phynexis-deps/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
9,445 Commits 60 Branches 70 Tags
1742decdcbecd0fc2a6effe14e6ff016eb47a9ca
Commit Graph
9445 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Martin Kroeker 1742decdcb Merge pull request #5375 from lowkeyrossi/CI_for_WoA 
Add CI support for building and validating OpenBLAS on WoA
 2025-07-15 21:16:03 +02:00
Martin Kroeker 08df0f02d9 Merge pull request #5382 from martin-frbg/issue5379 
Update cross-compilation instructions for the Android NDK
 2025-07-15 21:07:34 +02:00
Martin Kroeker 7d7757acd1 Update cross-compilation instructions for the Android NDK 2025-07-15 18:25:55 +02:00
Martin Kroeker 666e1081ac Merge pull request #5378 from martin-frbg/cpuid_lunarlake 
Add ID data for Intel Lunar Lake ("Core Ultra 200V series")
 2025-07-13 23:18:22 +02:00
Martin Kroeker 3ea6322eff Merge pull request #5377 from Mousius/test-fixes 
Improve bgemm and sbgemm testing
 2025-07-13 23:03:35 +02:00
Martin Kroeker 848e9e6ba7 Add ID data for Intel Lunar Lake ("Core Ultra 200V series") 2025-07-13 20:34:19 +02:00
Chris Sidebottom 3f110c8272 Improve bgemm and sbgemm testing 
- Fixes wrong return type for `is_close`
- Adds stricter compiler flags for test files so we don't see the above
issue again
- Re-uses test helper functions between compare_sgemm_sbgemm/bgemm.c
 2025-07-13 12:48:09 +00:00
newyork_loki cb2c726716 Add CI support for OpenBLAS on WoA 2025-07-12 14:37:30 +05:30
newyork_loki c8d41e4a32 Add CI support for OpenBLAS on WoA 2025-07-12 14:34:29 +05:30
Martin Kroeker 81b30d4538 Merge pull request #5374 from martin-frbg/fixup-5373 
Fix compilation of the new bgemm test
 2025-07-11 15:33:38 +02:00
Martin Kroeker aad97c7763 Fix return type declaration 2025-07-11 15:32:41 +02:00
Martin Kroeker 7acb122a98 Merge pull request #5373 from Mousius/bgemm-optimized 
Add optimized BGEMM kernel for NEOVERSEV1 target
 2025-07-11 11:56:56 +02:00
Chris SidebottomandYe Tao 740efd71c4 Add optimized BGEMM kernel for NEOVERSEV1 target 
This also improves the testing and generic kernel by re-using the BF16
conversion functions.

Built on top of https://github.com/OpenMathLib/OpenBLAS/pull/5357 and derived from https://github.com/OpenMathLib/OpenBLAS/pull/5287

Co-authored-by: Ye Tao <ye.tao@arm.com>
 2025-07-10 23:23:27 +00:00
Martin Kroeker e927373f62 Merge pull request #5371 from martin-frbg/fixup-5357 
Complete the infrastructure changes for adding BGEMM
 2025-07-10 16:38:37 +02:00
Martin Kroeker 9a272fece6 Re-enable the BGEMM tests 2025-07-10 15:02:59 +02:00
Martin Kroeker b54aec804e remove spurious include 2025-07-10 15:00:30 +02:00
Martin Kroeker 343830c26f Add BGEMM parameter tables 2025-07-10 14:59:46 +02:00
Martin Kroeker b37516add6 Add BGEMM parameters 2025-07-10 14:59:01 +02:00
Martin Kroeker d030f81380 Merge pull request #5369 from martin-frbg/lapack1144 
Fix workspace allocation in LAPACKE strsen/dtrsen (Reference-LAPACK PR 1144)
 2025-07-10 10:46:15 +02:00
Martin Kroeker b746f0eda3 Allocate IWORK to hold at least the one element for workspace queries 2025-07-10 08:58:16 +02:00
Martin Kroeker b8f66ba0ee Merge pull request #5367 from Mousius/bgemm-init 
Temporarily disable test_bgemm
 2025-07-10 00:57:41 +02:00
Martin Kroeker cdebb4fd4b Merge pull request #5365 from martin-frbg/issue5324 
Fix arm64 HAVE_SME setting for DYNAMIC_ARCH builds using CMake
 2025-07-09 22:50:54 +02:00
Martin Kroeker ff614575c9 Fix arm64 HAVE_SME setting for DYNAMIC_ARCH builds 2025-07-09 14:44:25 +02:00
Martin Kroeker 0e11537cab Merge pull request #5357 from Mousius/bgemm-init 
Add infrastructure for BGEMM
 2025-07-09 09:34:58 +02:00
Chris Sidebottom 8cd4be8d47 Temporarily disable test_bgemm 2025-07-09 08:27:18 +01:00
Chris Sidebottom 66d9185ebe Fix CMake support 2025-07-08 22:49:55 +00:00
Martin Kroeker 98aefb70b4 Merge pull request #5292 from isharif168/optimized_gemv_n_1x3 
Optimize gemv_n_sve_v1x3 kernel
 2025-07-08 21:05:43 +02:00
Martin Kroeker fd37406817 Merge branch 'develop' into optimized_gemv_n_1x3 2025-07-08 21:05:30 +02:00
Chris SidebottomandYe Tao 48394384ef Use correct constants for per-target BGEMM/SBGEMM 
This fixes the build and tests on `NEOVERSEV1` target, which was failing
with specific constants for `SBGEMM`

