"Fossies" - the Fresh Open Source Software Archive  

Source code changes of the file "crypto/bn/asm/rsaz-x86_64.pl" between
openssl-1.0.2t.tar.gz and openssl-1.0.2u.tar.gz

About: OpenSSL is a toolkit implementing the Transport Layer Security (TLS) and Secure Sockets Layer (SSL v2/v3) protocols as well as a full-strength general purpose cryptography library. Long Term Support (LTS) version (support will be provided until end of 2019).

rsaz-x86_64.pl  (openssl-1.0.2t):rsaz-x86_64.pl  (openssl-1.0.2u)
skipping to change at line 143 skipping to change at line 143
rsaz_512_sqr: # 25-29% faster than rsaz_512_mul rsaz_512_sqr: # 25-29% faster than rsaz_512_mul
push %rbx push %rbx
push %rbp push %rbp
push %r12 push %r12
push %r13 push %r13
push %r14 push %r14
push %r15 push %r15
subq \$128+24, %rsp subq \$128+24, %rsp
.Lsqr_body: .Lsqr_body:
movq $mod, %rbp # common argument movq $mod, %xmm1 # common off-load
movq ($inp), %rdx movq ($inp), %rdx
movq 8($inp), %rax movq 8($inp), %rax
movq $n0, 128(%rsp) movq $n0, 128(%rsp)
___ ___
$code.=<<___ if ($addx); $code.=<<___ if ($addx);
movl \$0x80100,%r11d movl \$0x80100,%r11d
andl OPENSSL_ia32cap_P+8(%rip),%r11d andl OPENSSL_ia32cap_P+8(%rip),%r11d
cmpl \$0x80100,%r11d # check for MULX and ADO/CX cmpl \$0x80100,%r11d # check for MULX and ADO/CX
je .Loop_sqrx je .Loop_sqrx
___ ___
$code.=<<___; $code.=<<___;
jmp .Loop_sqr jmp .Loop_sqr
.align 32 .align 32
.Loop_sqr: .Loop_sqr:
movl $times,128+8(%rsp) movl $times,128+8(%rsp)
#first iteration #first iteration
movq %rdx, %rbx movq %rdx, %rbx # 0($inp)
mov %rax, %rbp # 8($inp)
mulq %rdx mulq %rdx
movq %rax, %r8 movq %rax, %r8
movq 16($inp), %rax movq 16($inp), %rax
movq %rdx, %r9 movq %rdx, %r9
mulq %rbx mulq %rbx
addq %rax, %r9 addq %rax, %r9
movq 24($inp), %rax movq 24($inp), %rax
movq %rdx, %r10 movq %rdx, %r10
adcq \$0, %r10 adcq \$0, %r10
skipping to change at line 200 skipping to change at line 201
mulq %rbx mulq %rbx
addq %rax, %r13 addq %rax, %r13
movq 56($inp), %rax movq 56($inp), %rax
movq %rdx, %r14 movq %rdx, %r14
adcq \$0, %r14 adcq \$0, %r14
mulq %rbx mulq %rbx
addq %rax, %r14 addq %rax, %r14
movq %rbx, %rax movq %rbx, %rax
movq %rdx, %r15 adcq \$0, %rdx
adcq \$0, %r15
addq %r8, %r8 #shlq \$1, %r8 xorq %rcx,%rcx # rcx:r8 = r8 << 1
movq %r9, %rcx addq %r8, %r8
adcq %r9, %r9 #shld \$1, %r8, %r9 movq %rdx, %r15
adcq \$0, %rcx
mulq %rax mulq %rax
movq %rax, (%rsp) addq %r8, %rdx
addq %rdx, %r8 adcq \$0, %rcx
adcq \$0, %r9
movq %r8, 8(%rsp) movq %rax, (%rsp)
shrq \$63, %rcx movq %rdx, 8(%rsp)
#second iteration #second iteration
movq 8($inp), %r8
movq 16($inp), %rax movq 16($inp), %rax
mulq %r8 mulq %rbp
addq %rax, %r10 addq %rax, %r10
