84a1d76d1
Merge pull request #3866 from martin-frbg/issue3859 by
2022-12-15 22:58:15 +0100
57151b97a
(refs/pull/3866/head)
Fix INTERFACE64 builds on riscv and loongarch by
2022-12-15 18:52:46 +0100
52cdb0555
Merge pull request #3863 from martin-frbg/issue3862 by
2022-12-15 17:21:34 +0100
62341ac5e
(refs/pull/3863/head)
Fix missing parenthesis by
2022-12-15 12:30:16 +0100
5a294b0c8
Add -lm on any arm/arm64 BSD, not just FreeBSD by
2022-12-15 10:35:47 +0100
b231fbcd6
Merge pull request #3858 from glennpj/ifort by
2022-12-14 22:47:31 +0100
73dc03c7c
Merge pull request #3861 from martin-frbg/emcc-cleanup by
2022-12-14 17:58:47 +0100
05fbc8140
(refs/pull/3861/head)
rewrite the ifdef as Windows cl failed to parse it by
2022-12-14 15:16:53 +0100
8df791e51
Fix signatures of external functions in the f2c-generated C sources by
2022-12-14 14:06:55 +0100
48f415137
Fix signatures of external functions in the f2c-generated C sources by
2022-12-14 14:06:11 +0100
3eac96ccd
Fix signatures of external functions in the f2c-generated C sources by
2022-12-14 14:04:40 +0100
5b14be1f3
Leave out the Fortran character length arguments when compiling with emscripten by
2022-12-14 14:02:36 +0100
ff9a9222e
Fix function signatures by
2022-12-14 14:01:37 +0100
59e26f633
(refs/pull/3858/head)
Patch for Intel Fortran compiler by
2022-12-09 16:30:22 -0600
de4d5646e
Merge pull request #3857 from martin-frbg/issue3856 by
2022-12-09 08:25:54 +0100
f10c266b4
(refs/pull/3857/head)
Fix stride in shortcut path for small N by
2022-12-08 21:02:01 +0100
c17b5ce75
Merge pull request #3854 from martin-frbg/travis-gcc8arm by
2022-12-07 18:01:07 +0100
8531dbaa2
(refs/pull/3854/head)
Update .travis.yml by
2022-12-07 15:04:13 +0100
ce1a9ae8b
Add a DYNAMIC_ARCH build on Neoverse using older gcc8 by
2022-12-07 14:28:55 +0100
aab9c410e
Merge pull request #3853 from Mousius/fix-sve by
2022-12-06 23:55:33 +0100
60e49b851
(refs/pull/3852/head)
Fix typo in clobber list, should be xmm14 instead of ymm14. by
2022-12-06 16:30:46 -0500
f76e3de3a
(refs/pull/3853/head)
Remove SVE from Arm(R) Neoverse(TM) N1 CPU in Makefile by
2022-12-06 21:23:07 +0000
4afe1439a
Fix skylake fallback kernel name for old compilers. by
2022-12-06 16:09:54 -0500
5ceca1a4d
Add sscal.c + microkernels for Haswell, Zen, Skylake and newer. by
2022-12-06 14:05:49 -0500
729af6406
(refs/pull/3846/head)
bugfix for sbgemm_ncopy_8_neoversen2 by
2022-12-05 05:10:18 -0500
042e3c0e7
Merge pull request #3848 from bartoldeman/dscal-haswell-ymm by
2022-12-05 08:56:08 +0100
02763077d
Merge pull request #3851 from martin-frbg/lapack773 by
2022-12-04 14:52:36 +0100
d59dcd7b1
(refs/pull/3851/head)
Allocate work array when ijob is zero (Reference-LAPACK PR 733) by
2022-12-04 11:43:24 +0100
14aef9400
Merge pull request #3850 from martin-frbg/lapack765 by
2022-12-04 11:33:57 +0100
9b96990e5
(refs/pull/3850/head)
Check for NaN in ?GECON (Reference-LAPACK PR765) by
2022-12-03 20:33:27 +0100
1c1e0682a
Merge pull request #3849 from martin-frbg/lapack769 by
2022-12-03 20:08:20 +0100
00cc78cfb
(refs/pull/3849/head)
Fix uninitialized M in quick return (Reference-LAPACK 769) by
2022-12-03 16:19:20 +0100
9307b0fab
Fix uninitialized M in quick return (Reference-LAPACK 769) by
2022-12-03 16:17:54 +0100
d9993e21a
Refs #3825 Merge branch 'HellerZheng-develop' into risc-v by
