glibc/glibc-RHEL-15696-38.patch
DJ Delorie 02cfe04e36 Import Intel hyperscale improvements (RHEL-15696)
Resolves: RHEL-15696

Includes two additional (well, 1.5) upstream patches
to resolve roundeven redirects.
2023-12-15 17:33:06 -05:00

68 lines
2.1 KiB
Diff

From 3ec5d83d2a237d39e7fd6ef7a0bc8ac4c171a4a5 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.tools@gmail.com>
Date: Sat, 25 Jan 2020 14:19:40 -0800
Subject: [PATCH] x86-64: Avoid rep movsb with short distance [BZ #27130]
Content-type: text/plain; charset=UTF-8
When copying with "rep movsb", if the distance between source and
destination is N*4GB + [1..63] with N >= 0, performance may be very
slow. This patch updates memmove-vec-unaligned-erms.S for AVX and
AVX512 versions with the distance in RCX:
cmpl $63, %ecx
// Don't use "rep movsb" if ECX <= 63
jbe L(Don't use rep movsb")
Use "rep movsb"
Benchtests data with bench-memcpy, bench-memcpy-large, bench-memcpy-random
and bench-memcpy-walk on Skylake, Ice Lake and Tiger Lake show that its
performance impact is within noise range as "rep movsb" is only used for
data size >= 4KB.
---
.../multiarch/memmove-vec-unaligned-erms.S | 21 +++++++++++++++++++
1 file changed, 21 insertions(+)
diff --git a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
index 673b73aa..c475fed4 100644
--- a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
+++ b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
@@ -64,6 +64,13 @@
# endif
#endif
+/* Avoid short distance rep movsb only with non-SSE vector. */
+#ifndef AVOID_SHORT_DISTANCE_REP_MOVSB
+# define AVOID_SHORT_DISTANCE_REP_MOVSB (VEC_SIZE > 16)
+#else
+# define AVOID_SHORT_DISTANCE_REP_MOVSB 0
+#endif
+
#ifndef PREFETCH
# define PREFETCH(addr) prefetcht0 addr
#endif
@@ -255,7 +262,21 @@ L(movsb):
cmpq %r9, %rdi
/* Avoid slow backward REP MOVSB. */
jb L(more_8x_vec_backward)
+# if AVOID_SHORT_DISTANCE_REP_MOVSB
+ movq %rdi, %rcx
+ subq %rsi, %rcx
+ jmp 2f
+# endif
1:
+# if AVOID_SHORT_DISTANCE_REP_MOVSB
+ movq %rsi, %rcx
+ subq %rdi, %rcx
+2:
+/* Avoid "rep movsb" if RCX, the distance between source and destination,
+ is N*4GB + [1..63] with N >= 0. */
+ cmpl $63, %ecx
+ jbe L(more_2x_vec) /* Avoid "rep movsb" if ECX <= 63. */
+# endif
mov %RDX_LP, %RCX_LP
rep movsb
L(nop):
--
GitLab