JehanneOS/newlib
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

memcpy-armv7a.S: Improve performance with misaligned buffers.

Browse Source 
Adjust the conditions for entering the aligned copy loop to
improve performance on mutually misaligned buffer copies.

2013-07-01  Will Newton  <will.newton@linaro.org>

	* libc/machine/arm/memcpy-armv7a.S: Adjust entry to
	 aligned loop to improve misaligned copy performance.
This commit is contained in:
Will Newton 2013-07-01 09:58:34 +00:00
parent 562b70fbac
commit 5073668c61
2 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
newlib/ChangeLog
View File

@ -1,3 +1,8 @@
2013-07-01 Will Newton <will.newton@linaro.org>
* libc/machine/arm/memcpy-armv7a.S: Adjust entry to
aligned loop to improve misaligned copy performance.
2013-06-26 Jeff Johnston <jjohnstn@redhat.com>
* libc/include/stdio.h: Specify std streams always in terms

4
newlib/libc/machine/arm/memcpy-armv7a.S
View File

@ -242,8 +242,8 @@ def_fn memcpy p2align=6
.Lcpy_not_short:
/* At least 64 bytes to copy, but don't know the alignment yet. */
str tmp2, [sp, #-FRAME_SIZE]!
and tmp2, src, #3
and tmp1, dst, #3
and tmp2, src, #7
and tmp1, dst, #7
cmp tmp1, tmp2
bne .Lcpy_notaligned