projects / platform / upstream / openblas.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: e1038ea) | patch
s390x/GEMM: replace 0-init with peeled first iteration
authorMarius Hillenbrand <mhillen@linux.ibm.com>
Tue, 19 May 2020 12:30:44 +0000 (14:30 +0200)
committerMarius Hillenbrand <mhillen@linux.ibm.com>
Wed, 20 May 2020 08:23:35 +0000 (10:23 +0200)
commitbdd795ed03667861b762836aa64e4b2bd33bf485
treea36b74a585c0a88a67adbd7dff4a0a284c61c756tree | snapshot
parente1038ea8364b0957db9a4a71b308d9c3f1cdaa9dcommit | diff
s390x/GEMM: replace 0-init with peeled first iteration

... since it gains another ~2% of SGEMM and DGEMM performance on z15;
also, the code just called for that cleanup.

Signed-off-by: Marius Hillenbrand <mhillen@linux.ibm.com>
kernel/zarch/gemm_vec.c diff | blob | history
Domain: Machine Learning / ML Framework;