[PATCH] x86: Adding an upper bound for Enhanced REP MOVSB.

[sajan.karumanchi@amd.com]

From: Sajan Karumanchi <sajan.karumanchi@amd.com>

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_max_rep_movsb_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>
---
 sysdeps/x86/cacheinfo.c                           | 15 ++++++++++++++-
 .../x86_64/multiarch/memmove-vec-unaligned-erms.S |  4 ++--
 2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/sysdeps/x86/cacheinfo.c b/sysdeps/x86/cacheinfo.c
index 3fb4a028d8..9d7f8992be 100644
--- a/sysdeps/x86/cacheinfo.c
+++ b/sysdeps/x86/cacheinfo.c
@@ -1,5 +1,5 @@
 /* x86_64 cache info.
-   Copyright (C) 2003-2020 Free Software Foundation, Inc.
+   Copyright (C) 2003-2021 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
 
    The GNU C Library is free software; you can redistribute it and/or
@@ -533,6 +533,9 @@ long int __x86_shared_non_temporal_threshold attribute_hidden;
 /* Threshold to use Enhanced REP MOVSB.  */
 long int __x86_rep_movsb_threshold attribute_hidden = 2048;
 
+/* Threshold to stop using Enhanced REP MOVSB.  */
+long int __x86_max_rep_movsb_threshold attribute_hidden = 512 * 1024;
+
 /* Threshold to use Enhanced REP STOSB.  */
 long int __x86_rep_stosb_threshold attribute_hidden = 2048;
 
@@ -839,6 +842,11 @@ init_cacheinfo (void)
 	      /* Account for exclusive L2 and L3 caches.  */
 	      shared += core;
             }
+	  /* ERMS feature is implemented from 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.  */
+	  __x86_max_rep_movsb_threshold = core;
 	}
     }
 
@@ -909,6 +917,11 @@ init_cacheinfo (void)
   else
     __x86_rep_movsb_threshold = rep_movsb_threshold;
 
+  /* Setting the upper bound of ERMS to the known default value of
+     non-temporal threshold for architectures other than AMD.  */
+  if (cpu_features->basic.kind != arch_kind_amd)
+    __x86_max_rep_movsb_threshold = __x86_shared_non_temporal_threshold;
+
 # if HAVE_TUNABLES
   __x86_rep_stosb_threshold = cpu_features->rep_stosb_threshold;
 # endif
diff --git a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
index bd5dc1a3f3..c18eaf7ef6 100644
--- a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
+++ b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
@@ -1,5 +1,5 @@
 /* memmove/memcpy/mempcpy with unaligned load/store and rep movsb
-   Copyright (C) 2016-2020 Free Software Foundation, Inc.
+   Copyright (C) 2016-2021 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
 
    The GNU C Library is free software; you can redistribute it and/or
@@ -233,7 +233,7 @@ L(return):
 	ret
 
 L(movsb):
-	cmp	__x86_shared_non_temporal_threshold(%rip), %RDX_LP
+	cmp	__x86_max_rep_movsb_threshold(%rip), %RDX_LP
 	jae	L(more_8x_vec)
 	cmpq	%rsi, %rdi
 	jb	1f
-- 
2.25.1