platform/upstream/openblas.git
7 years agoARM64: Add the VULCAN Target
Ashwin Sekhar T K [Tue, 4 Oct 2016 08:50:20 +0000 (01:50 -0700)]
ARM64: Add the VULCAN Target

7 years agoCORTEXA57: Add assembly kernels for copy routines
Ashwin Sekhar T K [Tue, 4 Oct 2016 08:24:28 +0000 (01:24 -0700)]
CORTEXA57: Add assembly kernels for copy routines

7 years agoMerge pull request #1055 from ksraste/develop
Zhang Xianyi [Tue, 10 Jan 2017 05:58:26 +0000 (13:58 +0800)]
Merge pull request #1055 from ksraste/develop

Add msa optimization for AXPY, COPY, SCALE, SWAP

7 years agoAdding multi-threading for copy, dot, rot, and asum funcitons
jiahaipeng [Sun, 11 Dec 2016 09:09:50 +0000 (09:09 +0000)]
Adding multi-threading for copy, dot, rot, and asum funcitons

7 years agomodify the blas_l1_thread.c for support multi-threded for L1 fuction with return...
jiahaipeng [Sun, 11 Dec 2016 09:02:18 +0000 (09:02 +0000)]
modify the blas_l1_thread.c for support multi-threded for L1 fuction with return value

7 years agoMerge pull request #1057 from martin-frbg/lapacke-mingw
Martin Kroeker [Mon, 9 Jan 2017 19:45:26 +0000 (20:45 +0100)]
Merge pull request #1057 from martin-frbg/lapacke-mingw

Split the obj list of LAPACKE 3.7.0

7 years agoSplit the obj list of LAPACKE 3.7.0
Martin Kroeker [Mon, 9 Jan 2017 17:29:53 +0000 (18:29 +0100)]
Split the obj list of LAPACKE 3.7.0

Split obj list to allow building with mingw (argument list too long for the msys ar)

7 years agoAdd msa optimization for AXPY, COPY, SCALE, SWAP
kaustubh [Mon, 9 Jan 2017 12:57:23 +0000 (18:27 +0530)]
Add msa optimization for AXPY, COPY, SCALE, SWAP

Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
7 years agoAdd msa optimization for AXPY, COPY, SCALE, SWAP
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>
7 years agoMerge pull request #1054 from wernsaar/develop
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…

7 years agoprepared lapack/getrf functions for UNROLL values, that are not a power of two
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

7 years agoMerge branch 'z13' into develop
Zhang Xianyi [Mon, 9 Jan 2017 10:52:42 +0000 (05:52 -0500)]
Merge branch 'z13' into develop

Conflicts:
CONTRIBUTORS.md

7 years agoAdd USE_TRMM=1 for IBM z13 in kernel/Makefile.L3
Zhang Xianyi [Mon, 9 Jan 2017 10:48:09 +0000 (05:48 -0500)]
Add USE_TRMM=1 for IBM z13 in kernel/Makefile.L3

7 years agoMerge pull request #1053 from wernsaar/develop
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…

7 years agoprepared driver/level3 functions for UNROLL values, that are not a power of two
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

7 years agoMerge pull request #1050 from martin-frbg/fflags
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

7 years agoMerge pull request #1052 from martin-frbg/locking
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

7 years agoRelocate declaration of alloc_lock outside ifdef block
Martin Kroeker [Mon, 9 Jan 2017 00:10:43 +0000 (01:10 +0100)]
Relocate declaration of alloc_lock outside ifdef block

7 years agoFix thread data races detected by helgrind 3.12
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

7 years agoApply COMMON_OPT to default FFLAGS to avoid building non-optimized LAPACK by mistake
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

7 years agoMerge pull request #1049 from wernsaar/develop
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

7 years agoremoved blas_thread_shutdown from gensymbol
Werner Saar [Sun, 8 Jan 2017 07:51:30 +0000 (08:51 +0100)]
removed blas_thread_shutdown from gensymbol

7 years agoMerge pull request #1047 from brada4/erre
Zhang Xianyi [Sun, 8 Jan 2017 03:19:06 +0000 (11:19 +0800)]
Merge pull request #1047 from brada4/erre

Improve R benchmark timing

7 years agoMerge pull request #1040 from martin-frbg/develop
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

7 years agoMerge pull request #1036 from sva-img/develop
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.