movq 24($inp), %rax movq 24($inp), %rax
movq %rdx, %rbx movq %rdx, %rbx
adcq \$0, %rbx adcq \$0, %rbx
mulq %r8 mulq %rbp
addq %rax, %r11 addq %rax, %r11
movq 32($inp), %rax movq 32($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rbx, %r11 addq %rbx, %r11
movq %rdx, %rbx movq %rdx, %rbx
adcq \$0, %rbx adcq \$0, %rbx
mulq %r8 mulq %rbp
addq %rax, %r12 addq %rax, %r12
movq 40($inp), %rax movq 40($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rbx, %r12 addq %rbx, %r12
movq %rdx, %rbx movq %rdx, %rbx
adcq \$0, %rbx adcq \$0, %rbx
mulq %r8 mulq %rbp
addq %rax, %r13 addq %rax, %r13
movq 48($inp), %rax movq 48($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rbx, %r13 addq %rbx, %r13
movq %rdx, %rbx movq %rdx, %rbx
adcq \$0, %rbx adcq \$0, %rbx
mulq %r8 mulq %rbp
addq %rax, %r14 addq %rax, %r14
movq 56($inp), %rax movq 56($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rbx, %r14 addq %rbx, %r14
movq %rdx, %rbx movq %rdx, %rbx
adcq \$0, %rbx adcq \$0, %rbx
mulq %r8 mulq %rbp
addq %rax, %r15 addq %rax, %r15
movq %r8, %rax movq %rbp, %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rbx, %r15 addq %rbx, %r15
movq %rdx, %r8 adcq \$0, %rdx
movq %r10, %rdx
adcq \$0, %r8 xorq %rbx, %rbx # rbx:r10:r9 = r10:r9 << 1
addq %r9, %r9
add %rdx, %rdx movq %rdx, %r8
lea (%rcx,%r10,2), %r10 #shld \$1, %rcx, %r10 adcq %r10, %r10
movq %r11, %rbx adcq \$0, %rbx
adcq %r11, %r11 #shld \$1, %r10, %r11
mulq %rax mulq %rax
# rcx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
addq %rcx, %rax
movq 16($inp), %rbp
addq %rax, %r9 addq %rax, %r9
movq 24($inp), %rax
adcq %rdx, %r10 adcq %rdx, %r10
adcq \$0, %r11 adcq \$0, %rbx
movq %r9, 16(%rsp) movq %r9, 16(%rsp)
movq %r10, 24(%rsp) movq %r10, 24(%rsp)
shrq \$63, %rbx
#third iteration #third iteration
movq 16($inp), %r9 mulq %rbp
movq 24($inp), %rax
mulq %r9
addq %rax, %r12 addq %rax, %r12
movq 32($inp), %rax movq 32($inp), %rax
movq %rdx, %rcx movq %rdx, %rcx
adcq \$0, %rcx adcq \$0, %rcx
mulq %r9 mulq %rbp
addq %rax, %r13 addq %rax, %r13
movq 40($inp), %rax movq 40($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rcx, %r13 addq %rcx, %r13
movq %rdx, %rcx movq %rdx, %rcx
adcq \$0, %rcx adcq \$0, %rcx
mulq %r9 mulq %rbp
addq %rax, %r14 addq %rax, %r14
movq 48($inp), %rax movq 48($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rcx, %r14 addq %rcx, %r14
movq %rdx, %rcx movq %rdx, %rcx
adcq \$0, %rcx adcq \$0, %rcx
mulq %r9 mulq %rbp
movq %r12, %r10
lea (%rbx,%r12,2), %r12 #shld \$1, %rbx, %r12
addq %rax, %r15 addq %rax, %r15
movq 56($inp), %rax movq 56($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rcx, %r15 addq %rcx, %r15
movq %rdx, %rcx movq %rdx, %rcx
adcq \$0, %rcx adcq \$0, %rcx
mulq %r9 mulq %rbp
