forked from rpms/glibc
56 lines
3.0 KiB
Diff
56 lines
3.0 KiB
Diff
From 8b9a0af8ca012217bf90d1dc0694f85b49ae09da Mon Sep 17 00:00:00 2001
|
|
From: Noah Goldstein <goldstein.w.n@gmail.com>
|
|
Date: Tue, 18 Jul 2023 10:27:59 -0500
|
|
Subject: [PATCH] [PATCH v1] x86: Use `3/4*sizeof(per-thread-L3)` as low bound
|
|
for NT threshold.
|
|
Content-type: text/plain; charset=UTF-8
|
|
|
|
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 <dj@redhat.com>
|
|
---
|
|
sysdeps/x86/dl-cacheinfo.h | 15 ++++++++++++---
|
|
1 file changed, 12 insertions(+), 3 deletions(-)
|
|
|
|
[diff rebased by DJ]
|
|
diff -rup a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
|
|
--- a/sysdeps/x86/dl-cacheinfo.h 2023-07-25 00:38:43.343986368 -0400
|
|
+++ b/sysdeps/x86/dl-cacheinfo.h 2023-07-25 00:38:44.336025100 -0400
|
|
@@ -751,8 +751,8 @@ dl_init_cacheinfo (struct cpu_features *
|
|
|
|
/* The default setting for the non_temporal threshold is [1/8, 1/2] of size
|
|
of the chip's cache (depending on `cachesize_non_temporal_divisor` which
|
|
- is microarch specific. The defeault is 1/4). For most Intel and AMD
|
|
- processors with an initial release date between 2017 and 2023, a thread's
|
|
+ is microarch specific. The default is 1/4). For most Intel processors
|
|
+ with an initial release date between 2017 and 2023, a thread's
|
|
typical share of the cache is from 18-64MB. Using a reasonable size
|
|
fraction of L3 is meant to estimate the point where non-temporal stores
|
|
begin out-competing REP MOVSB. As well the point where the fact that
|
|
@@ -763,12 +763,21 @@ dl_init_cacheinfo (struct cpu_features *
|
|
the maximum thrashing capped at 1/associativity. */
|
|
unsigned long int non_temporal_threshold
|
|
= shared / cachesize_non_temporal_divisor;
|
|
+
|
|
+ /* 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
|