AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-11-09 23:00:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

x86-64: Avoid rep movsb with short distance [BZ #27130]

Browse Source 
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.
This commit is contained in:
H.J. Lu 2020-01-25 14:19:40 -08:00
parent cd6274089f
commit 3ec5d83d2a
1 changed files with 21 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
View File

@ -56,6 +56,13 @@
# 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
@ -243,7 +250,21 @@ 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):