5442aff21
(refs/pull/5294/head)
Accumulate results in output register explicitly by
2025-06-08 19:50:15 +0000
83fcab757
(refs/pull/5291/head)
Merge branch 'develop' of https://github.com/guoyuanplct/OpenBLAS into develop by
2025-06-05 21:58:13 +0800
2ae019161
fixed the performance problem in RISCV64_ZVL256 when OPENBLAS_K is small by
2025-06-05 21:53:03 +0800
fb89820f2
Merge branch 'develop' of https://github.com/Srangrang/OpenBLAS into develop by
2025-06-04 20:27:05 +0800
4e1a381e5
fix: resolve the compilation failure without zfh instruction by
2025-06-04 20:00:12 +0800
fa2b08b37
Merge pull request #1 from gkdddd/riscv_shgemm by
2025-06-03 21:00:19 +0800
670ec6f75
Added shgemm_kernel_8x8 for RISCV64_ZVL128B and shgemm_kernel_16x8 for RISCV64_ZVL256B by
2025-06-03 20:14:30 +0800
45aa27b64
(refs/pull/5287/head)
update init value of bgemm testcase by
2025-05-30 13:34:40 +0000
5d1651780
add neoversev1 bgemm kernels by
2025-05-30 13:07:38 +0000
63ce52ee7
change data type of bgemm alpha and beta from bfloat16 to fp32 and add makefiles changes for bgemm interface by
2025-05-29 10:51:29 +0000
21afc02c8
deploy: 02267d86f5 by
2025-05-29 14:39:10 +0000
02267d86f
Merge pull request #5288 from guoyuanplct/develop by
2025-05-29 07:38:38 -0700
d2003dc88
(refs/pull/5288/head)
del lines by
2025-05-29 18:38:22 +0800
45fd2d9b0
Optimized the axpby function. by
2025-05-29 17:50:44 +0800
082a9d28c
Resolve symbol conflicts when building sbgemm and bgemm together by
2025-05-22 10:45:54 +0000
59d0cf4a2
fix generic gemm_beta for bgemm by
2025-05-22 09:06:23 +0000
4d0fd1280
support dynamic arch of bgemm interface by
2025-05-21 13:58:27 +0000
1eb0815b0
support mutithreaded bgemm interface by
2025-05-21 11:01:42 +0000
abe9d38f7
add generic bgemm kernel and its test file by
2025-05-21 14:52:56 +0000
2ef36a1b0
add .c and .h files for bgemm interface by
2025-05-21 14:51:59 +0000
0a967797a
Add FP16 support for RISCV by
2025-05-27 14:34:57 +0800
fb8dc8ff5
(refs/pull/5285/head)
Add dummy2 flag handling by
2025-05-25 14:47:06 -0700
f280f4d66
(refs/pull/5284/head)
Update zscal.c by
2025-05-25 23:25:41 +0200
e1e5be594
Update zscal.c by
2025-05-25 22:57:50 +0200
decd97c05
Update zscal.c by
2025-05-25 22:35:31 +0200
1b716940e
handle dummy2 flag by
2025-05-25 13:06:05 -0700
16772ed07
Update cscal.c by
2025-05-25 19:56:39 +0200
e54f43bb4
Update cscal.c by
2025-05-25 19:41:25 +0200
c7285a140
Update cscal.c by
2025-05-25 19:09:02 +0200
184a52716
Update cscal.c by
2025-05-25 18:49:11 +0200
4f9be6d84
Update cscal.c by
2025-05-25 18:26:46 +0200
ae5bdb76f
Update cscal.c by
2025-05-25 16:10:10 +0200
344b14a37
Update cscal.c by
2025-05-25 15:37:08 +0200
35256671d
Update cscal.c by
2025-05-25 15:28:05 +0200
a1efb0361
Update cscal.c by
2025-05-25 13:48:25 +0200
80bf76583
Update cscal.c by
2025-05-25 13:22:29 +0200
b1008985a
Update cscal.c by
2025-05-25 13:04:43 +0200
41cd46c2a
Update cscal.c by
2025-05-25 12:55:18 +0200
7b915870e
Update cscal.c by
2025-05-25 12:29:26 +0200
ef01810dd
Update cscal.c by
2025-05-25 00:25:45 +0200
234bba381
Update cscal.c by
2025-05-25 00:16:57 +0200
62d8047c4
Update cscal.c by
2025-05-24 23:22:53 +0200
2a1754046
Update cscal.c by
2025-05-24 22:46:39 +0200
1c3fcfdbb
Update cscal.c by
2025-05-24 20:04:17 +0200
3c150610b
Update cscal.c by
2025-05-24 18:40:45 +0200
2996c25c9
add shgemm for RISCV_ZVL128B by
2025-05-24 23:55:49 +0800
05ed74583
Add files via upload by
2025-05-24 08:51:55 -0700
9df88344f
Add files via upload by
2025-05-24 08:50:49 -0700
b23efc584
add handling of dummy2 flag by
2025-05-24 17:49:45 +0200
dcef17c3a
add handling of dummy2 flag by
2025-05-24 06:38:41 -0700
43484f717
add handling of dummy2 flag by
2025-05-24 06:38:01 -0700
cf06250d3
(refs/pull/5282/head)
add handling of dummy2 flag by
2025-05-24 06:06:24 -0700
28f8fdaf0
(refs/pull/5281/head)
support flag for NaN/Inf handling and fix scaling of NaN/Inf values by
2025-05-23 14:59:59 +0200
669c847ce
(refs/pull/5280/head)
support extra flag for NaN handling by
2025-05-23 05:52:48 -0700
8622aad13
