kaustubh [Mon, 9 Jan 2017 12:52:09 +0000 (18:22 +0530)]
Add msa optimization for AXPY, COPY, SCALE, SWAP
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
Werner Saar [Mon, 9 Jan 2017 12:38:56 +0000 (13:38 +0100)]
Merge pull request #1054 from wernsaar/develop
prepared lapack/getrf functions for UNROLL values, that are not a pow…
Werner Saar [Mon, 9 Jan 2017 11:57:26 +0000 (12:57 +0100)]
prepared lapack/getrf functions for UNROLL values, that are not a power of two
Zhang Xianyi [Mon, 9 Jan 2017 10:52:42 +0000 (05:52 -0500)]
Merge branch 'z13' into develop
Conflicts:
CONTRIBUTORS.md
Zhang Xianyi [Mon, 9 Jan 2017 10:48:09 +0000 (05:48 -0500)]
Add USE_TRMM=1 for IBM z13 in kernel/Makefile.L3
Werner Saar [Mon, 9 Jan 2017 10:17:38 +0000 (11:17 +0100)]
Merge pull request #1053 from wernsaar/develop
prepared driver/level3 functions for UNROLL values, that are not a po…
Werner Saar [Mon, 9 Jan 2017 09:38:15 +0000 (10:38 +0100)]
prepared driver/level3 functions for UNROLL values, that are not a power of two
Zhang Xianyi [Mon, 9 Jan 2017 08:23:22 +0000 (16:23 +0800)]
Merge pull request #1050 from martin-frbg/fflags
Apply COMMON_OPT to default FFLAGS
Zhang Xianyi [Mon, 9 Jan 2017 08:22:58 +0000 (16:22 +0800)]
Merge pull request #1052 from martin-frbg/locking
Fix thread data races detected by helgrind 3.12
Martin Kroeker [Mon, 9 Jan 2017 00:10:43 +0000 (01:10 +0100)]
Relocate declaration of alloc_lock outside ifdef block
Martin Kroeker [Sun, 8 Jan 2017 22:33:51 +0000 (23:33 +0100)]
Fix thread data races detected by helgrind 3.12
Ref. #995, may possibly help solve issues seen in 660,883
Martin Kroeker [Sun, 8 Jan 2017 20:17:22 +0000 (21:17 +0100)]
Apply COMMON_OPT to default FFLAGS to avoid building non-optimized LAPACK by mistake
Werner Saar [Sun, 8 Jan 2017 08:30:19 +0000 (09:30 +0100)]
Merge pull request #1049 from wernsaar/develop
removed blas_thread_shutdown from gensymbol
Werner Saar [Sun, 8 Jan 2017 07:51:30 +0000 (08:51 +0100)]
removed blas_thread_shutdown from gensymbol
Zhang Xianyi [Sun, 8 Jan 2017 03:19:06 +0000 (11:19 +0800)]
Merge pull request #1047 from brada4/erre
Improve R benchmark timing
Zhang Xianyi [Sun, 8 Jan 2017 03:18:38 +0000 (11:18 +0800)]
Merge pull request #1040 from martin-frbg/develop
Use appropriate int32/int64 format for error number in message string
Zhang Xianyi [Sun, 8 Jan 2017 03:18:05 +0000 (11:18 +0800)]
Merge pull request #1036 from sva-img/develop
Added prefetch to CGEMV and ZGEMV.
