floraachy/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6,437 Commits 47 Branches 64 Tags
dbdb6861281d3127bf0fd514b26fe63b5343e1d6
Commit Graph

6437 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Martin Kroeker
dbdb686128 Merge pull request #3625 from RajalakshmiSR/P10_store 
POWER10: Changing store instructions for Level1 functions
 2022-05-15 00:24:35 +02:00
Rajalakshmi Srinivasaraghavan
b62173c5a0 POWER10: Changing store instructions for Level1 functions 
This patch changes 32 bytes stores to two 16 bytes stores
to fix a recent degradation due to 32 bytes stores.
 2022-05-12 11:17:33 -05:00
Martin Kroeker
ce814e84dc Merge pull request #3619 from martin-frbg/fixup-3613 
Initial attempt at proper cpu detection on RISCV
 2022-05-04 15:12:22 +02:00
Martin Kroeker
46d22150de Initial attempt at proper cpu detection on RISCV 2022-05-04 08:58:56 +02:00
Martin Kroeker
8f13ab94d2 Merge pull request #3613 from Rabenda/fix-riscv 
Fix riscv64 detect
 2022-05-04 07:22:47 +02:00
Martin Kroeker
7d6c0ae223 Merge pull request #3618 from martin-frbg/issue3606 
Automatically downgrade C910V to RISCV64_GENERIC if the compiler lacks vector support
 2022-05-04 07:22:25 +02:00
Martin Kroeker
18427f3759 Have getarch downgrade the RISCV C910V target to GENERIC if compiler lacks vector support 2022-05-03 23:29:55 +02:00
Martin Kroeker
d328636e58 Add compiler check for RISCV vector support 2022-05-03 23:27:50 +02:00
Martin Kroeker
06d1dd6ba8 Merge pull request #3616 from martin-frbg/issue3615 
Fix CMAKE generator rules for ?laswp_ncopy and ?neg_tcopy kernels
 2022-05-01 00:09:20 +02:00
Martin Kroeker
567d8853d1 rename lapack subtarget to lapack_overrides to avoid name clash with netlib in case-insensitive settings 2022-04-30 20:38:09 +02:00
Martin Kroeker
d502326e54 Merge pull request #3614 from martin-frbg/clapackfix 
Makefile fixes related to C_LAPACK, plus Travis CI fixes
 2022-04-30 20:35:17 +02:00
Martin Kroeker
96ddadf164 Update .travis.yml 2022-04-30 18:49:04 +02:00
Martin Kroeker
adaf03835b try to fix assembler errors on z13 2022-04-30 18:33:00 +02:00
Martin Kroeker
84cb58b7fb Fix generator rules for ?laswp_ncopy and ?neg_tcopy 2022-04-30 15:28:38 +02:00
Martin Kroeker
11f023b712 fix arch tags 2022-04-27 22:18:22 +02:00
Martin Kroeker
b4b9ccdbfa Remove leftover debug output 2022-04-27 21:59:45 +02:00
Martin Kroeker
24e99eca31 Avoid adding -lgfortran with NOFORTRAN 2022-04-27 20:31:42 +02:00
Martin Kroeker
3dd09e87bf Update NOFORTRAN message for fallback to C_LAPACK 2022-04-27 20:26:45 +02:00
Han Gao
8123324c99 Fix riscv64 arch detect 
Signed-off-by: Han Gao <gaohan@uniontech.com>
 2022-04-27 02:29:43 +08:00
Han Gao
3fc52ebcfb Fix other arch build in detect. 
When CORE is empty, use -march=loongson3a. Fix it.

Signed-off-by: Han Gao <gaohan@uniontech.com>
 2022-04-27 01:34:55 +08:00
Martin Kroeker
ee4244538c Merge pull request #3612 from nsait-linaro/fix-windows-make-build 
build: minor fixes to build on windows with make
 2022-04-25 15:51:34 +02:00
Niyas Sait
3f5d145cd4 build: minor fixes to build on windows with make 
This patch contains following fixes

1. Fix to build without PIC flag
2. Define LAPACK_COMPLEX_STRUCTURE for windows. Builds are failing
without it and changes are consistent with the CMake rules defined
in system.cmake (line 576)
 2022-04-25 00:01:12 +01:00
Martin Kroeker
18b19d135b C_LAPACK: Fixes to make it compile with MSVC (#3605) 
* Fix f2c-like support functions to compile with MSVC, and
re-enable C_LAPACK for MSVC in CMAKE

