floraachy/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
7,530 Commits 47 Branches 64 Tags
fea1d4f66c784fed7e5efc48abd025ff6ad2d9f8
Commit Graph

7530 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Martin Kroeker
fea1d4f66c Merge pull request #4294 from martin-frbg/lapack909 
Fix accumulation in LAPACK ?LASSQ (Reference-LAPACK PR 909)
 2023-11-07 12:23:16 +01:00
Martin Kroeker
6f11992dbb Merge pull request #4293 from martin-frbg/lapack927 
Fix potential integer overflow in LAPACK C/ZBDSQR (Reference-LAPACK PR 927)
 2023-11-07 10:53:28 +01:00
Martin Kroeker
f6ec777701 Fix accumulation (Reference-LAPACK PR 909) 2023-11-06 21:40:50 +01:00
Martin Kroeker
cf8295da5c Fix potential overflow in the calculation of MAXIT 2023-11-06 21:22:26 +01:00
Martin Kroeker
cd8eb83bae Fix allocations and compiler warnings in ZROTG (#4289) 
* Clean up ZROTG
 2023-11-05 18:13:37 +01:00
Martin Kroeker
25096e5afe Merge pull request #4287 from martin-frbg/issue4282 
Use SkylakeX ?ASUM microkernel for Cooperlake/Sapphirerapids as well
 2023-11-04 23:26:17 +01:00
Martin Kroeker
9019bc4945 Use SkylakeX ?ASUM microkernel for Cooperlake/Sapphirerapids as well 2023-11-04 22:10:06 +01:00
Martin Kroeker
4c6ee3f18e Merge pull request #4285 from martin-frbg/cortexfix 
Fix outdated KERNEL files for SVE Cortex by aliasing to ARMV8SVE
 2023-11-03 21:32:49 +01:00
Martin Kroeker
3bfa4d4dcc Fix outdated SVE kernel definitions for Cortex cpus by aliasing to ARMV8SVE 2023-11-03 14:55:31 +01:00
Martin Kroeker
59444415ac Merge pull request #4280 from ChipKerchner/dynamicDispatchAIXandClang 
Add dynamic dispatch to AIX and clang for Power
 2023-11-02 23:43:59 +01:00
Chip-Kerchner
7dcb2d67f2 Have POWER7 return arch=POWER6. 2023-11-01 15:23:28 -05:00
Chip-Kerchner
c8882bd9d8 Remove POWER7 from cpu list. 2023-11-01 14:53:55 -05:00
Chip-Kerchner
d8e6e2b04d Merge branch 'develop' into dynamicDispatchAIXandClang 2023-11-01 14:22:06 -05:00
Martin Kroeker
0de786cfa6 Merge pull request #4278 from martin-frbg/issue4277 
CirrusCI: Add FreeBSD clang/gfortran build with OpenMP
 2023-11-01 19:45:09 +01:00
Martin Kroeker
9f7c35a4a8 Merge pull request #4279 from martin-frbg/issue4269 
Increase the default GEMM buffer size on modern ARM server cpus
 2023-10-31 15:41:25 +01:00
Martin Kroeker
728788f667 typo fix 2023-10-31 11:08:22 +01:00
Martin Kroeker
d003ad630b Increase the default GEMM buffer size on modern ARM server cpus 2023-10-31 10:26:38 +01:00
Martin Kroeker
dc1c880782 fix libgfortran path on bsd 2023-10-28 23:14:36 +02:00
Martin Kroeker
289a5f6d9b work around libgfortran install issue on FreeBSD 2023-10-28 18:44:58 +02:00
Martin Kroeker
1cec1c0fc7 Add FreeBSD clang/gfortran build with OpenMP 2023-10-28 14:43:19 +02:00
Martin Kroeker
9d425a5fe7 Merge pull request #4276 from martin-frbg/issue4275 
Clarify make/make install in the README and update the TARGET list there
 2023-10-28 14:34:17 +02:00
Martin Kroeker
f5e1f20f4d Update target list 2023-10-27 17:10:37 +02:00
Martin Kroeker
a7f73c764c Clarify "make" options and the need to repeat them in the install step 2023-10-27 16:48:47 +02:00
Chip Kerchner
badfb2e60f Merge branch 'develop' into XLC-AIX 2023-10-26 09:19:31 -05:00
Martin Kroeker
96f8bb1eb9 Merge pull request #4272 from RajalakshmiSR/AIX_AS 
POWER: AIX: Make use of power10 optimization
 2023-10-24 12:08:51 +02:00
Rajalakshmi Srinivasaraghavan
980f702f72 POWER: AIX: Make use of power10 optimization 
POWER10 optimizations are disabled when using default AIX assembler.
As we have fixed many issues recently, enabling optimization path
for default assembler.
 2023-10-19 18:48:19 -05:00
Martin Kroeker
68906a98c7 Merge pull request #4271 from rgommers/homebrew-nightly-on-main-repo 
Run nightly Homebrew cron job only on the main repo, not on forks
 2023-10-19 13:28:24 +02:00
Ralf Gommers
6b8379d6d9 Run nightly Homebrew cron job only on the main repo, not on forks 
I noticed this because GitHub emailed me that it would disable the
nightly job because it hadn't changed for 3 months. It currently takes
30-50 minutes daily, and by default runs on all forks of the main
repository that have the relevant workflow yaml file. That serves little
purpose and wastes quite a bit of energy - so disable the runs outside
of the main repo.

