[Touch-packages] [Bug 1691848] Re: Python not compiled with -fexceptions in ppc64le
What about Python v2.7? -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to python2.7 in Ubuntu. https://bugs.launchpad.net/bugs/1691848 Title: Python not compiled with -fexceptions in ppc64le Status in python2.7 package in Ubuntu: New Status in python3.6 package in Ubuntu: Fix Released Bug description: Pytorch (https://github.com/pytorch/pytorch) is an application that is written in python, C and C++. There's high interoperalibity between code written in these languages therex. The issue is that there are cases when an exception is thrown by C++ code that subsequentely calls some C code before being caught. In ppc64le builds, without the -fexceptions gcc flag, such exceptions are not caught when the execution returns to C++ code from C code. This makes some Pytorch tests fail. Compiling CPython with -fexceptions seems to solve this issue. This was also reported to Debian: https://bugs.debian.org/cgi- bin/bugreport.cgi?bug=862925 ProblemType: Bug DistroRelease: Ubuntu 17.04 Package: python2.7 2.7.13-2 ProcVersionSignature: Ubuntu 4.10.0-19.21-generic 4.10.8 Uname: Linux 4.10.0-19-generic ppc64le .var.log.platform: Error: [Errno 13] Permission denied: '/var/log/platform' ApportVersion: 2.20.4-0ubuntu4 Architecture: ppc64el Date: Thu May 18 15:35:54 2017 InstallationDate: Installed on 2015-11-05 (560 days ago) InstallationMedia: Ubuntu-Server 15.04 "Vivid Vervet" - Release ppc64el (20150422) JournalErrors: Error: command ['journalctl', '-b', '--priority=warning', '--lines=1000'] failed with exit code 1: Hint: You are currently not seeing messages from other users and the system. Users in the 'systemd-journal' group can see all messages. Pass -q to turn off this notice. No journal files were opened due to insufficient permissions. ProcLoadAvg: 0.07 0.33 0.43 1/348 20166 ProcSwaps: Filename TypeSizeUsed Priority ProcVersion: Linux version 4.10.0-19-generic (buildd@bos01-ppc64el-009) (gcc version 6.3.0 20170321 (Ubuntu 6.3.0-10ubuntu1) ) #21-Ubuntu SMP Thu Apr 6 17:03:05 UTC 2017 SourcePackage: python2.7 UpgradeStatus: Upgraded to zesty on 2017-04-17 (30 days ago) cpu_cores: Number of cores present = 2 cpu_coreson: Number of cores online = 2 cpu_smt: SMT=8 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/python2.7/+bug/1691848/+subscriptions -- Mailing list: https://launchpad.net/~touch-packages Post to : touch-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~touch-packages More help : https://help.launchpad.net/ListHelp
[Touch-packages] [Bug 1667407] Re: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
@doko I already added the verification-done-xenial tag so I guess that's all that's needed to do, right? ** Tags removed: verification-done -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to coreutils in Ubuntu. https://bugs.launchpad.net/bugs/1667407 Title: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug Status in coreutils package in Ubuntu: Fix Released Status in coreutils source package in Xenial: Fix Committed Status in coreutils source package in Yakkety: Fix Released Status in coreutils package in Debian: Fix Released Bug description: [Impact] * Performance drop of 2x-3x on ppc64le when using sha256sum * Please backport this bug to last LTS as this application is widely used. * This fix is due to a optimization issue found on gcc v4.9 to gcc v7.0. [Test Case] * Run sha256sum with a big file and measure the time it takes. The patch improves this timing up to 3 times faster. [Regression Potential] * This patch is specifically for the sha256.o object, affecting only this binary. [Other Info] Michael Stone's improved patch: Index: coreutils-8.26/Makefile.in === --- coreutils-8.26.orig/Makefile.in 2016-11-30 13:34:55.0 -0500 +++ coreutils-8.26/Makefile.in 2017-02-22 07:18:55.352394058 -0500 @@ -14661,6 +14661,10 @@ $(TEST_LOGS): $(PROGRAMS) +ifeq ($(DEB_TARGET_ARCH), ppc64el) +lib/sha256.o: CFLAGS+=-fno-schedule-insns +endif + # Tell versions [3.59,3.63) of GNU make to not export all variables. # Otherwise a system limit (for SysV at least) may be exceeded. .NOEXPORT: Original bug description: The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m18.670s user0m16.566s sys 0m0.745s $ # now with the following patch: ## Check Michael Stone's patch for an improved version. $ diff Makefile.in ../Makefile.in 8989c8989 < @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ --- > @am__fastdepCC_TRUE@ $(COMPILE) $$([ "$@" == "lib/sha256.o" ] && echo "-fno-schedule-insns") -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ $ cp ../Makefile.in Makefile.in $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user':
