Martin Kroeker
0968dddf1a
Merge pull request #5409 from martin-frbg/issue5372
...
Work around gcc15.1 on POWER misoptimizing DGEMV at -O3
2025-07-30 10:36:39 -07:00
Martin Kroeker
eddfe1e6b3
Merge pull request #5408 from ChipKerchner/fixRISCV64GEMVInitializationAndWarnings
...
Fix bad vector zero initializer and other compiler warnings for RISC-V.
2025-07-30 08:43:08 -07:00
Martin Kroeker
a3b9c933c5
mark xbuffer as volatile to work around gcc15.1 optimizer bug
2025-07-30 17:05:36 +02:00
Chip Kerchner
72f082f31d
Fix bad vector zero initializer and other compiler warnings for RISC-V.
2025-07-30 14:04:43 +00:00
Martin Kroeker
9a64b32b44
Merge pull request #5406 from martin-frbg/fixbgemmtest
...
Fix building of bgemm tests on GEMM3M-capable (x86) targets
2025-07-28 23:17:29 -07:00
Martin Kroeker
b66a01f909
Fix building of bgemm tests on GEMM3M-capable (x86) targets
2025-07-28 22:43:28 +02:00
Martin Kroeker
a5e7c0e3e0
Merge pull request #5396 from abhishek-iitmadras/abhishekk_bfloat16
...
ARM64: Enable bfloat16 kernels by default
2025-07-28 13:39:08 -07:00
abhishek-fujitsu
6356190d06
fix gfortran link path in dynamic_arch.yml
2025-07-28 14:37:51 +05:30
abhishek-fujitsu
4c8dcb3a8f
Darwin/arm64: disable SVE/SME and fix gfortran link path
2025-07-26 16:59:46 +05:30
Martin Kroeker
33b50548eb
Merge pull request #5403 from martin-frbg/issue5402
...
Introduce a (crude) threshold to multithreading in STRMV/DTRMV
2025-07-25 20:10:47 +02:00
Martin Kroeker
c504aedca1
Merge pull request #5400 from Mousius/neoversev2-target
...
Add NEOVERSEV2 target support
2025-07-25 15:47:06 +02:00
Martin Kroeker
b9e107932a
add NeoverseV2
2025-07-25 15:44:34 +02:00
Martin Kroeker
2f89a5970e
fix NeoverseV2 typo
2025-07-25 15:43:37 +02:00
Martin Kroeker
a9e8fa06bf
Introduce a (crude) threshold to multithreading
2025-07-25 15:15:46 +02:00
Martin Kroeker
b4c2b34a45
Merge pull request #5401 from martin-frbg/followup-5397
...
Include float-bfloat conversion functions in ONLY_CBLAS builds as well
2025-07-25 13:56:13 +02:00
Martin Kroeker
c9204f7b6f
Merge pull request #5399 from Mousius/bgemm-8x4
...
Add optimized BGEMM for NEOVERSEN2 target
2025-07-25 11:20:52 +02:00
Martin Kroeker
a55e65dba9
Merge pull request #5391 from martin-frbg/issue5387
...
Use OpenBLAS_ROOT_DIR in OpenBLASConfig.cmake generation only if set
2025-07-25 09:28:46 +02:00
abhishek-fujitsu
0bc79da587
add neon header
2025-07-25 11:10:20 +05:30
abhishek-fujitsu
720a4743b9
update contribution list
2025-07-25 11:08:22 +05:30
abhishek-fujitsu
05fc88180c
ARM64: Enable bfloat16 kernels by default
2025-07-25 11:08:22 +05:30
Martin Kroeker
965463f177
Include float-bfloat conversion functions in ONLY_CBLAS builds as well
2025-07-24 23:33:20 +02:00
Martin Kroeker
4272cf8c7f
Merge pull request #5398 from martin-frbg/fixup-5394
...
Update ?GEMM-to-?GEMV forwarding settings for CMake
2025-07-24 23:29:39 +02:00
Chris Sidebottom
87247daadc
Add NEOVERSEV2 target support
...
Did a quick run around to make `TARGET=NEVOERSEV2` build successfully.
Fixes #5385
2025-07-24 12:40:31 +01:00
Chris Sidebottom
ea2faf0c9a
Add optimized BGEMM for NEOVERSEN2 target
...
