Zhang Xianyi [Fri, 15 Aug 2014 00:07:27 +0000 (08:07 +0800)]
Merge pull request #434 from wernsaar/develop
A lot of performance enhancements
wernsaar [Thu, 14 Aug 2014 17:00:30 +0000 (19:00 +0200)]
added optimized cgemv_n for haswell
wernsaar [Thu, 14 Aug 2014 12:10:29 +0000 (14:10 +0200)]
added optimized cgemv_t kernel for haswell
wernsaar [Wed, 13 Aug 2014 14:10:03 +0000 (16:10 +0200)]
optimized zgemv_n kernel for sandybridge
wernsaar [Wed, 13 Aug 2014 12:54:50 +0000 (14:54 +0200)]
added additional test values
wernsaar [Wed, 13 Aug 2014 11:54:19 +0000 (13:54 +0200)]
added fast return, if m or n < 1
wernsaar [Wed, 13 Aug 2014 11:42:22 +0000 (13:42 +0200)]
optimized zgemv_t_microk_haswell-2.c
wernsaar [Wed, 13 Aug 2014 10:54:18 +0000 (12:54 +0200)]
bugfix for zgemv_n_microk_haswell-2.c
wernsaar [Wed, 13 Aug 2014 10:18:03 +0000 (12:18 +0200)]
bugfix in zgemv_n_microk_sandy-2.c
wernsaar [Tue, 12 Aug 2014 10:15:41 +0000 (12:15 +0200)]
added optimized cgemv_t c-kernel
wernsaar [Tue, 12 Aug 2014 08:02:25 +0000 (10:02 +0200)]
bugfix in zgemv_n_microk_haswell-2.c
wernsaar [Tue, 12 Aug 2014 06:35:42 +0000 (08:35 +0200)]
modified algorithm for better numerical stability
wernsaar [Mon, 11 Aug 2014 14:57:52 +0000 (16:57 +0200)]
added optimized zgemv_t kernel for haswell
wernsaar [Mon, 11 Aug 2014 12:19:25 +0000 (14:19 +0200)]
add optimized zgemv_t kernel for bulldozer
wernsaar [Mon, 11 Aug 2014 11:10:12 +0000 (13:10 +0200)]
added optimized zgemv_t for haswell
wernsaar [Mon, 11 Aug 2014 07:13:18 +0000 (09:13 +0200)]
added optimimized zgemv_t c-kernel
wernsaar [Sun, 10 Aug 2014 09:57:24 +0000 (11:57 +0200)]
disabled optimized haswell zgemv_n kernel for windows ( bad rounding )
wernsaar [Sun, 10 Aug 2014 06:39:17 +0000 (08:39 +0200)]
added optimized zgemv_n kernel for haswell
wernsaar [Thu, 7 Aug 2014 20:30:20 +0000 (22:30 +0200)]
added zgemv_n c-function
wernsaar [Thu, 7 Aug 2014 08:08:54 +0000 (10:08 +0200)]
added optimized dgemv_t kernel for haswell
wernsaar [Thu, 7 Aug 2014 07:18:02 +0000 (09:18 +0200)]
added optimized dgemv_n kernel for haswell
wernsaar [Thu, 7 Aug 2014 05:49:33 +0000 (07:49 +0200)]
added optimized sgemv_t kernel for sandybridge
wernsaar [Wed, 6 Aug 2014 14:58:21 +0000 (16:58 +0200)]
enabled optimized nehalem sgemv_t kernel for windows
wernsaar [Wed, 6 Aug 2014 14:21:48 +0000 (16:21 +0200)]
added optimized sgemv_t kernel for nehalem
wernsaar [Wed, 6 Aug 2014 12:24:36 +0000 (14:24 +0200)]
enabled optimized sgemv kernels for windows
wernsaar [Wed, 6 Aug 2014 12:06:30 +0000 (14:06 +0200)]
enabled optimized sgemv kernels for windows
wernsaar [Wed, 6 Aug 2014 11:42:41 +0000 (13:42 +0200)]
added optimized sgemv_t kernel for haswell
wernsaar [Wed, 6 Aug 2014 10:12:17 +0000 (12:12 +0200)]
added optimized sgemv_t kernel
Zhang Xianyi [Tue, 5 Aug 2014 18:52:30 +0000 (02:52 +0800)]
Merge pull request #430 from wernsaar/develop
added a better optimized sgemv_n kernel
