Add files via upload

Browse Source

replaced most "vpermpd" with cheaper "vpermilpd" or "vperm2f128" to eliminate performance penalty on zen2 chips

...

This commit is contained in:

wjc404 2019-07-16 22:13:26 +08:00 committed by GitHub

parent 52e8b3824b

commit 1c65b0a686

No known key found for this signature in database

GPG Key ID: 4AEE18F83AFDEB23

1 changed files with 4795 additions and 0 deletions

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

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

4795

kernel/x86_64/dgemm_kernel_4x8_haswell.S Normal file

View File

File diff suppressed because it is too large Load Diff