Andrew [Sat, 7 Jan 2017 18:01:42 +0000 (19:01 +0100)]
anti GC and reflow
Andrew [Sat, 7 Jan 2017 18:01:21 +0000 (19:01 +0100)]
init
Werner Saar [Sat, 7 Jan 2017 14:09:56 +0000 (15:09 +0100)]
Merge pull request #1046 from wernsaar/develop
updated lapack to version 3.7.0 with latest patches from git
Werner Saar [Sat, 7 Jan 2017 13:27:08 +0000 (14:27 +0100)]
fix for appveyor test
Werner Saar [Sat, 7 Jan 2017 12:20:28 +0000 (13:20 +0100)]
updated exports/gensymbol for lapack-3.7.0
Werner Saar [Sat, 7 Jan 2017 07:41:42 +0000 (08:41 +0100)]
filtered out -fopenmp and fix for mingw
Werner Saar [Fri, 6 Jan 2017 15:35:20 +0000 (16:35 +0100)]
removed xerbla and lsame for Makefile
Werner Saar [Fri, 6 Jan 2017 15:14:53 +0000 (16:14 +0100)]
removed obj-files, that are moved to lapack 3.7.0
Werner Saar [Fri, 6 Jan 2017 12:42:31 +0000 (13:42 +0100)]
filtered out optimized functions
Werner Saar [Fri, 6 Jan 2017 10:48:40 +0000 (11:48 +0100)]
added lapack 3.7.0 with latest patches from git
Werner Saar [Fri, 6 Jan 2017 10:46:58 +0000 (11:46 +0100)]
removed lapack-devel.log
Werner Saar [Fri, 6 Jan 2017 10:44:57 +0000 (11:44 +0100)]
removed lapack 3.6.0
Martin Kroeker [Thu, 5 Jan 2017 18:15:36 +0000 (19:15 +0100)]
Merge pull request #1043 from quickwritereader/z13
Z13
Martin Kroeker [Wed, 4 Jan 2017 22:16:48 +0000 (23:16 +0100)]
Update xerbla.c
Abdurrauf [Wed, 4 Jan 2017 15:41:24 +0000 (19:41 +0400)]
Update README.md
Abdurrauf [Wed, 4 Jan 2017 15:32:33 +0000 (19:32 +0400)]
dtrmm and dgemm for z13
Martin Kroeker [Thu, 29 Dec 2016 23:45:59 +0000 (00:45 +0100)]
Use appropriate int32/int64 format for error number in message string
Shivraj Patil [Tue, 27 Dec 2016 06:03:51 +0000 (11:33 +0530)]
Added prefetch to CGEMV and ZGEMV.
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
Zhang Xianyi [Sun, 18 Dec 2016 06:48:22 +0000 (14:48 +0800)]
Merge pull request #1032 from kiwifb/OSX_target
Do not override MACOSX_DEPLOYMENT_TARGET if it is already defined.
Zhang Xianyi [Sun, 18 Dec 2016 06:47:59 +0000 (14:47 +0800)]
Merge pull request #1025 from mfoster96/develop
Fix for issue #1024: arm-linux-androideabi-g++ Compiler Error in /cpu…
Zhang Xianyi [Sun, 18 Dec 2016 06:46:52 +0000 (14:46 +0800)]
Merge pull request #1031 from kiwifb/make
Never use "make" in makefiles. Only $(MAKE).
Zhang Xianyi [Sun, 18 Dec 2016 06:46:16 +0000 (14:46 +0800)]
Merge pull request #1030 from ksraste/develop
Updated data prefetch in TRSM, ASUM, DOT functions
François Bissey [Wed, 14 Dec 2016 22:42:17 +0000 (11:42 +1300)]
Do not override MACOSX_DEPLOYMENT_TARGET if it is already defined.
François Bissey [Wed, 14 Dec 2016 22:38:23 +0000 (11:38 +1300)]
Never use "make" in makefiles. Only $(MAKE).
kaustubh [Wed, 14 Dec 2016 08:35:11 +0000 (14:05 +0530)]
Updated data prefetch in TRSM, ASUM, DOT functions
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
kaustubh [Tue, 13 Dec 2016 08:32:14 +0000 (14:02 +0530)]
Updated data prefetch in TRSM, ASUM, DOT functions
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
kaustubh [Tue, 13 Dec 2016 06:11:17 +0000 (11:41 +0530)]
Updated data prefetch in TRSM, ASUM, DOT functions
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
Zhang Xianyi [Fri, 9 Dec 2016 08:55:13 +0000 (16:55 +0800)]
Merge pull request #1017 from martin-frbg/develop
Make c_check, f_check convert any --exclude-libs arguments to linker flags
Michael Foster [Fri, 2 Dec 2016 17:28:31 +0000 (09:28 -0800)]
Fix for issue #1024: arm-linux-androideabi-g++ Compiler Error in /cpuid_arm.c
Line 77: Compiler requires non-void function to return a value
Zhang Xianyi [Fri, 2 Dec 2016 02:28:57 +0000 (10:28 +0800)]
Merge pull request #1015 from ararslan/aa/freebsd
Include system headers for blas_server on FreeBSD
Zhang Xianyi [Fri, 2 Dec 2016 02:27:51 +0000 (10:27 +0800)]
Merge pull request #996 from grisuthedragon/lapack-3.6.1
Lapack 3.6.1
Martin Kroeker [Tue, 22 Nov 2016 08:17:03 +0000 (09:17 +0100)]
Convert --exclude-libs argument to linker flag
Fixes build with TDM-GCC
Martin Kroeker [Tue, 22 Nov 2016 08:14:55 +0000 (09:14 +0100)]
Convert --exclude-libs argument to linker flag
Fixes build with TDM-GCC
Zhang Xianyi [Tue, 22 Nov 2016 07:54:56 +0000 (15:54 +0800)]
Merge pull request #1016 from ksraste/develop
Add data prefetch in DOT and ASUM functions
kaustubh [Tue, 22 Nov 2016 05:51:03 +0000 (11:21 +0530)]
Add data prefetch in DOT and ASUM functions
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
Alex Arslan [Thu, 17 Nov 2016 05:58:20 +0000 (21:58 -0800)]
Include system headers on FreeBSD
Zhang Xianyi [Mon, 7 Nov 2016 02:41:20 +0000 (10:41 +0800)]
Merge pull request #1002 from brada4/limpio
Remove few lines of dead code.
