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 <[email protected]>

This commit is contained in:

Denys Vlasenko

2015-02-10 18:54:27 -05:00

committed by

Rich Felker

parent bf2071eda3

commit 74e334dcd1

1 changed files with 1 additions and 1 deletions

									
										src/string/x86_64/memset.s
									
		+1
		-1
	
												View File
												
				@@ -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)