shrq \$63, %r10
addq %rax, %r8 addq %rax, %r8
movq %r9, %rax movq %rbp, %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rcx, %r8 addq %rcx, %r8
movq %rdx, %r9 adcq \$0, %rdx
adcq \$0, %r9
movq %r13, %rcx xorq %rcx, %rcx # rcx:r12:r11 = r12:r11 << 1
leaq (%r10,%r13,2), %r13 #shld \$1, %r12, %r13 addq %r11, %r11
movq %rdx, %r9
adcq %r12, %r12
adcq \$0, %rcx
mulq %rax mulq %rax
# rbx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
addq %rbx, %rax
movq 24($inp), %r10
addq %rax, %r11 addq %rax, %r11
movq 32($inp), %rax
adcq %rdx, %r12 adcq %rdx, %r12
adcq \$0, %r13 adcq \$0, %rcx
movq %r11, 32(%rsp) movq %r11, 32(%rsp)
movq %r12, 40(%rsp) movq %r12, 40(%rsp)
shrq \$63, %rcx
#fourth iteration #fourth iteration
movq 24($inp), %r10 mov %rax, %r11 # 32($inp)
movq 32($inp), %rax
mulq %r10 mulq %r10
addq %rax, %r14 addq %rax, %r14
movq 40($inp), %rax movq 40($inp), %rax
movq %rdx, %rbx movq %rdx, %rbx
adcq \$0, %rbx adcq \$0, %rbx
mov %rax, %r12 # 40($inp)
mulq %r10 mulq %r10
addq %rax, %r15 addq %rax, %r15
movq 48($inp), %rax movq 48($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rbx, %r15 addq %rbx, %r15
movq %rdx, %rbx movq %rdx, %rbx
adcq \$0, %rbx adcq \$0, %rbx
mov %rax, %rbp # 48($inp)
mulq %r10 mulq %r10
movq %r14, %r12
leaq (%rcx,%r14,2), %r14 #shld \$1, %rcx, %r14
addq %rax, %r8 addq %rax, %r8
movq 56($inp), %rax movq 56($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rbx, %r8 addq %rbx, %r8
movq %rdx, %rbx movq %rdx, %rbx
adcq \$0, %rbx adcq \$0, %rbx
mulq %r10 mulq %r10
shrq \$63, %r12
addq %rax, %r9 addq %rax, %r9
movq %r10, %rax movq %r10, %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rbx, %r9 addq %rbx, %r9
movq %rdx, %r10 adcq \$0, %rdx
adcq \$0, %r10
movq %r15, %rbx xorq %rbx, %rbx # rbx:r13:r14 = r13:r14 << 1
leaq (%r12,%r15,2),%r15 #shld \$1, %r14, %r15 addq %r13, %r13
movq %rdx, %r10
adcq %r14, %r14
adcq \$0, %rbx
mulq %rax mulq %rax
# rcx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
addq %rcx, %rax
addq %rax, %r13 addq %rax, %r13
movq %r12, %rax # 40($inp)
adcq %rdx, %r14 adcq %rdx, %r14
adcq \$0, %r15 adcq \$0, %rbx
movq %r13, 48(%rsp) movq %r13, 48(%rsp)
movq %r14, 56(%rsp) movq %r14, 56(%rsp)
shrq \$63, %rbx
#fifth iteration #fifth iteration
movq 32($inp), %r11
movq 40($inp), %rax
mulq %r11 mulq %r11
addq %rax, %r8 addq %rax, %r8
movq 48($inp), %rax movq %rbp, %rax # 48($inp)
movq %rdx, %rcx movq %rdx, %rcx
adcq \$0, %rcx adcq \$0, %rcx
mulq %r11 mulq %r11
addq %rax, %r9 addq %rax, %r9
movq 56($inp), %rax movq 56($inp), %rax
adcq \$0, %rdx adcq \$0, %rdx
movq %r8, %r12
leaq (%rbx,%r8,2), %r8 #shld \$1, %rbx, %r8
addq %rcx, %r9 addq %rcx, %r9
movq %rdx, %rcx movq %rdx, %rcx
adcq \$0, %rcx adcq \$0, %rcx
