mirror of
https://sourceware.org/git/glibc.git
synced 2025-01-08 10:20:15 +00:00
ba67bc8e0a
These implementations improve the time to run strchr{nul}
microbenchmark in glibc as below:
strchr-lasx reduces the runtime about 50%-83%
strchr-lsx reduces the runtime about 30%-67%
strchr-aligned reduces the runtime about 10%-20%
strchrnul-lasx reduces the runtime about 50%-83%
strchrnul-lsx reduces the runtime about 36%-65%
strchrnul-aligned reduces the runtime about 6%-10%
100 lines
2.4 KiB
ArmAsm
100 lines
2.4 KiB
ArmAsm
/* Optimized strchr implementation using basic Loongarch instructions.
|
|
Copyright (C) 2023 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
|
|
modify it under the terms of the GNU Lesser General Public
|
|
License as published by the Free Software Foundation; either
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with the GNU C Library. If not, see
|
|
<https://www.gnu.org/licenses/>. */
|
|
|
|
#include <sysdep.h>
|
|
#include <sys/regdef.h>
|
|
#include <sys/asm.h>
|
|
|
|
#if IS_IN (libc)
|
|
# define STRCHR_NAME __strchr_aligned
|
|
#else
|
|
# define STRCHR_NAME strchr
|
|
#endif
|
|
|
|
LEAF(STRCHR_NAME, 6)
|
|
slli.d t1, a0, 3
|
|
bstrins.d a0, zero, 2, 0
|
|
lu12i.w a2, 0x01010
|
|
ld.d t2, a0, 0
|
|
|
|
ori a2, a2, 0x101
|
|
andi a1, a1, 0xff
|
|
bstrins.d a2, a2, 63, 32
|
|
li.w t0, -1
|
|
|
|
mul.d a1, a1, a2
|
|
sll.d t0, t0, t1
|
|
slli.d a3, a2, 7
|
|
orn t2, t2, t0
|
|
|
|
sll.d t3, a1, t1
|
|
xor t4, t2, t3
|
|
sub.d a4, t2, a2
|
|
sub.d a5, t4, a2
|
|
|
|
|
|
andn a4, a4, t2
|
|
andn a5, a5, t4
|
|
or t0, a4, a5
|
|
and t0, t0, a3
|
|
|
|
bnez t0, L(end)
|
|
addi.d a0, a0, 8
|
|
L(loop):
|
|
ld.d t4, a0, 0
|
|
xor t2, t4, a1
|
|
|
|
sub.d a4, t4, a2
|
|
sub.d a5, t2, a2
|
|
andn a4, a4, t4
|
|
andn a5, a5, t2
|
|
|
|
or t0, a4, a5
|
|
and t0, t0, a3
|
|
bnez t0, L(end)
|
|
ld.d t4, a0, 8
|
|
|
|
|
|
addi.d a0, a0, 16
|
|
xor t2, t4, a1
|
|
sub.d a4, t4, a2
|
|
sub.d a5, t2, a2
|
|
|
|
andn a4, a4, t4
|
|
andn a5, a5, t2
|
|
or t0, a4, a5
|
|
and t0, t0, a3
|
|
|
|
beqz t0, L(loop)
|
|
addi.d a0, a0, -8
|
|
L(end):
|
|
and t0, a5, a3
|
|
and t1, a4, a3
|
|
|
|
ctz.d t0, t0
|
|
ctz.d t1, t1
|
|
srli.w t2, t0, 3
|
|
sltu t3, t1, t0
|
|
|
|
|
|
add.d a0, a0, t2
|
|
masknez a0, a0, t3
|
|
jr ra
|
|
END(STRCHR_NAME)
|