Commit Graph

7182 Commits

Author SHA1 Message Date
Martin Kroeker
fdb7d189cb Add pragma to restrict optimization 2023-06-24 12:32:07 +02:00
Martin Kroeker
5a0caf4476 Add pragma to restrict optimization 2023-06-24 12:31:00 +02:00
Martin Kroeker
1b1a881461 fix extraneous brace 2023-06-24 09:05:42 +02:00
Martin Kroeker
53d9e6f097 Fix Makefile.system 2023-06-23 10:55:04 +02:00
Martin Kroeker
7d2fb5a473 fix typo 2023-06-23 07:55:01 +02:00
Martin Kroeker
54b9ab45c5 fix missing endif 2023-06-23 02:49:23 +02:00
Martin Kroeker
13f0fe1f42 reenable 2023-06-23 02:41:17 +02:00
Martin Kroeker
81586e7b0a work around an optimizer bug in Xuantie's gfortran 2023-06-23 02:39:37 +02:00
Martin Kroeker
f0ac1373a3 Temporarily relax the tolerance for DSDOT 2023-06-22 18:31:13 +02:00
Martin Kroeker
65cb23007f Fix failures to handle increments of zero 2023-06-22 17:30:43 +02:00
Martin Kroeker
0f87ed2682 Disable all of test_potrs.c on RISCV for now 2023-06-22 15:13:19 +02:00
Martin Kroeker
61153f2c1f Disable the bigger POTRS test on RISCV64 for now 2023-06-19 17:50:12 +02:00
Martin Kroeker
3550698bf8 Use a smaller GEMM workload on RISCV targets 2023-06-19 15:04:17 +02:00
Martin Kroeker
a98c292a91 Merge pull request #4024 from Rabenda/add-c910v-ci
CI (C910V): add test
2023-06-18 20:29:25 +02:00
Martin Kroeker
619908a8c9 Merge pull request #4090 from martin-frbg/issue4029
Fix VLEV/VSEV_FLOAT macros to compile C910V target with t-head 2.6.1
2023-06-18 20:08:01 +02:00
Martin Kroeker
73b30b1dec Fix VLEV_FLOAT/VSEV_FLOAT macros to compile with t-head 2.6.1 2023-06-18 17:46:29 +02:00
Martin Kroeker
451cb53a11 Merge pull request #4088 from martin-frbg/lapack854
Fix potential stack overflows in LAPACK EIG tests (Reference-LAPACK PR 854)
2023-06-18 13:24:17 +02:00
Martin Kroeker
eb058c2ae2 Merge pull request #4087 from martin-frbg/lapack847
Improve variants of Cholesky and QR (Reference-LAPACK PR 847)
2023-06-18 11:39:52 +02:00
Martin Kroeker
0e55702b80 Use dynamic allocation in ?SYL01 tests (Reference-LAPACK PR 854) 2023-06-18 11:17:21 +02:00
Martin Kroeker
f524594d27 Replace SCEIL with CEILING intrinsic (Reference-LAPACK PR 847) 2023-06-18 10:11:30 +02:00
Martin Kroeker
f330f862f9 Delete and replace with CEILING intrinsic (Reference-LAPACK PR 847) 2023-06-18 10:08:36 +02:00
Martin Kroeker
2dae4a34a9 Fix description (Reference-LAPACK PR 847) 2023-06-18 10:05:03 +02:00
Martin Kroeker
35f2ce8340 Fix description (Reference-LAPACK PR 847) 2023-06-18 10:03:43 +02:00
Martin Kroeker
8b32cebfcc Fix description (Reference-LAPACK PR 847) 2023-06-18 10:02:12 +02:00
Martin Kroeker
ce7f4adb42 Fix description (Reference-LAPACK PR 847) 2023-06-18 10:00:49 +02:00
Martin Kroeker
5c742ad44c Fix description (Reference-LAPACK PR847) 2023-06-18 09:59:44 +02:00
Martin Kroeker
c7cf1ae95a Remove LL/sceil (same as CEILING intrinsic) (Reference-LAPACK PR847) 2023-06-18 08:46:27 +02:00
Martin Kroeker
c3a2d407a0 Merge pull request #4048 from imzhuhl/spr_sbgemm_fix
Sapphire Rapids sbgemm fix
2023-06-17 20:47:09 +02:00
Martin Kroeker
c94cfef30a CirrusCI: Add INTERFACE64 jobs on MacOS, FreeBSD, and on Linux arm64 (#4085)
* Add INTERFACE64 jobs on MacOS, FreeBSD, and on Linux arm64
2023-06-17 11:18:21 +02:00
Martin Kroeker
369cc0fa02 CirrusCI: Add basic FreeBSD build (#4082)
* Add basic FreeBSD build
2023-06-14 20:58:23 +02:00
Martin Kroeker
5759f905f2 Merge pull request #4077 from XiWeiGu/loongarch64_abi
LoongArch64: Add ABI detection for loongarch64
2023-06-14 11:35:12 +02:00
Martin Kroeker
db3366f503 Merge pull request #4071 from martin-frbg/fix4010
Drop extraneous escaping in the basename call
2023-06-13 20:59:27 +02:00
Martin Kroeker
ff618ac475 Rework removal of compiler options 2023-06-13 19:16:06 +02:00
Martin Kroeker
00057f416f Merge pull request #4081 from mikejuliet13/12jun3
POWER10: Fix compiler warnings
2023-06-12 16:51:08 +02:00
Manjul Mohan
58b88aa5f0 POWER10: Fix compiler warnings
This patch removes the warning messages related to unused variables in
sbgemm_kernel_power10.c.