This re-uses the existing NEOVERSEN2 8x4 `sbgemm` kernel to implement `bgemm`.
2025-07-24 10:59:28 +00:00
Martin Kroeker
a5b55f6fe3
remove CBLAS restriction on GEMM_GEMV forwarding
2025-07-24 09:30:58 +02:00
Martin Kroeker
a4f4662459
Merge pull request #5397 from omegacoleman/fix-cblas-bgemm
...
Fix cmake building with cblas_bgemm
2025-07-24 09:28:25 +02:00
Martin Kroeker
82954ba4ca
Update ?GEMM-to-?GEMV forwarding settings
2025-07-23 23:24:42 +02:00
Martin Kroeker
392d38168e
Merge pull request #5394 from Mousius/optimize-bgemv
...
Optimized BGEMV for NEOVERSEV1 target
2025-07-23 23:13:44 +02:00
youcai
41f9701ebc
Fix cmake building with cblas_bgemm
2025-07-23 22:10:53 +08:00
Martin Kroeker
f4caa61e47
Merge pull request #5395 from martin-frbg/fixloongsonCI
...
Fix libffi6 download in the Loongarch64_clang CI job (for now)
2025-07-23 14:36:30 +02:00
Martin Kroeker
444d03db9c
switch to another site that still has libffi6 (for now)
2025-07-23 14:04:11 +02:00
Chris Sidebottom
2c3cdaf74e
Optimized BGEMV for NEOVERSEV1 target
...
- Adds bgemv T based off of sbgemv T kernel
- Adds bgemv N which is slightly alterated to not use Y as an
accumulator due to the output being bf16 which results in loss of
precision
- Enables BGEMM_GEMV_FORWARD to proxy BGEMM to BGEMV with new kernels
2025-07-23 10:51:41 +01:00
Martin Kroeker
7d908564fe
Use OpenBLAS_ROOT_DIR in CMake config file generation only if set
2025-07-22 16:01:46 +02:00
Martin Kroeker
2f81d6e60c
Merge pull request #5390 from martin-frbg/issue5388-2
...
Declare the "small" complex DOT and AXPY kernels for RISCV-ZVL256B static in addition to inline
2025-07-22 13:05:14 +02:00
Martin Kroeker
e2d941e9af
Declare the "small" kernel static in addition to inline
2025-07-22 11:02:32 +02:00
Martin Kroeker
8214700930
Declare the "small" kernel static in addition to inline
2025-07-22 11:01:37 +02:00
Martin Kroeker
4ae8707b54
Merge pull request #5389 from martin-frbg/issue5388
...
Add cross-compilation parameters for RISCV64 targets in CMake
2025-07-22 10:57:59 +02:00
Martin Kroeker
b24212f5df
fix numbers
2025-07-21 22:54:52 +02:00
Martin Kroeker
6ff06f5483
Add cross-compilation data for RISCV64 targets
2025-07-21 22:42:15 +02:00
Martin Kroeker
d92f151634
Merge pull request #5386 from martin-frbg/issue5384
...
Fixes for some gcc warnings
2025-07-19 08:33:51 +02:00
Martin Kroeker
30dbca5051
fix misleading indentation to silence a gcc warning
2025-07-18 23:51:04 +02:00
Martin Kroeker
38e6999295
format cleanup
2025-07-18 23:45:08 +02:00
Martin Kroeker
3df503cafd
portability fix and cleanup
2025-07-18 23:41:57 +02:00
Martin Kroeker
39c90f9859
Merge pull request #5380 from quic/topic/sgemm_direct_sme1_alpha_beta
...
SME1 based direct kernel (with alpha and beta) for cblas_sgemm level 3
2025-07-18 23:23:39 +02:00
Rajendra Prasad Matcha
eae0abfdb6
SME1 based direct kernel with alpha and beta for cblas_sgemm level 3 API.
2025-07-17 16:14:31 +05:30
Martin Kroeker
ac8cbfdd8e
Merge pull request #5381 from Mousius/bgemv-infrastructure
...
Add infrastructure for BGEMV
2025-07-16 23:22:08 +02:00
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
Chris Sidebottom
947d7af4c9
Fix CMake references to bscal and bgemv
2025-07-15 15:41:53 +01:00
Martin Kroeker