deploy: 0163143fdd by
2025-05-22 07:33:03 +0000
0163143fd
Merge pull request #5278 from martin-frbg/fixup5276 by
2025-05-22 00:32:29 -0700
20f2ba014
(refs/pull/5278/head)
Move declaration of i for pre-C99 compilers by
2025-05-21 23:44:17 +0200
e2e6a4d90
Merge pull request #5276 from nakagawa-fj/gemm_2d_thread_partitioning by
2025-05-21 14:41:49 -0700
2b8dbfcb6
deploy: 9ef5995c22 by
2025-05-21 21:34:09 +0000
9ef5995c2
Merge pull request #5277 from martin-frbg/fixmingw32 by
2025-05-21 14:33:37 -0700
42b7d1f89
(refs/pull/5277/head)
Fix addressing of alpha in CBLAS by
2025-05-21 22:03:38 +0200
bd573a9d3
Expand mingw32 gfortran workaround to all versions after 14.1 by
2025-05-21 22:01:02 +0200
bf0b09d62
(refs/pull/5269/head)
Update CMakeLists.txt by
2025-05-21 16:51:38 +0200
d0c61c4c5
Update dynamic_arch.yml by
2025-05-21 16:51:04 +0200
2351a9800
(refs/pull/5276/head)
Update 2D thread-partitioned GEMM for M << N case. by
2025-05-21 21:21:52 +0900
f2daebeaa
deploy: a5f701c4ab by
2025-05-20 07:40:05 +0000
a5f701c4a
Merge pull request #5274 from martin-frbg/issue5247 by
2025-05-20 00:39:32 -0700
4ca76d9de
(refs/pull/5274/head)
Expressly provide a shared libs option by
2025-05-19 12:07:24 -0700
846a5436e
Merge pull request #5273 from martin-frbg/issue5259 by
2025-05-19 11:59:57 -0700
8779eac3b
(refs/pull/5273/head)
Do not add a 64 suffix to the library name if the user-provided suffix already contains it by
2025-05-19 08:55:14 -0700
b5e79f9ed
deploy: 3473118213 by
2025-05-19 15:21:53 +0000
347311821
Merge pull request #5272 from martin-frbg/issue5271 by
2025-05-19 08:17:57 -0700
f2022c23a
(refs/pull/5272/head)
Remove sve capability from NeoverseN1 and specify CortexX2/A?10 as arm8.4a by
2025-05-19 16:08:12 +0200
40c7163db
Update dynamic_arch.yml by
2025-05-19 08:48:25 +0200
7b4bcb96f
deploy: b5456c1b41 by
2025-05-18 20:54:34 +0000
b5456c1b4
Merge pull request #5260 from taoye9/enable_bf16_gemm_gemv_forward_on_arm64 by
2025-05-18 13:54:05 -0700
5743cee9d
Update dynamic_arch.yml by
2025-05-18 20:55:37 +0200
a611a6945
Update dynamic_arch.yml by
2025-05-18 17:30:24 +0200
7f2d7da65
Fix passing of variable alpha in the CBLAS case by
2025-05-18 13:19:22 +0200
b68b99095
Update dynamic_arch.yml by
2025-05-17 23:58:20 +0200
8b98564ea
set mingw C flags to -O2 as well by
2025-05-17 21:03:03 +0200
5a322f21a
Merge pull request #5268 from martin-frbg/fix-dyn-sgemmdirect by
2025-05-17 10:30:23 -0700
44f075183
limit mingw Release builds to -O2 for Fortran by
2025-05-17 19:21:15 +0200
f2ac793b8
deploy: 0b0bb9951d by
2025-05-17 12:35:20 +0000
6680e0592
(refs/pull/5268/head)
Fix conditional inclusion of SGEMM_KERNEL_DIRECT by
2025-05-17 05:12:15 -0700
0b0bb9951
Merge pull request #5265 from guoyuanplct/develop by
2025-05-17 05:08:47 -0700
7732a5520
(refs/pull/5265/head)
Add retry mechanism after deadlock timeout for c910v. by
2025-05-16 18:24:46 +0800
acb2cdcf4
(refs/pull/5266/head, timeout-riscv-ci)
Add a timeout and move the utests to the end of the test by
2025-05-15 17:02:46 +0200
be9f7550b
Format Code by
2025-05-15 18:55:47 +0800
ffc39d60e
(refs/pull/5264/head)
Update apple_m.yml by
2025-05-15 18:38:20 +0800
4d213653d
(refs/pull/5263/head)
kernel/riscv64:Added support for omatcopy on riscv64. by
2025-05-15 13:29:14 +0800
8436e56fa
deploy: 8afddc1a81 by
2025-05-14 09:40:59 +0000
8afddc1a8
Merge pull request #5262 from guoyuanplct/develop by
2025-05-14 02:40:32 -0700
9a7e3f102
(refs/pull/5262/head)
kernel/riscv64:Fixed the bug of openblas_utest_ext failing in c/zgemv and some c/zgbmv tests: by
2025-05-14 00:09:26 +0800
1c8c0c0e4
deploy: 5366902f9d by
2025-05-13 12:48:32 +0000
5366902f9
Merge pull request #5261 from ErnstPeng/fix-lasx by
2025-05-13 05:48:05 -0700
a978ad318
(refs/pull/5261/head)
Loongarch64: add C functions of zgemm_ncopy_16 by
2025-05-13 16:09:12 +0800
0ccb05058
Loongarch64: fixed cgemm_ncopy_16_lasx by
2025-05-13 16:08:33 +0800
e1a6703cf
Cleanup and GEMMTR fixes by
2025-05-12 13:21:40 -0700
4341911ff
Fix CBLAS_?GEMMTR name generation by
2025-05-12 13:09:57 -0700