floraachy
/
OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,414 Commits 47 Branches 64 Tags 71 MiB
Commit Graph

3414 Commits

Author SHA1 Message Date
Martin Kroeker 5f8f0583d4
Merge branch 'develop' into fc-1847 2018-11-07 08:47:52 +01:00
Martin Kroeker 974a6a30f2
Merge pull request #1858 from brada4/buff-1847 
Add minimum threshold for number of buffers
 2018-11-07 08:46:55 +01:00
Andrew 9531d0e175 lets fit it in one 4k page 2018-11-06 17:51:24 +00:00
Andrew 40cce0e353 handle cmake too 2018-11-06 09:45:49 +00:00
Andrew 3fd41313fc add low bound for number of buffers 2018-11-06 09:40:13 +00:00
Andrew a931afe269 init 2018-11-06 09:39:05 +00:00
Andrew 7d3502b500 Add -frecursive gfortran option by default 2018-11-06 08:20:55 +00:00
Andrew 066f8065d1 init 2018-11-06 08:19:08 +00:00
Renato Golin fb5b2177ca [Arm64) Revert A53 detection as A57 
This patch reverts the decision of treating A53 like A57, which was
based on an analysis done on server class hardware and is not
representative of all A53s out there.

Fixes #1855.
 2018-11-05 11:34:49 +00:00
Martin Kroeker f1c02273cb
Merge pull request #1846 from fenrus75/threadsize 
gemm/dgemm: add a way for an arch kernel to specify preferred sizes
 2018-11-02 13:18:01 +01:00
Martin Kroeker 661035477c
Merge pull request #1850 from martin-frbg/issue1811 
Restore Android/ARMv7 build fix from #778
 2018-11-02 09:50:51 +01:00
Martin Kroeker aa7e47aa0a
Merge pull request #1849 from martin-frbg/aix_install2 
Use installbsd on AIX
 2018-11-01 20:39:16 +01:00
Martin Kroeker 9c177d270b
Restore Android/ARMv7 build fix from #778 
for #1811
 2018-11-01 18:50:25 +01:00
Martin Kroeker b025523197
Use installbsd on AIX 
(and fix misplaced parenthesis from previous commit). See #1803
 2018-11-01 18:26:08 +01:00
Martin Kroeker 5b50bd36f7
Merge pull request #1845 from martin-frbg/aix_install 
Accomodate AIX install, which has different syntax
 2018-11-01 09:53:10 +01:00
Arjan van de Ven 5b708e5eb1 sgemm/dgemm: add a way for an arch kernel to specify prefered sizes 
The current gemm threading code can make very unfortunate choices, for
example on my 10 core system a 1024x1024x1024 matrix multiply ends up
chunking into blocks of 102... which is not a vector friendly size
and performance ends up horrible.

this patch adds a helper define where an architecture can specify
a preference for size multiples.
This is different from existing defines that are minimum sizes and such.

The performance increase with this patch for the 1024x1024x1024 sgemm
is 2.3x (!!)
 2018-11-01 01:43:20 +00:00
Arjan van de Ven dcc5d6291e skylakex: Make the sgemm/dgemm beta code robust for a N=0 or M=0 case 
in the threading code there are cases where N or M can become 0,
and the optimized beta code did not handle this well, leading
to a crash

during the audit for the crash a few edge conditions on the if statements
were found and fixed as well
 2018-11-01 01:42:09 +00:00
Martin Kroeker 7b5aea52bb
Accomodate AIX install, which has different syntax 
for #1803
 2018-10-31 21:50:34 +01:00
Martin Kroeker f5595d0262
Merge pull request #1843 from martin-frbg/aix_numprocs 
Add get_num_procs implementation for AIX
 2018-10-31 21:25:15 +01:00
Martin Kroeker 326d394a0f
Add get_num_procs implementation for AIX 
(and copy HAIKU implementation to the non-TLS version of the code as well)
 2018-10-31 18:38:22 +01:00
Martin Kroeker 6af8e35a24
Merge pull request #1837 from embray/set-num-thread-after-fork 
Ensure that blas_thread_init has been called in openblas_set_num_threads
 2018-10-30 12:41:24 +01:00
Erik M. Bray 38cf5d9364 ensure that threading has been initialized in the first place before calling openblas_set_num_threads 2018-10-28 21:16:52 +00:00
Martin Kroeker 8a43baacb2
Merge pull request #1836 from martin-frbg/zen2core 
Fix detection of Ryzen2 (missing CORE_ZEN)
 2018-10-28 20:00:01 +01:00
Martin Kroeker 64ca44873b
Fix detection of Ryzen2 (missing CORE_ZEN) 2018-10-28 18:36:55 +01:00
fengrl 2d8064174c
register push/pop command change 
64bit push/pop register command should be used. Otherwise, data will lost.
 2018-10-26 17:55:15 +08:00
Martin Kroeker 76a66eaac8
Merge pull request #1829 from ashwinyes/develop_aarch64_dynamic_arch_support 
Add DYNAMIC_ARCH support for ARM64
 2018-10-23 18:14:28 +02:00
Andrew 2992e3886a disable threading in C/ZSWAP copying from S/DSWAP 2018-10-22 23:21:49 +03:00
Ashwin Sekhar T K d5aeff636f ARM64: Enable DYNAMIC_ARCH 
Enable DYNAMIC_ARCH feature on ARM64. This patch uses the cpuid
feature in linux kernel to detect the core type at runtime
(https://www.kernel.org/doc/Documentation/arm64/cpu-feature-registers.txt).

