lib/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2025-09-11 12:10:50 +03:00
Code Activity

x86: Optimizing memcpy for AMD Zen architecture.

Browse Source 
Modifying the shareable cache '__x86_shared_cache_size', which is a
factor in computing the non-temporal threshold parameter
'__x86_shared_non_temporal_threshold' to optimize memcpy for AMD Zen
architectures.
In the existing implementation, the shareable cache is computed as 'L3
per thread, L2 per core'. Recomputing this shareable cache as 'L3 per
CCX(Core-Complex)' has brought in performance gains.
As per the large bench variant results, this patch also addresses the
regression problem on AMD Zen architectures.

Reviewed-by: Premachandra Mallappa <premachandra.mallappa@amd.com>
This commit is contained in:
Sajan Karumanchi
2020-10-28 13:05:33 +05:30
committed by Florian Weimer
parent 641a124845
commit 59803e81f9
1 changed files with 26 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
sysdeps/x86/cacheinfo.h
View File

@@ -320,7 +320,7 @@ init_cacheinfo (void)
threads = 1 << ((ecx >> 12) & 0x0f); threads = 1 << ((ecx >> 12) & 0x0f);
} }
if (threads == 0) if (threads == 0 || cpu_features->basic.family >= 0x17)
{ {
/* If APIC ID width is not available, use logical /* If APIC ID width is not available, use logical
processor count. */ processor count. */
@@ -335,13 +335,30 @@ init_cacheinfo (void)
if (threads > 0) if (threads > 0)
shared /= threads; shared /= threads;
/* Account for exclusive L2 and L3 caches. */ /* Get shared cache per ccx for Zen architectures. */
shared += core; if (cpu_features->basic.family >= 0x17)
} {
unsigned int eax;
/* Get number of threads share the L3 cache in CCX. */
__cpuid_count (0x8000001D, 0x3, eax, ebx, ecx, edx);
unsigned int threads_per_ccx = ((eax >> 14) & 0xfff) + 1;
shared *= threads_per_ccx;
}
else
{
/* Account for exclusive L2 and L3 caches. */
shared += core;
}
}
} }
if (cpu_features->data_cache_size != 0) if (cpu_features->data_cache_size != 0)
data = cpu_features->data_cache_size; {
if (data == 0 || cpu_features->basic.kind != arch_kind_amd)
data = cpu_features->data_cache_size;
}
if (data > 0) if (data > 0)
{ {
@@ -354,7 +371,10 @@ init_cacheinfo (void)
} }
if (cpu_features->shared_cache_size != 0) if (cpu_features->shared_cache_size != 0)
shared = cpu_features->shared_cache_size; {
if (shared == 0 || cpu_features->basic.kind != arch_kind_amd)
shared = cpu_features->shared_cache_size;
}
if (shared > 0) if (shared > 0)
{ {