7 years agoanti GC and reflow
Andrew [Sat, 7 Jan 2017 18:01:42 +0000 (19:01 +0100)]
anti GC and reflow

7 years agoinit
Andrew [Sat, 7 Jan 2017 18:01:21 +0000 (19:01 +0100)]
init

7 years agoMerge pull request #1046 from wernsaar/develop
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

7 years agofix for appveyor test
Werner Saar [Sat, 7 Jan 2017 13:27:08 +0000 (14:27 +0100)]
fix for appveyor test

7 years agoupdated exports/gensymbol for lapack-3.7.0
Werner Saar [Sat, 7 Jan 2017 12:20:28 +0000 (13:20 +0100)]
updated exports/gensymbol for lapack-3.7.0

7 years agofiltered out -fopenmp and fix for mingw
Werner Saar [Sat, 7 Jan 2017 07:41:42 +0000 (08:41 +0100)]
filtered out -fopenmp and fix for mingw

7 years agoremoved xerbla and lsame for Makefile
Werner Saar [Fri, 6 Jan 2017 15:35:20 +0000 (16:35 +0100)]
removed xerbla and lsame for Makefile

7 years agoremoved obj-files, that are moved to lapack 3.7.0
Werner Saar [Fri, 6 Jan 2017 15:14:53 +0000 (16:14 +0100)]
removed obj-files, that are moved to lapack 3.7.0

7 years agofiltered out optimized functions
Werner Saar [Fri, 6 Jan 2017 12:42:31 +0000 (13:42 +0100)]
filtered out optimized functions

7 years agoadded lapack 3.7.0 with latest patches from git
Werner Saar [Fri, 6 Jan 2017 10:48:40 +0000 (11:48 +0100)]
added lapack 3.7.0 with latest patches from git

7 years agoremoved lapack-devel.log
Werner Saar [Fri, 6 Jan 2017 10:46:58 +0000 (11:46 +0100)]
removed lapack-devel.log

7 years agoremoved lapack 3.6.0
Werner Saar [Fri, 6 Jan 2017 10:44:57 +0000 (11:44 +0100)]
removed lapack 3.6.0

7 years agoMerge pull request #1043 from quickwritereader/z13
Martin Kroeker [Thu, 5 Jan 2017 18:15:36 +0000 (19:15 +0100)]
Merge pull request #1043 from quickwritereader/z13

Z13

7 years agoUpdate xerbla.c
Martin Kroeker [Wed, 4 Jan 2017 22:16:48 +0000 (23:16 +0100)]
Update xerbla.c

7 years agoUpdate README.md
Abdurrauf [Wed, 4 Jan 2017 15:41:24 +0000 (19:41 +0400)]
Update README.md

7 years agodtrmm and dgemm for z13
Abdurrauf [Wed, 4 Jan 2017 15:32:33 +0000 (19:32 +0400)]
dtrmm and dgemm for z13

7 years agoUse appropriate int32/int64 format for error number in message string
Martin Kroeker [Thu, 29 Dec 2016 23:45:59 +0000 (00:45 +0100)]
Use appropriate int32/int64 format for error number in message string

7 years agoAdded prefetch to CGEMV and ZGEMV.
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>
7 years agoMerge pull request #1032 from kiwifb/OSX_target
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.

7 years agoMerge pull request #1025 from mfoster96/develop
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…

7 years agoMerge pull request #1031 from kiwifb/make
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).

7 years agoMerge pull request #1030 from ksraste/develop
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

7 years agoDo not override MACOSX_DEPLOYMENT_TARGET if it is already defined.
François Bissey [Wed, 14 Dec 2016 22:42:17 +0000 (11:42 +1300)]
Do not override MACOSX_DEPLOYMENT_TARGET if it is already defined.

7 years agoNever use "make" in makefiles. Only $(MAKE).
François Bissey [Wed, 14 Dec 2016 22:38:23 +0000 (11:38 +1300)]
Never use "make" in makefiles. Only $(MAKE).

7 years agoUpdated data prefetch in TRSM, ASUM, DOT functions
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>
7 years agoUpdated data prefetch in TRSM, ASUM, DOT functions
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>
7 years agoUpdated data prefetch in TRSM, ASUM, DOT functions
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>
7 years agoMerge pull request #1017 from martin-frbg/develop
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

7 years agoFix for issue #1024: arm-linux-androideabi-g++ Compiler Error in /cpuid_arm.c
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

7 years agoMerge pull request #1015 from ararslan/aa/freebsd
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

7 years agoMerge pull request #996 from grisuthedragon/lapack-3.6.1
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

7 years agoConvert --exclude-libs argument to linker flag
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

7 years agoConvert --exclude-libs argument to linker flag
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

7 years agoMerge pull request #1016 from ksraste/develop
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

7 years agoAdd 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>
7 years agoInclude system headers on FreeBSD
Alex Arslan [Thu, 17 Nov 2016 05:58:20 +0000 (21:58 -0800)]
Include system headers on FreeBSD

7 years agoMerge pull request #1002 from brada4/limpio
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.

