aboutsummaryrefslogtreecommitdiff
path: root/sysdeps/x86_64
diff options
context:
space:
mode:
Diffstat (limited to 'sysdeps/x86_64')
-rw-r--r--sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S20
1 files changed, 10 insertions, 10 deletions
diff --git a/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S b/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S
index 47630dd97b..9d1921033e 100644
--- a/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S
+++ b/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S
@@ -137,18 +137,18 @@ L(exit):
.p2align 4
L(between_2_3):
- /* Load as big endian with overlapping loads and bswap to avoid
- branches. */
- movzwl -2(%rdi, %rdx), %eax
- movzwl -2(%rsi, %rdx), %ecx
- shll $16, %eax
- shll $16, %ecx
- movzwl (%rdi), %edi
- movzwl (%rsi), %esi
- orl %edi, %eax
- orl %esi, %ecx
+ /* Load as big endian to avoid branches. */
+ movzwl (%rdi), %eax
+ movzwl (%rsi), %ecx
+ shll $8, %eax
+ shll $8, %ecx
bswap %eax
bswap %ecx
+ movzbl -1(%rdi, %rdx), %edi
+ movzbl -1(%rsi, %rdx), %esi
+ orl %edi, %eax
+ orl %esi, %ecx
+ /* Subtraction is okay because the upper 8 bits a zero. */
subl %ecx, %eax
ret