memcpy-armv7a.S: Improve performance with misaligned buffers.
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:
parent
562b70fbac
commit
5073668c61
@ -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>
|
2013-06-26 Jeff Johnston <jjohnstn@redhat.com>
|
||||||
|
|
||||||
* libc/include/stdio.h: Specify std streams always in terms
|
* libc/include/stdio.h: Specify std streams always in terms
|
||||||
|
@ -242,8 +242,8 @@ def_fn memcpy p2align=6
|
|||||||
.Lcpy_not_short:
|
.Lcpy_not_short:
|
||||||
/* At least 64 bytes to copy, but don't know the alignment yet. */
|
/* At least 64 bytes to copy, but don't know the alignment yet. */
|
||||||
str tmp2, [sp, #-FRAME_SIZE]!
|
str tmp2, [sp, #-FRAME_SIZE]!
|
||||||
and tmp2, src, #3
|
and tmp2, src, #7
|
||||||
and tmp1, dst, #3
|
and tmp1, dst, #7
|
||||||
cmp tmp1, tmp2
|
cmp tmp1, tmp2
|
||||||
bne .Lcpy_notaligned
|
bne .Lcpy_notaligned
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user