diff options
| author | Kenny Root <kroot@google.com> | 2015-09-25 02:36:32 +0000 |
|---|---|---|
| committer | Android Git Automerger <android-git-automerger@android.com> | 2015-09-25 02:36:32 +0000 |
| commit | d947d006e7a7ebcfdfe642e686250caf2028c2c1 (patch) | |
| tree | dd743d9d64af3145fe96b8d5fc2f3427544794bd /src/crypto/sha/asm/sha1-586.pl | |
| parent | 00bc53f6f4436972b7a8dcf2c1e5fd0ad7515872 (diff) | |
| parent | b8494591d1b1a143f3b192d845c238bbf3bc629d (diff) | |
| download | external_boringssl-d947d006e7a7ebcfdfe642e686250caf2028c2c1.zip external_boringssl-d947d006e7a7ebcfdfe642e686250caf2028c2c1.tar.gz external_boringssl-d947d006e7a7ebcfdfe642e686250caf2028c2c1.tar.bz2 | |
am b8494591: Revert "Revert "external/boringssl: sync with upstream.""
* commit 'b8494591d1b1a143f3b192d845c238bbf3bc629d':
Revert "Revert "external/boringssl: sync with upstream.""
Diffstat (limited to 'src/crypto/sha/asm/sha1-586.pl')
| -rw-r--r-- | src/crypto/sha/asm/sha1-586.pl | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/crypto/sha/asm/sha1-586.pl b/src/crypto/sha/asm/sha1-586.pl index 4895eb3..e0b5d83 100644 --- a/src/crypto/sha/asm/sha1-586.pl +++ b/src/crypto/sha/asm/sha1-586.pl @@ -66,9 +66,9 @@ # switch to AVX alone improves performance by as little as 4% in # comparison to SSSE3 code path. But below result doesn't look like # 4% improvement... Trouble is that Sandy Bridge decodes 'ro[rl]' as -# pair of µ-ops, and it's the additional µ-ops, two per round, that +# pair of µ-ops, and it's the additional µ-ops, two per round, that # make it run slower than Core2 and Westmere. But 'sh[rl]d' is decoded -# as single µ-op by Sandy Bridge and it's replacing 'ro[rl]' with +# as single µ-op by Sandy Bridge and it's replacing 'ro[rl]' with # equivalent 'sh[rl]d' that is responsible for the impressive 5.1 # cycles per processed byte. But 'sh[rl]d' is not something that used # to be fast, nor does it appear to be fast in upcoming Bulldozer |