mov %rax, %r14 # 56($inp)
mulq %r11 mulq %r11
shrq \$63, %r12
addq %rax, %r10 addq %rax, %r10
movq %r11, %rax movq %r11, %rax
adcq \$0, %rdx adcq \$0, %rdx
addq %rcx, %r10 addq %rcx, %r10
movq %rdx, %r11 adcq \$0, %rdx
adcq \$0, %r11
movq %r9, %rcx xorq %rcx, %rcx # rcx:r8:r15 = r8:r15 << 1
leaq (%r12,%r9,2), %r9 #shld \$1, %r8, %r9 addq %r15, %r15
movq %rdx, %r11
adcq %r8, %r8
adcq \$0, %rcx
mulq %rax mulq %rax
# rbx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
addq %rbx, %rax
addq %rax, %r15 addq %rax, %r15
movq %rbp, %rax # 48($inp)
adcq %rdx, %r8 adcq %rdx, %r8
adcq \$0, %r9 adcq \$0, %rcx
movq %r15, 64(%rsp) movq %r15, 64(%rsp)
movq %r8, 72(%rsp) movq %r8, 72(%rsp)
shrq \$63, %rcx
#sixth iteration #sixth iteration
movq 40($inp), %r12
movq 48($inp), %rax
mulq %r12 mulq %r12
addq %rax, %r10 addq %rax, %r10
movq 56($inp), %rax movq %r14, %rax # 56($inp)
movq %rdx, %rbx movq %rdx, %rbx
adcq \$0, %rbx adcq \$0, %rbx
mulq %r12 mulq %r12
addq %rax, %r11 addq %rax, %r11
movq %r12, %rax movq %r12, %rax
movq %r10, %r15
leaq (%rcx,%r10,2), %r10 #shld \$1, %rcx, %r10
adcq \$0, %rdx adcq \$0, %rdx
shrq \$63, %r15
addq %rbx, %r11 addq %rbx, %r11
movq %rdx, %r12 adcq \$0, %rdx
adcq \$0, %r12
movq %r11, %rbx xorq %rbx, %rbx # rbx:r10:r9 = r10:r9 << 1
leaq (%r15,%r11,2), %r11 #shld \$1, %r10, %r11 addq %r9, %r9
movq %rdx, %r12
adcq %r10, %r10
adcq \$0, %rbx
mulq %rax mulq %rax
# rcx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
addq %rcx, %rax
addq %rax, %r9 addq %rax, %r9
movq %r14, %rax # 56($inp)
adcq %rdx, %r10 adcq %rdx, %r10
adcq \$0, %r11 adcq \$0, %rbx
movq %r9, 80(%rsp) movq %r9, 80(%rsp)
movq %r10, 88(%rsp) movq %r10, 88(%rsp)
#seventh iteration #seventh iteration
movq 48($inp), %r13 mulq %rbp
movq 56($inp), %rax
mulq %r13
addq %rax, %r12 addq %rax, %r12
movq %r13, %rax movq %rbp, %rax
movq %rdx, %r13 adcq \$0, %rdx
adcq \$0, %r13
xorq %r14, %r14 xorq %rcx, %rcx # rcx:r12:r11 = r12:r11 << 1
shlq \$1, %rbx addq %r11, %r11
adcq %r12, %r12 #shld \$1, %rbx, %r12 movq %rdx, %r13
adcq %r13, %r13 #shld \$1, %r12, %r13 adcq %r12, %r12
adcq %r14, %r14 #shld \$1, %r13, %r14 adcq \$0, %rcx
mulq %rax mulq %rax
# rbx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
addq %rbx, %rax
addq %rax, %r11 addq %rax, %r11
movq %r14, %rax # 56($inp)
adcq %rdx, %r12 adcq %rdx, %r12
adcq \$0, %r13 adcq \$0, %rcx
movq %r11, 96(%rsp) movq %r11, 96(%rsp)
movq %r12, 104(%rsp) movq %r12, 104(%rsp)
#eighth iteration #eighth iteration
movq 56($inp), %rax xorq %rbx, %rbx # rbx:r13 = r13 << 1
mulq %rax addq %r13, %r13
addq %rax, %r13 adcq \$0, %rbx
adcq \$0, %rdx
addq %rdx, %r14
movq %r13, 112(%rsp) mulq %rax
