This is the mail archive of the mailing list for the glibc project.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [PATCH RFC] Imporve 64bit memset performance for Haswell CPU with AVX2 instruction

On Wed, Jun 04, 2014 at 03:00:05PM +0800, Ling Ma wrote:
> H.J
> The website changed IP, now the code is available again:
> ,
> and also gziped as attachment in this mail.
> Thanks
> Ling
Now performance looks ok for me, but few formating problems.
With these fixed I would be satisfied H.J do you have comments?

There is possible followup to also optimize __bzero like we do in
general case.

Then second followup would be decrease function size by reshuffling
blocks, on several places there are 15/16 free bytes due alignment.

Formatting problems are here:

+	vpxor	%xmm0, %xmm0, %xmm0
+	vmovd %esi, %xmm1
+	mov	%rdi, %rsi
+	mov	%rdi, %rax


+	vmovd %xmm0, %rcx
+	cmp	$8, %dl
+	jb	L(less_8bytes)
+	mov %rcx, (%rdi)
+	mov %rcx, -0x08(%rsi)
+	ret
+	.p2align 4
+	cmp	$4, %dl
+	jb	L(less_4bytes)
+	mov %ecx, (%rdi)
+	mov %ecx, -0x04(%rsi)
+	ret

and here

+	mov	%rax, %rsi
+	vmovd %xmm0, %eax
+	mov	%rdx, %rcx

As I mentioned code size one trick is that instructions 
with -128 argument are shorter than with 128. You could save 16
bytes with following modification, however it must be tested if 
it improves performance.

--- x	2014-06-05 18:20:35.313645591 +0200
+++ sysdeps/x86_64/multiarch/memset-avx2.S	2014-06-05
18:22:25.068642767 +0200
@@ -95,7 +95,6 @@
 	.p2align 4
 	vinserti128 $1, %xmm0, %ymm0, %ymm0
-	mov	$0x80, %rcx
 	add	%rdx, %rsi
 	mov	%rdi, %r9
 	vmovdqu	%ymm0, (%rdi)
@@ -105,15 +104,15 @@
 	add	%r9, %rdx
 	cmp	$4096, %rdx
 	ja	L(gobble_data)
-	sub	%ecx, %edx
+	add	$-128, %edx
 	vmovdqa	%ymm0, (%rdi)
 	vmovdqa	%ymm0, 0x20(%rdi)
 	vmovdqa	%ymm0, 0x40(%rdi)
 	vmovdqa	%ymm0, 0x60(%rdi)
-	add	%rcx, %rdi
-	sub	%ecx, %edx
-	jae	L(gobble_128_loop)
+	sub	$-128, %rdi
+	add	$-128, %edx
+	jb	L(gobble_128_loop)
 	vmovdqu	%ymm0, -0x80(%rsi)
 	vmovdqu	%ymm0, -0x60(%rsi)
 	vmovdqu	%ymm0, -0x40(%rsi)

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]