summaryrefslogtreecommitdiff
path: root/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl
diff options
context:
space:
mode:
Diffstat (limited to 'deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl')
-rwxr-xr-xdeps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl27
1 files changed, 24 insertions, 3 deletions
diff --git a/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl b/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl
index 820de3d6f6..64e668f140 100755
--- a/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl
+++ b/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl
@@ -53,6 +53,11 @@ if (!$addx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
$addx = ($1>=12);
}
+if (!$addx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|based on LLVM) ([3-9])\.([0-9]+)/) {
+ my $ver = $2 + $3/100.0; # 3.1->3.01, 3.10->3.10
+ $addx = ($ver>=3.03);
+}
+
# int bn_mul_mont_gather5(
$rp="%rdi"; # BN_ULONG *rp,
$ap="%rsi"; # const BN_ULONG *ap,
@@ -1779,6 +1784,15 @@ sqr8x_reduction:
.align 32
.L8x_tail_done:
add (%rdx),%r8 # can this overflow?
+ adc \$0,%r9
+ adc \$0,%r10
+ adc \$0,%r11
+ adc \$0,%r12
+ adc \$0,%r13
+ adc \$0,%r14
+ adc \$0,%r15 # can't overflow, because we
+ # started with "overhung" part
+ # of multiplication
xor %rax,%rax
neg $carry
@@ -3125,6 +3139,15 @@ sqrx8x_reduction:
.align 32
.Lsqrx8x_tail_done:
add 24+8(%rsp),%r8 # can this overflow?
+ adc \$0,%r9
+ adc \$0,%r10
+ adc \$0,%r11
+ adc \$0,%r12
+ adc \$0,%r13
+ adc \$0,%r14
+ adc \$0,%r15 # can't overflow, because we
+ # started with "overhung" part
+ # of multiplication
mov $carry,%rax # xor %rax,%rax
sub 16+8(%rsp),$carry # mov 16(%rsp),%cf
@@ -3168,13 +3191,11 @@ my ($rptr,$nptr)=("%rdx","%rbp");
my @ri=map("%r$_",(10..13));
my @ni=map("%r$_",(14..15));
$code.=<<___;
- xor %rbx,%rbx
+ xor %ebx,%ebx
sub %r15,%rsi # compare top-most words
adc %rbx,%rbx
mov %rcx,%r10 # -$num
- .byte 0x67
or %rbx,%rax
- .byte 0x67
mov %rcx,%r9 # -$num
xor \$1,%rax
sar \$3+2,%rcx # cf=0