diff options
Diffstat (limited to 'src/crypto/modes/asm/ghashv8-armx.pl')
| -rw-r--r-- | src/crypto/modes/asm/ghashv8-armx.pl | 24 |
1 files changed, 12 insertions, 12 deletions
diff --git a/src/crypto/modes/asm/ghashv8-armx.pl b/src/crypto/modes/asm/ghashv8-armx.pl index 686951f..3a7b8d8 100644 --- a/src/crypto/modes/asm/ghashv8-armx.pl +++ b/src/crypto/modes/asm/ghashv8-armx.pl @@ -54,7 +54,7 @@ my ($Xl,$Xm,$Xh,$IN)=map("q$_",(0..3)); my ($t0,$t1,$t2,$xC2,$H,$Hhl,$H2)=map("q$_",(8..14)); $code=<<___; -#include "arm_arch.h" +#include <openssl/arm_arch.h> .text ___ @@ -148,10 +148,10 @@ gcm_gmult_v8: #endif vext.8 $IN,$t1,$t1,#8 - vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo + vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo veor $t1,$t1,$IN @ Karatsuba pre-processing - vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi - vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) + vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi + vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) vext.8 $t1,$Xl,$Xh,#8 @ Karatsuba post-processing veor $t2,$Xl,$Xh @@ -239,7 +239,7 @@ $code.=<<___; #endif vext.8 $In,$t1,$t1,#8 veor $IN,$IN,$Xl @ I[i]^=Xi - vpmull.p64 $Xln,$H,$In @ H·Ii+1 + vpmull.p64 $Xln,$H,$In @ H·Ii+1 veor $t1,$t1,$In @ Karatsuba pre-processing vpmull2.p64 $Xhn,$H,$In b .Loop_mod2x_v8 @@ -248,14 +248,14 @@ $code.=<<___; .Loop_mod2x_v8: vext.8 $t2,$IN,$IN,#8 subs $len,$len,#32 @ is there more data? - vpmull.p64 $Xl,$H2,$IN @ H^2.lo·Xi.lo + vpmull.p64 $Xl,$H2,$IN @ H^2.lo·Xi.lo cclr $inc,lo @ is it time to zero $inc? vpmull.p64 $Xmn,$Hhl,$t1 veor $t2,$t2,$IN @ Karatsuba pre-processing - vpmull2.p64 $Xh,$H2,$IN @ H^2.hi·Xi.hi + vpmull2.p64 $Xh,$H2,$IN @ H^2.hi·Xi.hi veor $Xl,$Xl,$Xln @ accumulate - vpmull2.p64 $Xm,$Hhl,$t2 @ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi) + vpmull2.p64 $Xm,$Hhl,$t2 @ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi) vld1.64 {$t0},[$inp],$inc @ load [rotated] I[i+2] veor $Xh,$Xh,$Xhn @@ -280,7 +280,7 @@ $code.=<<___; vext.8 $In,$t1,$t1,#8 vext.8 $IN,$t0,$t0,#8 veor $Xl,$Xm,$t2 - vpmull.p64 $Xln,$H,$In @ H·Ii+1 + vpmull.p64 $Xln,$H,$In @ H·Ii+1 veor $IN,$IN,$Xh @ accumulate $IN early vext.8 $t2,$Xl,$Xl,#8 @ 2nd phase of reduction @@ -304,10 +304,10 @@ $code.=<<___; veor $IN,$IN,$Xl @ inp^=Xi veor $t1,$t0,$t2 @ $t1 is rotated inp^Xi - vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo + vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo veor $t1,$t1,$IN @ Karatsuba pre-processing - vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi - vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) + vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi + vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) vext.8 $t1,$Xl,$Xh,#8 @ Karatsuba post-processing veor $t2,$Xl,$Xh |