diff options
author | Andy Polyakov <appro@openssl.org> | 2011-09-15 20:22:59 +0000 |
---|---|---|
committer | Andy Polyakov <appro@openssl.org> | 2011-09-15 20:22:59 +0000 |
commit | 8ca28da0a798d2289b71b750dad191066600c166 (patch) | |
tree | f99b2ae7ab9bbee9c5f98cc928d0a799d969eac5 /crypto/aes/asm/vpaes-x86_64.pl | |
parent | b889a6046be029cb9874a78ab262471b184b5467 (diff) |
Integrate Vector Permutation AES into build system.
Diffstat (limited to 'crypto/aes/asm/vpaes-x86_64.pl')
-rw-r--r-- | crypto/aes/asm/vpaes-x86_64.pl | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/crypto/aes/asm/vpaes-x86_64.pl b/crypto/aes/asm/vpaes-x86_64.pl index 3ea85d23e8..01011defbd 100644 --- a/crypto/aes/asm/vpaes-x86_64.pl +++ b/crypto/aes/asm/vpaes-x86_64.pl @@ -21,7 +21,7 @@ # about its alignment... # # Performance summary. aes-x86_64.pl column lists large-block CBC -# encrypt/decrypt/with-hypert-hreading-off(*) results in cycles per +# encrypt/decrypt/with-hyper-threading-off(*) results in cycles per # byte processed with 128-bit key, and vpaes-x86_64.pl column - # encrypt/decrypt. # @@ -40,7 +40,8 @@ # (**) "Core 2" refers to initial 65nm design, a.k.a. Conroe. # # (***) Less impressive improvement on Core 2 and Atom is due to slow -# pshufb, yet it's respectable +40%/78% improvement on Core 2. +# pshufb, yet it's respectable +40%/78% improvement on Core 2 +# (as implied, over "hyper-threading-safe" code path). # # <appro@openssl.org> @@ -57,7 +58,7 @@ die "can't locate x86_64-xlate.pl"; open STDOUT,"| $^X $xlate $flavour $output"; -$PREFIX="AES"; +$PREFIX="vpaes"; $code.=<<___; .text |