lib/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2025-08-01 10:06:57 +03:00
Code Activity

x86: Add seperate non-temporal tunable for memset

Browse Source 
The tuning for non-temporal stores for memset vs memcpy is not always
the same. This includes both the exact value and whether non-temporal
stores are profitable at all for a given arch.

This patch add `x86_memset_non_temporal_threshold`. Currently we
disable non-temporal stores for non Intel vendors as the only
benchmarks showing its benefit have been on Intel hardware.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
This commit is contained in:
Noah Goldstein
2024-05-24 12:38:51 -05:00
parent 5bf0ab8057
commit 46b5e98ef6
7 changed files with 49 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
sysdeps/x86/dl-diagnostics-cpu.c
View File

@ -94,6 +94,8 @@ _dl_diagnostics_cpu (void)
cpu_features->shared_cache_size);
print_cpu_features_value ("non_temporal_threshold",
cpu_features->non_temporal_threshold);
print_cpu_features_value ("memset_non_temporal_threshold",
cpu_features->memset_non_temporal_threshold);
print_cpu_features_value ("rep_movsb_threshold",
cpu_features->rep_movsb_threshold);
print_cpu_features_value ("rep_movsb_stop_threshold",