If this feature is missing in kernel, then the user should use the
OPENBLAS_CORETYPE env variable to select the desired core type.
 2018-10-22 01:49:35 -07:00
Ashwin Sekhar T K af2837c392 ARM64: Remove #define ARMV8 for THUNDERX 2018-10-22 01:49:35 -07:00
Ashwin Sekhar T K e7b66cd36e ARM64: Fix DYNAMIC_ARCH compilation for cores which dont use GEMM3M 2018-10-22 01:45:51 -07:00
Ashwin Sekhar T K d50abc8903 ARM64: Move parameters from parameter.c to param.h 
Remove the runtime setting of P, Q, R parameters for
targets ARMV8, THUNDERX2T99. Instead set them as constants
in param.h at compile time.
 2018-10-22 01:45:51 -07:00
Ashwin Sekhar T K 351a0c777c ARM64: Remove XGENE1 references 
Remove XGENE1 target as the implementation for the
same is incomplete. Moreover whoever wishes to use
on XGENE1 can use the generic ARMV8 target as there
are no XGENE1 specific optimizations in OpenBLAS.
 2018-10-22 01:45:51 -07:00
Martin Kroeker e3c262e5cf
Merge pull request #1825 from brada4/hemv 
Delay _hemv threading in attempt to address #1820
 2018-10-21 20:34:05 +02:00
Andrew a293bdcd5e re-arrange new code for readability 2018-10-20 21:37:53 +03:00
Andrew c7bbf9c987 Attempt to tame _hemv threading #1820 2018-10-20 11:13:29 +03:00
Andrew 898a8dcaba init 2018-10-20 10:55:04 +03:00
Martin Kroeker 71c6deed60
Merge pull request #1821 from ashwinyes/develop_aarch64_armv8neonkernels 
Use ThunderX2 Neon Kernels for ARMV8 Target
 2018-10-18 08:13:05 +02:00
Ashwin Sekhar T K 21f46a1cf2 ARM64: Use THUNDERX2T99 Neon Kernels for ARMV8 
Currently the generic ARMV8 target uses C implementations
for many routines. Replace these with the neon implementations
written for THUNDERX2T99 target which are upto 6x faster for
certain routines.
 2018-10-17 10:44:37 -07:00
Ashwin Sekhar T K caf339412f ARM64: Remove dependency of THUNDERX2T99 Makefile on CORTEXA57 Makefile 2018-10-17 08:02:40 -07:00
Ashwin Sekhar T K 8001fdcd2a ARM64: Remove dependency of THUNDERX Makefile on ARMV8 Makefile 2018-10-17 08:02:16 -07:00
Ashwin Sekhar T K 162e312832 ARM64: Remove dependency of CORTEXA57 Makefile on ARMV8 Makefile 2018-10-17 08:01:45 -07:00
Ashwin Sekhar T K c3d93caa8d ARM64: Remove dependency of XGENE1 Makefile on ARMV8 Makefile 2018-10-17 08:01:27 -07:00
Martin Kroeker a71923514f
Merge pull request #1815 from fenrus75/sgemm_beta_fix 
enable the SGEMM/SKX C based kernel
 2018-10-14 19:57:34 +02:00
Arjan van de Ven 55b244ca0d enable the SGEMM/SKX C based kernel 
In QA the final bug was found so now the sklyakex sgemm C based kernel can
be activated....
 2018-10-12 09:30:35 +00:00
Martin Kroeker 2263d3906c
Merge pull request #1812 from martin-frbg/issue1806-2 
Use KERNEL_DEFINITIONS rather than COMMON_OPTS to pass -march=skylake…
 2018-10-11 21:51:31 +02:00
Martin Kroeker 81c9985c3a
Use KERNEL_DEFINITIONS rather than COMMON_OPTS to pass -march=skylake-avx512 2018-10-11 11:03:27 +02:00
Martin Kroeker 56ebc7b53e
Merge pull request #1808 from martin-frbg/issue1806 
Add -march=skylake-avx512 to CFLAGS when the target is Skylake
 2018-10-11 07:48:08 +02:00
Martin Kroeker c5f88f5a57
Merge pull request #1807 from xianyi/revert-1798-cmake-avx512 
Revert "Add -march=skylake-avx512 when required"
 2018-10-11 07:47:53 +02:00
Martin Kroeker 8a11ec19d1
Syntax fix 2018-10-10 23:47:35 +02:00
Martin Kroeker fa53b903db
Add -march=skylake-avx512 to CFLAGS when the target is Skylake 
Should fix 1806 and #1801
 2018-10-10 19:22:01 +02:00