Re: memcpy performance regressions 2.19 -> 2.24(5)

["H.J. Lu" <hjl.tools@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 817 bytes --]

On Thu, May 18, 2017 at 1:59 PM, Erich Elsen <eriche@google.com> wrote:
> Hi H.J.,
>
> I was on vacation, sorry for the slow reply.  The updated benchmark
> still shows the same behavior, thanks.
>
> I'll try my hand at creating a patch that makes that variable
> __x86_shared_non_temporal_threshold a tunable.  It will be necessary
> to do internal experiments anyway.
>

__x86_shared_non_temporal_threshold was set to 6 times of per-core
shared cache size, based on the large memcpy micro benchmark in glibc
on a 8-core processor.  For a processor with more than 8 cores, the
threshold is too low.  Set __x86_shared_non_temporal_threshold to the
3/4 of the total shared cache size so that it is unchanged on 8-core
processors.  On processors with less than 8 cores, the threshold is
lower.

Any comments?

-- 
H.J.

[-- Attachment #2: 0001-x86-Update-__x86_shared_non_temporal_threshold.patch --]
[-- Type: text/x-patch, Size: 1495 bytes --]

From bfb716e07b77f0ed8e0c2689d5cd01e2c8251fc5 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.tools@gmail.com>
Date: Fri, 12 May 2017 13:38:04 -0700
Subject: [PATCH] x86: Update __x86_shared_non_temporal_threshold

__x86_shared_non_temporal_threshold was set to 6 times of per-core
shared cache size, based on the large memcpy micro benchmark in glibc
on a 8-core processor.  For a processor with more than 8 cores, the
threshold is too low.  Set __x86_shared_non_temporal_threshold to the
3/4 of the total shared cache size so that it is unchanged on 8-core
processors.  On processors with less than 8 cores, the threshold is
lower.

	* sysdeps/x86/cacheinfo.c (__x86_shared_non_temporal_threshold):
	Set to the 3/4 of the total shared cache size.
---
 sysdeps/x86/cacheinfo.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/sysdeps/x86/cacheinfo.c b/sysdeps/x86/cacheinfo.c
index 1ccbe41..3434d97 100644
--- a/sysdeps/x86/cacheinfo.c
+++ b/sysdeps/x86/cacheinfo.c
@@ -766,6 +766,8 @@ intel_bug_no_cache_info:
 
   /* The large memcpy micro benchmark in glibc shows that 6 times of
      shared cache size is the approximate value above which non-temporal
-     store becomes faster.  */
-  __x86_shared_non_temporal_threshold = __x86_shared_cache_size * 6;
+     store becomes faster on a 8-core processor.  This is the 3/4 of the
+     total shared cache size.  */
+  __x86_shared_non_temporal_threshold
+    = __x86_shared_cache_size * threads * 3 / 4;
 }
-- 
2.9.4