mirror of https://github.com/xianyi/OpenBLAS.git
cdc668d82b
OpenBLAS has a fancy algorithm for copying the input data while laying it out in a more CPU friendly memory layout. This is great for large matrixes; the cost of the copy is easily ammortized by the gains from the better memory layout. But for small matrixes (on CPUs that can do efficient unaligned loads) this copy can be a net loss. This patch adds (for SKYLAKEX initially) a "sgemm direct" mode, that bypasses the whole copy machinary for ALPHA=1/BETA=0/... standard arguments, for small matrixes only. What is small? For the non-threaded case this has been measured to be in the M*N*K = 28 * 512 * 512 range, while in the threaded case it's less, around M*N*K = 1 * 512 * 512 |
||
|---|---|---|
| .. | ||
| alpha | ||
| arm | ||
| arm64 | ||
| generic | ||
| ia64 | ||
| mips | ||
| mips64 | ||
| power | ||
| sparc | ||
| x86 | ||
| x86_64 | ||
| zarch | ||
| CMakeLists.txt | ||
| Makefile | ||
| Makefile.L1 | ||
| Makefile.L2 | ||
| Makefile.L3 | ||
| Makefile.LA | ||
| setparam-ref.c | ||