2022-12-03 12:01:29 +0800
e5313f53d
Merge branch 'develop' of https://github.com/HellerZheng/OpenBLAS_riscv_x280 into HellerZheng-develop by
2022-12-03 12:00:52 +0800
e284c048d
Merge branch 'develop' into risc-v by
2022-12-03 11:56:55 +0800
0a24f631e
Merge pull request #3844 from Mousius/switch-ratio-16 by
2022-12-02 12:48:43 +0100
65984fbe6
Merge pull request #3847 from bartoldeman/scal-benchmark by
2022-12-02 11:51:50 +0100
f6f0d13b9
Merge pull request #3842 from Mousius/sve-dot by
2022-12-02 08:30:51 +0100
5c3169ecd
(refs/pull/3848/head)
dscal: use ymm registers in Haswell microkernel by
2022-12-01 07:48:05 -0500
eea006a68
(refs/pull/3842/head)
Wrap SVE header with __has_include check by
2022-11-29 17:53:38 +0000
fd4f52c79
Add SVE implementation for sdot/ddot by
2022-11-17 06:49:57 +0000
b6a4ef98b
Merge pull request #3845 from Mousius/asimd-dot-opt by
2022-11-30 21:07:30 +0100
2fb096315
(refs/pull/3844/head)
Set SWITCH_RATIO for Arm(R) Neoverse(TM) V1 CPUs by
2022-11-25 14:46:24 +0000
bae45d94d
(refs/pull/3847/head)
scal benchmark: eliminate y, move init/timing out of loop by
2022-11-29 08:02:45 -0500
fdac8a97c
Add sbgemm_ncopy_8 and sbgemm_tcopy_4 by
2022-11-29 04:46:14 -0500
387e8970c
(refs/pull/3825/head)
Fix merge problem; Update compiling COMMON_OPT per review comments. by
2022-11-28 21:42:29 -0800
135718eaf
Improve the performance of sbgemm_tcopy on neoversen2 by
2022-11-28 04:17:54 -0500
4f7b77e08
(refs/pull/3845/head)
Remove unnecessary instructions from Advanced SIMD dot by
2022-11-25 15:24:32 +0000
e9a911fb9
Merge pull request #3841 from martin-frbg/lapack755+764 by
2022-11-23 22:38:06 +0100
bf0e8d67b
Merge pull request #3840 from martin-frbg/lapack760 by
2022-11-23 19:16:25 +0100
a5470521e
(refs/pull/3841/head)
Fix array indexation in copy, and fix test (Reference-LAPACK PR764) by
2022-11-23 15:31:25 +0100
b0393ea4e
Fix test (Reference-LAPACK PR764) by
2022-11-23 15:27:46 +0100
0d26f1a4c
Fix wrong indexation in test (Reference-LAPACK PR755) by
2022-11-23 15:22:27 +0100
19fd2d7f0
Use LSAME for character comparison (Reference-LAPACK PR755) by
2022-11-23 15:19:07 +0100
663bf68db
Merge pull request #3839 from martin-frbg/lapack758 by
2022-11-23 14:57:56 +0100
c2ba4e624
(refs/pull/3840/head)
Remove unnecessary return in void function call (Reference-LAPACK PR760) by
2022-11-23 10:43:34 +0100
74962c7f5
Remove unnecessary return in void function call (Reference-LAPACK PR760) by
2022-11-23 10:42:29 +0100
d952cbf7b
Remove unnecessary return in void function call (Reference-LAPACK PR760) by
2022-11-23 10:41:50 +0100
7694ff495
Remove unnecessary return in void function call (Reference-LAPACK PR760) by
2022-11-23 10:40:59 +0100
825ae316e
Fix typo in EXTERNAL (Reference-LAPACK PR760) by
2022-11-23 10:36:10 +0100
730ed549e
Fix typo in EXTERNAL (Reference-LAPACK PR760) by
2022-11-23 10:35:23 +0100
bc3393f70
(refs/pull/3839/head)
Fix array dimension (Reference-LAPACK 758) by
2022-11-23 10:31:18 +0100
0b2f8dabb
Fix array dimension (Reference-LAPACK 758) by
2022-11-23 10:30:35 +0100
b4c922844
Merge pull request #3838 from martin-frbg/lapa311 by
2022-11-22 17:39:51 +0100
e6e2a6365
(refs/pull/3838/head)
Update LAPACK version number to 3.11.0 by
2022-11-22 14:02:21 +0100
8408357ba
Update LAPACK version number to 3.11.0 by
2022-11-22 14:01:48 +0100
ba8fb8b4b
