diff options
| author | Yingshiuan Pan <yingshiuan.pan@linaro.org> | 2015-04-23 04:07:59 +0100 |
|---|---|---|
| committer | Steve Kondik <steve@cyngn.com> | 2015-10-31 14:40:52 -0700 |
| commit | a07f3db2022ecec62f0238fcd4095c3b284c9204 (patch) | |
| tree | 1a1ca6d025fda8448d2010f0ef108ddb3b8cfe05 /libc/arch-arm/cortex-a7 | |
| parent | d103c301949c9ca75f5a2c90c253498ed797502d (diff) | |
| download | bionic-a07f3db2022ecec62f0238fcd4095c3b284c9204.zip bionic-a07f3db2022ecec62f0238fcd4095c3b284c9204.tar.gz bionic-a07f3db2022ecec62f0238fcd4095c3b284c9204.tar.bz2 | |
libc: arm: add optimized memchr implementation
This optimization is extracted from cortex-strings and bionic-ized,
and applied to arm-v7a cpus (a7, a9, a15, a53, denver, krait).
I ran stringbench[1] on ARM Juno, this optimization could outperform
origin C implementation by 77%.
[1] https://android.git.linaro.org/gitweb/platform/external/stringbench.git
Change-Id: I1c3fb0c89ce2b3ee7e44f492367b6caf6db58ccf
Signed-off-by: Yingshiuan Pan <yingshiuan.pan@linaro.org>
Diffstat (limited to 'libc/arch-arm/cortex-a7')
| -rw-r--r-- | libc/arch-arm/cortex-a7/cortex-a7.mk | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/libc/arch-arm/cortex-a7/cortex-a7.mk b/libc/arch-arm/cortex-a7/cortex-a7.mk index b6af4da..3629a57 100644 --- a/libc/arch-arm/cortex-a7/cortex-a7.mk +++ b/libc/arch-arm/cortex-a7/cortex-a7.mk @@ -12,6 +12,7 @@ libc_bionic_src_files_arm += \ arch-arm/cortex-a15/bionic/strlen.S \ libc_bionic_src_files_arm += \ + arch-arm/generic/bionic/memchr.S \ arch-arm/generic/bionic/memcmp.S \ libc_bionic_src_files_arm += \ |