818bf3062
Merge pull request #4490 from ChipKerchner/missingCPUIDsForAIX by
2024-02-07 17:31:26 +0100
344763331
Merge pull request #4484 from martin-frbg/lapack981 by
2024-02-07 15:22:48 +0100
574912f53
Add missing CPU ID definitions for old versions of AIX. by
2024-02-07 07:54:06 -0600
08ce6b1c1
(refs/pull/4490/head)
Add missing CPU ID definitions for old versions of AIX. by
2024-02-07 07:54:06 -0600
fb99fc2e6
(refs/pull/4488/head)
fix type conversion warnings by
2024-02-07 13:42:08 +0100
08e479f95
Merge pull request #4487 from ErnstPeng/feature-branch by
2024-02-07 13:19:04 +0100
25b300bbe
improve internal names by
2024-02-06 23:40:01 +0100
9ef10ffa4
Handle prefixed and suffixed libnames, optionally suppress softlinking by
2024-02-06 23:38:19 +0100
1ed69ea1c
improve naming by
2024-02-06 23:35:12 +0100
d4db6a9f1
Separate the interface for SBGEMMT from GEMMT due to differences in GEMV arguments by
2024-02-06 22:23:47 +0100
fe3da43b7
(refs/pull/4487/head)
Optimized zgemm kernel 8*4 LASX, 4*4 LSX and cgemm kernel 8*4 LSX for LoongArch by
2024-02-06 11:49:01 +0800
345a408ff
(refs/pull/4486/head)
Optimized cgemm kernel 16*4 LASX for LoongArch by
2024-02-06 10:48:49 +0800
440edfd99
Add option to suppress versioning of the internal name by
2024-02-05 21:44:50 +0100
63fbffddf
Add option FIXED_LIBNAME to suppress versioning and softlinking by
2024-02-05 21:44:03 +0100
e5d2725e5
Merge pull request #4185 from XiWeiGu/mips_enable_msa by
2024-02-05 15:50:16 +0100
479e4af08
(refs/pull/4484/head)
Rescale input vector more often to minimize relative error (Reference-LAPACK PR 981) by
2024-02-05 15:35:24 +0100
a4fde2c5a
Merge pull request #4451 from martin-frbg/overflow_reset by
2024-02-05 07:27:04 +0100
b537528fe
Merge pull request #4480 from XiWeiGu/loongarch64-fixed-{s/d}amin-lsx by
2024-02-05 06:24:50 +0100
bc7154a80
Merge pull request #4482 from martin-frbg/issue4476 by
2024-02-04 23:13:10 +0100
6d8a273cc
Handle zero increment(s) in C910V ?AXPBY (#4483) by
2024-02-04 22:07:51 +0100
05cf63492
(refs/pull/4483/head)
Update zaxpby_vector.c by
2024-02-04 20:50:18 +0100
2cab2ca29
Update axpby_vector.c by
2024-02-04 20:49:41 +0100
d65c01e3d
Handle zero increment(s) by
2024-02-04 20:27:49 +0100
dbcf4f8b7
Merge pull request #4479 from XiWeiGu/loongarch-opt-axpby by
2024-02-04 19:50:28 +0100
dc802dd63
Merge pull request #4474 from ChipKerchner/sgemmIncopy_PR by
2024-02-04 18:51:09 +0100
e30767522
Merge pull request #4478 from martin-frbg/issue4475 by
2024-02-04 16:36:40 +0100
033168cdf
Merge pull request #4481 from martin-frbg/cpuid_riscv by
2024-02-04 14:09:44 +0100
a29f91ae9
Merge pull request #4471 from ChipKerchner/fixMakefileAIXOpenMP by
2024-02-04 12:13:26 +0100
e61d96303
(refs/pull/4482/head)
Fix missing NO_AVX2 fallback for SapphireRapids by
2024-02-04 10:05:20 +0100
d02c61e82
(refs/pull/4481/head)
Update lowercase cpunames for RISC-V by
2024-02-04 10:01:27 +0100
7228c708d
Merge pull request #4461 from markdryan/cpuid_riscv64_crash by
2024-02-04 09:57:00 +0100
adde72532
(refs/pull/4480/head)
LoongArch64: Fixed {s/d}amin LSX optimization by
2024-02-04 14:43:08 +0800
7bc93d95a
(refs/pull/4479/head)
LoongArch64: Opt {c/z}axpby by
