OSchip
/
OpenBLAS
mirror of https://github.com/xianyi/OpenBLAS.git
0
0
Fork 2
Code Issues Packages Projects Releases Wiki Activity
9,676 Commits 58 Branches 70 Tags 121 MiB
Commit Graph

2619 Commits

Author SHA1 Message Date
Martin Kroeker edaa73fd24
Hide the local 2VLx2VL symbol as static is insufficient for this with gcc 2025-08-20 06:33:28 -07:00
Martin Kroeker 501728a354
adjust register 20 accesses to 21 after moving x18 2025-08-20 06:24:38 -07:00
Martin Kroeker 107c883c8a
Update SME-related kernels 2025-08-19 05:13:28 -07:00
Martin Kroeker 05dbb54362
Delete misplaced file 2025-08-19 05:12:09 -07:00
Martin Kroeker 0bc19a1335
Update SME kernel details 2025-08-18 14:38:16 -07:00
Martin Kroeker ca542f319f
Add VORTEXM4 2025-08-18 08:41:38 -07:00
Martin Kroeker 0203657f40
Add sgemm_direct_performant for ARM64 2025-08-18 01:42:32 -07:00
Martin Kroeker e82bcd2740
Update ARM64 sgemm_direct object generation 2025-08-18 01:41:13 -07:00
Martin Kroeker 731f4dd686
Add VORTEXM4 settings 2025-08-18 01:39:35 -07:00
Martin Kroeker 53d3bb50cc
Get symbol name from build system; change b.first to b.mi for AppleClang compatibility 2025-08-18 01:37:50 -07:00
Martin Kroeker 08a00326a4
Build symbol name from build system variables 2025-08-18 01:35:41 -07:00
Martin Kroeker 89898fc499
Add sgemm_direct_performant for switching between direct and regular kernels 2025-08-18 01:31:40 -07:00
Martin Kroeker 22c6607db9
Use ASMNAME to get symbol name from build system; leave x18 unused as reserved on MacOS 2025-08-18 01:30:10 -07:00
Martin Kroeker ca22e28ca1
Rename sgemm_direct_sme1.S to sgemm_direct_sme1_2VLx2VL.S 2025-08-18 01:25:44 -07:00
Martin Kroeker 9d6df1dd3e
Merge pull request #5422 from ChipKerchner/addRVVVectorizedPacking 
Add and use vectorized packing in ZVL128B and ZVL256B for RISCV
 2025-08-16 13:45:35 -07:00
Martin Kroeker f3b2a15fad
Merge pull request #5420 from yuanjia111/develop 
Move the value assignment of vector x in gemv_n_sve.c to the outermos…
 2025-08-16 12:06:53 -07:00
Chip Kerchner 64401b4417 Disable vectorized packing for DGEMM - since it is slower than scalar. 2025-08-13 13:41:12 +00:00
Chip Kerchner c00afc86a6 Add and use vectorized packing to ZVL128B and ZVL256B. Up to 3x+ faster than generic scalar functions. 2025-08-12 17:18:56 +00:00
yuanjia 803e8d4838 Move the value assignment of vector x in gemv_n_sve.c to the outermost loop to reduce the repeated data retrieval. 
1.Verify correctness using BLAS-Tester
    2.Using the built-in benchmark to verify performance, the performance of float and doule type improved by about 60% and about 40% respectively.The test command is:
     export OMP_NUM_THREADS=1;numactl -C 10 -l ./sgemv.goto 3000 4000 100
     export OMP_NUM_THREADS=1;numactl -C 10 -l ./dgemv.goto 3000 4000 100
 2025-08-12 18:03:16 +08:00
Chris Sidebottom 5f47b872f1 Remove older kernels for BGEMM on NEOVERSEV1 2025-08-11 09:25:19 +00:00
Chris Sidebottom 114316f361 Optimize SBGEMM / BGEMM for NEOVERSEV1 further 
This changes the kernels to pack full SVE vectors and reduces the
overall complexity of the inner GEMM loop.
 2025-08-11 09:25:13 +00:00
Martin Kroeker f1ee61ea30
Include NEON header for the bfloat conversion functions 2025-08-04 00:21:39 -07:00
Martin Kroeker b3ffd5524a
Include NEON header for the bfloat conversion functions 2025-08-04 00:20:28 -07:00
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 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 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 0bc79da587 add neon header 2025-07-25 11:10:20 +05:30
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
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 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 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 947d7af4c9 Fix CMake references to bscal and bgemv 2025-07-15 15:41:53 +01:00
Chris Sidebottom e105411460 Add infrastructure for bgemv/bscal 
- Sets up all the various entrypoints for `bgemv`
- Adds `bscal` for use in the `bgemv` interface
- Adds test cases for comparing `sgemv` and `bgemv`
- Adds generic kernels for `bgemv_n` and `bgemv_t` which are accurate
enough to pass above tests
 2025-07-15 14:48:57 +01:00
Chris Sidebottom 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 343830c26f
Add BGEMM parameter tables 2025-07-10 14:59:46 +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 66d9185ebe Fix CMake support 2025-07-08 22:49:55 +00:00
