop: 0.01211 s ~Mflops: 0.048 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=0.99106x): 0.012s -> 0.01211s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01659s (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 0.02399s; avg 0.007998s ( +/- 0.19/ 0.25 %); best 0.007983s; worst 0.008018s; std dev. 1.474e-05 (taking best). -Reference operation time is 0.00798297 s (0.07215 Mflops) with 12 threads. -After split step 4: tpop: 0.007983 s ~Mflops: 0.072 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.503x: 0.012s -> 0.007983s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01198s (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 0.02398s; avg 0.007993s ( +/- 0.16/ 0.09 %); best 0.00798s; worst 0.008s; std dev. 8.913e-06 (taking best). -Reference operation time is 0.00798011 s (0.07218 Mflops) with 12 threads. -After split step 5: tpop: 0.00798 s ~Mflops: 0.072 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00036x): 0.007983s -> 0.00798s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.012s (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 0.02398s; avg 0.007992s ( +/- 0.20/ 0.14 %); best 0.007976s; worst 0.008003s; std dev. 1.152e-05 (taking best). -Reference operation time is 0.00797606 s (0.07222 Mflops) with 12 threads. -After split step 6: tpop: 0.007976 s ~Mflops: 0.072 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00087x): 0.007983s -> 0.007976s, so IGNORING this instance. -A total of 6 split steps (of max 6) (28 -> 28 subms) took 0.3122s (of which 0.1006s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.335e-05s analyzing) -Total split + benchmarking process took 0.3122s, equivalent to 39.1/26.0 new/old ops (0.05988s for 2 clones -- as 7.5/5.0 ops, or 3.8/2.5 ops per clone), SPEEDUP of 1.503x -Applying multi-split (28 -> 28 leaves, 4 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.503x (0.012s -> 0.007983s), will amortize in 77.7 ops by saving 0.004016s per op. -In 1 tuning rounds (tot. 0.49s, 0.11s for constructor, 3 clones) obtained a SPEEDUP of 50.3% (1.503x) (from 0.048 to 0.07215 Mflops). -After 0.492039s, global autotuning declared speedup of 1.50306 x, when using threads count of 12 and a new matrix: -(6 x 6)[0x557a0f3fa1d0]{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 3 merge steps (of max 6) (28 -> 10 subms) took 0.164s (of which 0.008471s partitioning, 0s I/O); computing times: 9.608e-05s in par. loops, 1.383e-05s sorting, 1.287e-05s analyzing) +Total merge + benchmarking process took 0.164s, equivalent to 25.6/20.5 new/old ops (0.07847s for 3 clones -- as 12.3/9.8 ops, or 4.1/3.3 ops per clone), SPEEDUP of 1.250x +Applying multi-merge (28 -> 16 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.250x (0.007997s -> 0.0064s), will amortize in 102.7 ops by saving 0.001597s per op. +In 1 tuning rounds (tot. 0.22s, 0.078s for constructor, 3 clones) obtained a SPEEDUP of 25.0% (1.25x) (from 0.07203 to 0.09 Mflops). +After 0.218887s, global autotuning declared speedup of 1.24956 x, when using threads count of 12 and a new matrix: +(6 x 6)[0x55b13779b960]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' 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' @@ -9269,9 +9273,9 @@ 4 0 DIFF PRINT TEST END Beginning large binary search test. -Detected 25215512576 bytes of memory, comprehensive of 18600169472 of free memory. +Detected 25208029184 bytes of memory, comprehensive of 15261745152 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 (17592186041335 MB) than on the maximal coordinate indices array (18446744070479809536) allows. +Will perform the test using less memory (17592186038948 MB) than on the maximal coordinate indices array (18446744067975991296) allows. Skipping test: too little memory. Skipping large binary search test. BASIC SPARSE BLAS TEST: BEGIN @@ -9280,7 +9284,7 @@ got RSB_IO_WANT_IS_INITIALIZED_MARKER: 1 INIT INTERFACE TEST: END (SUCCESS) DEVEL PRINT TEST: BEGIN -(4 x 4)[0x5640eef943a0]{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)[0x561fd22253a0]{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 +9293,8 @@ RSB_FLAG_ASSEMBLED_IN_COO_ARRAYS | RSB_FLAG_OWN_PARTITIONING_ARRAYS | RSB_FLAG_SORT_INPUT -(2 x 2)[0x5640eef944b0]{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)[0x5640eef945c0]{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)[0x561fd22254b0]{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)[0x561fd22255c0]{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%) @@ -9298,9 +9302,9 @@ ( 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)[0x5640eef944b0]{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)[0x5640eef945c0]{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)[0x5640eef943a0]{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)[0x561fd22254b0]{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)[0x561fd22255c0]{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)[0x561fd22253a0]{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 | @@ -9318,8 +9322,8 @@ 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 30.017924 s, max allowed was 30.000000. - PASSED:19781 +Terminating testing earlier due to user timeout request: test took 30.011966 s, max allowed was 30.000000. + PASSED:4238 FAILED:0 ADVANCED SPARSE BLAS TEST: END (SUCCESS) gmake qtests -C librsbpp @@ -9328,7 +9332,7 @@ gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' ./rsbtt -if ! test -f G.mtx ; then cp -p /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/G.mtx . ; fi ; /bin/bash /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/test.sh +if ! test -f G.mtx ; then cp -p /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/G.mtx . ; fi ; /bin/sh /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/test.sh ++ ./rsbpp Td,s G.mtx ++ grep Z-sort ++ wc -l @@ -9401,8 +9405,8 @@ ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF -++ wc -l ++ grep Recursing +++ wc -l + test 4 = 4 ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 @@ -9467,7 +9471,7 @@ 0 0 0 0 before tuning for SPMV: -(3 x 3)[0x55e200c2dd30]{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)[0x5615c4f78640]{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 @@ -9556,18 +9560,18 @@ BEGIN Rsb_Matrix_test_multimatrix_ms_mnrhs BEGIN -(3 x 3)[0x55e200c5dd40]{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 1.3125: -(3 x 3)[0x55e200c5e560]{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)[0x55e200c5dd40]{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 1.1831: -(3 x 3)[0x55e200c5e560]{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)[0x55e200c5dd40]{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)[0x5615c4fa3440]{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)[0x5615c4fa3440]{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)[0x5615c4fa58c0]{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 1.10698: +(3 x 3)[0x5615c4faef30]{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)[0x5615c4fa3440]{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 1.11579: +(3 x 3)[0x5615c4faef30]{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)[0x5615c4fa3440]{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)[0x55e200c5dd40]{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)[0x55e200c48410]{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 1.1: -(3 x 3)[0x55e200c5e560]{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)[0x5615c4fa3440]{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 ! @@ -9584,10 +9588,10 @@ ./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 infom01-amd64 +running on i-capture-the-hostname Built without the MKL. ( ! ./rsbtest --unrecognized-option-triggers-abort ) -running on infom01-amd64 +running on i-capture-the-hostname /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest/.libs/rsbtest: unrecognized option '--unrecognized-option-triggers-abort' unrecognized option, aborting. ( ./rsbtest --no-tune --max_t 0.01 --skip-loading-hermitian-matrices --skip-loading-unsymmetric-matrices --tune-maxt 10 --tune-maxr 10 --verbose-tuning --extra-verbose-interface --min_t 0.01 --max_t 0.01 --mintimes 1 --maxtimes 1 --verbose --skip-loading-symmetric-matrices A.mtx | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q skip ) @@ -9596,7 +9600,7 @@ ( ! ./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 infom01-amd64 +running on i-capture-the-hostname Will not invoke autotuning routine. Benchmark will sample for at most 0.01 s Built without render support! @@ -9648,7 +9652,7 @@ gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' /usr/bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu' - /bin/bash ./libtool --mode=install /usr/bin/install -c librsb.la '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu' + /bin/sh ./libtool --mode=install /usr/bin/install -c librsb.la '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu' libtool: install: /usr/bin/install -c .libs/librsb.so.0.0.0 /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu/librsb.so.0.0.0 libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu && { ln -s -f librsb.so.0.0.0 librsb.so.0 || { rm -f librsb.so.0 && ln -s librsb.so.0.0.0 librsb.so.0; }; }) libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu && { ln -s -f librsb.so.0.0.0 librsb.so || { rm -f librsb.so && ln -s librsb.so.0.0.0 librsb.so; }; }) @@ -9658,7 +9662,7 @@ libtool: install: ranlib /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu/librsb.a libtool: warning: remember to run 'libtool --finish /usr/lib/x86_64-linux-gnu' /usr/bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' - /bin/bash ./libtool --mode=install /usr/bin/install -c rsbench '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' + /bin/sh ./libtool --mode=install /usr/bin/install -c rsbench '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' libtool: warning: 'librsb.la' has not been installed in '/usr/lib/x86_64-linux-gnu' libtool: install: /usr/bin/install -c .libs/rsbench /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin/rsbench /usr/bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' @@ -9785,12 +9789,12 @@ dh_gencontrol dh_md5sums dh_builddeb -dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-6.1_amd64.deb'. -dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-6.1_amd64.deb'. -dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-6.1_amd64.deb'. +dpkg-deb: building package 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-6.1_all.deb'. dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-6.1_amd64.deb'. dpkg-deb: building package 'librsb0t64' in '../librsb0t64_1.3.0.2+dfsg-6.1_amd64.deb'. -dpkg-deb: building package 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-6.1_all.deb'. +dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-6.1_amd64.deb'. +dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-6.1_amd64.deb'. +dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-6.1_amd64.deb'. dpkg-genbuildinfo --build=binary -O../librsb_1.3.0.2+dfsg-6.1_amd64.buildinfo dpkg-genchanges --build=binary -O../librsb_1.3.0.2+dfsg-6.1_amd64.changes dpkg-genchanges: info: binary-only upload (no source code included) @@ -9799,12 +9803,14 @@ 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/2972863/tmp/hooks/B01_cleanup starting +I: user script /srv/workspace/pbuilder/2972863/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/3725028 and its subdirectories -I: Current time: Thu Jun 6 20:28:15 -12 2024 -I: pbuilder-time-stamp: 1717748895 +I: removing directory /srv/workspace/pbuilder/2972863 and its subdirectories +I: Current time: Fri Jul 11 05:17:50 +14 2025 +I: pbuilder-time-stamp: 1752160670