[Touch-packages] [Bug 1667407] Re: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
Tested on xenial (16.04). Test input of 465MB took 4.5s (version 8.25-2ubuntu3~16.04) instead of 15.1s (version 8.25-2ubuntu2). Thanks ** Tags removed: removal-candidate ** Tags added: verification-done-xenial -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to coreutils in Ubuntu. https://bugs.launchpad.net/bugs/1667407 Title: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug Status in coreutils package in Ubuntu: Fix Released Status in coreutils source package in Xenial: Fix Committed Status in coreutils source package in Yakkety: Fix Released Status in coreutils package in Debian: Fix Released Bug description: [Impact] * Performance drop of 2x-3x on ppc64le when using sha256sum * Please backport this bug to last LTS as this application is widely used. * This fix is due to a optimization issue found on gcc v4.9 to gcc v7.0. [Test Case] * Run sha256sum with a big file and measure the time it takes. The patch improves this timing up to 3 times faster. [Regression Potential] * This patch is specifically for the sha256.o object, affecting only this binary. [Other Info] Michael Stone's improved patch: Index: coreutils-8.26/Makefile.in === --- coreutils-8.26.orig/Makefile.in 2016-11-30 13:34:55.0 -0500 +++ coreutils-8.26/Makefile.in 2017-02-22 07:18:55.352394058 -0500 @@ -14661,6 +14661,10 @@ $(TEST_LOGS): $(PROGRAMS) +ifeq ($(DEB_TARGET_ARCH), ppc64el) +lib/sha256.o: CFLAGS+=-fno-schedule-insns +endif + # Tell versions [3.59,3.63) of GNU make to not export all variables. # Otherwise a system limit (for SysV at least) may be exceeded. .NOEXPORT: Original bug description: The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m18.670s user0m16.566s sys 0m0.745s $ # now with the following patch: ## Check Michael Stone's patch for an improved version. $ diff Makefile.in ../Makefile.in 8989c8989 < @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ --- > @am__fastdepCC_TRUE@ $(COMPILE) $$([ "$@" == "lib/sha256.o" ] && echo "-fno-schedule-insns") -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ $ cp ../Makefile.in Makefile.in $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built
[Touch-packages] [Bug 1667407] Re: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
Is that all? Please point out if I missed something. -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to coreutils in Ubuntu. https://bugs.launchpad.net/bugs/1667407 Title: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug Status in coreutils package in Ubuntu: Fix Released Status in coreutils source package in Xenial: Fix Committed Status in coreutils source package in Yakkety: Fix Released Status in coreutils package in Debian: Fix Released Bug description: [Impact] * Performance drop of 2x-3x on ppc64le when using sha256sum * Please backport this bug to last LTS as this application is widely used. * This fix is due to a optimization issue found on gcc v4.9 to gcc v7.0. [Test Case] * Run sha256sum with a big file and measure the time it takes. The patch improves this timing up to 3 times faster. [Regression Potential] * This patch is specifically for the sha256.o object, affecting only this binary. [Other Info] Michael Stone's improved patch: Index: coreutils-8.26/Makefile.in === --- coreutils-8.26.orig/Makefile.in 2016-11-30 13:34:55.0 -0500 +++ coreutils-8.26/Makefile.in 2017-02-22 07:18:55.352394058 -0500 @@ -14661,6 +14661,10 @@ $(TEST_LOGS): $(PROGRAMS) +ifeq ($(DEB_TARGET_ARCH), ppc64el) +lib/sha256.o: CFLAGS+=-fno-schedule-insns +endif + # Tell versions [3.59,3.63) of GNU make to not export all variables. # Otherwise a system limit (for SysV at least) may be exceeded. .NOEXPORT: Original bug description: The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m18.670s user0m16.566s sys 0m0.745s $ # now with the following patch: ## Check Michael Stone's patch for an improved version. $ diff Makefile.in ../Makefile.in 8989c8989 < @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ --- > @am__fastdepCC_TRUE@ $(COMPILE) $$([ "$@" == "lib/sha256.o" ] && echo "-fno-schedule-insns") -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ $ cp ../Makefile.in Makefile.in $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type
[Touch-packages] [Bug 1667407] Re: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
Hi, is there anything else I can do in order to have the 8.25-2ubuntu3 on yakkety? (not on proposed) -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to coreutils in Ubuntu. https://bugs.launchpad.net/bugs/1667407 Title: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug Status in coreutils package in Ubuntu: Fix Released Status in coreutils source package in Xenial: Fix Committed Status in coreutils source package in Yakkety: Fix Committed Status in coreutils package in Debian: Fix Released Bug description: [Impact] * Performance drop of 2x-3x on ppc64le when using sha256sum * Please backport this bug to last LTS as this application is widely used. * This fix is due to a optimization issue found on gcc v4.9 to gcc v7.0. [Test Case] * Run sha256sum with a big file and measure the time it takes. The patch improves this timing up to 3 times faster. [Regression Potential] * This patch is specifically for the sha256.o object, affecting only this binary. [Other Info] Michael Stone's improved patch: Index: coreutils-8.26/Makefile.in === --- coreutils-8.26.orig/Makefile.in 2016-11-30 13:34:55.0 -0500 +++ coreutils-8.26/Makefile.in 2017-02-22 07:18:55.352394058 -0500 @@ -14661,6 +14661,10 @@ $(TEST_LOGS): $(PROGRAMS) +ifeq ($(DEB_TARGET_ARCH), ppc64el) +lib/sha256.o: CFLAGS+=-fno-schedule-insns +endif + # Tell versions [3.59,3.63) of GNU make to not export all variables. # Otherwise a system limit (for SysV at least) may be exceeded. .NOEXPORT: Original bug description: The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m18.670s user0m16.566s sys 0m0.745s $ # now with the following patch: ## Check Michael Stone's patch for an improved version. $ diff Makefile.in ../Makefile.in 8989c8989 < @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ --- > @am__fastdepCC_TRUE@ $(COMPILE) $$([ "$@" == "lib/sha256.o" ] && echo "-fno-schedule-insns") -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ $ cp ../Makefile.in Makefile.in $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization
[Touch-packages] [Bug 1667407] Re: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
just to give an idea, to verify the sha256 of ubuntu-16.10-server- ppc64el.iso: 8.25-2ubuntu2 : 0m15.204s 8.25-2ubuntu3~16.10: 0m4.952s great! ** Tags removed: verification-needed ** Tags added: verification-done -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to coreutils in Ubuntu. https://bugs.launchpad.net/bugs/1667407 Title: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug Status in coreutils package in Ubuntu: Fix Released Status in coreutils source package in Xenial: Fix Committed Status in coreutils source package in Yakkety: Fix Committed Status in coreutils package in Debian: Fix Released Bug description: [Impact] * Performance drop of 2x-3x on ppc64le when using sha256sum * Please backport this bug to last LTS as this application is widely used. * This fix is due to a optimization issue found on gcc v4.9 to gcc v7.0. [Test Case] * Run sha256sum with a big file and measure the time it takes. The patch improves this timing up to 3 times faster. [Regression Potential] * This patch is specifically for the sha256.o object, affecting only this binary. [Other Info] Michael Stone's improved patch: Index: coreutils-8.26/Makefile.in === --- coreutils-8.26.orig/Makefile.in 2016-11-30 13:34:55.0 -0500 +++ coreutils-8.26/Makefile.in 2017-02-22 07:18:55.352394058 -0500 @@ -14661,6 +14661,10 @@ $(TEST_LOGS): $(PROGRAMS) +ifeq ($(DEB_TARGET_ARCH), ppc64el) +lib/sha256.o: CFLAGS+=-fno-schedule-insns +endif + # Tell versions [3.59,3.63) of GNU make to not export all variables. # Otherwise a system limit (for SysV at least) may be exceeded. .NOEXPORT: Original bug description: The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m18.670s user0m16.566s sys 0m0.745s $ # now with the following patch: ## Check Michael Stone's patch for an improved version. $ diff Makefile.in ../Makefile.in 8989c8989 < @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ --- > @am__fastdepCC_TRUE@ $(COMPILE) $$([ "$@" == "lib/sha256.o" ] && echo "-fno-schedule-insns") -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ $ cp ../Makefile.in Makefile.in $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will
[Touch-packages] [Bug 1667407] Re: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
Fix verified on coreutils_8.25-2ubuntu3~16.10_ppc64el.deb -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to coreutils in Ubuntu. https://bugs.launchpad.net/bugs/1667407 Title: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug Status in coreutils package in Ubuntu: Fix Released Status in coreutils source package in Xenial: Fix Committed Status in coreutils source package in Yakkety: Fix Committed Status in coreutils package in Debian: Fix Released Bug description: [Impact] * Performance drop of 2x-3x on ppc64le when using sha256sum * Please backport this bug to last LTS as this application is widely used. * This fix is due to a optimization issue found on gcc v4.9 to gcc v7.0. [Test Case] * Run sha256sum with a big file and measure the time it takes. The patch improves this timing up to 3 times faster. [Regression Potential] * This patch is specifically for the sha256.o object, affecting only this binary. [Other Info] Michael Stone's improved patch: Index: coreutils-8.26/Makefile.in === --- coreutils-8.26.orig/Makefile.in 2016-11-30 13:34:55.0 -0500 +++ coreutils-8.26/Makefile.in 2017-02-22 07:18:55.352394058 -0500 @@ -14661,6 +14661,10 @@ $(TEST_LOGS): $(PROGRAMS) +ifeq ($(DEB_TARGET_ARCH), ppc64el) +lib/sha256.o: CFLAGS+=-fno-schedule-insns +endif + # Tell versions [3.59,3.63) of GNU make to not export all variables. # Otherwise a system limit (for SysV at least) may be exceeded. .NOEXPORT: Original bug description: The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m18.670s user0m16.566s sys 0m0.745s $ # now with the following patch: ## Check Michael Stone's patch for an improved version. $ diff Makefile.in ../Makefile.in 8989c8989 < @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ --- > @am__fastdepCC_TRUE@ $(COMPILE) $$([ "$@" == "lib/sha256.o" ] && echo "-fno-schedule-insns") -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ $ cp ../Makefile.in Makefile.in $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target
Re: [Touch-packages] [Bug 1667407] Re: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
> -Original Message- > From: boun...@canonical.com [mailto:boun...@canonical.com] On Behalf Of > Lukasz Zemczak > Sent: quinta-feira, 2 de março de 2017 10:31 > To: Gustavo Serra Scalet <gustavo.sca...@eldorado.org.br> > Subject: [Bug 1667407] Re: improve 2x-3x sha256sum performance on > ppc64le due to current gcc optimization bug > > Could we get the bug details updated to follow the SRU template? Done > Also, checking the SRU upload, one thing I don't particularly like is > that the attached patch has no description. Yes, the change is self- > explanatory, but some context in patch descriptions is always welcome. > Won't block on that though as I see some of the existing patches in the > package have empty 'Description:' fields anyway... Then I'd add to Michael Stone's patch: diff --git i/Makefile.in w/Makefile.in index bdf9a43..7a43897 100644 --- i/Makefile.in +++ w/Makefile.in @@ -14434,6 +14434,13 @@ $(factor_tests): $(tf)/run.sh $(tf)/create-test.sh $(TEST_LOGS): $(PROGRAMS) +# REMOVE THIS HANDLING FOR PPC64 IF GCC > 7.0 IS USED +# Shutting off -fschedule-insns optimization due to huge performance drop +# (around 2 to 3 times). +ifeq ($(DEB_TARGET_ARCH), ppc64el) +lib/sha256.o: CFLAGS+=-fno-schedule-insns +endif + # Tell versions [3.59,3.63) of GNU make to not export all variables. # Otherwise a system limit (for SysV at least) may be exceeded. .NOEXPORT: -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to coreutils in Ubuntu. https://bugs.launchpad.net/bugs/1667407 Title: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug Status in coreutils package in Ubuntu: Fix Released Status in coreutils source package in Xenial: New Status in coreutils source package in Yakkety: New Status in coreutils package in Debian: Fix Released Bug description: [Impact] * Performance drop of 2x-3x on ppc64le when using sha256sum * Please backport this bug to last LTS as this application is widely used. * This fix is due to a optimization issue found on gcc v4.9 to gcc v7.0. [Test Case] * Run sha256sum with a big file and measure the time it takes. The patch improves this timing up to 3 times faster. [Regression Potential] * This patch is specifically for the sha256.o object, affecting only this binary. [Other Info] Michael Stone's improved patch: Index: coreutils-8.26/Makefile.in === --- coreutils-8.26.orig/Makefile.in 2016-11-30 13:34:55.0 -0500 +++ coreutils-8.26/Makefile.in 2017-02-22 07:18:55.352394058 -0500 @@ -14661,6 +14661,10 @@ $(TEST_LOGS): $(PROGRAMS) +ifeq ($(DEB_TARGET_ARCH), ppc64el) +lib/sha256.o: CFLAGS+=-fno-schedule-insns +endif + # Tell versions [3.59,3.63) of GNU make to not export all variables. # Otherwise a system limit (for SysV at least) may be exceeded. .NOEXPORT: Original bug description: The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d
[Touch-packages] [Bug 1667407] Re: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
** Description changed: - Dear Maintainer, + [Impact] + * Performance drop of 2x-3x on ppc64le when using sha256sum + + * Please backport this bug to last LTS as this application is widely + used. + + * This fix is due to a optimization issue found on gcc v4.9 to gcc + v7.0. + + [Test Case] + + * Run sha256sum with a big file and measure the time it takes. The + patch improves this timing up to 3 times faster. + + [Regression Potential] + + * This patch is specifically for the sha256.o object, affecting only + this binary. + + [Other Info] + + Michael Stone's improved patch: + + Index: coreutils-8.26/Makefile.in + === + --- coreutils-8.26.orig/Makefile.in 2016-11-30 13:34:55.0 -0500 + +++ coreutils-8.26/Makefile.in 2017-02-22 07:18:55.352394058 -0500 + @@ -14661,6 +14661,10 @@ + + $(TEST_LOGS): $(PROGRAMS) + + +ifeq ($(DEB_TARGET_ARCH), ppc64el) + +lib/sha256.o: CFLAGS+=-fno-schedule-insns + +endif + + + # Tell versions [3.59,3.63) of GNU make to not export all variables. + # Otherwise a system limit (for SysV at least) may be exceeded. + .NOEXPORT: + + Original bug description: + The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] - int *a = utmp_ent->ut_addr_v6; - ^~~~ + int *a = utmp_ent->ut_addr_v6; + ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m18.670s user0m16.566s sys 0m0.745s $ # now with the following patch: ## Check Michael Stone's patch for an improved version. $ diff Makefile.in ../Makefile.in 8989c8989 < @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ --- > @am__fastdepCC_TRUE@ $(COMPILE) $$([ "$@" == "lib/sha256.o" ] && echo "-fno-schedule-insns") -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ $ cp ../Makefile.in Makefile.in $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] - int *a = utmp_ent->ut_addr_v6; - ^~~~ + int *a = utmp_ent->ut_addr_v6; + ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m5.903s user0m5.560s sys 0m0.255s -- You received this bug notification because you are a member of Ubuntu
[Touch-packages] [Bug 1667407] Re: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