Merge pull request #3837 from martin-frbg/lapack655+697 by
2022-11-22 13:51:57 +0100
cabf9453e
Merge pull request #3836 from martin-frbg/lapack665+735 by
2022-11-22 09:25:24 +0100
3918d8504
nrm2 simple optimization by
2022-11-21 19:06:07 -0800
d32135755
(refs/pull/3837/head)
Fix bug in DORCSD2BY1 (from Reference-LAPACK PR697) by
2022-11-21 21:19:44 +0100
afcd7e88b
Improve convergence of DLAED4/SLAED4 (Reference-LAPACK PR655) by
2022-11-21 21:18:39 +0100
f8f2bebf1
(refs/pull/3836/head)
Fix function documentation for LAPACK ?TPRFB (Reference-LAPACK PR665) by
2022-11-21 20:01:47 +0100
c45edcb53
Fix typo in comment (Reference-LAPACK PR735) by
2022-11-21 19:59:33 +0100
880a3fb20
Merge pull request #3835 from martin-frbg/lapack217 by
2022-11-21 19:56:28 +0100
50aba0291
(refs/pull/3835/head)
Simplify ?SYSWAPR and fix its documentation (Reference-LAPACK 217) by
2022-11-21 18:00:31 +0100
0b68dd6a9
Merge pull request #3834 from martin-frbg/lapack631 by
2022-11-21 08:30:14 +0100
934349925
Merge pull request #3833 from martin-frbg/lapack712+747 by
2022-11-21 08:29:49 +0100
7ae4269ad
(refs/pull/3834/head)
Use new algorithms for computing Givens rotations (Reference-LAPACK PR631) by
2022-11-20 22:52:28 +0100
e00f0fb26
(refs/pull/3833/head)
Fix function documentation (Reference-LAPACK PR747) by
2022-11-20 22:46:58 +0100
31d214598
Set scale early for robust triangular solvers (Reference-LAPACK PR712) by
2022-11-20 22:44:36 +0100
1d5a3aff0
Merge pull request #3832 from martin-frbg/lapack681+698 by
2022-11-20 22:40:52 +0100
c6816bb57
(refs/pull/3832/head)
Use normwise criterion in multishift QZ (Reference-LAPACK PR698) by
2022-11-20 19:39:12 +0100
6f09e4c12
Improve FMA usage in ?LAQR5 (Reference-LAPACK PR681) by
2022-11-20 19:37:28 +0100
f63c93274
Merge pull request #3831 from martin-frbg/lapack647+697+702 by
2022-11-20 19:34:41 +0100
aaea0804b
(refs/pull/3831/head)
Fix function documentation (Reference-LAPACK PR697) by
2022-11-20 16:38:57 +0100
b94682050
Fix uninitialized variable (Reference-LAPACK PR647) by
2022-11-20 16:36:19 +0100
9e29312c8
Fix type precision and function documentation (Reference-LAPACK PRs 647+702) by
2022-11-20 16:34:45 +0100
b1102fe25
Merge pull request #3830 from martin-frbg/lapack691+698 by
2022-11-20 16:29:46 +0100
3f31b6912
(refs/pull/3830/head)
Add quick return if scaling with one (Reference-LAPACK PR674) by
2022-11-20 13:30:25 +0100
60af35bfa
Fix workspace query for ?SYEVD and ?HEEVD (Reference-LAPACK PR691) by
2022-11-20 13:25:21 +0100
eea163638
Use normwise criterion for INF eigenvalues in QZ (Reference-LAPACK PR698) by
2022-11-20 13:22:55 +0100
1714d640f
Merge pull request #3829 from martin-frbg/lapack684+739 by
2022-11-20 13:06:51 +0100
88cd91c49
(refs/pull/3829/head)
Fix stray character by
2022-11-19 23:15:20 +0100
f157d6d67
Add C equivalents of ?GELST (for Reference-LAPACK PR739) by
2022-11-19 22:50:57 +0100
5ff46f409
Add ?GELST (Reference-LAPACK PR739) by
2022-11-19 22:49:31 +0100
1d32ce513
Add ?GELST (Reference-LAPACK PR739) by
2022-11-19 22:42:50 +0100
1497336b2
Add tests for ?GELST (Reference-LAPACK PR739) by
2022-11-19 22:39:16 +0100
d0afbd8d2
Add new routines for ?GELST similar to ?GELS (Reference-LAPACK PR739) by
2022-11-19 22:34:42 +0100
63014e99a
Cast work array sizes to integer (Reference-LAPACK PR 684) by
2022-11-19 22:31:33 +0100