diff options
| author | Danila Kutenin <danilak@google.com> | 2022-06-27 16:12:13 +0000 |
|---|---|---|
| committer | Szabolcs Nagy <szabolcs.nagy@arm.com> | 2022-07-06 09:26:20 +0100 |
| commit | 3c9980698988ef64072f1fac339b180f52792faf (patch) | |
| tree | 3c32dabb3fcbfa564647fcedd9be5c7674a30fc2 /sysdeps/unix/sysv/linux/mips/mips64/n32/libc.abilist | |
| parent | bd0b58837c7df091046e7531642f379a52e1e157 (diff) | |
| download | glibc-3c9980698988ef64072f1fac339b180f52792faf.tar.gz glibc-3c9980698988ef64072f1fac339b180f52792faf.tar.xz glibc-3c9980698988ef64072f1fac339b180f52792faf.zip | |
aarch64: Optimize string functions with shrn instruction
We found that string functions were using AND+ADDP to find the nibble/syndrome mask but there is an easier opportunity through `SHRN dst.8b, src.8h, 4` (shift right every 2 bytes by 4 and narrow to 1 byte) and has same latency on all SIMD ARMv8 targets as ADDP. There are also possible gaps for memcmp but that's for another patch. We see 10-20% savings for small-mid size cases (<=128) which are primary cases for general workloads.
Diffstat (limited to 'sysdeps/unix/sysv/linux/mips/mips64/n32/libc.abilist')
0 files changed, 0 insertions, 0 deletions