One other possibility (as performed by Fedora) is to have libcrypto (from openssl) configured through the "--with-openssl=yes" parameter. -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to coreutils in Ubuntu. https://bugs.launchpad.net/bugs/1667407 Title: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug Status in coreutils package in Ubuntu: New Status in coreutils package in Debian: Unknown Bug description: Dear Maintainer, The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m18.670s user0m16.566s sys 0m0.745s $ # now with the following patch: ## Check Michael Stone's patch for an improved version. $ diff Makefile.in ../Makefile.in 8989c8989 < @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ --- > @am__fastdepCC_TRUE@ $(COMPILE) $$([ "$@" == "lib/sha256.o" ] && echo "-fno-schedule-insns") -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ $ cp ../Makefile.in Makefile.in $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m5.903s user0m5.560s sys 0m0.255s To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/coreutils/+bug/1667407/+subscriptions -- Mailing list: https://launchpad.net/~touch-packages Post to : touch-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~touch-packages More help : https://help.launchpad.net/ListHelp
[Touch-packages] [Bug 1667407] [NEW] improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug
Public bug reported: Dear Maintainer, The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m18.670s user0m16.566s sys 0m0.745s $ # now with the following patch: ## Check Michael Stone's patch for an improved version. $ diff Makefile.in ../Makefile.in 8989c8989 < @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ --- > @am__fastdepCC_TRUE@ $(COMPILE) $$([ "$@" == "lib/sha256.o" ] && echo > "-fno-schedule-insns") -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ $ cp ../Makefile.in Makefile.in $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso configure: WARNING: libacl development library was not found or not usable. configure: WARNING: GNU coreutils will be built without ACL support. configure: WARNING: libattr development library was not found or not usable. configure: WARNING: GNU coreutils will be built without xattr support. configure: WARNING: libcap library was not found or not usable. configure: WARNING: GNU coreutils will be built without capability support. configure: WARNING: libgmp development library was not found or not usable. configure: WARNING: GNU coreutils will be built without GMP support. src/who.c: In function 'print_user': src/who.c:454:20: warning: initialization discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers] int *a = utmp_ent->ut_addr_v6; ^~~~ d14bdb413ea6cdc8d9354fcbc37a834b7de0c23f992deb0c6764d0fd5d65408e /home/gut/ubuntu-16.10-server-ppc64el.iso real0m5.903s user0m5.560s sys 0m0.255s ** Affects: coreutils (Ubuntu) Importance: Undecided Status: New ** Tags: regression-release -- You received this bug notification because you are a member of Ubuntu Touch seeded packages, which is subscribed to coreutils in Ubuntu. https://bugs.launchpad.net/bugs/1667407 Title: improve 2x-3x sha256sum performance on ppc64le due to current gcc optimization bug Status in coreutils package in Ubuntu: New Bug description: Dear Maintainer, The sha256sum provided by coreutils (without openssl) is performing poorly with gcc versions >= 4.9 until 7.0 (currently under development). The reason for that is the -fschedule-insns optimization that is used with -O2. By simply deactivating it, there is a performance improvement of 2 to 3 times. I'm using Ubuntu 16.10 and the coreutils package version 8.25-2ubuntu2. Please check the following closed debian bug report: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=854053 Be aware of the following conditions that are required: * If ppc64le * If gcc being used is >= 4.9 and < 7.0 Notes: 1) gcc-7 is not affected by this bug (verified on 20170129 snapshot). 2) clang is not affected by this bug (verified on v3.8 and v3.9). 3) strangely the sha512 is not affected by this. Below a demonstration of how it performs on my POWER8 machine: === $ (./configure && make -j9) > /dev/null && time src/sha256sum ~/ubuntu-16.10-server-ppc64el.iso