movq %r14, 120(%rsp) # rcx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
addq %rcx, %rax
addq %r13, %rax
adcq %rbx, %rdx
movq (%rsp), %r8 movq (%rsp), %r8
movq 8(%rsp), %r9 movq 8(%rsp), %r9
movq 16(%rsp), %r10 movq 16(%rsp), %r10
movq 24(%rsp), %r11 movq 24(%rsp), %r11
movq 32(%rsp), %r12 movq 32(%rsp), %r12
movq 40(%rsp), %r13 movq 40(%rsp), %r13
movq 48(%rsp), %r14 movq 48(%rsp), %r14
movq 56(%rsp), %r15 movq 56(%rsp), %r15
movq %xmm1, %rbp
movq %rax, 112(%rsp)
movq %rdx, 120(%rsp)
call __rsaz_512_reduce call __rsaz_512_reduce
addq 64(%rsp), %r8 addq 64(%rsp), %r8
adcq 72(%rsp), %r9 adcq 72(%rsp), %r9
adcq 80(%rsp), %r10 adcq 80(%rsp), %r10
adcq 88(%rsp), %r11 adcq 88(%rsp), %r11
adcq 96(%rsp), %r12 adcq 96(%rsp), %r12
adcq 104(%rsp), %r13 adcq 104(%rsp), %r13
adcq 112(%rsp), %r14 adcq 112(%rsp), %r14
skipping to change at line 527 skipping to change at line 534
jnz .Loop_sqr jnz .Loop_sqr
___ ___
if ($addx) { if ($addx) {
$code.=<<___; $code.=<<___;
jmp .Lsqr_tail jmp .Lsqr_tail
.align 32 .align 32
.Loop_sqrx: .Loop_sqrx:
movl $times,128+8(%rsp) movl $times,128+8(%rsp)
movq $out, %xmm0 # off-load movq $out, %xmm0 # off-load
movq %rbp, %xmm1 # off-load
#first iteration #first iteration
mulx %rax, %r8, %r9 mulx %rax, %r8, %r9
mov %rax, %rbx
mulx 16($inp), %rcx, %r10 mulx 16($inp), %rcx, %r10
xor %rbp, %rbp # cf=0, of=0 xor %rbp, %rbp # cf=0, of=0
mulx 24($inp), %rax, %r11 mulx 24($inp), %rax, %r11
adcx %rcx, %r9 adcx %rcx, %r9
mulx 32($inp), %rcx, %r12 .byte 0xc4,0x62,0xf3,0xf6,0xa6,0x20,0x00,0x00,0x00 # mulx 32($inp), %rcx, %r12
adcx %rax, %r10 adcx %rax, %r10
mulx 40($inp), %rax, %r13 .byte 0xc4,0x62,0xfb,0xf6,0xae,0x28,0x00,0x00,0x00 # mulx 40($inp), %rax, %r13
adcx %rcx, %r11 adcx %rcx, %r11
.byte 0xc4,0x62,0xf3,0xf6,0xb6,0x30,0x00,0x00,0x00 # mulx 48($inp), %rcx, %r14 mulx 48($inp), %rcx, %r14
adcx %rax, %r12 adcx %rax, %r12
adcx %rcx, %r13 adcx %rcx, %r13
.byte 0xc4,0x62,0xfb,0xf6,0xbe,0x38,0x00,0x00,0x00 # mulx 56($inp), %rax, %r15 mulx 56($inp), %rax, %r15
adcx %rax, %r14 adcx %rax, %r14
adcx %rbp, %r15 # %rbp is 0 adcx %rbp, %r15 # %rbp is 0
mov %r9, %rcx mulx %rdx, %rax, $out
shld \$1, %r8, %r9 mov %rbx, %rdx # 8($inp)
shl \$1, %r8 xor %rcx, %rcx
adox %r8, %r8
xor %ebp, %ebp adcx $out, %r8
mulx %rdx, %rax, %rdx adox %rbp, %rcx
adcx %rdx, %r8 adcx %rbp, %rcx
mov 8($inp), %rdx
adcx %rbp, %r9
mov %rax, (%rsp) mov %rax, (%rsp)
mov %r8, 8(%rsp) mov %r8, 8(%rsp)
#second iteration #second iteration
mulx 16($inp), %rax, %rbx .byte 0xc4,0xe2,0xfb,0xf6,0x9e,0x10,0x00,0x00,0x00 # mulx 16($inp), %rax, %rbx
adox %rax, %r10 adox %rax, %r10
adcx %rbx, %r11 adcx %rbx, %r11
.byte 0xc4,0x62,0xc3,0xf6,0x86,0x18,0x00,0x00,0x00 # mulx 24($inp), $out, %r8 mulx 24($inp), $out, %r8