wernsaar [Tue, 5 Aug 2014 18:14:29 +0000 (20:14 +0200)]
bugfix in sgemv_n.c
wernsaar [Tue, 5 Aug 2014 17:42:56 +0000 (19:42 +0200)]
changed default x86_64 sgemv_n kernel to sgemv_n.c
wernsaar [Tue, 5 Aug 2014 12:52:54 +0000 (14:52 +0200)]
enabled optimized sgemv_n kernels for windows
wernsaar [Tue, 5 Aug 2014 11:28:39 +0000 (13:28 +0200)]
changed long to blaslong for windows compatibility
wernsaar [Tue, 5 Aug 2014 08:50:08 +0000 (10:50 +0200)]
added optimized sgemv_n kernel for nehalem
wernsaar [Tue, 5 Aug 2014 06:53:09 +0000 (08:53 +0200)]
optimized sgemv_n kernel for sandybridge
wernsaar [Tue, 5 Aug 2014 06:04:47 +0000 (08:04 +0200)]
updated haswell optimized sgmv_n kernel
wernsaar [Mon, 4 Aug 2014 14:22:11 +0000 (16:22 +0200)]
modified sgemv_n for haswell
wernsaar [Mon, 4 Aug 2014 12:29:01 +0000 (14:29 +0200)]
added a better optimized sgemv_n kernel for bulldozer and piledriver
Zhang Xianyi [Mon, 4 Aug 2014 00:12:23 +0000 (08:12 +0800)]
Merge pull request #429 from idunham/numprocs
Fix link error on Linux/musl.
Isaac Dunham [Sun, 3 Aug 2014 22:06:30 +0000 (15:06 -0700)]
Fix link error on Linux/musl.
get_nprocs() is a GNU convenience function equivalent to POSIX2008
sysconf(_SC_NPROCESSORS_ONLN); the latter should be available in unistd.h
on any current *nix. (OS X supports this call since 10.5, and FreeBSD
currently supports it. But this commit does not change FreeBSD or OS X
versions.)
Zhang Xianyi [Sat, 2 Aug 2014 16:57:44 +0000 (00:57 +0800)]
Merge pull request #427 from wernsaar/develop
added experimental support for big numa machines
wernsaar [Sat, 2 Aug 2014 11:40:16 +0000 (13:40 +0200)]
added experimental support for big numa machines
Zhang Xianyi [Sat, 2 Aug 2014 07:34:41 +0000 (15:34 +0800)]
Merge pull request #426 from wernsaar/develop
added benchmark program for lapack ?getri functions
wernsaar [Fri, 1 Aug 2014 21:10:08 +0000 (23:10 +0200)]
bugfix for linux affinity code
wernsaar [Fri, 1 Aug 2014 19:08:37 +0000 (21:08 +0200)]
added benchmarks for lapack potrf, potrs and potri functions
wernsaar [Fri, 1 Aug 2014 06:55:20 +0000 (08:55 +0200)]
added benchmark program for lapack ?getri functions
Zhang Xianyi [Fri, 1 Aug 2014 00:04:16 +0000 (08:04 +0800)]
Merge pull request #425 from wernsaar/develop
added benchmark for lapack ?geev routines
wernsaar [Thu, 31 Jul 2014 10:35:38 +0000 (12:35 +0200)]
bugfix for zgeev
wernsaar [Thu, 31 Jul 2014 08:35:25 +0000 (10:35 +0200)]
added lapack geev benchmark
Zhang Xianyi [Thu, 31 Jul 2014 05:54:07 +0000 (13:54 +0800)]
Merge pull request #424 from ihnorton/fix_arm_cpuid
cpuid_arm: fix detection when cpuinfo uses "Processor"
Isaiah Norton [Thu, 31 Jul 2014 04:59:30 +0000 (04:59 +0000)]
cpuid_arm: fix detection when cpuinfo uses "Processor"
instead of "model name"
wernsaar [Wed, 30 Jul 2014 12:00:19 +0000 (14:00 +0200)]
bugfix in cholesky.c
wernsaar [Wed, 30 Jul 2014 11:03:42 +0000 (13:03 +0200)]
