mirror of
git://git.musl-libc.org/musl
synced 2024-12-16 03:35:06 +00:00
x86_64/memset: avoid performing final store twice
The code does a potentially misaligned 8-byte store to fill the tail of the buffer. Then it fills the initial part of the buffer which is a multiple of 8 bytes. Therefore, if size is divisible by 8, we were storing last word twice. This patch decrements byte count before dividing it by 8, making one less store in "size is divisible by 8" case, and not changing anything in all other cases. All at the cost of replacing one MOV insn with LEA insn. Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
This commit is contained in:
parent
bf2071eda3
commit
74e334dcd1
@ -9,7 +9,7 @@ memset:
|
||||
cmp $16,%rdx
|
||||
jb 1f
|
||||
|
||||
mov %rdx,%rcx
|
||||
lea -1(%rdx),%rcx
|
||||
mov %rdi,%r8
|
||||
shr $3,%rcx
|
||||
mov %rax,-8(%rdi,%rdx)
|
||||
|
Loading…
Reference in New Issue
Block a user