Loading crypto/bn/asm/x86_64-mont5.pl +7 −9 Original line number Original line Diff line number Diff line Loading @@ -1934,6 +1934,7 @@ __bn_sqr8x_reduction: .align 32 .align 32 .L8x_tail_done: .L8x_tail_done: xor %rax,%rax add (%rdx),%r8 # can this overflow? add (%rdx),%r8 # can this overflow? adc \$0,%r9 adc \$0,%r9 adc \$0,%r10 adc \$0,%r10 Loading @@ -1941,10 +1942,8 @@ __bn_sqr8x_reduction: adc \$0,%r12 adc \$0,%r12 adc \$0,%r13 adc \$0,%r13 adc \$0,%r14 adc \$0,%r14 adc \$0,%r15 # can't overflow, because we adc \$0,%r15 # started with "overhung" part adc \$0,%rax # of multiplication xor %rax,%rax neg $carry neg $carry .L8x_no_tail: .L8x_no_tail: Loading Loading @@ -3384,6 +3383,7 @@ __bn_sqrx8x_reduction: .align 32 .align 32 .Lsqrx8x_tail_done: .Lsqrx8x_tail_done: xor %rax,%rax add 24+8(%rsp),%r8 # can this overflow? add 24+8(%rsp),%r8 # can this overflow? adc \$0,%r9 adc \$0,%r9 adc \$0,%r10 adc \$0,%r10 Loading @@ -3391,10 +3391,8 @@ __bn_sqrx8x_reduction: adc \$0,%r12 adc \$0,%r12 adc \$0,%r13 adc \$0,%r13 adc \$0,%r14 adc \$0,%r14 adc \$0,%r15 # can't overflow, because we adc \$0,%r15 # started with "overhung" part adc \$0,%rax # of multiplication mov $carry,%rax # xor %rax,%rax sub 16+8(%rsp),$carry # mov 16(%rsp),%cf sub 16+8(%rsp),$carry # mov 16(%rsp),%cf .Lsqrx8x_no_tail: # %cf is 0 if jumped here .Lsqrx8x_no_tail: # %cf is 0 if jumped here Loading @@ -3409,7 +3407,7 @@ __bn_sqrx8x_reduction: adc 8*5($tptr),%r13 adc 8*5($tptr),%r13 adc 8*6($tptr),%r14 adc 8*6($tptr),%r14 adc 8*7($tptr),%r15 adc 8*7($tptr),%r15 adc %rax,%rax # top-most carry adc \$0,%rax # top-most carry mov 32+8(%rsp),%rbx # n0 mov 32+8(%rsp),%rbx # n0 mov 8*8($tptr,%rcx),%rdx # modulo-scheduled "%r8" mov 8*8($tptr,%rcx),%rdx # modulo-scheduled "%r8" Loading Loading
crypto/bn/asm/x86_64-mont5.pl +7 −9 Original line number Original line Diff line number Diff line Loading @@ -1934,6 +1934,7 @@ __bn_sqr8x_reduction: .align 32 .align 32 .L8x_tail_done: .L8x_tail_done: xor %rax,%rax add (%rdx),%r8 # can this overflow? add (%rdx),%r8 # can this overflow? adc \$0,%r9 adc \$0,%r9 adc \$0,%r10 adc \$0,%r10 Loading @@ -1941,10 +1942,8 @@ __bn_sqr8x_reduction: adc \$0,%r12 adc \$0,%r12 adc \$0,%r13 adc \$0,%r13 adc \$0,%r14 adc \$0,%r14 adc \$0,%r15 # can't overflow, because we adc \$0,%r15 # started with "overhung" part adc \$0,%rax # of multiplication xor %rax,%rax neg $carry neg $carry .L8x_no_tail: .L8x_no_tail: Loading Loading @@ -3384,6 +3383,7 @@ __bn_sqrx8x_reduction: .align 32 .align 32 .Lsqrx8x_tail_done: .Lsqrx8x_tail_done: xor %rax,%rax add 24+8(%rsp),%r8 # can this overflow? add 24+8(%rsp),%r8 # can this overflow? adc \$0,%r9 adc \$0,%r9 adc \$0,%r10 adc \$0,%r10 Loading @@ -3391,10 +3391,8 @@ __bn_sqrx8x_reduction: adc \$0,%r12 adc \$0,%r12 adc \$0,%r13 adc \$0,%r13 adc \$0,%r14 adc \$0,%r14 adc \$0,%r15 # can't overflow, because we adc \$0,%r15 # started with "overhung" part adc \$0,%rax # of multiplication mov $carry,%rax # xor %rax,%rax sub 16+8(%rsp),$carry # mov 16(%rsp),%cf sub 16+8(%rsp),$carry # mov 16(%rsp),%cf .Lsqrx8x_no_tail: # %cf is 0 if jumped here .Lsqrx8x_no_tail: # %cf is 0 if jumped here Loading @@ -3409,7 +3407,7 @@ __bn_sqrx8x_reduction: adc 8*5($tptr),%r13 adc 8*5($tptr),%r13 adc 8*6($tptr),%r14 adc 8*6($tptr),%r14 adc 8*7($tptr),%r15 adc 8*7($tptr),%r15 adc %rax,%rax # top-most carry adc \$0,%rax # top-most carry mov 32+8(%rsp),%rbx # n0 mov 32+8(%rsp),%rbx # n0 mov 8*8($tptr,%rcx),%rdx # modulo-scheduled "%r8" mov 8*8($tptr,%rcx),%rdx # modulo-scheduled "%r8" Loading
Rich Salz <rsalz@openssl.org>