diff options
Diffstat (limited to 'sysdeps/x86/dl-cacheinfo.h')
| -rw-r--r-- | sysdeps/x86/dl-cacheinfo.h | 11 |
1 files changed, 10 insertions, 1 deletions
diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h index c885b23f7a..c35bf73467 100644 --- a/sysdeps/x86/dl-cacheinfo.h +++ b/sysdeps/x86/dl-cacheinfo.h @@ -872,12 +872,21 @@ dl_init_cacheinfo (struct cpu_features *cpu_features) provides proper LRU hints so that the maximum thrashing capped at 1/associativity. */ unsigned long int non_temporal_threshold = shared / 4; + + /* If the computed non_temporal_threshold <= 3/4 * per-thread L3, we most + likely have incorrect/incomplete cache info in which case, default to + 3/4 * per-thread L3 to avoid regressions. */ + unsigned long int non_temporal_threshold_lowbound + = shared_per_thread * 3 / 4; + if (non_temporal_threshold < non_temporal_threshold_lowbound) + non_temporal_threshold = non_temporal_threshold_lowbound; + /* If no ERMS, we use the per-thread L3 chunking. Normal cacheable stores run a higher risk of actually thrashing the cache as they don't have a HW LRU hint. As well, their performance in highly parallel situations is noticeably worse. */ if (!CPU_FEATURE_USABLE_P (cpu_features, ERMS)) - non_temporal_threshold = shared_per_thread * 3 / 4; + non_temporal_threshold = non_temporal_threshold_lowbound; #if HAVE_TUNABLES /* NB: The REP MOVSB threshold must be greater than VEC_SIZE * 8. */ |