Martin Kroeker
cd8ac192a9
fix improper function prototypes (empty parentheses)
2023-09-30 12:58:30 +02:00
Martin Kroeker
675cd551da
fix improper function prototypes (empty parentheses)
2023-09-30 12:56:38 +02:00
Martin Kroeker
13ba4edf43
fix function prototypes (empty parentheses)
2023-09-30 12:53:35 +02:00
Martin Kroeker
c6b1d8e7a3
fix improper function prototypes (empty parentheses)
2023-09-30 12:52:06 +02:00
Martin Kroeker
c4bd4a2e5d
fix improper function prototypes (empty parentheses)
2023-09-30 12:49:24 +02:00
Martin Kroeker
ccbb91e4a7
fix improper function prototypes (empty parentheses)
2023-09-30 12:46:34 +02:00
Martin Kroeker
189627709e
Merge pull request #4244 from XiWeiGu/loongarch64_fixed_dynamic_arch
...
Loongarch64 fixed dynamic arch
2023-09-30 10:16:43 +02:00
Martin Kroeker
5ac0ec70a1
Merge pull request #4245 from RajalakshmiSR/xlf_fix
...
powerpc: Fix build errors with xlf
2023-09-29 23:51:53 +02:00
Rajalakshmi Srinivasaraghavan
a11e1e10f4
powerpc: Fix build errors with xlf
...
This patch fixes errors when using xlf as fortran compiler on Linux.
Tested with gcc/xlf and clang/xlf compiler combinations.
2023-09-29 10:32:34 -05:00
gxw
211bb35dee
gh-actions: Adding DYNAMIC_ARCH test for LoongArch64
2023-09-27 11:08:03 +08:00
gxw
d15e0a055c
LoongArch64: Fixed compilation issues when enable DYNAMIC_ARCH
2023-09-27 10:05:27 +08:00
Martin Kroeker
e2ca22f8d8
Merge pull request #4242 from XiWeiGu/loongarch64_dtrsm
...
LoongArch64: Add dtrsm kernel
2023-09-26 19:21:48 +02:00
gxw
4670eb1462
LoongArch64: Add dtrsm kernel
2023-09-26 15:45:14 +08:00
Martin Kroeker
138ed79fe7
Merge pull request #4238 from martin-frbg/issue4237
...
Fix building on POWER with IBM XLF 16.1.1
2023-09-24 14:31:33 +02:00
Martin Kroeker
2a9981a244
Add -lgomp when IBM xlf is combined with gcc in OPENMP builds
2023-09-24 10:19:11 +02:00
Martin Kroeker
7a96908d0c
Add -lgomp when IBM xlf is combined with gcc in OPENMP builds
2023-09-24 10:18:24 +02:00
Martin Kroeker
4de963dc17
Enforce trailing underscores on symbols when IBM xlf is combined with gcc
2023-09-24 10:16:37 +02:00
Martin Kroeker
8012afcabb
Avoid using some gcc-specific flags with IBM xlf
2023-09-24 10:15:12 +02:00
Martin Kroeker
bb47183222
Force -qextname for trailing underscore generation when IBM xlf is used with gcc
2023-09-24 10:13:47 +02:00
Martin Kroeker
b926e70ebd
Fix typo in build rule of "profiled" sbgemm
2023-09-21 23:07:32 +02:00
Martin Kroeker
2390e0bfbc
Quote the BU (underscore) option as it may not be set
2023-09-21 23:04:25 +02:00
Martin Kroeker
44e6e5479b
Use the C compiler for the C SBGEMM test source
2023-09-21 23:01:21 +02:00
Martin Kroeker
48b1b7cbc9
Merge pull request #4233 from martin-frbg/issue4216
...
Fix handling of additional buffer structures in case of overflow
2023-09-21 11:12:52 +02:00
Martin Kroeker
bb90b6dfcd
Merge pull request #4157 from steppi/cirun
...
Set up arm64 graviton CI using cirun
2023-09-21 07:28:40 +02:00
Martin Kroeker
7e939fb831
Fix handling of additional buffer structures in case of overflow
2023-09-19 23:33:39 +02:00
Martin Kroeker
bb2f1ec3b0
Merge pull request #4222 from dev-zero/bugfix/correct-thread-warning
...
memory: show correct number of max threads
2023-09-17 00:02:46 +02:00
Martin Kroeker
466e6115d3
Merge pull request #4230 from martin-frbg/lapack907
...
