Allow ILP32 compilation in AArch64 assembly pack.

[openssl.git] / crypto / sha / asm / sha512-armv8.pl

diff --git a/crypto/sha/asm/sha512-armv8.pl b/crypto/sha/asm/sha512-armv8.pl
index bd7a0a5662e0a236f8f35dcdedd83954c9a7d1f8..7d69f0f4958dad08329eb4bc603986fcd24acf10 100644 (file)
--- a/crypto/sha/asm/sha512-armv8.pl
+++ b/crypto/sha/asm/sha512-armv8.pl
@@ -14,8 +14,10 @@
 #
 #              SHA256-hw       SHA256(*)       SHA512
 # Apple A7     1.97            10.5 (+33%)     6.73 (-1%(**))
 #
 #              SHA256-hw       SHA256(*)       SHA512
 # Apple A7     1.97            10.5 (+33%)     6.73 (-1%(**))

-# Cortex-A53   2.38            15.6 (+110%)    10.1 (+190%(***))
+# Cortex-A53   2.38            15.5 (+115%)    10.0 (+150%(***))

 # Cortex-A57   2.31            11.6 (+86%)     7.51 (+260%(***))
 # Cortex-A57   2.31            11.6 (+86%)     7.51 (+260%(***))

+# Denver       2.01            10.5 (+26%)     6.70 (+8%)
+# X-Gene                       20.0 (+100%)    12.8 (+300%(***))

 # 
 # (*)  Software SHA256 results are of lesser relevance, presented
 #      mostly for informational purposes.
 # 
 # (*)  Software SHA256 results are of lesser relevance, presented
 #      mostly for informational purposes.


@@ -25,11 +27,18 @@
 # (***)        Super-impressive coefficients over gcc-generated code are
 #      indication of some compiler "pathology", most notably code
 #      generated with -mgeneral-regs-only is significanty faster
 # (***)        Super-impressive coefficients over gcc-generated code are
 #      indication of some compiler "pathology", most notably code
 #      generated with -mgeneral-regs-only is significanty faster

-#      and lags behind assembly only by 50-90%.
+#      and the gap is only 40-90%.

 
 $flavour=shift;
 $output=shift;
 
 $flavour=shift;
 $output=shift;

-open STDOUT,">$output";
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+die "can't locate arm-xlate.pl";
+
+open OUT,"| \"$^X\" $xlate $flavour $output";
+*STDOUT=*OUT;

 
 if ($output =~ /512/) {
        $BITS=512;
 
 if ($output =~ /512/) {
        $BITS=512;


@@ -153,13 +162,18 @@ $code.=<<___;
 
 .text
 
 
 .text
 

+.extern        OPENSSL_armcap_P

 .globl $func
 .type  $func,%function
 .align 6
 $func:
 ___
 $code.=<<___   if ($SZ==4);
 .globl $func
 .type  $func,%function
 .align 6
 $func:
 ___
 $code.=<<___   if ($SZ==4);

+#ifdef __ILP32__
+       ldrsw   x16,.LOPENSSL_armcap_P
+#else

        ldr     x16,.LOPENSSL_armcap_P
        ldr     x16,.LOPENSSL_armcap_P

+#endif

        adr     x17,.LOPENSSL_armcap_P
        add     x16,x16,x17
        ldr     w16,[x16]
        adr     x17,.LOPENSSL_armcap_P
        add     x16,x16,x17
        ldr     w16,[x16]


@@ -182,7 +196,7 @@ $code.=<<___;
        ldp     $E,$F,[$ctx,#4*$SZ]
        add     $num,$inp,$num,lsl#`log(16*$SZ)/log(2)` // end of input
        ldp     $G,$H,[$ctx,#6*$SZ]
        ldp     $E,$F,[$ctx,#4*$SZ]
        add     $num,$inp,$num,lsl#`log(16*$SZ)/log(2)` // end of input
        ldp     $G,$H,[$ctx,#6*$SZ]

-       adr     $Ktbl,K$BITS
+       adr     $Ktbl,.LK$BITS

        stp     $ctx,$num,[x29,#96]
 
 .Loop:
        stp     $ctx,$num,[x29,#96]
 
 .Loop:


@@ -232,8 +246,8 @@ $code.=<<___;
 .size  $func,.-$func
 
 .align 6
 .size  $func,.-$func
 
 .align 6

-.type  K$BITS,%object
-K$BITS:
+.type  .LK$BITS,%object
+.LK$BITS:

 ___
 $code.=<<___ if ($SZ==8);
        .quad   0x428a2f98d728ae22,0x7137449123ef65cd
 ___
 $code.=<<___ if ($SZ==8);
        .quad   0x428a2f98d728ae22,0x7137449123ef65cd


@@ -298,10 +312,14 @@ $code.=<<___ if ($SZ==4);
        .long   0       //terminator
 ___
 $code.=<<___;
        .long   0       //terminator
 ___
 $code.=<<___;

-.size  K$BITS,.-K$BITS
+.size  .LK$BITS,.-.LK$BITS

 .align 3
 .LOPENSSL_armcap_P:
 .align 3
 .LOPENSSL_armcap_P:

+#ifdef __ILP32__
+       .long   OPENSSL_armcap_P-.
+#else

        .quad   OPENSSL_armcap_P-.
        .quad   OPENSSL_armcap_P-.

+#endif

 .asciz "SHA$BITS block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
 .align 2
 ___
 .asciz "SHA$BITS block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
 .align 2
 ___


@@ -323,7 +341,7 @@ sha256_block_armv8:
        add             x29,sp,#0
 
        ld1.32          {$ABCD,$EFGH},[$ctx]
        add             x29,sp,#0
 
        ld1.32          {$ABCD,$EFGH},[$ctx]

-       adr             $Ktbl,K256
+       adr             $Ktbl,.LK256

 
 .Loop_hw:
        ld1             {@MSG[0]-@MSG[3]},[$inp],#64
 
 .Loop_hw:
        ld1             {@MSG[0]-@MSG[3]},[$inp],#64