From 1c3ecf5858b1765379cb6232203b9fe29a2516e7 Mon Sep 17 00:00:00 2001 From: Noah Goldstein Date: Tue, 18 Jul 2023 10:27:59 -0500 Subject: x86: Use `3/4*sizeof(per-thread-L3)` as low bound for NT threshold. On some machines we end up with incomplete cache information. This can make the new calculation of `sizeof(total-L3)/custom-divisor` end up lower than intended (and lower than the prior value). So reintroduce the old bound as a lower bound to avoid potentially regressing code where we don't have complete information to make the decision. Reviewed-by: DJ Delorie (cherry picked from commit 8b9a0af8ca012217bf90d1dc0694f85b49ae09da) --- sysdeps/x86/dl-cacheinfo.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h index 79fb8cc5e3..627cf57efe 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; /* SIZE_MAX >> 4 because memmove-vec-unaligned-erms right-shifts the value of 'x86_non_temporal_threshold' by `LOG_4X_MEMCPY_THRESH` (4) and it is best if that operation cannot overflow. Minimum of 0x4040 (16448) because the -- cgit v1.2.3