aarch64: revert memcpy optimze for kunpeng to avoid performance degradation
Commit Message
In commit 863d775c481704baaa41855fc93e5a1ca2dc6bf6, kunpeng920 is added to default memcpy version,
however, there is performance degradation when the copy size is some large bytes, eg: 100k.
This is the result, tested in glibc-2.28:
before backport after backport Performance improvement
memcpy_1k 0.005 0.005 0.00%
memcpy_10k 0.032 0.029 10.34%
memcpy_100k 0.356 0.429 -17.02%
memcpy_1m 7.470 11.153 -33.02%
This is the demo
#include "stdio.h"
#include "string.h"
#include "stdlib.h"
char a[1024*1024] = {12};
char b[1024*1024] = {13};
int main(int argc, char *argv[])
{
int i = atoi(argv[1]);
int j;
int size = atoi(argv[2]);
for (j = 0; j < i; j++)
memcpy(b, a, size*1024);
return 0;
}
# gcc -g -O0 memcpy.c -o memcpy
# time taskset -c 10 ./memcpy 100000 1024
Co-authored-by: liqingqing <liqingqing3@huawei.com>
---
sysdeps/aarch64/multiarch/memcpy.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Comments
Hi,
Since I don't have access to this specific hardware, it would be good
if the original author, Xuelei Zhang, of the change could certify this
reversion is ok.
It should be ok during the freeze since it just a selection of an
already tested implementation for an specific chip implementation.
On 20/01/2021 04:20, Shuo Wang wrote:
> In commit 863d775c481704baaa41855fc93e5a1ca2dc6bf6, kunpeng920 is added to default memcpy version,
> however, there is performance degradation when the copy size is some large bytes, eg: 100k.
> This is the result, tested in glibc-2.28:
> before backport after backport Performance improvement
> memcpy_1k 0.005 0.005 0.00%
> memcpy_10k 0.032 0.029 10.34%
> memcpy_100k 0.356 0.429 -17.02%
> memcpy_1m 7.470 11.153 -33.02%
>
> This is the demo
> #include "stdio.h"
> #include "string.h"
> #include "stdlib.h"
>
> char a[1024*1024] = {12};
> char b[1024*1024] = {13};
> int main(int argc, char *argv[])
> {
> int i = atoi(argv[1]);
> int j;
> int size = atoi(argv[2]);
>
> for (j = 0; j < i; j++)
> memcpy(b, a, size*1024);
> return 0;
> }
>
> # gcc -g -O0 memcpy.c -o memcpy
> # time taskset -c 10 ./memcpy 100000 1024
>
> Co-authored-by: liqingqing <liqingqing3@huawei.com>
>
> ---
> sysdeps/aarch64/multiarch/memcpy.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/sysdeps/aarch64/multiarch/memcpy.c b/sysdeps/aarch64/multiarch/memcpy.c
> index 27259d3386..0e0a5cbcfb 100644
> --- a/sysdeps/aarch64/multiarch/memcpy.c
> +++ b/sysdeps/aarch64/multiarch/memcpy.c
> @@ -37,7 +37,7 @@ extern __typeof (__redirect_memcpy) __memcpy_falkor attribute_hidden;
> libc_ifunc (__libc_memcpy,
> (IS_THUNDERX (midr)
> ? __memcpy_thunderx
> - : (IS_FALKOR (midr) || IS_PHECDA (midr) || IS_KUNPENG920 (midr)
> + : (IS_FALKOR (midr) || IS_PHECDA (midr)
> ? __memcpy_falkor
> : (IS_THUNDERX2 (midr) || IS_THUNDERX2PA (midr)
> ? __memcpy_thunderx2
>
@@ -37,7 +37,7 @@ extern __typeof (__redirect_memcpy) __memcpy_falkor attribute_hidden;
libc_ifunc (__libc_memcpy,
(IS_THUNDERX (midr)
? __memcpy_thunderx
- : (IS_FALKOR (midr) || IS_PHECDA (midr) || IS_KUNPENG920 (midr)
+ : (IS_FALKOR (midr) || IS_PHECDA (midr)
? __memcpy_falkor
: (IS_THUNDERX2 (midr) || IS_THUNDERX2PA (midr)
? __memcpy_thunderx2