diff options
Diffstat (limited to 'deps/openssl/openssl/crypto/sha/asm/sha512-586.pl')
| -rw-r--r-- | deps/openssl/openssl/crypto/sha/asm/sha512-586.pl | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/deps/openssl/openssl/crypto/sha/asm/sha512-586.pl b/deps/openssl/openssl/crypto/sha/asm/sha512-586.pl index 3873934b69..867ce30b97 100644 --- a/deps/openssl/openssl/crypto/sha/asm/sha512-586.pl +++ b/deps/openssl/openssl/crypto/sha/asm/sha512-586.pl @@ -32,6 +32,7 @@ # Sandy Bridge 58 - 35 11.9 11.2 # Ivy Bridge 50 - 33 11.5 8.17 # Haswell 46 - 29 11.3 7.66 +# Skylake 40 - 26 13.3 7.25 # Bulldozer 121 - 50 14.0 13.5 # VIA Nano 91 - 52 33 14.7 # Atom 126 - 68 48(***) 14.7 @@ -41,7 +42,7 @@ # (*) whichever best applicable. # (**) x86_64 assembler performance is presented for reference # purposes, the results are for integer-only code. -# (***) paddq is increadibly slow on Atom. +# (***) paddq is incredibly slow on Atom. # # IALU code-path is optimized for elder Pentiums. On vanilla Pentium # performance improvement over compiler generated code reaches ~60%, @@ -61,7 +62,7 @@ require "x86asm.pl"; $output=pop; open STDOUT,">$output"; -&asm_init($ARGV[0],"sha512-586.pl",$ARGV[$#ARGV] eq "386"); +&asm_init($ARGV[0],$ARGV[$#ARGV] eq "386"); $sse2=0; for (@ARGV) { $sse2=1 if (/-DOPENSSL_IA32_SSE2/); } @@ -384,7 +385,7 @@ if ($sse2) { &set_label("16_79_sse2",16); for ($j=0;$j<2;$j++) { # 2x unroll - #&movq ("mm7",&QWP(8*(9+16-1),"esp")); # prefetched in BODY_00_15 + #&movq ("mm7",&QWP(8*(9+16-1),"esp")); # prefetched in BODY_00_15 &movq ("mm5",&QWP(8*(9+16-14),"esp")); &movq ("mm1","mm7"); &psrlq ("mm7",1); |