diff mbox

[2/1,v2,neleai/string-x64] Microoptimize strcmp-sse2-unaligned more.

Message ID 20150620103548.GA21670@domone
State New
Headers show

Commit Message

Ondřej Bílka June 20, 2015, 10:35 a.m. UTC 
On Sat, Jun 20, 2015 at 12:22:56PM +0200, Ondřej Bílka wrote:
> On Sat, Jun 20, 2015 at 10:35:25AM +0200, Ondřej Bílka wrote:
> > 
> > Hi,
> > 
> > When I read strcmp again to improve strncmp and add avx2 strcmp 
> > I found that I made several mistakes, mainly caused by first optimizing 
> > c template and then fixing assembly.
> > 
> > First was mainly my idea to simplify handling cross-page check by oring
> > src and dest. I recall that I first did complex crosspage handling where
> > false positives were cheap. Then I found that due to size it has big
> > overhead and simple loop was faster when testing with firefox. 
> > That turned original decision into bad one.
> > 
> > Second is to reorganize loop instructions so that after loop ends I could 
> > simply find last byte without recalculating much, using trick that last
> > 16 bit mask could be ored with previous three as its relevant only when
> > previous three were zero.
> > 
> > Final one is that gcc generates bad loops in regards where to increment
> > pointers. You should place them after loads that use them, not at start
> > of loop like gcc does. That change is responsible for 10% improvement
> > for large sizes.
> > 
> > Final are microoptimizations that save few bytes without measurable
> > performance impact like using eax instead rax to save byte or moving
> > unnecessary zeroing instruction when they are not needed.
> > 
> > Profile data are here, shortly with avx2 for haswell that I will submit
> > next.
> > 
> > http://kam.mff.cuni.cz/~ondra/benchmark_string/strcmp_profile.html
> > 
> > OK to commit this?
> >
> I missed few microoptimizations. These save few bytes, no measurable
> impact.
>  
>  	* sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S
>  	(__strcmp_sse2_unaligned): Add several microoptimizations.
>
This one.
diff mbox

Patch

diff --git a/sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S b/sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S
index 03d1b11..9a8f685 100644
--- a/sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S
+++ b/sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S
@@ -76,19 +76,17 @@  L(return):
 	subl	%edx, %eax
 	ret
 
-
 L(main_loop_header):
 	leaq	64(%rdi), %rdx
-	movl	$4096, %ecx
 	andq	$-64, %rdx
 	subq	%rdi, %rdx
 	leaq	(%rdi, %rdx), %rax
 	addq	%rsi, %rdx
-	movq	%rdx, %rsi
-	andl	$4095, %esi
-	subq	%rsi, %rcx
-	shrq	$6, %rcx
-	movq	%rcx, %rsi
+	movl	$4096, %esi
+	mov	%edx, %ecx
+	andl	$4095, %ecx
+	sub	%ecx, %esi
+	shr	$6, %esi
 
 	.p2align 4
 L(loop):
@@ -140,10 +138,9 @@  L(back_to_loop):
 
 	.p2align 4
 L(loop_cross_page):
-	xor	%ecx, %ecx
-	movq	%rdx, %r9
-	and	$63, %r9
-	subq	%r9, %rcx
+	mov	%edx, %ecx
+	and	$63, %ecx
+	neg	%rcx
 
 	movdqa	(%rdx, %rcx), %xmm0
 	movdqa	16(%rdx, %rcx), %xmm1
@@ -177,8 +174,8 @@  L(loop_cross_page):
 	orq	%rcx, %rdi
 	salq	$48, %rsi
 	orq	%rsi, %rdi
-	movq	%r9, %rcx
-	movq	$63, %rsi
+	mov	%edx, %ecx
+	mov	$63, %esi
 	shrq	%cl, %rdi
 	test	%rdi, %rdi
 	je	L(back_to_loop)