adox $out, %r11 adox $out, %r11
.byte 0x66
adcx %r8, %r12 adcx %r8, %r12
mulx 32($inp), %rax, %rbx mulx 32($inp), %rax, %rbx
adox %rax, %r12 adox %rax, %r12
adcx %rbx, %r13 adcx %rbx, %r13
mulx 40($inp), $out, %r8 mulx 40($inp), $out, %r8
adox $out, %r13 adox $out, %r13
adcx %r8, %r14 adcx %r8, %r14
.byte 0xc4,0xe2,0xfb,0xf6,0x9e,0x30,0x00,0x00,0x00 # mulx 48($inp), %rax, %rbx .byte 0xc4,0xe2,0xfb,0xf6,0x9e,0x30,0x00,0x00,0x00 # mulx 48($inp), %rax, %rbx
adox %rax, %r14 adox %rax, %r14
adcx %rbx, %r15 adcx %rbx, %r15
.byte 0xc4,0x62,0xc3,0xf6,0x86,0x38,0x00,0x00,0x00 # mulx 56($inp), $out, %r8 .byte 0xc4,0x62,0xc3,0xf6,0x86,0x38,0x00,0x00,0x00 # mulx 56($inp), $out, %r8
adox $out, %r15 adox $out, %r15
adcx %rbp, %r8 adcx %rbp, %r8
mulx %rdx, %rax, $out
adox %rbp, %r8 adox %rbp, %r8
.byte 0x48,0x8b,0x96,0x10,0x00,0x00,0x00 # mov 16($inp), %rdx
mov %r11, %rbx xor %rbx, %rbx
shld \$1, %r10, %r11 adox %r9, %r9
shld \$1, %rcx, %r10 # rcx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
adcx %rcx, %rax
xor %ebp,%ebp adox %r10, %r10
mulx %rdx, %rax, %rcx
mov 16($inp), %rdx
adcx %rax, %r9 adcx %rax, %r9
adcx %rcx, %r10 adox %rbp, %rbx
adcx %rbp, %r11 adcx $out, %r10
adcx %rbp, %rbx
mov %r9, 16(%rsp) mov %r9, 16(%rsp)
.byte 0x4c,0x89,0x94,0x24,0x18,0x00,0x00,0x00 # mov %r10, 24( %rsp) .byte 0x4c,0x89,0x94,0x24,0x18,0x00,0x00,0x00 # mov %r10, 24( %rsp)
#third iteration #third iteration
.byte 0xc4,0x62,0xc3,0xf6,0x8e,0x18,0x00,0x00,0x00 # mulx 24($inp), $out, %r9 mulx 24($inp), $out, %r9
adox $out, %r12 adox $out, %r12
adcx %r9, %r13 adcx %r9, %r13
mulx 32($inp), %rax, %rcx mulx 32($inp), %rax, %rcx
adox %rax, %r13 adox %rax, %r13
adcx %rcx, %r14 adcx %rcx, %r14
mulx 40($inp), $out, %r9 .byte 0xc4,0x62,0xc3,0xf6,0x8e,0x28,0x00,0x00,0x00 # mulx 40($inp), $out, %r9
adox $out, %r14 adox $out, %r14
adcx %r9, %r15 adcx %r9, %r15
.byte 0xc4,0xe2,0xfb,0xf6,0x8e,0x30,0x00,0x00,0x00 # mulx 48($inp), %rax, %rcx .byte 0xc4,0xe2,0xfb,0xf6,0x8e,0x30,0x00,0x00,0x00 # mulx 48($inp), %rax, %rcx
adox %rax, %r15 adox %rax, %r15
adcx %rcx, %r8 adcx %rcx, %r8
.byte 0xc4,0x62,0xc3,0xf6,0x8e,0x38,0x00,0x00,0x00 # mulx 56($inp), $out, %r9 mulx 56($inp), $out, %r9
adox $out, %r8 adox $out, %r8
adcx %rbp, %r9 adcx %rbp, %r9
mulx %rdx, %rax, $out
adox %rbp, %r9 adox %rbp, %r9
mov 24($inp), %rdx
mov %r13, %rcx xor %rcx, %rcx
shld \$1, %r12, %r13 adox %r11, %r11
shld \$1, %rbx, %r12 # rbx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
adcx %rbx, %rax
xor %ebp, %ebp adox %r12, %r12
mulx %rdx, %rax, %rdx
adcx %rax, %r11 adcx %rax, %r11
adcx %rdx, %r12 adox %rbp, %rcx
mov 24($inp), %rdx adcx $out, %r12
adcx %rbp, %r13 adcx %rbp, %rcx
mov %r11, 32(%rsp) mov %r11, 32(%rsp)
