diff mbox

[v2] ARM: Improve armv7 memcpy performance.

Message ID 5220B5A1.40903@linaro.org
State Superseded
Headers show

Commit Message

Will Newton Aug. 30, 2013, 3:09 p.m. UTC 
Only enter the aligned copy loop with buffers that can be 8-byte
aligned. This improves performance slightly on Cortex-A9 and
Cortex-A15 cores for large copies with buffers that are 4-byte
aligned but not 8-byte aligned.

ports/ChangeLog.arm:

2013-08-30  Will Newton  <will.newton@linaro.org>

	* sysdeps/arm/armv7/multiarch/memcpy_impl.S: Tighten check
	on entry to aligned copy loop to improve performance.
---
 ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Changes in v2:
 - Improved description

Comments

Carlos O'Donell Aug. 30, 2013, 5:16 p.m. UTC | #1 
On 08/30/2013 11:09 AM, Will Newton wrote:
> 
> Only enter the aligned copy loop with buffers that can be 8-byte
> aligned. This improves performance slightly on Cortex-A9 and
> Cortex-A15 cores for large copies with buffers that are 4-byte
> aligned but not 8-byte aligned.
> 
> ports/ChangeLog.arm:
> 
> 2013-08-30  Will Newton  <will.newton@linaro.org>
> 
> 	* sysdeps/arm/armv7/multiarch/memcpy_impl.S: Tighten check
> 	on entry to aligned copy loop to improve performance.

How did you test this?

Did you use the glibc performance microbenchmark?

Does the microbenchmark show gains with this change? What are the numbers?

Cheers,
Carlos.

> ---
>  ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> Changes in v2:
>  - Improved description
> 
> diff --git a/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S b/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S
> index 3decad6..6e84173 100644
> --- a/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S
> +++ b/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S
> @@ -369,8 +369,8 @@ ENTRY(memcpy)
>  	cfi_adjust_cfa_offset (FRAME_SIZE)
>  	cfi_rel_offset (tmp2, 0)
>  	cfi_remember_state
> -	and	tmp2, src, #3
> -	and	tmp1, dst, #3
> +	and	tmp2, src, #7
> +	and	tmp1, dst, #7
>  	cmp	tmp1, tmp2
>  	bne	.Lcpy_notaligned
>
diff mbox

Patch

diff --git a/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S b/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S
index 3decad6..6e84173 100644
--- a/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S
+++ b/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S
@@ -369,8 +369,8 @@  ENTRY(memcpy)
 	cfi_adjust_cfa_offset (FRAME_SIZE)
 	cfi_rel_offset (tmp2, 0)
 	cfi_remember_state
-	and	tmp2, src, #3
-	and	tmp1, dst, #3
+	and	tmp2, src, #7
+	and	tmp1, dst, #7
 	cmp	tmp1, tmp2
 	bne	.Lcpy_notaligned