Add Broadwell performance results.

[openssl.git] / crypto / modes / asm / ghash-x86_64.pl

diff --git a/crypto/modes/asm/ghash-x86_64.pl b/crypto/modes/asm/ghash-x86_64.pl
index 0810c7ab9a0ceca2a5a7f61f6a38092a1b30eb52..6e656ca13b8029cdf105cdd92df58b4e21d0d938 100644 (file)
--- a/crypto/modes/asm/ghash-x86_64.pl
+++ b/crypto/modes/asm/ghash-x86_64.pl
@@ -63,7 +63,9 @@
 # Sandy Bridge 1.80(+8%)
 # Ivy Bridge   1.80(+7%)
 # Haswell      0.55(+93%) (if system doesn't support AVX)
+# Broadwell    0.45(+110%)(if system doesn't support AVX)
 # Bulldozer    1.49(+27%)
+# Silvermont   2.88(+13%)
 
 # March 2013
 #
@@ -72,7 +74,8 @@
 # CPUs such as Sandy and Ivy Bridge can execute it, the code performs
 # sub-optimally in comparison to above mentioned version. But thanks
 # to Ilya Albrekht and Max Locktyukhin of Intel Corp. we knew that
-# it performs in 0.41 cycles per byte on Haswell processor.
+# it performs in 0.41 cycles per byte on Haswell processor, and in
+# 0.29 on Broadwell.
 #
 # [1] http://rt.openssl.org/Ticket/Display.html?id=2900&user=guest&pass=guest
 
@@ -102,8 +105,8 @@ if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
        $avx = ($1>=10) + ($1>=11);
 }
 
-if (!$avx && `$ENV{CC} -v 2>&1` =~ /LLVM ([3-9]\.[0-9]+)/) {
-       $avx = ($1>=3.0) + ($1>=3.1);
+if (!$avx && `$ENV{CC} -v 2>&1` =~ /(^clang version|based on LLVM) ([3-9]\.[0-9]+)/) {
+       $avx = ($2>=3.0) + ($2>3.0);
 }
 
 open OUT,"| \"$^X\" $xlate $flavour $output";