OSchip
/
OpenBLAS
mirror of https://github.com/xianyi/OpenBLAS.git
0
0
Fork 2
Code Issues Packages Projects Releases Wiki Activity
10,714 Commits 58 Branches 70 Tags 121 MiB
Commit Graph

19 Commits

Author SHA1 Message Date
Martin Kroeker cb8199dda2
Add error return on buffer assignment failure 2026-08-07 12:20:19 +02:00
Martin Kroeker 63ad298a67
Merge branch 'develop' into attrib-hidden 2026-07-21 20:00:16 +02:00
moluopro 18b41f3c4d interface: gate ARM64 STRMM direct fast path 2026-07-09 13:42:12 +08:00
Martin Kroeker 26c4eb65d1
Restore the quick return in common code - the earlier one is CBLAS only 2026-05-15 20:10:51 +02:00
Martin Kroeker fd862d43b6
Remove redundant quick return 2026-04-22 15:36:57 +02:00
Martin Kroeker 74486799bb
Move quick return out of the scope of the DYNAMIC_ARCH conditional for SME 2026-04-22 12:22:09 +02:00
mattip be7da1f111 add visibility=default to exported functions, visibility=hidden to most assembler 2026-02-05 06:31:17 +11:00
Martin Kroeker 682f61e8b8
Add prototype for gotoblas_corename 2025-10-19 14:37:39 -07:00
Martin Kroeker 83d3e0ed1a
fix copy/paste 2025-10-19 14:16:46 -07:00
Martin Kroeker f4ee3aec88
Allow VortexM4 on the SME fast path only with non-gcc compilers 2025-10-19 13:43:11 -07:00
changjua 644ea07ef9 Support for SME1 based strmm_direct kernel for cblas_strmm level 3 API 2025-10-10 10:48:27 +08:00
Martin Kroeker 0bd956fd21 Correct length of name string in xerbla call 2019-04-27 22:49:04 +02:00
Martin Kroeker 8533aca964
Avoid penalizing tall skinny matrices 2019-01-23 10:03:00 +01:00
Martin Kroeker cda81cfae0
Shift transition to multithreading towards larger matrix sizes 
See #1886 and JuliaRobotics issue 500. trsm benchmarks on Haswell and Zen showed that with these values performance is roughly doubled for matrix sizes between 8x8 and 14x14, and still 10 to 20 percent better near the new cutoff at 32x32.
 2019-01-19 00:10:01 +01:00
Craig Donner 66316b9f4c Improve performance of GEMM for small matrices when SMP is defined. 
Always checking num_cpu_avail() regardless of whether threading will actually
be used adds noticeable overhead for small matrices.  Most other uses of
num_cpu_avail() do so only if threading will be used, so do the same here.
 2018-06-07 15:29:13 +01:00
Martin Kroeker 2c222f1faa
Modify complex CBLAS functions to take void pointers 
Modify complex CBLAS functions to take void pointers instead of float or double arguments (to bring the prototypes in line with netlib and other implementations' cblas.h)
 2017-11-05 15:53:14 +01:00
Werner Saar f8f2e261fe use only 1 thread if m or n < 2*GEMM_MULTITHREAD_THRESHOLD 2015-05-06 10:41:53 +02:00
Timothy Gu 6c2ead30f0 Remove all trailing whitespace except lapack-netlib 
Signed-off-by: Timothy Gu <timothygu99@gmail.com>
 2014-06-27 12:05:18 -07:00
Xianyi Zhang 342bbc3871 Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00