Martin Kroeker fd37406817
Merge branch 'develop' into optimized_gemv_n_1x3 2025-07-08 21:05:30 +02:00
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
Iha, Taisei f7ad906b49 Performance improvements of [SD]DOT with loop-unrolling on A64FX 2025-07-04 22:57:44 +09:00
Martin Kroeker d96daa220d
Merge pull request #5290 from Srangrang/develop 
Add support for FP16 to openBLAS and shgemm on RISCV
 2025-06-24 23:10:15 +02:00
Martin Kroeker ee26caffb3
Merge pull request #5309 from davidz-ampere/dev-ampereone 
Add support for Ampere AmpereOne processors
 2025-06-24 12:27:08 +02:00
davidz-ampere aa90ab4142 Add support for Ampere AmpereOne processors 2025-06-24 00:12:34 -04:00
Ian McInerney badef1d32e Update sbgemm_tcopy_4_neoversev1 kernel to use standard C types 2025-06-19 14:26:16 +01:00
Martin Kroeker 3318a2b904
override CDOT and ZDOT with the generic C kernel 2025-06-17 22:41:40 +02:00
davidz-ampere 84730068af reduce duplicate kernel code 2025-06-17 03:05:34 -04:00
davidz-ampere be68ef03b4 Add support for Ampere processors 2025-06-15 22:00:40 -04:00
Srangrang 9f13b2c6ac style: modify HALF to BFLOAT16 in benchmark folder 2025-06-15 20:57:05 +08:00
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 e338d34ce1
fix path 2025-06-13 13:37:15 +02:00
Martin Kroeker d36093d084
temporarily change default C/ZSCAL to the non-asm implementation 2025-06-13 13:32:02 +02:00
Martin Kroeker b3c90564d7
resync with the generic arm version for inf/nan handling 2025-06-13 00:54:27 -07:00
Martin Kroeker 6bdc7f9eb7
Merge pull request #5300 from martin-frbg/fixup5296 
kernel/riscv64: Fix cscal/zscal for riscv64_generic
 2025-06-12 15:02:22 -07:00
Martin Kroeker 73af02b89f
use dummy2 as Inf/NAN handling flag 2025-06-12 13:33:56 -07:00
Martin Kroeker 549a9f1dbb
Disable the default SSE kernels for CSCAL/ZSCAL for now 2025-06-12 18:54:33 +02:00
Martin Kroeker 58eeb9041c
fix handling of dummy2 2025-06-12 03:03:01 -07:00
Martin Kroeker 7c77537b25
Merge pull request #5297 from martin-frbg/zscal_x86_sparc 
kernel/(x86|sparc): Fix cscal and zscal by reverting to the generic C kernels
 2025-06-12 01:10:35 -07:00
Martin Kroeker 63287e1855
Merge pull request #5296 from martin-frbg/zscal_riscv 
kernel/riscv64: Fix cscal and zscal
 2025-06-12 01:10:15 -07:00
Martin Kroeker d2855d3dab
Merge pull request #5285 from martin-frbg/zscal_zarch 
kernel/zarch: Fix cscal and zscal
 2025-06-12 01:09:52 -07:00
Martin Kroeker 1408be5fe0
Merge pull request #5282 from martin-frbg/zscal_power 
kernel/power: Fixed cscal and zscal
 2025-06-12 01:04:38 -07:00
Martin Kroeker 1589d0b21e
Merge pull request #5281 from martin-frbg/zscal_arm64 
kernel/arm64: fixed cscal and zscal
 2025-06-12 01:04:18 -07:00
Martin Kroeker a86419fb66
Merge pull request #5280 from martin-frbg/zscal_x86_64 
kernel/x86_64: fixed cscal and zscal
 2025-06-12 01:03:55 -07:00
Martin Kroeker 11ff18bb0f
Merge pull request #5081 from XiWeiGu/kernel_generic_fixed_cscal_zscal 
kernel/generic: Fixed cscal and zscal
 2025-06-12 01:03:00 -07:00
Martin Kroeker f4194fc65f
Merge branch 'develop' into la64_fixed_cscal_zscal 2025-06-11 14:28:41 -07:00
Martin Kroeker e12132abd4
Use generic C/ZSCAL kernels to address inf/nan handling for now 2025-06-11 22:12:10 +02:00
Martin Kroeker 1cefbea7ea
Use generic SCAL kernels to address inf/nan handling for now 2025-06-11 22:10:46 +02:00
Sharif Inamdar 8279e68805 Optimize gemv_n_sve_v1x3 kernel 
- Calculate predicate outside the loop
- Divide matrix in blocks of 3
 2025-06-11 10:16:56 +00:00
Martin Kroeker f18b7a46bf
add dummy2 flag handling for inf/nan agnostic zeroing 2025-06-11 01:47:43 -07:00
Martin Kroeker fe220a0d7d
Merge pull request #5291 from guoyuanplct/develop 
kernel/riscv64:fixed the performance problem in RISCV64_ZVL256 when OPENBLAS_K is small
 2025-06-09 23:42:04 -07:00
Arne Juul 5442aff218 Accumulate results in output register explicitly 2025-06-09 19:03:22 +00:00
guoyuanplct 2ae019161a fixed the performance problem in RISCV64_ZVL256 when OPENBLAS_K is small 2025-06-05 21:53:03 +08:00
Srangrang fb89820f20 Merge branch 'develop' of https://github.com/Srangrang/OpenBLAS into develop 2025-06-04 20:27:05 +08:00
Srangrang 4e1a381e5b fix: resolve the compilation failure without zfh instruction 
- modify the macro conditions in Makefile.system
- Delete development test code