Signed-off-by: Manjul Mohan <manjul@linux.vnet.ibm.com>
2023-06-12 01:08:59 -04:00
Martin Kroeker
0f41a4664f Merge pull request #4079 from martin-frbg/gitign
Gitignore: Ignore LAPACK's la_constants.mod
2023-06-10 15:19:07 +02:00
Martin Kroeker
ee80dd8371 Ignore LAPACK's la_constants.mod 2023-06-10 00:40:47 +02:00
Martin Kroeker
95a584e252 Merge pull request #4078 from martin-frbg/nv_cmake
Add support for NVIDIA HPC (nvc,pgf95) in CMAKE builds
2023-06-09 20:40:59 +02:00
Martin Kroeker
d2144b2981 Add NVHPC 2023-06-09 19:01:15 +02:00
Martin Kroeker
f8c8b22740 Add NVHPC(pgf95) 2023-06-09 18:58:52 +02:00
Martin Kroeker
2993a73262 Add NVHPC(nvc) 2023-06-09 18:56:13 +02:00
gxw
67d1e72e8b LoongArch64: Add ABI detection for loongarch64
If lp64d ABI is supported, it is used; otherwise,
it falls back to the lp64 ABI.
2023-06-08 20:25:35 +08:00
Martin Kroeker
5a4fac1376 Merge pull request #4075 from martin-frbg/issue4072
Treat f95 as gfortran in CMAKE builds
2023-06-06 14:53:35 +02:00
Martin Kroeker
f981e37dda Treat f95 as gfortran 2023-06-05 20:34:31 +02:00
Martin Kroeker
b1f6d90a11 Drop extraneous escaping in the basename call 2023-06-03 23:21:39 +02:00
Martin Kroeker
23693f09a2 Merge pull request #4062 from angsch/develop
Improve input argument checks of gemmt
2023-05-31 19:56:51 +02:00
Martin Kroeker
11d867731a Add Apple m1/iphoneos (cross)build in Cirrus CI (#4052)
* Add Apple m1/iphoneos (cross)build
2023-05-31 19:35:16 +02:00
Martin Kroeker
ef80dbfdb3 Merge pull request #4068 from martin-frbg/lapack832
Remove unused variable SMIN from ?BDSQR (Reference-LAPACK PR 832)
2023-05-31 14:08:17 +02:00
Martin Kroeker
92720c2f1e Remove unused variable SMIN (Reference-LAPACK 832) 2023-05-31 11:33:32 +02:00
Martin Kroeker
d4c6934f1a Merge pull request #4067 from martin-frbg/lapack836
Fix potential segfault in LAPACKE S/DGEESX (Reference-LAPACK PR 836)
2023-05-31 10:30:46 +02:00