Co-authored-by: Ye Tao <ye.tao@arm.com>
 2025-07-08 16:23:27 +01:00
Chris Sidebottom 73bf0b941a Add bgemm to gensymbol 2025-07-08 16:22:43 +01:00
Chris SidebottomandYe Tao f95e7b0e32 Add infrastructure for BGEMM 
Setting up all the infrastructure for BGEMM support in OpenBLAS, hopefully I found all the right places.

Derived mostly from the previous work done in https://github.com/OpenMathLib/OpenBLAS/pull/5287

Co-authored-by: Ye Tao <ye.tao@arm.com>
 2025-07-08 16:22:41 +01:00
Martin Kroeker 15d6e58510 Merge pull request #5364 from martin-frbg/blashalf 
change BLAS_HALF to BLAS_BFLOAT16 in parallelized POTRF (another missed rename)
 2025-07-08 17:14:50 +02:00
Martin Kroeker 04bb5acd79 change BLAS_HALF to BLAS_BFLOAT16 (another missed rename) 2025-07-08 14:40:22 +02:00
Martin Kroeker 3d31887073 Merge pull request #5362 from Mousius/fix-bf16 
Fix SBGEMM BFLOAT16 build
 2025-07-08 14:35:50 +02:00
Martin Kroeker 0ddf8ebd42 Merge pull request #5354 from pratiklp00/p11 
Add Support for POWER11
 2025-07-08 11:52:18 +02:00
Martin Kroeker d2ea9bbb6d Merge pull request #5363 from guoyuanplct/develop 
Update CONTRIBUTORS.md
 2025-07-08 11:47:18 +02:00
guoyuanplct 4ff549a450 Update CONTRIBUTORS.md 2025-07-08 17:16:51 +08:00
guoyuanplct 309c48e327 Update CONTRIBUTORS.md 2025-07-08 17:13:27 +08:00
Chris Sidebottom 552e1c7a7a Correct compiler flags for NEOVERSEV1 target 2025-07-07 11:26:36 +00:00
Chris Sidebottom 46b9b7a080 Also enable BFLOAT16 for make cirun 2025-07-07 10:41:12 +00:00
Chris Sidebottom eaaa628af2 Enable BUILD_BFLOAT16 in cirun 2025-07-07 10:20:17 +00:00
Chris Sidebottom 7a97c4ca97 Rename HALF -> BFLOAT16 in some more places 2025-07-07 10:13:39 +00:00
Martin Kroeker ee6560c89f Merge pull request #5360 from sertonix/cpuid-arm 
Fix cpuid.S on arm
 2025-07-07 07:41:56 +02:00
Sertonix 8d11e4630c Fix cpuid.S on arm 
The ARM assembly syntax differs a bit

Fixes 61b9339d3a getarch/cpuid.S: Fix warning about executable stack

Signed-off-by: Sertonix <sertonix@posteo.net>
 2025-07-06 23:48:10 +02:00
Martin Kroeker 03a4afcf14 Merge pull request #5359 from martin-frbg/gitign_isnan 
update gitignore configuration
 2025-07-05 22:26:55 +02:00
Martin Kroeker 901de8f33a remove lapacke_mangling.h and add la_xisnan.mod 2025-07-05 20:35:16 +02:00
Martin Kroeker ce6991780a Merge pull request #5356 from ilina-linaro/ilina-woa 
Update README.md to include Windows on Arm64
 2025-07-05 19:07:45 +02:00
Martin Kroeker df013c5e28 Merge pull request #5358 from iha-taisei/dot_unroll 
Performance improvements of [SD]DOT with loop-unrolling on A64FX
 2025-07-04 23:38:32 +02:00
Iha, Taisei f7ad906b49 Performance improvements of [SD]DOT with loop-unrolling on A64FX 2025-07-04 22:57:44 +09:00
Lina Iyer 7f360001f9 Update README.md to include Windows on Arm64 
Update README.md to indicate that binaries are available for Windows on ARM64
 2025-07-03 07:15:20 -06:00