diff options
| author | Wilco Dijkstra <wilco.dijkstra@arm.com> | 2024-12-24 18:01:59 +0000 |
|---|---|---|
| committer | Wilco Dijkstra <wilco.dijkstra@arm.com> | 2025-02-20 15:31:50 +0000 |
| commit | 163b1bbb76caba4d9673c07940c5930a1afa7548 (patch) | |
| tree | 8b99d9c978ffdd89299c245ea01916ea4c0b1621 /sysdeps/aarch64/multiarch/ifunc-impl-list.c | |
| parent | 5a4573be6f96ff49111bb6cae767676b5aafa7a8 (diff) | |
| download | glibc-163b1bbb76caba4d9673c07940c5930a1afa7548.tar.xz glibc-163b1bbb76caba4d9673c07940c5930a1afa7548.zip | |
AArch64: Add SVE memset
Add SVE memset based on the generic memset with predicated load for sizes < 16.
Unaligned memsets of 128-1024 are improved by ~20% on average by using aligned
stores for the last 64 bytes. Performance of random memset benchmark improves
by ~2% on Neoverse V1.
Reviewed-by: Yury Khrustalev <yury.khrustalev@arm.com>
Diffstat (limited to 'sysdeps/aarch64/multiarch/ifunc-impl-list.c')
| -rw-r--r-- | sysdeps/aarch64/multiarch/ifunc-impl-list.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/sysdeps/aarch64/multiarch/ifunc-impl-list.c b/sysdeps/aarch64/multiarch/ifunc-impl-list.c index 0481e450be..8dc314b67d 100644 --- a/sysdeps/aarch64/multiarch/ifunc-impl-list.c +++ b/sysdeps/aarch64/multiarch/ifunc-impl-list.c @@ -57,6 +57,7 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL_ADD (array, i, memset, 1, __memset_kunpeng) #if HAVE_AARCH64_SVE_ASM IFUNC_IMPL_ADD (array, i, memset, sve && !bti && zva_size == 256, __memset_a64fx) + IFUNC_IMPL_ADD (array, i, memset, sve && zva_size == 64, __memset_sve_zva64) #endif IFUNC_IMPL_ADD (array, i, memset, mops, __memset_mops) IFUNC_IMPL_ADD (array, i, memset, 1, __memset_generic)) |