Zhang Xianyi [Mon, 7 Nov 2016 02:26:13 +0000 (10:26 +0800)]
Merge pull request #1010 from martin-frbg/cpuid
Add TARGETs for newer Intel CPUs - Kaby Lake, Knights Landing, Apollo Lake
Zhang Xianyi [Mon, 7 Nov 2016 02:25:51 +0000 (10:25 +0800)]
Merge pull request #1009 from martin-frbg/getarch-newline-fix
Getarch newline fix
Martin Kroeker [Sun, 6 Nov 2016 22:27:30 +0000 (23:27 +0100)]
Add files via upload
Martin Kroeker [Sun, 6 Nov 2016 22:26:39 +0000 (23:26 +0100)]
Add files via upload
Martin Kroeker [Sun, 6 Nov 2016 22:26:04 +0000 (23:26 +0100)]
Add files via upload
Martin Kroeker [Sun, 6 Nov 2016 16:38:20 +0000 (17:38 +0100)]
Add files via upload
Martin Kroeker [Sun, 6 Nov 2016 16:37:37 +0000 (17:37 +0100)]
Delete CMakeLists.txt
Martin Kroeker [Sun, 6 Nov 2016 16:29:33 +0000 (17:29 +0100)]
Fix spurious define in openblas_config.h
TARGET as specified with make is already return-terminated when getarch reads it. This led to an empty line written to config_last.h that awk in Makefile.install then expanded to a spurious "#define OPENBLAS_" in openblas_config.h (as noted by "kmb" on the mailing list)
Martin Kroeker [Sat, 5 Nov 2016 12:38:57 +0000 (13:38 +0100)]
Update CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 12:30:40 +0000 (13:30 +0100)]
Update CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 12:26:01 +0000 (13:26 +0100)]
Update CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 12:11:32 +0000 (13:11 +0100)]
Update CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 12:05:05 +0000 (13:05 +0100)]
Update CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 11:59:05 +0000 (12:59 +0100)]
Update CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 11:47:15 +0000 (12:47 +0100)]
Update CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 10:55:45 +0000 (11:55 +0100)]
Consolidate debug options
Use BUILD_DEBUG option only if CMAKE_BUILD_TYPE is not set
Consolidate debug postfixes in install target
Andrew [Mon, 31 Oct 2016 11:46:56 +0000 (12:46 +0100)]
remove dead code
Andrew [Sat, 29 Oct 2016 21:44:02 +0000 (23:44 +0200)]
new branch
Martin Koehler [Wed, 26 Oct 2016 19:43:41 +0000 (21:43 +0200)]
Move remaining OpenBLAS related changes from 3.6.0 to 3.6.1
Martin Koehler [Wed, 26 Oct 2016 19:34:56 +0000 (21:34 +0200)]
Fix #971
Martin Koehler [Wed, 26 Oct 2016 19:17:12 +0000 (21:17 +0200)]
Fix threshold in nep.in
Martin Köhler [Wed, 26 Oct 2016 14:03:00 +0000 (16:03 +0200)]
Fix MingW build
Martin Köhler [Wed, 26 Oct 2016 13:19:40 +0000 (15:19 +0200)]
Update gitignore
Martin Köhler [Wed, 26 Oct 2016 13:14:13 +0000 (15:14 +0200)]
Import LAPACK: top directory
Martin Köhler [Wed, 26 Oct 2016 13:13:03 +0000 (15:13 +0200)]
Import LAPACK: TESTING directory
Martin Köhler [Wed, 26 Oct 2016 13:12:09 +0000 (15:12 +0200)]
