OSchip
/
OpenBLAS
mirror of https://github.com/xianyi/OpenBLAS.git
0
0
Fork 2
Code Issues Packages Projects Releases Wiki Activity
10,687 Commits 58 Branches 70 Tags 121 MiB
Commit Graph

65 Commits

Author SHA1 Message Date
Martin Kroeker 63ad298a67
Merge branch 'develop' into attrib-hidden 2026-07-21 20:00:16 +02:00
Rajendra Prasad Matcha c32eefd87f Fix incorrect leading dimension check for SME SGEMM direct kernel path 
For row-major matrices, the tight-packing condition should be k==lda
(A is m×k), n==ldb (B is k×n), and n==ldc (C is m×n). The old check
used m==lda and k==ldc, which prevented the SME/direct kernel from
being invoked except when m==k==n (square matrices).

Fixes https://github.com/OpenMathLib/OpenBLAS/issues/5794
 2026-05-12 15:45:36 +05:30
mattip be7da1f111 add visibility=default to exported functions, visibility=hidden to most assembler 2026-02-05 06:31:17 +11:00
Alex James d2906e8787
Fix ARMV9SME/VORTEXM4 GEMM compilation with SMP disabled 
gemm.c currently declares gotoblas_corename in SMP-enabled builds, but
the ARMV9SME and VORTEXM4 targets call gotoblas_corename even when SMP
is disabled. Fix compilation of the ARMV9SME and VORTEXM4 targets with
SMP disabled by unconditionally declaring gotoblas_corename for
DYNAMIC_ARCH builds.
 2026-01-17 22:03:29 -08:00
Martin Kroeker 643a0b53b0
Allow VortexM4 on the direct_SME fast path only for clang-based compilers 2025-10-19 13:37:38 -07:00
Martin Kroeker 20f5ed1a94
Merge branch 'OpenMathLib:develop' into issue5414 2025-10-08 05:27:28 -07:00
Martin Kroeker fa912ce852
rework definitions of ?FLOAT16_GEMM_GEMV_FORWARD 2025-10-08 11:11:52 +02:00
Chris Sidebottom 37fc3bbca0 Add Infrastructure for SHGEMV 
This adds all the relevant bits and pieces to add a `shgemv` path as
well as a future `hgemm`/`hgemv` path in a similar model to `sb` and `b`
interfaces.

I've also fixed a few bits and pieces around `shgemm` which didn't build
in a few situations.
 2025-10-07 15:03:24 +00:00
Martin Kroeker 1b88c9c742
remove debugging printouts 2025-08-24 13:48:22 -07:00
Martin Kroeker 7f89c6f353
smh-based direct sgemm currently requires leading dimensions to be same as matrix dimension 2025-08-23 14:20:15 -07:00
Martin Kroeker de91afd2ae
Move SGEMM_DIRECT after the CBLAS parameter check and add sgemm_direct_performant for ARM64 2025-08-18 01:44:21 -07:00
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
Chris Sidebottom 66d9185ebe Fix CMake support 2025-07-08 22:49:55 +00:00
Chris Sidebottom 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
Srangrang ec14e1648c fix: resolve non-RISCV host build failed issue 
- adjust interface to disable "small matrix" pathway
- separate HFLOAT16 from BFLOAT16
- remove SHGEMM_UNROLL_M and SHGEMM_UNROLL_N equal conditions