2024-01-24 16:11:45 +0800
1e1f487dc
LoongArch64: Fixed {s/d}axpby by
2024-02-01 19:57:05 +0800
3597827c9
utest: add axpby by
2024-02-01 16:33:58 +0800
68d354814
(refs/pull/4478/head)
Fix incompatible pointer type in BFLOAT16 mode by
2024-02-04 01:14:22 +0100
3848d4e9f
Merge pull request #4477 from martin-frbg/c910caxpy by
2024-02-04 01:10:57 +0100
4d8dee508
(refs/pull/4477/head)
temporarily disable the CAXPY/ZAXPY kernels by
2024-02-04 01:05:03 +0100
27816fa92
Merge pull request #4472 from sergei-lewis/dev/slewis/merge-from-riscv by
2024-02-03 20:56:11 +0100
b6949ce74
add axpyc to cmake build by
2024-02-02 14:42:27 +0300
441339104
fix test ext cmake build by
2024-02-02 13:49:39 +0300
f68e9989c
Remove zero rows/columns matcopy tests by
2024-02-02 12:26:23 +0300
87ba528d8
(refs/pull/4532/head)
Changed C files to straighten out indentation. Removed commented lines from other file. by
2024-02-01 18:46:07 -0600
461cf9083
Merge remote-tracking branch 'origin/develop' into cgemm_zgemm_c_code by
2024-02-01 12:40:04 -0600
ddac75e0e
Adding .C versions of CGEMM and ZGEMM by
2024-02-01 12:24:25 -0600
2bb7ea64a
(refs/pull/4474/head)
Only vectorize 64-bit version for Power8. by
2024-02-01 08:11:43 -0600
3ffd6868d
(refs/pull/4472/head)
Merge branch 'develop' into dev/slewis/merge-from-riscv by
2024-02-01 11:29:41 +0000
a3b0ef659
Restore riscv64 fixes from develop branch: dot product double precision accumulation, zscal NaN handling by
2024-02-01 10:26:02 +0000
ec74dcd21
Merge pull request #4470 from martin-frbg/issue4455 by
2024-01-31 23:51:01 +0100
61c8e19f9
(refs/pull/4471/head)
Fix Makefile to support OpenMP on AIX for xlc (clang) with xlf. by
2024-01-31 15:27:50 -0600
42cb567f0
more cleanup by
2024-01-31 13:24:28 -0800
47bd06476
(refs/pull/4470/head)
Fix names in build rules by
2024-01-31 20:49:43 +0100
349a4bf04
Update f_check.cmake by
2024-01-31 19:23:59 +0100
7c8843707
rename and fix reference to removed variable by
2024-01-31 18:38:40 +0100
a7d004e82
Fix CBLAS prototype by
2024-01-31 17:55:42 +0100
b54cda849
Unify creation of CBLAS interfaces for ?AMIN/?AMAX and C/ZAXPYC between gmake and cmake builds by
2024-01-31 16:00:52 +0100
1a6fdb035
Add prototypes for extensions ?AMIN/?AMAX and CAXPYC/ZAXPYC by
2024-01-31 15:57:57 +0100
d1343302b
Merge pull request #4465 from XiWeiGu/utest-zscal by
2024-01-31 14:19:19 +0100
218e5309a
CI: Add github workflow using Apple M by
2024-01-31 12:31:44 +0100
969601a1d
(refs/pull/4465/head)
X86_64: Fixed bug in zscal by
2024-01-31 11:20:25 +0800
b21be2eda
(refs/pull/4467/head)
Add CBLAS interfaces for the extensions ?AMIN, ?AMAX and SCAXPYC/DZAXPYC by
2024-01-30 23:19:57 +0100
896f0169c
Unify generation of (C/Z)AXPYC, CBLAS_SCA(MIN/MAX), CBLAS:_DZA(MIN/MAX) by
2024-01-30 23:18:35 +0100
98c9ff319
Merge pull request #4464 from XiWeiGu/loongarch64-zscal by
2024-01-30 22:53:29 +0100
9f0630187
Merge pull request #4463 from XiWeiGu/loongarch64-zamax-zamin by
2024-01-30 18:01:30 +0100
09bb48d1b
Vectorize in-copy packing/copying for SGEMM - 4X faster. by
2024-01-30 09:13:16 -0600
bb043a021
utest: Add tests for zscal by
2024-01-30 17:27:59 +0800
83ce97a4c
(refs/pull/4464/head)
