This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH 2/2] aarch64: Optimized memcpy and memmove for Kunpeng processor
- From: Yikun Jiang <yikunkero at gmail dot com>
- To: Xuelei Zhang <zhangxuelei4 at huawei dot com>
- Cc: libc-alpha at sourceware dot org
- Date: Wed, 16 Oct 2019 10:14:19 +0800
- Subject: Re: [PATCH 2/2] aarch64: Optimized memcpy and memmove for Kunpeng processor
- References: <20191014034456.11548-1-zhangxuelei4@huawei.com>
> diff --git a/sysdeps/aarch64/multiarch/Makefile b/sysdeps/aarch64/multiarch/Makefile
> index 4150b89a90..aa1f612e9e 100644
> --- a/sysdeps/aarch64/multiarch/Makefile
> +++ b/sysdeps/aarch64/multiarch/Makefile
> @@ -1,6 +1,7 @@
> ifeq ($(subdir),string)
> sysdep_routines += memcpy_generic memcpy_thunderx memcpy_thunderx2 \
> - memcpy_falkor memmove_falkor \
> + memcpy_falkor memcpy_kunpeng \
> + memmove_falkor memmove_kunpeng \
> memset_generic memset_falkor memset_emag \
> memchr_generic memchr_nosimd \
> strlen_generic strlen_asimd
It seems we should remove the "memmove_kunpeng", and only add
the "memcpy_kunpeng" in here.
> +ENTRY_ALIGN (MEMMOVE, 6)
> +
> + DELOUSE (0)
> + DELOUSE (1)
> + DELOUSE (2)
> +
> + sub tmp1, dstin, src
> + cmp count, 512
> + ccmp tmp1, count, 2, hi
> + b.lo L(move_long)
> + cmp count, 96
> + ccmp tmp1, count, 2, hi
> + b.lo L(move_middle)
> +
> +END (MEMMOVE)
nit: remember to remove the trailing space.