diff options
Diffstat (limited to 'openssl/crypto/bn/asm')
| -rw-r--r-- | openssl/crypto/bn/asm/alpha-mont.pl | 36 | ||||
| -rw-r--r-- | openssl/crypto/bn/asm/s390x.S | 86 |
2 files changed, 63 insertions, 59 deletions
diff --git a/openssl/crypto/bn/asm/alpha-mont.pl b/openssl/crypto/bn/asm/alpha-mont.pl index f7e0ca164..c63458e94 100644 --- a/openssl/crypto/bn/asm/alpha-mont.pl +++ b/openssl/crypto/bn/asm/alpha-mont.pl @@ -41,8 +41,12 @@ $j="s4"; $m1="s5"; $code=<<___; +#indef __linux__ +#include <asm/regdef.h> +#else #include <asm.h> #include <regdef.h> +#endif .text @@ -76,7 +80,7 @@ bn_mul_mont: ldq $aj,8($ap) subq sp,AT,sp ldq $bi,0($bp) # bp[0] - mov -4096,AT + lda AT,-4096(zero) # mov -4096,AT ldq $n0,0($n0) and sp,AT,sp @@ -106,9 +110,9 @@ bn_mul_mont: .align 4 .L1st: .set noreorder - ldq $aj,($aj) + ldq $aj,0($aj) addl $j,1,$j - ldq $nj,($nj) + ldq $nj,0($nj) lda $tp,8($tp) addq $alo,$hi0,$lo0 @@ -159,12 +163,12 @@ bn_mul_mont: .align 4 .Louter: s8addq $i,$bp,$bi - ldq $hi0,($ap) + ldq $hi0,0($ap) ldq $aj,8($ap) - ldq $bi,($bi) - ldq $hi1,($np) + ldq $bi,0($bi) + ldq $hi1,0($np) ldq $nj,8($np) - ldq $tj,(sp) + ldq $tj,0(sp) mulq $hi0,$bi,$lo0 umulh $hi0,$bi,$hi0 @@ -195,10 +199,10 @@ bn_mul_mont: .set noreorder ldq $tj,8($tp) #L0 nop #U1 - ldq $aj,($aj) #L1 + ldq $aj,0($aj) #L1 s8addq $j,$np,$nj #U0 - ldq $nj,($nj) #L0 + ldq $nj,0($nj) #L0 nop #U1 addq $alo,$hi0,$lo0 #L1 lda $tp,8($tp) @@ -247,7 +251,7 @@ bn_mul_mont: addq $hi1,v0,$hi1 addq $hi1,$hi0,$lo1 - stq $j,($tp) + stq $j,0($tp) cmpult $lo1,$hi0,$hi1 addq $lo1,$tj,$lo1 cmpult $lo1,$tj,AT @@ -265,8 +269,8 @@ bn_mul_mont: mov 0,$hi0 # clear borrow bit .align 4 -.Lsub: ldq $lo0,($tp) - ldq $lo1,($np) +.Lsub: ldq $lo0,0($tp) + ldq $lo1,0($np) lda $tp,8($tp) lda $np,8($np) subq $lo0,$lo1,$lo1 # tp[i]-np[i] @@ -274,7 +278,7 @@ bn_mul_mont: subq $lo1,$hi0,$lo0 cmpult $lo1,$lo0,$hi0 or $hi0,AT,$hi0 - stq $lo0,($rp) + stq $lo0,0($rp) cmpult $tp,$tj,v0 lda $rp,8($rp) bne v0,.Lsub @@ -288,7 +292,7 @@ bn_mul_mont: bis $bp,$ap,$ap # ap=borrow?tp:rp .align 4 -.Lcopy: ldq $aj,($ap) # copy or in-place refresh +.Lcopy: ldq $aj,0($ap) # copy or in-place refresh lda $tp,8($tp) lda $rp,8($rp) lda $ap,8($ap) @@ -309,8 +313,8 @@ bn_mul_mont: lda sp,48(sp) ret (ra) .end bn_mul_mont -.rdata -.asciiz "Montgomery Multiplication for Alpha, CRYPTOGAMS by <appro\@openssl.org>" +.ascii "Montgomery Multiplication for Alpha, CRYPTOGAMS by <appro\@openssl.org>" +.align 2 ___ print $code; diff --git a/openssl/crypto/bn/asm/s390x.S b/openssl/crypto/bn/asm/s390x.S index 8f45f5d51..43fcb79bc 100644 --- a/openssl/crypto/bn/asm/s390x.S +++ b/openssl/crypto/bn/asm/s390x.S @@ -1,4 +1,4 @@ -.ident "s390x.S, version 1.0" +.ident "s390x.S, version 1.1" // ==================================================================== // Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL // project. @@ -24,67 +24,67 @@ bn_mul_add_words: bler %r14 // if (len<=0) return 0; stmg %r6,%r10,48(%r15) + lghi %r10,3 lghi %r8,0 // carry = 0 - srag %r10,%r4,2 // cnt=len/4 - jz .Loop1_madd + nr %r10,%r4 // len%4 + sra %r4,2 // cnt=len/4 + jz .Loop1_madd // carry is incidentally cleared if branch taken + algr zero,zero // clear carry .Loop4_madd: lg %r7,0(%r2,%r3) // ap[i] mlgr %r6,%r5 // *=w - algr %r7,%r8 // +=carry + alcgr %r7,%r8 // +=carry alcgr %r6,zero alg %r7,0(%r2,%r1) // +=rp[i] - alcgr %r6,zero stg %r7,0(%r2,%r1) // rp[i]= lg %r9,8(%r2,%r3) mlgr %r8,%r5 - algr %r9,%r6 + alcgr %r9,%r6 alcgr %r8,zero alg %r9,8(%r2,%r1) - alcgr %r8,zero stg %r9,8(%r2,%r1) lg %r7,16(%r2,%r3) mlgr %r6,%r5 - algr %r7,%r8 + alcgr %r7,%r8 alcgr %r6,zero alg %r7,16(%r2,%r1) - alcgr %r6,zero stg %r7,16(%r2,%r1) lg %r9,24(%r2,%r3) mlgr %r8,%r5 - algr %r9,%r6 + alcgr %r9,%r6 alcgr %r8,zero alg %r9,24(%r2,%r1) - alcgr %r8,zero stg %r9,24(%r2,%r1) la %r2,32(%r2) // i+=4 - brct %r10,.Loop4_madd + brct %r4,.Loop4_madd - lghi %r10,3 - nr %r4,%r10 // cnt=len%4 - jz .Lend_madd + la %r10,1(%r10) // see if len%4 is zero ... + brct %r10,.Loop1_madd // without touching condition code:-) + +.Lend_madd: + alcgr %r8,zero // collect carry bit + lgr %r2,%r8 + lmg %r6,%r10,48(%r15) + br %r14 .Loop1_madd: lg %r7,0(%r2,%r3) // ap[i] mlgr %r6,%r5 // *=w - algr %r7,%r8 // +=carry + alcgr %r7,%r8 // +=carry alcgr %r6,zero alg %r7,0(%r2,%r1) // +=rp[i] - alcgr %r6,zero stg %r7,0(%r2,%r1) // rp[i]= lgr %r8,%r6 la %r2,8(%r2) // i++ - brct %r4,.Loop1_madd + brct %r10,.Loop1_madd -.Lend_madd: - lgr %r2,%r8 - lmg %r6,%r10,48(%r15) - br %r14 + j .Lend_madd .size bn_mul_add_words,.-bn_mul_add_words // BN_ULONG bn_mul_words(BN_ULONG *r2,BN_ULONG *r3,int r4,BN_ULONG r5); @@ -99,57 +99,57 @@ bn_mul_words: bler %r14 // if (len<=0) return 0; stmg %r6,%r10,48(%r15) + lghi %r10,3 lghi %r8,0 // carry = 0 - srag %r10,%r4,2 // cnt=len/4 - jz .Loop1_mul + nr %r10,%r4 // len%4 + sra %r4,2 // cnt=len/4 + jz .Loop1_mul // carry is incidentally cleared if branch taken + algr zero,zero // clear carry .Loop4_mul: lg %r7,0(%r2,%r3) // ap[i] mlgr %r6,%r5 // *=w - algr %r7,%r8 // +=carry - alcgr %r6,zero + alcgr %r7,%r8 // +=carry stg %r7,0(%r2,%r1) // rp[i]= lg %r9,8(%r2,%r3) mlgr %r8,%r5 - algr %r9,%r6 - alcgr %r8,zero + alcgr %r9,%r6 stg %r9,8(%r2,%r1) lg %r7,16(%r2,%r3) mlgr %r6,%r5 - algr %r7,%r8 - alcgr %r6,zero + alcgr %r7,%r8 stg %r7,16(%r2,%r1) lg %r9,24(%r2,%r3) mlgr %r8,%r5 - algr %r9,%r6 - alcgr %r8,zero + alcgr %r9,%r6 stg %r9,24(%r2,%r1) la %r2,32(%r2) // i+=4 - brct %r10,.Loop4_mul + brct %r4,.Loop4_mul - lghi %r10,3 - nr %r4,%r10 // cnt=len%4 - jz .Lend_mul + la %r10,1(%r10) // see if len%4 is zero ... + brct %r10,.Loop1_mul // without touching condition code:-) + +.Lend_mul: + alcgr %r8,zero // collect carry bit + lgr %r2,%r8 + lmg %r6,%r10,48(%r15) + br %r14 .Loop1_mul: lg %r7,0(%r2,%r3) // ap[i] mlgr %r6,%r5 // *=w - algr %r7,%r8 // +=carry - alcgr %r6,zero + alcgr %r7,%r8 // +=carry stg %r7,0(%r2,%r1) // rp[i]= lgr %r8,%r6 la %r2,8(%r2) // i++ - brct %r4,.Loop1_mul + brct %r10,.Loop1_mul -.Lend_mul: - lgr %r2,%r8 - lmg %r6,%r10,48(%r15) - br %r14 + j .Lend_mul .size bn_mul_words,.-bn_mul_words // void bn_sqr_words(BN_ULONG *r2,BN_ULONG *r2,int r4) |