mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-21 12:30:06 +00:00
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 <goldstein.w.n@gmail.com>
This commit is contained in:
parent
c19457aec6
commit
9dc645cb56
@ -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;
|
||||
|
@ -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
|
||||
|
Loading…
Reference in New Issue
Block a user