Import LAPACK: SRC directory
Martin Köhler [Wed, 26 Oct 2016 13:06:08 +0000 (15:06 +0200)]
Import LAPACK: LAPACKE directory
Martin Köhler [Wed, 26 Oct 2016 13:04:39 +0000 (15:04 +0200)]
Import LAPACK: INSTALL directory
Martin Köhler [Wed, 26 Oct 2016 13:03:51 +0000 (15:03 +0200)]
Import LAPACK: DOCS directory
Martin Köhler [Wed, 26 Oct 2016 13:03:16 +0000 (15:03 +0200)]
Import LAPACK: CMAKE directory
Martin Köhler [Wed, 26 Oct 2016 13:02:41 +0000 (15:02 +0200)]
Import LAPACK: CBLAS directory
Martin Köhler [Wed, 26 Oct 2016 13:02:09 +0000 (15:02 +0200)]
Import LAPACK: BLAS directory
Martin Kroeker [Wed, 19 Oct 2016 13:27:22 +0000 (15:27 +0200)]
Add CMAKE install target
Add CMAKE install target (copied from a patch provided by PrimarchOfTheSpaceWolves in #957)
Zhang Xianyi [Tue, 18 Oct 2016 04:38:52 +0000 (12:38 +0800)]
Merge pull request #986 from ksraste/develop
SGEMM, DGEMM, CGEMM, ZGEMM functions data prefetch
kaustubh [Mon, 17 Oct 2016 12:59:38 +0000 (18:29 +0530)]
SGEMM, DGEMM, CGEMM, ZGEMM functions data prefetch
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
Zhang Xianyi [Mon, 17 Oct 2016 03:33:16 +0000 (11:33 +0800)]
Merge pull request #984 from ksraste/develop
STRSM, DTRSM functions data prefetch
Zhang Xianyi [Mon, 17 Oct 2016 03:32:57 +0000 (11:32 +0800)]
Merge pull request #981 from howard0su/develop
USE NPROCESSOR_CONF instaed of NPORCESSOR_ONLN
Zhang Xianyi [Mon, 17 Oct 2016 03:32:20 +0000 (11:32 +0800)]
Merge pull request #982 from martin-frbg/develop
Change file comments to work around clang 3.9 assembler bug; add support for Bay Trail atom
Martin Kroeker [Sun, 16 Oct 2016 20:51:42 +0000 (22:51 +0200)]
Merge pull request #1 from martin-frbg/martin-frbg-patch-1
Add Intel "Bay Trail" atom cpu
Martin Kroeker [Sun, 16 Oct 2016 20:48:58 +0000 (22:48 +0200)]
Merge pull request #2 from martin-frbg/martin-frbg-patch-1-1
Update cpuid_x86.c
Martin Kroeker [Sun, 16 Oct 2016 20:45:44 +0000 (22:45 +0200)]
Update cpuid_x86.c
Add Bay Trail "Pentium N3520" atom cpu
Martin Kroeker [Sun, 16 Oct 2016 20:40:00 +0000 (22:40 +0200)]
Update dynamic.c
Add Bay Trail "Pentium N3520" atom
kaustubh [Fri, 14 Oct 2016 11:11:28 +0000 (16:41 +0530)]
STRSM, DTRSM functions data prefetch
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
Martin Kroeker [Thu, 13 Oct 2016 14:51:08 +0000 (16:51 +0200)]
Change file comments to work around clang 3.9 assembler bug
Howard Su [Thu, 13 Oct 2016 12:37:50 +0000 (12:37 +0000)]
USE NPROCESSOR_CONF instaed of NPORCESSOR_ONLN
to determine the number of CPU. In ARM platform,
online CPU will increasing when there is more workload.
while configure cpu is the max number of CPU.
Zhang Xianyi [Thu, 13 Oct 2016 02:17:07 +0000 (10:17 +0800)]
Fixed #979. Patch for NetBSD.
projects / platform / upstream / openblas.git / log