.byte 0x4c,0x89,0xa4,0x24,0x28,0x00,0x00,0x00 # mov %r12, 40( %rsp) mov %r12, 40(%rsp)
#fourth iteration #fourth iteration
.byte 0xc4,0xe2,0xfb,0xf6,0x9e,0x20,0x00,0x00,0x00 # mulx 32($inp), %rax, %rbx mulx 32($inp), %rax, %rbx
adox %rax, %r14 adox %rax, %r14
adcx %rbx, %r15 adcx %rbx, %r15
mulx 40($inp), $out, %r10 mulx 40($inp), $out, %r10
adox $out, %r15 adox $out, %r15
adcx %r10, %r8 adcx %r10, %r8
mulx 48($inp), %rax, %rbx mulx 48($inp), %rax, %rbx
adox %rax, %r8 adox %rax, %r8
adcx %rbx, %r9 adcx %rbx, %r9
mulx 56($inp), $out, %r10 mulx 56($inp), $out, %r10
adox $out, %r9 adox $out, %r9
adcx %rbp, %r10 adcx %rbp, %r10
mulx %rdx, %rax, $out
adox %rbp, %r10 adox %rbp, %r10
mov 32($inp), %rdx
.byte 0x66 xor %rbx, %rbx
mov %r15, %rbx adox %r13, %r13
shld \$1, %r14, %r15 # rcx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
shld \$1, %rcx, %r14 adcx %rcx, %rax
adox %r14, %r14
xor %ebp, %ebp
mulx %rdx, %rax, %rdx
adcx %rax, %r13 adcx %rax, %r13
adcx %rdx, %r14 adox %rbp, %rbx
mov 32($inp), %rdx adcx $out, %r14
adcx %rbp, %r15 adcx %rbp, %rbx
mov %r13, 48(%rsp) mov %r13, 48(%rsp)
mov %r14, 56(%rsp) mov %r14, 56(%rsp)
#fifth iteration #fifth iteration
.byte 0xc4,0x62,0xc3,0xf6,0x9e,0x28,0x00,0x00,0x00 # mulx 40($inp), $out, %r11 mulx 40($inp), $out, %r11
adox $out, %r8 adox $out, %r8
adcx %r11, %r9 adcx %r11, %r9
mulx 48($inp), %rax, %rcx mulx 48($inp), %rax, %rcx
adox %rax, %r9 adox %rax, %r9
adcx %rcx, %r10 adcx %rcx, %r10
mulx 56($inp), $out, %r11 mulx 56($inp), $out, %r11
adox $out, %r10 adox $out, %r10
adcx %rbp, %r11 adcx %rbp, %r11
mulx %rdx, %rax, $out
mov 40($inp), %rdx
adox %rbp, %r11 adox %rbp, %r11
mov %r9, %rcx xor %rcx, %rcx
shld \$1, %r8, %r9 adox %r15, %r15
shld \$1, %rbx, %r8 # rbx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
adcx %rbx, %rax
xor %ebp, %ebp adox %r8, %r8
mulx %rdx, %rax, %rdx
adcx %rax, %r15 adcx %rax, %r15
adcx %rdx, %r8 adox %rbp, %rcx
mov 40($inp), %rdx adcx $out, %r8
adcx %rbp, %r9 adcx %rbp, %rcx
mov %r15, 64(%rsp) mov %r15, 64(%rsp)
mov %r8, 72(%rsp) mov %r8, 72(%rsp)
#sixth iteration #sixth iteration
.byte 0xc4,0xe2,0xfb,0xf6,0x9e,0x30,0x00,0x00,0x00 # mulx 48($inp), %rax, %rbx .byte 0xc4,0xe2,0xfb,0xf6,0x9e,0x30,0x00,0x00,0x00 # mulx 48($inp), %rax, %rbx
adox %rax, %r10 adox %rax, %r10
adcx %rbx, %r11 adcx %rbx, %r11
.byte 0xc4,0x62,0xc3,0xf6,0xa6,0x38,0x00,0x00,0x00 # mulx 56($inp), $out, %r12 .byte 0xc4,0x62,0xc3,0xf6,0xa6,0x38,0x00,0x00,0x00 # mulx 56($inp), $out, %r12
adox $out, %r11 adox $out, %r11
adcx %rbp, %r12 adcx %rbp, %r12
mulx %rdx, %rax, $out
adox %rbp, %r12 adox %rbp, %r12
mov 48($inp), %rdx
mov %r11, %rbx xor %rbx, %rbx
shld \$1, %r10, %r11 adox %r9, %r9