7 years agoMerge pull request #1010 from martin-frbg/cpuid
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

7 years agoMerge pull request #1009 from martin-frbg/getarch-newline-fix
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

7 years agoAdd files via upload
Martin Kroeker [Sun, 6 Nov 2016 22:27:30 +0000 (23:27 +0100)]
Add files via upload

7 years agoAdd files via upload
Martin Kroeker [Sun, 6 Nov 2016 22:26:39 +0000 (23:26 +0100)]
Add files via upload

7 years agoAdd files via upload
Martin Kroeker [Sun, 6 Nov 2016 22:26:04 +0000 (23:26 +0100)]
Add files via upload

7 years agoAdd files via upload
Martin Kroeker [Sun, 6 Nov 2016 16:38:20 +0000 (17:38 +0100)]
Add files via upload

7 years agoDelete CMakeLists.txt
Martin Kroeker [Sun, 6 Nov 2016 16:37:37 +0000 (17:37 +0100)]
Delete CMakeLists.txt

7 years agoFix spurious define in openblas_config.h
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)

7 years agoUpdate CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 12:38:57 +0000 (13:38 +0100)]
Update CMakeLists.txt

7 years agoUpdate CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 12:30:40 +0000 (13:30 +0100)]
Update CMakeLists.txt

7 years agoUpdate CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 12:26:01 +0000 (13:26 +0100)]
Update CMakeLists.txt

7 years agoUpdate CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 12:11:32 +0000 (13:11 +0100)]
Update CMakeLists.txt

7 years agoUpdate CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 12:05:05 +0000 (13:05 +0100)]
Update CMakeLists.txt

7 years agoUpdate CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 11:59:05 +0000 (12:59 +0100)]
Update CMakeLists.txt

7 years agoUpdate CMakeLists.txt
Martin Kroeker [Sat, 5 Nov 2016 11:47:15 +0000 (12:47 +0100)]
Update CMakeLists.txt

7 years agoConsolidate debug options
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

7 years agoremove dead code
Andrew [Mon, 31 Oct 2016 11:46:56 +0000 (12:46 +0100)]
remove dead code

7 years agonew branch
Andrew [Sat, 29 Oct 2016 21:44:02 +0000 (23:44 +0200)]
new branch

7 years agoMove remaining OpenBLAS related changes from 3.6.0 to 3.6.1
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

7 years agoFix #971
Martin Koehler [Wed, 26 Oct 2016 19:34:56 +0000 (21:34 +0200)]
Fix #971

7 years agoFix threshold in nep.in
Martin Koehler [Wed, 26 Oct 2016 19:17:12 +0000 (21:17 +0200)]
Fix threshold in nep.in

7 years agoFix MingW build
Martin Köhler [Wed, 26 Oct 2016 14:03:00 +0000 (16:03 +0200)]
Fix MingW build

7 years agoUpdate gitignore
Martin Köhler [Wed, 26 Oct 2016 13:19:40 +0000 (15:19 +0200)]
Update gitignore

7 years agoImport LAPACK: top directory
Martin Köhler [Wed, 26 Oct 2016 13:14:13 +0000 (15:14 +0200)]
Import LAPACK: top directory

7 years agoImport LAPACK: TESTING directory
Martin Köhler [Wed, 26 Oct 2016 13:13:03 +0000 (15:13 +0200)]
Import LAPACK: TESTING directory

7 years agoImport LAPACK: SRC directory
Martin Köhler [Wed, 26 Oct 2016 13:12:09 +0000 (15:12 +0200)]
Import LAPACK: SRC directory

7 years agoImport LAPACK: LAPACKE directory
Martin Köhler [Wed, 26 Oct 2016 13:06:08 +0000 (15:06 +0200)]
Import LAPACK: LAPACKE directory

7 years agoImport LAPACK: INSTALL directory
Martin Köhler [Wed, 26 Oct 2016 13:04:39 +0000 (15:04 +0200)]
Import LAPACK: INSTALL directory

7 years agoImport LAPACK: DOCS directory
Martin Köhler [Wed, 26 Oct 2016 13:03:51 +0000 (15:03 +0200)]
Import LAPACK: DOCS directory

7 years agoImport LAPACK: CMAKE directory
Martin Köhler [Wed, 26 Oct 2016 13:03:16 +0000 (15:03 +0200)]
Import LAPACK: CMAKE directory

7 years agoImport LAPACK: CBLAS directory
Martin Köhler [Wed, 26 Oct 2016 13:02:41 +0000 (15:02 +0200)]
Import LAPACK: CBLAS directory

7 years agoImport LAPACK: BLAS directory
Martin Köhler [Wed, 26 Oct 2016 13:02:09 +0000 (15:02 +0200)]
Import LAPACK: BLAS directory

7 years agoAdd CMAKE install target
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)

7 years agoMerge pull request #986 from ksraste/develop
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

7 years agoSGEMM, 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>
7 years agoMerge pull request #984 from ksraste/develop
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

7 years agoMerge pull request #981 from howard0su/develop
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

7 years agoMerge pull request #982 from martin-frbg/develop
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