This will not disable the runs on forks already made in the past that
contain this workflow file, but it does save 3 months worth of runs on
every new fork that is created.

[skip ci]
 2023-10-19 11:38:26 +02:00
Martin Kroeker
0799b0d215 Merge pull request #4266 from martin-frbg/gh-mingw-ucrt 
GH Workflows: Switch MINGW-W64 jobs to UCRT
 2023-10-18 18:58:32 +02:00
Martin Kroeker
5c411ac7a8 Merge pull request #4268 from martin-frbg/issue4267 
Fix unwanted "hard" fallback to Prescott in runtime detection of Intel cpus
 2023-10-18 17:47:33 +02:00
Martin Kroeker
e12aaed13d Fix unwanted fallthrough from Intel Family 6 to 15 in case of identification failure 2023-10-18 16:28:54 +02:00
Martin Kroeker
f8c230c21c Switch MINGW-W64 jobs to UCRT 2023-10-18 11:58:54 +02:00
Martin Kroeker
c28d71c6fb Merge pull request #4265 from martin-frbg/issue4228 
Fix compilation with (the fortran compiler from) Cray CCE
 2023-10-17 15:08:30 +02:00
Martin Kroeker
b41cab0875 Need to use override to actually strip down the already defined FFLAGS for NAG and CCE Fortran 2023-10-16 22:20:59 +02:00
Martin Kroeker
301e2ecc49 Cray Fortran uses -O in combinations like -O omp so don't filter that out 2023-10-16 22:15:46 +02:00
Martin Kroeker
66c2c41e99 Merge pull request #4260 from RajalakshmiSR/AIX-M4 
POWER: Increase macro size limit for AIX
 2023-10-13 10:51:23 +02:00
Martin Kroeker
425bcc1f8b Merge pull request #4256 from ChipKerchner/fixBfloat16BitsStruct 
Fix bfloat16_bits union so that it always the sizeof unsigned short for AIX.
 2023-10-12 22:01:50 +02:00
Martin Kroeker
789cdcc94f Merge pull request #4259 from martin-frbg/azureosxclang 
AzureCI: move OSX-Clang jobs to macOS-12 to resolve setup/build timeouts
 2023-10-12 20:04:28 +02:00
Rajalakshmi Srinivasaraghavan
9f42570e33 POWER: Increase macro size limit for AIX 
This patch increases the macro size limit from 4096 to 16384 to
allow compiling larger assembly files in AIX.
Tested with GCC and IBM Open XL C.
 2023-10-12 12:37:40 -05:00
Martin Kroeker
9f49aef91b Merge pull request #4255 from RajalakshmiSR/AIX-P10 
POWER10: Fix compilation issues with Open XL C
 2023-10-12 18:59:17 +02:00
Martin Kroeker
fe75c88a2c AzureCI: move OSX-Clang jobs to macOS-12 to resolve setup/build timeouts 2023-10-12 18:20:09 +02:00
Chip-Kerchner
d46eba06a7 Pack structure only on AIX. 2023-10-12 09:41:33 -05:00
Martin Kroeker
90231bfc4e Merge pull request #4258 from martin-frbg/issue4257 
Fix build on Fujitsu A64FX
 2023-10-12 16:38:28 +02:00
Martin Kroeker
e7d05402e0 Fix up S/D GEMM copy function definitions after #4009 2023-10-12 14:24:53 +02:00
Chip-Kerchner
e98e3c4783 Fix float32_bits union so that it always the sizeof float. 2023-10-11 18:05:55 -05:00
Chip-Kerchner
97a61d0577 Fix bfloat16_bits union so that it always the sizeof unsigned short. 2023-10-11 17:36:43 -05:00
Rajalakshmi Srinivasaraghavan
71d733e5f7 POWER: Avoid m4 conversions for C files 
This patch removes intermediate m4 conversions used in sbgemm
compilation as it is not needed for .c files.
Tested on AIX with gcc and IBM Open XL C.
 2023-10-11 17:18:42 -05:00
Rajalakshmi Srinivasaraghavan
82fc29a57a POWER10: Fallback to POWER8 functions 
As cgemm and zgemm kernels are not optimized for big endian falling
back to POWER8 versions.  Tested on AIX using gcc and Open XL C.
 2023-10-11 17:04:42 -05:00
Martin Kroeker
bf3183d31d Merge pull request #4253 from martin-frbg/issue4239-2 
Require "classic ld" with XCODE 15.x on Mac
 2023-10-10 18:44:08 +02:00
Martin Kroeker
103d6f4e42 Require "classic ld" with XCODE 15.x on Mac 2023-10-10 16:15:52 +02:00