Add include directory options for assembler files that include from crypto/

[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..006215ecb1891c7dceb2dab25f557c72304ee9e4 100644 (file)
--- a/crypto/modes/asm/ghash-x86_64.pl
+++ b/crypto/modes/asm/ghash-x86_64.pl
@@ -63,7 +63,10 @@
 # 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)
+# Skylake      0.44(+110%)(if system doesn't support AVX)
 # Bulldozer    1.49(+27%)
+# Silvermont   2.88(+13%)
 
 # March 2013
 #
@@ -72,7 +75,8 @@
 # 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, in
+# 0.29 on Broadwell, and in 0.36 on Skylake.
 #
 # [1] http://rt.openssl.org/Ticket/Display.html?id=2900&user=guest&pass=guest
 
@@ -89,7 +93,7 @@ die "can't locate x86_64-xlate.pl";
 
 if (`$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1`
                =~ /GNU assembler version ([2-9]\.[0-9]+)/) {
-       $avx = ($1>=2.19) + ($1>=2.22);
+       $avx = ($1>=2.20) + ($1>=2.22);
 }
 
 if (!$avx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) &&
@@ -102,8 +106,8 @@ if (!$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|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/) {
+       $avx = ($2>=3.0) + ($2>3.0);
 }
 
 open OUT,"| \"$^X\" $xlate $flavour $output";
@@ -573,15 +577,15 @@ $code.=<<___ if (0 || (&reduction_alg9($Xhi,$Xi)&&0));
        # experimental alternative. special thing about is that there
        # no dependency between the two multiplications... 
        mov             \$`0xE1<<1`,%eax
-       mov             \$0xA040608020C0E000,%r10       # ((7..0)·0xE0)&0xff
+       mov             \$0xA040608020C0E000,%r10       # ((7..0)·0xE0)&0xff
        mov             \$0x07,%r11d
        movq            %rax,$T1
        movq            %r10,$T2
        movq            %r11,$T3                # borrow $T3
        pand            $Xi,$T3
-       pshufb          $T3,$T2                 # ($Xi&7)·0xE0
+       pshufb          $T3,$T2                 # ($Xi&7)·0xE0
        movq            %rax,$T3
-       pclmulqdq       \$0x00,$Xi,$T1          # ·(0xE1<<1)
+       pclmulqdq       \$0x00,$Xi,$T1          # ·(0xE1<<1)
        pxor            $Xi,$T2
        pslldq          \$15,$T2
        paddd           $T2,$T2                 # <<(64+56+1)
@@ -654,7 +658,7 @@ $code.=<<___;
        je              .Lskip4x
 
        sub             \$0x30,$len
-       mov             \$0xA040608020C0E000,%rax       # ((7..0)·0xE0)&0xff
+       mov             \$0xA040608020C0E000,%rax       # ((7..0)·0xE0)&0xff
        movdqu          0x30($Htbl),$Hkey3
        movdqu          0x40($Htbl),$Hkey4