From 9dc645cb569af8db58dab2a1b296421f29c0cd4f Mon Sep 17 00:00:00 2001 From: MayShao-oc Date: Sat, 29 Jun 2024 11:58:28 +0800 Subject: [PATCH] x86: Set default non_temporal_threshold for Zhaoxin processors Current 'non_temporal_threshold' set to 'non_temporal_threshold_lowbound' on Zhaoxin processors without ERMS. The default 'non_temporal_threshold_lowbound' is too small for the KH-40000 and KX-7000 Zhaoxin processors, this patch updates the value to 'shared / cachesize_non_temporal_divisor'. Reviewed-by: Noah Goldstein --- sysdeps/x86/cpu-features.c | 1 + sysdeps/x86/dl-cacheinfo.h | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c index 1927f65699..e501e084ef 100644 --- a/sysdeps/x86/cpu-features.c +++ b/sysdeps/x86/cpu-features.c @@ -1065,6 +1065,7 @@ https://www.intel.com/content/www/us/en/support/articles/000059422/processors.ht /* Yongfeng and Shijidadao mircoarch tuning. */ case 0x5b: + cpu_features->cachesize_non_temporal_divisor = 2; case 0x6b: cpu_features->preferred[index_arch_AVX_Fast_Unaligned_Load] &= ~bit_arch_AVX_Fast_Unaligned_Load; diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h index 3a6ec4ef9f..5e77345a6e 100644 --- a/sysdeps/x86/dl-cacheinfo.h +++ b/sysdeps/x86/dl-cacheinfo.h @@ -934,8 +934,10 @@ dl_init_cacheinfo (struct cpu_features *cpu_features) /* 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)) + noticeably worse. Zhaoxin processors are an exception, the lowbound is not + suitable for them based on actual test data. */ + if (!CPU_FEATURE_USABLE_P (cpu_features, ERMS) + && cpu_features->basic.kind != arch_kind_zhaoxin) 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