diff options
| author | Jung-uk Kim <jkim@FreeBSD.org> | 2017-05-25 19:38:38 +0000 |
|---|---|---|
| committer | Jung-uk Kim <jkim@FreeBSD.org> | 2017-05-25 19:38:38 +0000 |
| commit | 12df5ad9af4981f5d3c31a9819d31618c0f1af51 (patch) | |
| tree | 97e3336a3054b8d8a0150b9d414934f73c99cb30 /crypto/bn/asm | |
| parent | 5315173646e65b5025be33013edc33eb9658e683 (diff) | |
| download | src-12df5ad9af4981f5d3c31a9819d31618c0f1af51.tar.gz src-12df5ad9af4981f5d3c31a9819d31618c0f1af51.zip | |
Import OpenSSL 1.0.2l.vendor/openssl/1.0.2l
Notes
Notes:
svn path=/vendor-crypto/openssl/dist/; revision=318897
svn path=/vendor-crypto/openssl/1.0.2l/; revision=318898; tag=vendor/openssl/1.0.2l
Diffstat (limited to 'crypto/bn/asm')
| -rwxr-xr-x | crypto/bn/asm/sparcv9-mont.pl | 29 |
1 files changed, 16 insertions, 13 deletions
diff --git a/crypto/bn/asm/sparcv9-mont.pl b/crypto/bn/asm/sparcv9-mont.pl index b8fb1e8a25dc..d8662878006e 100755 --- a/crypto/bn/asm/sparcv9-mont.pl +++ b/crypto/bn/asm/sparcv9-mont.pl @@ -290,7 +290,7 @@ ___ ######## .Lbn_sqr_mont gives up to 20% *overall* improvement over ######## code without following dedicated squaring procedure. ######## -$sbit="%i2"; # re-use $bp! +$sbit="%o5"; $code.=<<___; .align 32 @@ -403,7 +403,7 @@ $code.=<<___; mulx $apj,$mul0,$acc0 mulx $npj,$mul1,$acc1 add $acc0,$car0,$car0 - add $tpj,$car1,$car1 + add $tpj,$sbit,$sbit ld [$ap+$j],$apj ! ap[j] and $car0,$mask,$acc0 ld [$np+$j],$npj ! np[j] @@ -412,7 +412,7 @@ $code.=<<___; ld [$tp+8],$tpj ! tp[j] add $acc0,$acc0,$acc0 add $j,4,$j ! j++ - or $sbit,$acc0,$acc0 + add $sbit,$acc0,$acc0 srlx $acc0,32,$sbit and $acc0,$mask,$acc0 cmp $j,$num @@ -426,12 +426,12 @@ $code.=<<___; mulx $apj,$mul0,$acc0 mulx $npj,$mul1,$acc1 add $acc0,$car0,$car0 - add $tpj,$car1,$car1 + add $tpj,$sbit,$sbit and $car0,$mask,$acc0 srlx $car0,32,$car0 add $acc1,$car1,$car1 add $acc0,$acc0,$acc0 - or $sbit,$acc0,$acc0 + add $sbit,$acc0,$acc0 srlx $acc0,32,$sbit and $acc0,$mask,$acc0 add $acc0,$car1,$car1 @@ -439,7 +439,7 @@ $code.=<<___; srlx $car1,32,$car1 add $car0,$car0,$car0 - or $sbit,$car0,$car0 + add $sbit,$car0,$car0 add $car0,$car1,$car1 add $car2,$car1,$car1 st $car1,[$tp+4] @@ -499,7 +499,7 @@ $code.=<<___; .Lsqr_inner2: mulx $apj,$mul0,$acc0 mulx $npj,$mul1,$acc1 - add $tpj,$car1,$car1 + add $tpj,$sbit,$sbit add $acc0,$car0,$car0 ld [$ap+$j],$apj ! ap[j] and $car0,$mask,$acc0 @@ -507,7 +507,7 @@ $code.=<<___; srlx $car0,32,$car0 add $acc0,$acc0,$acc0 ld [$tp+8],$tpj ! tp[j] - or $sbit,$acc0,$acc0 + add $sbit,$acc0,$acc0 add $j,4,$j ! j++ srlx $acc0,32,$sbit and $acc0,$mask,$acc0 @@ -522,12 +522,12 @@ $code.=<<___; .Lsqr_no_inner2: mulx $apj,$mul0,$acc0 mulx $npj,$mul1,$acc1 - add $tpj,$car1,$car1 + add $tpj,$sbit,$sbit add $acc0,$car0,$car0 and $car0,$mask,$acc0 srlx $car0,32,$car0 add $acc0,$acc0,$acc0 - or $sbit,$acc0,$acc0 + add $sbit,$acc0,$acc0 srlx $acc0,32,$sbit and $acc0,$mask,$acc0 add $acc0,$car1,$car1 @@ -536,7 +536,7 @@ $code.=<<___; srlx $car1,32,$car1 add $car0,$car0,$car0 - or $sbit,$car0,$car0 + add $sbit,$car0,$car0 add $car0,$car1,$car1 add $car2,$car1,$car1 st $car1,[$tp+4] @@ -581,14 +581,17 @@ $code.=<<___; !.Lsqr_last mulx $npj,$mul1,$acc1 - add $tpj,$car1,$car1 + add $tpj,$acc0,$acc0 + srlx $acc0,32,$tmp0 + and $acc0,$mask,$acc0 + add $tmp0,$sbit,$sbit add $acc0,$car1,$car1 add $acc1,$car1,$car1 st $car1,[$tp] srlx $car1,32,$car1 add $car0,$car0,$car0 ! recover $car0 - or $sbit,$car0,$car0 + add $sbit,$car0,$car0 add $car0,$car1,$car1 add $car2,$car1,$car1 st $car1,[$tp+4] |