Related to issue#5279
 2025-06-04 20:00:12 +08:00
gkdddd 670ec6f757 Added shgemm_kernel_8x8 for RISCV64_ZVL128B and shgemm_kernel_16x8 for RISCV64_ZVL256B 
Added HFLOAT16 support for RISCV64
Added shgemm_kernel_8x8 for RISCV64_ZVL128B and shgemm_kernel_16x8 for RISCV64_ZVL256B based on HFLOAT16
The instruction sets used are ZVFH and ZFH, which need to be supported by RVV1.0

Related to issue #5279
Co-authored-by Linjin Li <linjin_li@163.com>
 2025-06-03 20:14:30 +08:00
guoyuanplct d2003dc886 del lines 2025-05-29 18:38:22 +08:00
guoyuanplct 45fd2d9b07 Optimized the axpby function. 2025-05-29 17:50:44 +08:00
Martin Kroeker fb8dc8ff5c
Add dummy2 flag handling 2025-05-25 14:47:06 -07:00
Srangrang 2996c25c94 add shgemm for RISCV_ZVL128B 2025-05-24 23:55:49 +08:00
Martin Kroeker cf06250d36
add handling of dummy2 flag 2025-05-24 06:06:24 -07:00
Martin Kroeker 28f8fdaf0f
support flag for NaN/Inf handling and fix scaling of NaN/Inf values 2025-05-23 14:59:59 +02:00
Martin Kroeker 669c847ceb
support extra flag for NaN handling 2025-05-23 05:52:48 -07:00
Martin Kroeker 0b0bb9951d
Merge pull request #5265 from guoyuanplct/develop 
kernel/riscv64:Added support for omatcopy on RISCV64_ZVL256B
 2025-05-17 05:08:47 -07:00
guoyuanplct be9f7550b5 Format Code 2025-05-15 18:55:47 +08:00
guoyuanplct 4d213653d8 kernel/riscv64:Added support for omatcopy on riscv64. 2025-05-15 13:29:14 +08:00
Martin Kroeker 8afddc1a81
Merge pull request #5262 from guoyuanplct/develop 
kernel/riscv64:Fixed the bug of openblas_utest_ext failing in c/zgemv and some c/zgbmv tests:
 2025-05-14 02:40:32 -07:00
guoyuanplct 9a7e3f102b kernel/riscv64:Fixed the bug of openblas_utest_ext failing in c/zgemv and some c/zgbmv tests: 2025-05-14 00:09:26 +08:00
pengxu a978ad3180 Loongarch64: add C functions of zgemm_ncopy_16 2025-05-13 16:09:12 +08:00
pengxu 0ccb050583 Loongarch64: fixed cgemm_ncopy_16_lasx 2025-05-13 16:08:33 +08:00
Martin Kroeker 5141a90993
Fix ARMV9SME target in DYNAMIC_ARCH and add SME query code for MacOS (#5222) 
* Fix ARMV9SME target and add support_sme1 code for MacOS
* make sgemm_direct unconditionally available on all arm64
* build a (dummy) sgemm_direct kernel on all arm64





* Update dynamic_arm64.c
 2025-05-10 22:39:32 +02:00
Martin Kroeker 151b74284e
Merge pull request #5203 from quic/fix-sgemmdirect-sme1 
Add vector registers to clobber list to prevent compiler optimization.
 2025-05-09 05:39:47 -07:00
Martin Kroeker cba32d001a
Merge pull request #5245 from guoyuanplct/develop 
Optimized RVV_ZVL256B Implementation of zgemv_n
 2025-05-01 03:04:38 -07:00
pengxu f19e72c402 Loongarch64: fixed swap_lasx 2025-04-30 16:42:52 +08:00
pengxu b471fa337b Loongarch64: fixed snrm2_lasx 2025-04-30 16:42:36 +08:00
pengxu 57bb46bedf Loongarch64: fixed rot_lasx 2025-04-30 16:42:22 +08:00
pengxu 6dc4ca2391 Loongarch64: fixed icamax_lasx 2025-04-30 16:42:12 +08:00
pengxu b528b1b8ea Loongarch64: fixed iamax_lasx 2025-04-30 16:41:58 +08:00