SHA-1/SSSE3: Improve performance on large buffers
authorJussi Kivilinna <jussi.kivilinna@iki.fi>
Tue, 17 Dec 2013 13:35:38 +0000 (15:35 +0200)
committerJussi Kivilinna <jussi.kivilinna@iki.fi>
Tue, 17 Dec 2013 13:48:32 +0000 (15:48 +0200)
commit6fd0dd2a5f1362f91e2861cd9d300341a43842a5
treedf605eb526e039be53a88b948167e301632fa049
parent50b8c8342d023038a4b528af83153293dd2756ea
SHA-1/SSSE3: Improve performance on large buffers

* cipher/sha1-ssse3-amd64.S (RNBLKS): New.
(_gcry_sha1_transform_amd64_ssse3): Handle multiple input blocks, with
software pipelining of next data block processing.
* cipher/sha1.c [USE_SSSE3] (_gcry_sha1_transform_amd64_ssse3): Add
'nblks'.
(transform) [USE_SSSE3]: Pass nblks to assembly function.
--

Patch gives small improvement for large buffer processing, on Intel i5-4570
speed goes from 4.80 c/B to 4.61 c/B.

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
cipher/sha1-ssse3-amd64.S
cipher/sha1.c