Related to PR#5290
Co-authored-by Martin
 2025-06-15 20:25:15 +08:00
Martin Kroeker 6680e0592f
Fix conditional inclusion of SGEMM_KERNEL_DIRECT 2025-05-17 05:12:15 -07:00
Martin Kroeker 09ba099461
make throttling code conditional on SMP 2025-02-25 12:10:48 +01:00
Marek Michalowski b723c1b7b7 Add thread throttling profile for SGEMM on `NEOVERSEV2` 2025-02-20 10:28:21 +00:00
Vaisakh K V d23eb3b93e Support for SME1 based sgemm_direct kernel for cblas_sgemm level 3 API 
* Added ARMV9SME target
* Added SGEMM_DIRECT kernel based on SME1
 2025-02-13 14:51:21 +05:30
Chris Daley cb48505251 optimize gemv forwarding on ARM64 systems 2024-10-24 21:05:26 -07:00
Chip Kerchner 36bd3eeddf Vectorize BF16 GEMV (VSX & MMA). Use GEMM_GEMV_FORWARD_BF16 (for Power). 2024-10-13 13:46:11 -05:00
gxw 48698b2b1d LoongArch64: Rename core 
Use microarchitecture name instead of meaningless strings to name the core,
the legacy core is still retained.
1. Rename LOONGSONGENERIC to LA64_GENERIC
2. Rename LOONGSON3R5 to LA464
3. Rename LOONGSON2K1000 to LA264
 2024-09-29 09:35:21 +08:00
Martin Kroeker 7878976236
disable forwarding from SBGEMM to SBGEMV for now 2024-08-08 18:03:38 +02:00
Chris Sidebottom b26424c6a2 Allow opt into GEMM -> GEMV forwarding 2024-07-31 13:09:14 +01:00
Chris Sidebottom 90eb863d4b Re-add accidental removal 2024-07-31 13:09:14 +01:00
Chris Sidebottom 28b5334f22 Complete implementation of GEMV forwarding 2024-07-31 13:09:14 +01:00
Martin Kroeker 3db5dbc88e forward to GEMV when one argument is actually a vector 2024-07-31 13:09:14 +01:00
gxw 637c650f4f loongarch64: Add buffer offset for target LOONGSON3R5 2024-05-10 11:42:53 +08:00
Martin Kroeker 93d975d8fd
Merge pull request #4593 from XiWeiGu/loongarch_add_buffer_offset 
loongarch: Optimizing the performance of the GEMM on servers
 2024-04-10 14:23:31 +02:00
gxw d8c4ea8793 loongarch: Optimizing the performance of the GEMM on servers 2024-04-09 09:03:34 -04:00
Martin Kroeker a3354a7630
Cap the number of parallel threads 2024-03-27 22:00:30 +01:00
Honglin Zhu 71e4125795 Fix syscall error on non-x86 platform 2023-05-22 21:59:59 +08:00
Honglin Zhu 90f041e348 Invoke the syscall to allow the use of amx tiles 2023-05-19 10:48:18 +08:00
Wangyang Guo 4289cf048d sbgemm: avoid falling into SGEMM_KERNEL_DIRECT 2021-09-07 21:30:46 +08:00
Wangyang Guo 2e44ca0136 sbgemm: add missing cblas_sbgemm definition 2021-08-30 17:40:30 +08:00
Wangyang Guo 1d83ca4bca Small Matrix: support BFLOAT16 data type 2021-08-30 17:40:20 +08:00
Wangyang Guo c17d6dacb2 Small Matrix: skip compile in unimplemented data type 2021-08-05 05:46:13 +00:00
Wangyang Guo aa50185647 Small Matrix: better handle with GEMM3M marco 2021-08-05 02:45:53 +00:00
Wangyang Guo 478d1086c1 Small Matrix: support DYNAMIC_ARCH build 2021-08-04 03:12:41 +00:00
Wangyang Guo 5dc7c3c8e5 Small Matrix: add GEMM_SMALL_MATRIX_PERMIT to tune small matrics case 2021-08-02 07:06:54 +00:00
Xianyi Zhang 6022e5629c Refs #2587 fix small matrix c/zgemm bug. 2021-08-02 07:06:54 +00:00
Xianyi Zhang 57ed58cefe Refs #2587 Add small matrix optimization reference kernel for c/zgemm. 2021-08-02 07:06:54 +00:00
Xianyi Zhang 17d32a4a82 Change a1b0 gemm to b0 gemm. 2021-08-02 07:06:54 +00:00
Xianyi Zhang 4271cfcc6f Fix gemm interface bug for small matrix. 2021-08-02 07:06:51 +00:00
Xianyi Zhang be3349405d Add alpha=1.0 beta=0.0 for small gemm. 2021-08-02 07:01:47 +00:00
Xianyi Zhang 0a2077901c Add small marix optimization kernel interface. 
make SMALL_MATRIX_OPT=1
 2021-08-02 07:01:47 +00:00
Martin Kroeker 7bb59fceb7
Clean up some warnings 2021-07-11 16:00:29 +02:00
Gordon Fossum 8b599836db Add error message token for SBGEMM in gemm.c 2021-05-04 13:55:02 -05:00
Alex Henrie 6f32991eae Don't define the mode variable when not needed in gemm functions 2021-01-14 19:40:31 -07:00