extented plot-filter.sh for linpack and cholesky benchmarks
Zhang Xianyi [Wed, 30 Jul 2014 09:09:58 +0000 (17:09 +0800)]
Merge pull request #422 from wernsaar/develop
optimization of sandybridge cgemm-kernel
wernsaar [Tue, 29 Jul 2014 17:07:21 +0000 (19:07 +0200)]
optimization of sandybridge cgemm-kernel
Zhang Xianyi [Tue, 29 Jul 2014 07:50:00 +0000 (15:50 +0800)]
Merge pull request #421 from wernsaar/develop
optimized sgemm- and cgemm-kernel for haswell
wernsaar [Tue, 29 Jul 2014 06:53:09 +0000 (08:53 +0200)]
optimized cgemm kernel for haswell
wernsaar [Mon, 28 Jul 2014 09:50:01 +0000 (11:50 +0200)]
optimized sgemm kernel for haswell
Zhang Xianyi [Sun, 27 Jul 2014 15:30:14 +0000 (23:30 +0800)]
Merge pull request #420 from wernsaar/develop
Optimizations for HASWELL
wernsaar [Sun, 27 Jul 2014 09:51:42 +0000 (11:51 +0200)]
optimized zgemm kernel for haswell
wernsaar [Fri, 25 Jul 2014 09:59:17 +0000 (11:59 +0200)]
optimizations for trsm
wernsaar [Fri, 25 Jul 2014 08:00:23 +0000 (10:00 +0200)]
optimizations for trmm
wernsaar [Thu, 24 Jul 2014 16:43:31 +0000 (18:43 +0200)]
allow to set custom value for ?GEMM_DEFAULT_UNROLL_MN, optimizations for syrk
wernsaar [Mon, 21 Jul 2014 12:50:24 +0000 (14:50 +0200)]
added a sample plot-filter scripts and a header file for gnuplot
wernsaar [Mon, 21 Jul 2014 05:50:54 +0000 (07:50 +0200)]
added symv benchmark
wernsaar [Mon, 21 Jul 2014 04:25:42 +0000 (06:25 +0200)]
add benchmark for ger
Zhang Xianyi [Sun, 20 Jul 2014 15:35:17 +0000 (23:35 +0800)]
Merge pull request #419 from wernsaar/develop
added optimized sgemv kernels for Sandy Bridge, Haswell, Bullldozer, and Piledriver.
wernsaar [Sun, 20 Jul 2014 12:52:25 +0000 (14:52 +0200)]
added sgemv_n microkernel for haswell
wernsaar [Sun, 20 Jul 2014 12:08:04 +0000 (14:08 +0200)]
optimized sgemv_n_microk_sandy.c
wernsaar [Sun, 20 Jul 2014 11:17:47 +0000 (13:17 +0200)]
added sgemv_n microkernel for sandybridge
wernsaar [Sun, 20 Jul 2014 09:30:32 +0000 (11:30 +0200)]
added sgemv_t microkernel for haswell
wernsaar [Sun, 20 Jul 2014 08:48:41 +0000 (10:48 +0200)]
bugfix in sgemv_t_microk_sandy.c
wernsaar [Sun, 20 Jul 2014 08:21:08 +0000 (10:21 +0200)]
added sgemv_t microkernel for sandybridge
wernsaar [Sat, 19 Jul 2014 13:48:07 +0000 (15:48 +0200)]
added optimized sgemv_t for bulldozer and piledriver
wernsaar [Sat, 19 Jul 2014 05:15:34 +0000 (07:15 +0200)]
don't use this sgemv_n on Windows
Zhang Xianyi [Fri, 18 Jul 2014 15:13:18 +0000 (23:13 +0800)]
Merge pull request #414 from staticfloat/sf/symlinkfix
Don't create an absolute symlink when installing on Darwin
wernsaar [Fri, 18 Jul 2014 09:25:21 +0000 (11:25 +0200)]
performance optimizations for sgemv_n
wernsaar [Thu, 17 Jul 2014 21:15:07 +0000 (23:15 +0200)]
added blocked sgemv_n and microkernel for bulldozer and piledriver
Zhang Xianyi [Thu, 17 Jul 2014 07:02:01 +0000 (15:02 +0800)]
Refs #415. Fixed the x86/i386 compiling bug with DYNAMIC_ARCH=1.
