mirror of
https://sourceware.org/git/glibc.git
synced 2025-09-11 12:10:50 +03:00
106 lines
2.7 KiB
ArmAsm
106 lines
2.7 KiB
ArmAsm
/* Optimized memrchr implementation using LoongArch LSX instructions.
|
|
Copyright (C) 2023-2025 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) && !defined __loongarch_soft_float
|
|
|
|
# define MEMRCHR __memrchr_lsx
|
|
|
|
LEAF(MEMRCHR, 6)
|
|
beqz a2, L(ret0)
|
|
addi.d a2, a2, -1
|
|
add.d a3, a0, a2
|
|
andi t1, a3, 0x1f
|
|
|
|
bstrins.d a3, zero, 4, 0
|
|
addi.d t1, t1, 1
|
|
vld vr0, a3, 0
|
|
vld vr1, a3, 16
|
|
|
|
sub.d t2, zero, t1
|
|
li.d t3, -1
|
|
vreplgr2vr.b vr2, a1
|
|
andi t4, a0, 0x1f
|
|
|
|
srl.d t2, t3, t2
|
|
vseq.b vr0, vr0, vr2
|
|
vseq.b vr1, vr1, vr2
|
|
vmsknz.b vr0, vr0
|
|
|
|
|
|
vmsknz.b vr1, vr1
|
|
vilvl.h vr0, vr1, vr0
|
|
movfr2gr.s t0, fa0
|
|
and t0, t0, t2
|
|
|
|
bltu a2, t1, L(end)
|
|
bnez t0, L(found)
|
|
bstrins.d a0, zero, 4, 0
|
|
L(loop):
|
|
vld vr0, a3, -32
|
|
|
|
vld vr1, a3, -16
|
|
addi.d a3, a3, -32
|
|
vseq.b vr0, vr0, vr2
|
|
vseq.b vr1, vr1, vr2
|
|
|
|
beq a0, a3, L(out)
|
|
vmax.bu vr3, vr0, vr1
|
|
vseteqz.v fcc0, vr3
|
|
bcnez fcc0, L(loop)
|
|
|
|
|
|
vmsknz.b vr0, vr0
|
|
vmsknz.b vr1, vr1
|
|
vilvl.h vr0, vr1, vr0
|
|
movfr2gr.s t0, fa0
|
|
|
|
L(found):
|
|
addi.d a0, a3, 31
|
|
clz.w t1, t0
|
|
sub.d a0, a0, t1
|
|
jr ra
|
|
|
|
L(out):
|
|
vmsknz.b vr0, vr0
|
|
vmsknz.b vr1, vr1
|
|
vilvl.h vr0, vr1, vr0
|
|
movfr2gr.s t0, fa0
|
|
|
|
L(end):
|
|
sll.d t2, t3, t4
|
|
and t0, t0, t2
|
|
addi.d a0, a3, 31
|
|
clz.w t1, t0
|
|
|
|
|
|
sub.d a0, a0, t1
|
|
maskeqz a0, a0, t0
|
|
jr ra
|
|
L(ret0):
|
|
move a0, zero
|
|
|
|
jr ra
|
|
END(MEMRCHR)
|
|
|
|
libc_hidden_builtin_def (MEMRCHR)
|
|
#endif
|