core: dispatch matmul

Browse Source

- gemm: keep baseline only (lapack is 10x+ faster, lets reduce binary size)
- transform / distTransform
- scaleAdd (32f/64f only)
- Mahalanobis: keep baseline only (no perf tests)
- mulTransposed: keep baseline only (no perf tests)
- dot

...

This commit is contained in:

Alexander Alekhin

2019-02-14 16:00:17 +03:00

parent fbde57dba8

commit cd66f6e3db

4 changed files with 308 additions and 3575 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

modules/core/src/matmul.dispatch.cpp

+130 -2429

File diff suppressed because it is too large Load Diff

modules/core/src/matmul.simd.hpp

+176 -1146

File diff suppressed because it is too large Load Diff