Elliot Saba [Wed, 16 Jul 2014 19:31:27 +0000 (15:31 -0400)]
Don't create an absolute symlink when installing on Darwin
wernsaar [Wed, 16 Jul 2014 15:08:43 +0000 (17:08 +0200)]
changed string GFORTRAN to lowercase
Zhang Xianyi [Wed, 16 Jul 2014 10:04:18 +0000 (18:04 +0800)]
OpenBLAS 0.2.10 version.
Zhang Xianyi [Wed, 16 Jul 2014 00:37:55 +0000 (08:37 +0800)]
Refs #401. Added NO_AVX2 flag for old binutils (e.g. RHEL6)
wernsaar [Tue, 15 Jul 2014 14:27:02 +0000 (16:27 +0200)]
adjust number of threads for small size in cgemv and zgemv
wernsaar [Tue, 15 Jul 2014 14:04:46 +0000 (16:04 +0200)]
adjust number of threads for sgemv and dgemv
wernsaar [Tue, 15 Jul 2014 12:41:35 +0000 (14:41 +0200)]
adjusted number of threads for small size
wernsaar [Tue, 15 Jul 2014 11:35:36 +0000 (13:35 +0200)]
added benchmark for gemv
Zhang Xianyi [Mon, 14 Jul 2014 14:39:22 +0000 (22:39 +0800)]
Merge pull request #413 from wernsaar/develop
additional benchmarks
wernsaar [Sun, 13 Jul 2014 16:29:19 +0000 (18:29 +0200)]
added additional test value to dstest.in
wernsaar [Sun, 13 Jul 2014 16:26:38 +0000 (18:26 +0200)]
added additional test value
wernsaar [Sun, 13 Jul 2014 08:49:43 +0000 (10:49 +0200)]
segment violation in x86_64 sgemv kernels
wernsaar [Sun, 13 Jul 2014 08:46:14 +0000 (10:46 +0200)]
segment violation in sgemv kernels
wernsaar [Sat, 12 Jul 2014 14:20:29 +0000 (16:20 +0200)]
modified pathes to atlas, mkl and acml
wernsaar [Sat, 12 Jul 2014 09:54:39 +0000 (11:54 +0200)]
added conf option for number of loops
wernsaar [Fri, 11 Jul 2014 14:31:05 +0000 (16:31 +0200)]
added her2k benchmark
wernsaar [Fri, 11 Jul 2014 14:16:48 +0000 (16:16 +0200)]
added herk benchmark
wernsaar [Fri, 11 Jul 2014 13:26:34 +0000 (15:26 +0200)]
add hemm benchmark
wernsaar [Fri, 11 Jul 2014 12:48:25 +0000 (14:48 +0200)]
added syr2k benchmark
wernsaar [Fri, 11 Jul 2014 12:21:25 +0000 (14:21 +0200)]
added syrk benchmark
wernsaar [Fri, 11 Jul 2014 11:51:08 +0000 (13:51 +0200)]
added trsm benchmark
projects / platform / upstream / openblas.git / log