aboutsummaryrefslogtreecommitdiff
path: root/sysdeps/x86/dl-cacheinfo.h
diff options
context:
space:
mode:
authorSajan Karumanchi <sajan.karumanchi@amd.com>2021-02-02 12:42:14 +0100
committerFlorian Weimer <fweimer@redhat.com>2021-02-02 12:42:15 +0100
commit6e02b3e9327b7dbb063958d2b124b64fcb4bbe3f (patch)
treef5fa119e5c2db62c16cdbaaa01d856da390e607a /sysdeps/x86/dl-cacheinfo.h
parentcaa60b79f8c98e97455078542a14b4c750e48ede (diff)
downloadglibc-6e02b3e9327b7dbb063958d2b124b64fcb4bbe3f.zip
glibc-6e02b3e9327b7dbb063958d2b124b64fcb4bbe3f.tar.gz
glibc-6e02b3e9327b7dbb063958d2b124b64fcb4bbe3f.tar.bz2
x86: Adding an upper bound for Enhanced REP MOVSB.
In the process of optimizing memcpy for AMD machines, we have found the vector move operations are outperforming enhanced REP MOVSB for data transfers above the L2 cache size on Zen3 architectures. To handle this use case, we are adding an upper bound parameter on enhanced REP MOVSB:'__x86_rep_movsb_stop_threshold'. As per large-bench results, we are configuring this parameter to the L2 cache size for AMD machines and applicable from Zen3 architecture supporting the ERMS feature. For architectures other than AMD, it is the computed value of non-temporal threshold parameter. Reviewed-by: Premachandra Mallappa <premachandra.mallappa@amd.com>
Diffstat (limited to 'sysdeps/x86/dl-cacheinfo.h')
-rw-r--r--sysdeps/x86/dl-cacheinfo.h15
1 files changed, 14 insertions, 1 deletions
diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
index a31fa07..374ba82 100644
--- a/sysdeps/x86/dl-cacheinfo.h
+++ b/sysdeps/x86/dl-cacheinfo.h
@@ -704,7 +704,7 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
int max_cpuid_ex;
long int data = -1;
long int shared = -1;
- long int core;
+ long int core = -1;
unsigned int threads = 0;
unsigned long int level1_icache_size = -1;
unsigned long int level1_dcache_size = -1;
@@ -886,6 +886,18 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
#endif
}
+ unsigned long int rep_movsb_stop_threshold;
+ /* ERMS feature is implemented from AMD Zen3 architecture and it is
+ performing poorly for data above L2 cache size. Henceforth, adding
+ an upper bound threshold parameter to limit the usage of Enhanced
+ REP MOVSB operations and setting its value to L2 cache size. */
+ if (cpu_features->basic.kind == arch_kind_amd)
+ rep_movsb_stop_threshold = core;
+ /* Setting the upper bound of ERMS to the computed value of
+ non-temporal threshold for architectures other than AMD. */
+ else
+ rep_movsb_stop_threshold = non_temporal_threshold;
+
/* The default threshold to use Enhanced REP STOSB. */
unsigned long int rep_stosb_threshold = 2048;
@@ -935,4 +947,5 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
cpu_features->non_temporal_threshold = non_temporal_threshold;
cpu_features->rep_movsb_threshold = rep_movsb_threshold;
cpu_features->rep_stosb_threshold = rep_stosb_threshold;
+ cpu_features->rep_movsb_stop_threshold = rep_movsb_stop_threshold;
}