From 54e99a96ec3b97f53ee018bfa8dbbef2dd13f1e8 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 7 Jun 2024 23:04:47 +0000
Subject: [PATCH 05/10] x86: Enable non-temporal memset tunable for AMD

In commit 46b5e98ef6f1 ("x86: Add seperate non-temporal tunable for
memset") a tunable threshold for enabling non-temporal memset was added,
but only for Intel hardware.

Since that commit, new benchmark results suggest that non-temporal
memset is beneficial on AMD, as well, so allow this tunable to be set
for AMD.

See:
https://docs.google.com/spreadsheets/d/1opzukzvum4n6-RUVHTGddV6RjAEil4P2uMjjQGLbLcU/edit?usp=sharing
which has been updated to include data using different stategies for
large memset on AMD Zen2, Zen3, and Zen4.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
---
 sysdeps/x86/dl-cacheinfo.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
index 9f27da21ce..dfdb4069c7 100644
--- a/sysdeps/x86/dl-cacheinfo.h
+++ b/sysdeps/x86/dl-cacheinfo.h
@@ -1048,11 +1048,11 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
   if (CPU_FEATURE_USABLE_P (cpu_features, FSRM))
     rep_movsb_threshold = 2112;
 
-  /* Non-temporal stores in memset have only been tested on Intel hardware.
-     Until we benchmark data on other x86 processor, disable non-temporal
-     stores in memset. */
+  /* Non-temporal stores are more performant on Intel and AMD hardware above
+     non_temporal_threshold. Enable this for both Intel and AMD hardware. */
   unsigned long int memset_non_temporal_threshold = SIZE_MAX;
-  if (cpu_features->basic.kind == arch_kind_intel)
+  if (cpu_features->basic.kind == arch_kind_intel
+      || cpu_features->basic.kind == arch_kind_amd)
       memset_non_temporal_threshold = non_temporal_threshold;
 
    /* For AMD CPUs that support ERMS (Zen3+), REP MOVSB is in a lot of
-- 
2.17.1