* Add MSVC&flang build to Azure CI in order to check C_LAPACK correctness
 2022-04-17 17:49:38 +02:00
Martin Kroeker
d09b9dd0cc Merge pull request #3607 from martin-frbg/issue3603 
Fix undefined PREFETCHSIZEs in PPC440 GEMV kernels
 2022-04-16 12:54:35 +02:00
Martin Kroeker
05dcfa176e fix undefined prefetchsizes 2022-04-16 10:04:27 +02:00
Martin Kroeker
2bbb9f05c7 fix undefined prefetchsize 2022-04-16 10:00:10 +02:00
Martin Kroeker
8144a498ad Merge pull request #3604 from mmuetzel/ci 
Adapt commands for tests with GNU make.
 2022-04-11 19:31:26 +02:00
Markus Mützel
430bea00ba Adapt commands for tests with GNU make. 2022-04-11 11:45:05 +02:00
Martin Kroeker
b7873605d4 Use f2c translations of LAPACK when no Fortran compiler is available (#3539) 
* Add C equivalents of the Fortran routines from Reference-LAPACK as fallbacks, and C_LAPACK variable to trigger their use
 2022-04-09 22:38:58 +02:00
Martin Kroeker
2edcd9b9dc Merge pull request #3601 from mmuetzel/ci 
Consolidate actions on GitHub runners.
 2022-04-09 22:25:15 +02:00
Martin Kroeker
848c4e881d Merge pull request #3602 from martin-frbg/fixup3600 
Fix missing braces from previous commit (PR3600)
 2022-04-09 22:23:45 +02:00
Martin Kroeker
74dba0c90a Fix missing braces from previous commit (PR3600) 2022-04-09 20:03:36 +02:00
Markus Mützel
2aa8086bdd Consolidate actions on GitHub runners. 
Re-organize build matrix for Ubuntu and MacOS runners.
Don't start runners that don't do anything.
Run tests.
 2022-04-09 18:46:27 +02:00
Martin Kroeker
bef3871833 Disable flang (over-)optimizations in BLAS tests (#3600) 
* limit flang optimizations to -O2
 2022-04-09 17:14:24 +02:00
Martin Kroeker
65a14d4b40 Merge pull request #3593 from e4t/Fix_build_targets_Makefile_prebuild 
Fix build targets in Makefile.prebuild
 2022-04-07 14:25:15 +02:00
Martin Kroeker
145ccf8943 Prevent powershell from adding a BOM to test input (#3595) 
* Prevent addition of a BOM to test input (which would distort the names of output files)
 2022-04-07 14:24:19 +02:00
Egbert Eich
454128824e Fix build targets in Makefile.prebuild 
- config.h was used as target even when it wasn't generated.
  This only worked because the 'dummy' target always triggers
  a full rebuild.
  It is however better to specify the exact target that is to
  be rebuilt do avoid confusion.
- Explicitly mark 'dummy' as a 'phony' target.

Signed-off-by: Egbert Eich <eich@suse.com>
 2022-04-05 11:36:03 +02:00
Martin Kroeker
4dbdc28c25 Merge pull request #3590 from mmuetzel/ci-msys2 
Add action for MSYS2 builds.
 2022-04-03 19:53:38 +02:00
Markus Mützel
67714aea71 Add action for MSYS2 builds. 2022-03-31 11:07:18 +02:00
Martin Kroeker
ad4598143b Merge pull request #3575 from mmuetzel/lapacke-win64 
Fix LAPACKE with 64-bit indexing on Windows.
 2022-03-29 20:04:04 +02:00
Martin Kroeker
d5ed695632 Merge pull request #3588 from martin-frbg/fix3586 
Fix mistaken declaration of CortexX1 as ArmV9 in PR#3586
 2022-03-29 19:36:27 +02:00
Martin Kroeker
1d4e703f50 Merge pull request #3589 from e4t/Exclude_paramter.c_symbols_with_DYNAMIC_ARCH 
Do not include symbols defined in driver/others/parameter.c in DYNAMI…
 2022-03-29 19:35:56 +02:00
Egbert Eich
5e6d160020 Do not include symbols defined in driver/others/parameter.c in DYNAMIC_ARCH 
driver/others/parameter.c does not get build during DYNAMIC_ARCH, thus,
do not declare its symbols. This will make the build fail early and in
an obvious way if functions are trying to use these symbols.

Signed-off-by: Egbert Eich <eich@suse.com>
 2022-03-29 10:01:28 +02:00
Martin Kroeker
a55a06c269 Update param.h 2022-03-28 18:10:08 +02:00
Martin Kroeker
abbc65cff4 Cortex X1 is only Arm8.2 2022-03-28 17:40:27 +02:00
Martin Kroeker
d93cf7f23c fix defines for CORTEX-X 2022-03-28 17:37:06 +02:00
Martin Kroeker
48e421934f CortexX1 is only ArmV8 2022-03-28 17:31:26 +02:00
Martin Kroeker
115bc9b98f CortexX1 is ARMV8 like A7x 2022-03-28 17:28:29 +02:00
Martin Kroeker
848722926c CortexX1 is only ARMV8 2022-03-28 17:18:56 +02:00
Martin Kroeker
8002048217 Merge pull request #3587 from e4t/fix_avx512 
Use CC and full command line instead of hard-coding gcc for AVX512 ch…
 2022-03-28 14:58:32 +02:00