Increase work array size in S/DTGEX2 to avoid overflow (Reference-LAPACK PR 907)
2023-09-16 20:13:13 +02:00
Martin Kroeker
1285b53e39
Make IWORK array larger to avoid overflow
2023-09-14 20:22:11 +02:00
Martin Kroeker
7779bb6fb1
Make IWORK array larger to avoid overflow
2023-09-14 20:21:06 +02:00
Martin Kroeker
0606102460
Merge pull request #4229 from martin-frbg/issue4228
...
Add la_constants.o to SCLAUX/DZLAUX in LAPACK Makefile
2023-09-14 16:15:54 +02:00
Martin Kroeker
fb97cc4d5e
Add la_constants.o to SCLAUX/DZLAUX
2023-09-14 10:46:23 +02:00
Tiziano Müller
6a611db560
memory: show correct number of max threads
2023-09-10 08:44:07 +02:00
Martin Kroeker
6bc079687f
Merge pull request #4218 from XiWeiGu/loongarch64_sgemv
...
LoongArch64: Add sgemv kernel
2023-09-08 13:35:35 +02:00
Martin Kroeker
cd36b8fff7
Merge pull request #4214 from martin-frbg/issue4212
...
Disable SVE targets in DYNAMIC_ARCH when compiler is gcc on macOS
2023-09-05 20:43:44 +02:00
Martin Kroeker
09911f077e
Disable SVE targets for DYNAMIC_ARCH when compiling with (homebrew)gcc on macOS/arm64
2023-09-05 16:33:40 +02:00
Martin Kroeker
c3f2a3c0ca
Update version to 0.3.24.dev
2023-09-04 08:40:25 +02:00
Martin Kroeker
4867cf5dd7
Update version to 0.3.24.dev
2023-09-04 08:39:40 +02:00
gxw
f2cf929374
LoongArch64: Add sgemv kernel
2023-09-04 14:28:37 +08:00
Martin Kroeker
f29a0d1a7d
Merge pull request #4211 from xianyi/release-0.3.0
...
merge release-0.3.24 back into develop to copy tag
2023-09-03 23:25:58 +02:00
Martin Kroeker
9f815cf1bf
Update version to 0.3.24
2023-09-03 22:58:32 +02:00
Martin Kroeker
3c49711f1e
Update version to 0.3.24
2023-09-03 22:57:22 +02:00
Martin Kroeker
2c68822cde
Merge pull request #4210 from xianyi/develop
...
merge develop into 0.3.0 for 0.3.24
2023-09-03 22:55:22 +02:00
Martin Kroeker
3c51bd0fbf
Merge pull request #4209 from martin-frbg/changelog0324
...
Update Changelog for 0.3.24
2023-09-03 22:51:03 +02:00
Martin Kroeker
5d73041068
Update Changelog for 0.3.24
2023-09-03 19:05:53 +02:00
Martin Kroeker
8e6d93359d
Merge pull request #4196 from TiborGY/obsolete_inlines
...
Modernize obsolete inline order
2023-09-03 14:12:42 +02:00
Martin Kroeker
33797c44fc
Merge pull request #4143 from martin-frbg/issue4130
...
Update to use safe scaling algorithm from Reference-LAPACK PR 527
2023-09-01 14:20:25 +02:00
Martin Kroeker
ee310e3533
Merge pull request #4208 from XiWeiGu/loongarch64_toolchain
...
LoongArch64: Compatible with early internal toolchain
2023-09-01 10:50:01 +02:00
Martin Kroeker
42909ce57d
Merge branch 'xianyi:develop' into issue4130
2023-09-01 09:05:58 +02:00
Martin Kroeker
a2a184572c
update zrotg
2023-08-31 23:42:12 +02:00
gxw
394a1fd1bf
LoongArch64: Compatible with early internal toolchain
...
__loongarch_grlen and __loongarch_frlen were introduced in gcc version 8.3.0
(Loongnix 8.3.0-6.lnd.vec.31) internally within Loongson to standardize the
general and floating-point register widths. However, previous versions did
not have them, requiring additional checks to be added.
2023-08-31 16:55:29 +08:00