projects / platform / upstream / openblas.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 73128f3) | patch
Fix the integer overflow issue for large matrix size
authorWang, Long <long1.wang@intel.com>
Wed, 20 Nov 2019 03:50:37 +0000 (11:50 +0800)
committerWang, Long <long1.wang@intel.com>
Wed, 20 Nov 2019 06:11:17 +0000 (14:11 +0800)
commit0caf1434c928d39373499ffc02abe645945485d8
tree99273e5ed089535a7c1f1b7baa536001f8420d5atree | snapshot
parent73128f3883e3fb37523bb4ce032e261d679e9024commit | diff
Fix the integer overflow issue for large matrix size

For large matrix, e.g. M=N=K, and M>1290, int mnk=M*N*K will overflow.
This will lead to wrong branching to single-threading. The performance
is downgraded significantly.

Signed-off-by: Wang, Long <long1.wang@intel.com>
kernel/x86_64/sgemm_kernel_16x4_skylakex.c diff | blob | history
kernel/x86_64/sgemm_kernel_16x4_skylakex_2.c diff | blob | history
Domain: Machine Learning / ML Framework;