diff options
Diffstat (limited to 'deps/openssl/openssl/crypto/aes/asm/aesni-x86.pl')
-rw-r--r-- | deps/openssl/openssl/crypto/aes/asm/aesni-x86.pl | 8 |
1 files changed, 5 insertions, 3 deletions
diff --git a/deps/openssl/openssl/crypto/aes/asm/aesni-x86.pl b/deps/openssl/openssl/crypto/aes/asm/aesni-x86.pl index ed1a47c30c..b351fca28e 100644 --- a/deps/openssl/openssl/crypto/aes/asm/aesni-x86.pl +++ b/deps/openssl/openssl/crypto/aes/asm/aesni-x86.pl @@ -62,7 +62,9 @@ # Westmere 3.77/1.37 1.37 1.52 1.27 # * Bridge 5.07/0.98 0.99 1.09 0.91 1.10 # Haswell 4.44/0.80 0.97 1.03 0.72 0.76 +# Skylake 2.68/0.65 0.65 0.66 0.64 0.66 # Silvermont 5.77/3.56 3.67 4.03 3.46 4.03 +# Goldmont 3.84/1.39 1.39 1.63 1.31 1.70 # Bulldozer 5.80/0.98 1.05 1.24 0.93 1.23 $PREFIX="aesni"; # if $PREFIX is set to "AES", the script @@ -78,7 +80,7 @@ $output = pop; open OUT,">$output"; *STDOUT=*OUT; -&asm_init($ARGV[0],$0); +&asm_init($ARGV[0]); &external_label("OPENSSL_ia32cap_P"); &static_label("key_const"); @@ -237,7 +239,7 @@ sub aesni_generate1 # fully unrolled loop # can schedule aes[enc|dec] every cycle optimal interleave factor # equals to corresponding instructions latency. 8x is optimal for # * Bridge, but it's unfeasible to accommodate such implementation -# in XMM registers addreassable in 32-bit mode and therefore maximum +# in XMM registers addressable in 32-bit mode and therefore maximum # of 6x is used instead... sub aesni_generate2 @@ -1051,7 +1053,7 @@ if ($PREFIX eq "aesni") { &set_label("ctr32_one_shortcut",16); &movups ($inout0,&QWP(0,$rounds_)); # load ivec &mov ($rounds,&DWP(240,$key)); - + &set_label("ctr32_one"); if ($inline) { &aesni_inline_generate1("enc"); } |