floraachy
/
OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
8,757 Commits 47 Branches 64 Tags 71 MiB
Commit Graph

8757 Commits

Author SHA1 Message Date
Chip Kerchner 2391dc1c0f Merge branch 'vectorizeBF16GEMV' of github.ibm.com:PowerAppLibs/OpenBLAS into vectorizeBF16GEMV 2024-10-13 13:48:33 -05:00
Chip Kerchner 36bd3eeddf Vectorize BF16 GEMV (VSX & MMA). Use GEMM_GEMV_FORWARD_BF16 (for Power). 2024-10-13 13:46:11 -05:00
Chip Kerchner f8e113f27b Replace types with include file. 2024-10-13 10:55:03 -05:00
Chip Kerchner a53a197934 Merge remote-tracking branch 'origin/develop' into vectorizeBF16GEMV 2024-10-12 15:15:17 -05:00
Martin Kroeker 3184b7f209
Merge pull request #4933 from ChipKerchner/thread_sbgemv 
Change multi-threading logic for SBGEMV to be the same as SGEMV.
 2024-10-12 17:19:41 +02:00
Chip Kerchner 0082240044 Merge branch 'thread_sbgemv' into vectorizeBF16GEMV 2024-10-11 16:13:59 -05:00
Chip Kerchner 1d51ca5798 Change multi-threading logic for SBGEMV to be the same as SGEMV. 2024-10-11 16:08:48 -05:00
Chip Kerchner c8f53b85ce Merge remote-tracking branch 'origin/develop' into vectorizeBF16GEMV 2024-10-11 11:10:20 -05:00
Martin Kroeker 18a23c23f7
Merge pull request #4929 from martin-frbg/issue4905 
Fix CBLAS_?GEMMT filling in the wrong triangle for Row-Major
 2024-10-11 08:54:02 +02:00
Martin Kroeker 5a79446bdb
Merge pull request #4918 from HaoZeke/testFixes 
TST,BUG: Explicitly allow running tests multiple times
 2024-10-10 21:53:18 +02:00
Martin Kroeker 7ba6591ff2
Merge branch 'OpenMathLib:develop' into issue4905 2024-10-10 21:50:38 +02:00
Martin Kroeker 550bc77832
Fix expectation values for CblasRowMajor order 2024-10-10 20:39:29 +02:00
Martin Kroeker e0ad20f72b
Merge pull request #4932 from martin-frbg/cirrusosxndk 
Update Android NDK install path for M1/armv7 crossbuild on CirrusCI
 2024-10-10 16:18:07 +02:00
Martin Kroeker e4bc5e4718
remove stray quote 2024-10-10 11:02:56 +02:00
Martin Kroeker b89fb9632f
Update Android NDK install path for M1/armv7 crossbuild 2024-10-10 10:19:11 +02:00
Martin Kroeker e52d9b4cf1
Merge pull request #4928 from austinpagan/czgemm_in_c 
CGEMM & ZGEMM using C code, Power only, P10 only.
 2024-10-09 20:26:21 +02:00
Martin Kroeker dbd83762f9
Merge pull request #4926 from NickelWenzel/fix_arm64_windows_and_uwp 
fix: add missing NO_AFFINITY checks
 2024-10-09 19:48:16 +02:00
Martin Kroeker 9762464718
Fix CBLAS interface filling in the wrong triangle for Row-Major 2024-10-09 18:06:39 +02:00
Gordon Fossum 0b7fb5c791 CGEMM & ZGEMM using C code. 2024-10-09 09:42:23 -05:00
NickelWenzel bee123e8e3
fix: add missing NO_AFFINITY checks 2024-10-09 16:36:40 +02:00
Martin Kroeker 7ac5b9011f
Merge pull request #4923 from martin-frbg/zen5 
Add preliminary cpu autodetection for Zen5/5c
 2024-10-09 16:18:47 +02:00
Martin Kroeker 2c3b87a082
Add preliminary cpu autodetection for Zen5/5c 2024-10-08 23:07:42 +02:00
Martin Kroeker 73c1882129
Merge pull request #4922 from martin-frbg/issue4904-2 
Update names of Loongarch64 targets in cmake cross-building
 2024-10-07 13:24:14 +02:00
Martin Kroeker bc0691a556
