diff options
Diffstat (limited to 'sysdeps')
| -rw-r--r-- | sysdeps/aarch64/multiarch/memset_oryon1.S | 26 | ||||
| -rw-r--r-- | sysdeps/x86_64/multiarch/strncat-evex.S | 4 |
2 files changed, 2 insertions, 28 deletions
diff --git a/sysdeps/aarch64/multiarch/memset_oryon1.S b/sysdeps/aarch64/multiarch/memset_oryon1.S index 6fa28a9..b63c16e 100644 --- a/sysdeps/aarch64/multiarch/memset_oryon1.S +++ b/sysdeps/aarch64/multiarch/memset_oryon1.S @@ -93,8 +93,6 @@ L(set_long): cmp count, 256 ccmp valw, 0, 0, cs b.eq L(try_zva) - cmp count, #32768 - b.hi L(set_long_with_nontemp) /* Small-size or non-zero memset does not use DC ZVA. */ sub count, dstend, dst @@ -117,30 +115,6 @@ L(set_long): stp val, val, [dstend, -16] ret -L(set_long_with_nontemp): - /* Small-size or non-zero memset does not use DC ZVA. */ - sub count, dstend, dst - - /* Adjust count and bias for loop. By subtracting extra 1 from count, - it is easy to use tbz instruction to check whether loop tailing - count is less than 33 bytes, so as to bypass 2 unnecessary stps. */ - sub count, count, 64+16+1 - -1: stnp val, val, [dst, 16] - stnp val, val, [dst, 32] - stnp val, val, [dst, 48] - stnp val, val, [dst, 64] - add dst, dst, #64 - subs count, count, 64 - b.hs 1b - - tbz count, 5, 1f /* Remaining count is less than 33 bytes? */ - stnp val, val, [dst, 16] - stnp val, val, [dst, 32] -1: stnp val, val, [dstend, -32] - stnp val, val, [dstend, -16] - ret - L(try_zva): /* Write the first and last 64 byte aligned block using stp rather than using DC ZVA as it is faster. */ diff --git a/sysdeps/x86_64/multiarch/strncat-evex.S b/sysdeps/x86_64/multiarch/strncat-evex.S index e6717bd..fbec351 100644 --- a/sysdeps/x86_64/multiarch/strncat-evex.S +++ b/sysdeps/x86_64/multiarch/strncat-evex.S @@ -44,7 +44,7 @@ # define VPCMPEQ vpcmpeqd # define CHAR_SIZE 4 -# define REP_MOVS rep movsd +# define REP_MOVS rep movsl # define VMASK_REG VR10 # define FIND_FIRST_ONE(src, dst) movl $CHAR_PER_VEC, %dst; bsf %src, %dst @@ -514,7 +514,7 @@ L(page_cross_small): cmova %edx, %ecx # ifdef USE_AS_WCSCPY - rep movsd + rep movsl # else rep movsb # endif |