diff options
| author | Amrita H S <amritahs@linux.vnet.ibm.com> | 2023-12-06 11:43:11 -0500 |
|---|---|---|
| committer | Rajalakshmi Srinivasaraghavan <rajis@linux.ibm.com> | 2023-12-07 11:10:40 -0600 |
| commit | 3367d8e180848030d1646f088759f02b8dfe0d6f (patch) | |
| tree | 1300c2911e4f08b4861bf144b6bcbc54e193b51b /sysdeps/powerpc/powerpc64/multiarch/ifunc-impl-list.c | |
| parent | 546a1ba664626603660b595662249d524e429013 (diff) | |
| download | glibc-3367d8e180848030d1646f088759f02b8dfe0d6f.tar.gz glibc-3367d8e180848030d1646f088759f02b8dfe0d6f.tar.xz glibc-3367d8e180848030d1646f088759f02b8dfe0d6f.zip | |
powerpc: Optimized strcmp for power10
This patch is based on __strcmp_power9 and __strlen_power10.
Improvements from __strcmp_power9:
1. Uses new POWER10 instructions
- This code uses lxvp to decrease contention on load
by loading 32 bytes per instruction.
2. Performance implication
- This version has around 30% better performance on average.
- Performance regression is seen for a specific combination
of sizes and alignments. Some of them is observed without
changes also, while rest may be induced by the patch.
Signed-off-by: Amrita H S <amritahs@linux.vnet.ibm.com>
Reviewed-by: Paul E. Murphy <murphyp@linux.ibm.com>
Diffstat (limited to 'sysdeps/powerpc/powerpc64/multiarch/ifunc-impl-list.c')
| -rw-r--r-- | sysdeps/powerpc/powerpc64/multiarch/ifunc-impl-list.c | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/sysdeps/powerpc/powerpc64/multiarch/ifunc-impl-list.c b/sysdeps/powerpc/powerpc64/multiarch/ifunc-impl-list.c index fc26dd0e17..965dd17786 100644 --- a/sysdeps/powerpc/powerpc64/multiarch/ifunc-impl-list.c +++ b/sysdeps/powerpc/powerpc64/multiarch/ifunc-impl-list.c @@ -378,6 +378,10 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL (i, name, strcmp, #ifdef __LITTLE_ENDIAN__ IFUNC_IMPL_ADD (array, i, strcmp, + (hwcap2 & PPC_FEATURE2_ARCH_3_1) + && (hwcap & PPC_FEATURE_HAS_VSX), + __strcmp_power10) + IFUNC_IMPL_ADD (array, i, strcmp, hwcap2 & PPC_FEATURE2_ARCH_3_00 && hwcap & PPC_FEATURE_HAS_ALTIVEC, __strcmp_power9) |