shld \$1, %rcx, %r10 # rcx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
adcx %rcx, %rax
xor %ebp, %ebp adox %r10, %r10
mulx %rdx, %rax, %rdx
adcx %rax, %r9 adcx %rax, %r9
adcx %rdx, %r10 adcx $out, %r10
mov 48($inp), %rdx adox %rbp, %rbx
adcx %rbp, %r11 adcx %rbp, %rbx
mov %r9, 80(%rsp) mov %r9, 80(%rsp)
mov %r10, 88(%rsp) mov %r10, 88(%rsp)
#seventh iteration #seventh iteration
.byte 0xc4,0x62,0xfb,0xf6,0xae,0x38,0x00,0x00,0x00 # mulx 56($inp), %rax, %r13 .byte 0xc4,0x62,0xfb,0xf6,0xae,0x38,0x00,0x00,0x00 # mulx 56($inp), %rax, %r13
adox %rax, %r12 adox %rax, %r12
adox %rbp, %r13 adox %rbp, %r13
xor %r14, %r14 mulx %rdx, %rax, $out
shld \$1, %r13, %r14 xor %rcx, %rcx
shld \$1, %r12, %r13
shld \$1, %rbx, %r12
xor %ebp, %ebp
mulx %rdx, %rax, %rdx
adcx %rax, %r11
adcx %rdx, %r12
mov 56($inp), %rdx mov 56($inp), %rdx
adcx %rbp, %r13 adox %r11, %r11
# rbx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
adcx %rbx, %rax
adox %r12, %r12
adcx %rax, %r11
adox %rbp, %rcx
adcx $out, %r12
adcx %rbp, %rcx
.byte 0x4c,0x89,0x9c,0x24,0x60,0x00,0x00,0x00 # mov %r11, 96( %rsp) .byte 0x4c,0x89,0x9c,0x24,0x60,0x00,0x00,0x00 # mov %r11, 96( %rsp)
.byte 0x4c,0x89,0xa4,0x24,0x68,0x00,0x00,0x00 # mov %r12, 104 (%rsp) .byte 0x4c,0x89,0xa4,0x24,0x68,0x00,0x00,0x00 # mov %r12, 104 (%rsp)
#eighth iteration #eighth iteration
mulx %rdx, %rax, %rdx mulx %rdx, %rax, %rdx
adox %rax, %r13 xor %rbx, %rbx
adox %rbp, %rdx adox %r13, %r13
# rcx <= 2 and rax <= 0xFFFF..F9, so carry must be zero here
adcx %rcx, %rax
adox %rbp, %rbx
adcx %r13, %rax
adcx %rdx, %rbx
.byte 0x66
add %rdx, %r14
movq %r13, 112(%rsp)
movq %r14, 120(%rsp)
movq %xmm0, $out movq %xmm0, $out
movq %xmm1, %rbp movq %xmm1, %rbp
movq 128(%rsp), %rdx # pull $n0 movq 128(%rsp), %rdx # pull $n0
movq (%rsp), %r8 movq (%rsp), %r8
movq 8(%rsp), %r9 movq 8(%rsp), %r9
movq 16(%rsp), %r10 movq 16(%rsp), %r10
movq 24(%rsp), %r11 movq 24(%rsp), %r11
movq 32(%rsp), %r12 movq 32(%rsp), %r12
movq 40(%rsp), %r13 movq 40(%rsp), %r13
movq 48(%rsp), %r14 movq 48(%rsp), %r14
movq 56(%rsp), %r15 movq 56(%rsp), %r15
movq %rax, 112(%rsp)
movq %rbx, 120(%rsp)
call __rsaz_512_reducex call __rsaz_512_reducex
addq 64(%rsp), %r8 addq 64(%rsp), %r8
adcq 72(%rsp), %r9 adcq 72(%rsp), %r9
adcq 80(%rsp), %r10 adcq 80(%rsp), %r10
adcq 88(%rsp), %r11 adcq 88(%rsp), %r11
adcq 96(%rsp), %r12 adcq 96(%rsp), %r12
adcq 104(%rsp), %r13 adcq 104(%rsp), %r13
adcq 112(%rsp), %r14 adcq 112(%rsp), %r14
adcq 120(%rsp), %r15 adcq 120(%rsp), %r15
 End of changes. 111 change blocks. 
186 lines changed or deleted 199 lines changed or added

Home  |  About  |  Features  |  All  |  Newest  |  Dox  |  Diffs  |  RSS Feeds  |  Screenshots  |  Comments  |  Imprint  |  Privacy  |  HTTP(S)