Merge pull request #4920 from martin-frbg/issue4917 
Fix potential inaccuracy in multithreaded level3 related to SWITCH_RATIO
 2024-10-07 08:26:03 +02:00
Martin Kroeker b0346e72f4
update names of loongarch64 targets for cross-compilation 2024-10-06 22:48:33 +02:00
Martin Kroeker 9c707dc6b9
Update dynamic arch list to new target scheme 2024-10-06 22:46:03 +02:00
Martin Kroeker 9783dd07ab
Rename KERNEL.LOONGSONGENERIC to KERNEL.LA64_GENERIC 2024-10-06 22:43:11 +02:00
Martin Kroeker 0dfe42d62a
Merge pull request #4919 from martin-frbg/issue4916-2 
Handle inf/nan in ppc440 s/dscal
 2024-10-06 22:29:28 +02:00
Chip Kerchner d6bb8dcfd1 Common code. 2024-10-06 14:13:43 -05:00
Martin Kroeker 8a1710dd0d
don't apply switch_ratio to tail of loop 2024-10-06 20:03:32 +02:00
Martin Kroeker c9e92348a6
Handle inf/nan if dummy2 flag is set 2024-10-06 19:57:17 +02:00
Rohit Goswami d9f368dfe6
TST: Signal abort for ctest failures correctly 2024-10-05 16:24:16 +00:00
Rohit Goswami 722e4ae07a
MAINT: Explicitly replace instead of unknown 2024-10-05 16:23:02 +00:00
Rohit Goswami a6b7751881
BUG: Allow tests to be run multiple times 
Without failures due to existing files
 2024-10-05 16:22:56 +00:00
Chip Kerchner 9ac0fb0111 Merge branch 'develop' into vectorizeBF16GEMV 2024-10-04 06:49:53 -05:00
Martin Kroeker 624e9d110e
Merge pull request #4916 from martin-frbg/issue4901 
Fix SIGILL/SIGSEGV in PPCG4 SGEMM and fix NAN handling in PPCG4 SSCAL/DSCAL
 2024-10-03 23:25:45 +02:00
Martin Kroeker d714013ab9
change sgemm kernel to 4x4 as the 16x4 altivec goes out of bounds 2024-10-03 22:04:20 +02:00
Martin Kroeker 7c4f3638fd
switch PPCG4 SGEMM kernel to 4x4 2024-10-03 22:00:15 +02:00
Chip Kerchner 915a6d6e44 Add casting. 2024-10-03 14:08:21 -05:00
Chip Kerchner 7ec3c16d82 Remove beta from optimized functions. 2024-10-03 13:27:33 -05:00
Martin Kroeker 54afc24e4d
Merge pull request #4906 from XiWeiGu/arm64_cmake_small_matrix_opt 
ARM64: Enable SMALL_MATRIX_OPT when compiling with CMake
 2024-10-03 20:05:11 +02:00
Martin Kroeker b4495a8fb8
Merge branch 'develop' into arm64_cmake_small_matrix_opt 2024-10-03 20:04:52 +02:00
Martin Kroeker 68eefe60b9
Merge pull request #4915 from martin-frbg/issue4907 
Support LoongArch64 compilation with LLVM
 2024-10-03 18:29:29 +02:00
Martin Kroeker 4f00f02567
Do not add -mabi flags for Loongson when the compiler is flang 2024-10-03 16:06:33 +02:00
Martin Kroeker f817f26062
Add simpler EPILOGUE for clang 2024-10-03 16:01:10 +02:00
Martin Kroeker a492181665
filter out Loongarch -mabi options for flang-new 2024-10-03 15:58:47 +02:00
Martin Kroeker de421b7764
Merge pull request #4904 from XiWeiGu/la64_cross_cmake 
LoongArch64: Enable cmake cross-compilation
 2024-10-03 15:53:57 +02:00
Martin Kroeker edaf5933c4
Merge pull request #4913 from martin-frbg/issue4912 
Declare the input array in CBLAS_?GEADD as const in cblas.h
 2024-10-02 23:37:15 +02:00
Martin Kroeker 71131406ae
Declare the input array in CBLAS_?GEADD as const 2024-10-02 18:32:48 +02:00
Chip Kerchner 7cc00f68c9 Remove more duplicate. 2024-10-01 11:23:32 -05:00