LoongArch64: Handle NAN and INF by
2024-01-30 16:54:14 +0800
0d7fe5ea6
clean up whitespace by
2024-01-29 22:33:47 -0800
3d4dfd008
(refs/pull/4463/head)
Benchmark: Rename the executable file names for {sc/dz}a{min/max} by
2024-01-30 11:25:59 +0800
a79d11740
LoogArch64: Fixed bug for {s/d}amin by
2024-01-30 11:03:56 +0800
519ea6e87
utest: Add utest for the {sc/dz}amax and {s/d/sc/dz}amin by
2024-01-30 10:39:22 +0800
1093def0d
Merge branch 'risc-v' into develop by
2024-01-29 11:11:39 +0000
889212113
Merge pull request #4462 from martin-frbg/issue4449 by
2024-01-26 22:41:16 +0100
48a4c4d45
(refs/pull/4462/head)
Use +sve in arch declarations of the fallback paths for SVE targets by
2024-01-26 16:30:52 +0100
e0b610d01
(refs/pull/4461/head)
Harmonize riscv64 LIBNAME for forced and non-forced targets by
2024-01-26 13:57:33 +0000
ec2aa32eb
Fix crash in cpuid_riscv64.c by
2024-01-25 15:20:58 +0000
47218d827
(refs/pull/4460/head)
Remove erroneous early exit for alpha=(1,0) that skipped conjugation by
2024-01-26 14:32:10 +0100
776dbf66f
Add prototypes for ?GEMMT by
2024-01-26 14:29:39 +0100
c08994be5
Add prototypes for ?GEMMT by
2024-01-26 14:26:49 +0100
41515e6e7
Fixed handling of complex conjugate matrices and error codes for complex cases by
2024-01-26 14:25:38 +0100
889c5d026
(risc-v)
Merge pull request #4456 from kseniyazaytseva/riscv-rvv10 by
2024-01-26 13:31:09 +0100
4e2a32ff5
Merge pull request #4454 from kseniyazaytseva/riscv-rvv07 by
2024-01-26 11:40:46 +0100
276e3ebf9
LoongArch64: Add dzamax and dzamin opt by
2024-01-26 10:03:50 +0800
a21b2fa5e
Merge pull request #4452 from kseniyazaytseva/riscv-generic by
2024-01-24 17:52:25 +0100
73530b03f
(refs/pull/4454/head)
remove RISCV64_ZVL256B additional extentions by
2024-01-24 11:38:14 +0300
86943afa9
Fix x280 taget include riscv_vector.h by
2024-01-24 10:53:13 +0300
d938aed7f
(refs/pull/4451/head)
reset "mem structure overflowed" state on shutdown by
2024-01-23 17:15:53 +0100
9c49a81d5
Resolve conflicts by
2024-01-23 19:08:53 +0300
e1afb2381
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets by
2023-04-07 11:13:23 +0300
f1ff4c5c0
(refs/pull/4191/merge)
Merge 76d675bd55 into d6a5174e9c by
2024-01-22 11:11:12 +0300
d6a5174e9
Merge pull request #4447 from RevySR/update-thead-toolchains by
2024-01-22 08:10:02 +0100
304a9b60a
(refs/pull/4447/head)
Update T-Head toolchains v2.8.0 by
2024-01-21 14:32:52 +0000
f5de4fad2
Merge pull request #4444 from Mousius/part-mapping by
2024-01-20 15:55:07 +0100
aaf65210c
(refs/pull/4444/head)
Add dynamic support for Arm(R) Neoverse(TM) V2 processor by
2024-01-19 19:04:21 +0000
10c22f4a3
Merge pull request #4355 from imaginationtech/img-riscv64-zvl128b by
2024-01-19 13:51:07 +0100
ccbc3f875
(refs/pull/4355/head)
[RISC-V] Add RISCV64_ZVL128B target to common_riscv64.h by
2024-01-19 12:40:00 +0000
deecfb1a3
Merge branch 'risc-v' into img-riscv64-zvl128b by
2024-01-19 12:26:38 +0000
f51d36ecb
(refs/pull/4397/merge)
Merge 75fe9c21e5 into 500442cf96 by
2024-01-18 19:07:43 -0800
c99e231fc
Fix rand_generate by
2024-01-18 23:54:51 +0300
bf39c0d8b
Added new tests for BLAS-like and BLAS API in utest by
2023-06-23 14:51:39 +0300