foundationdb/flow/aarch64/memcmp.S

136 lines
2.7 KiB
ArmAsm

/* memcmp - compare memory
*
* Copyright (c) 2013-2020, Arm Limited.
* SPDX-License-Identifier: MIT
*/
/* Assumptions:
*
* ARMv8-a, AArch64, unaligned accesses.
*/
#include "asmdefs.h"
/* Parameters and result. */
#define src1 x0
#define src2 x1
#define limit x2
#define result w0
/* Internal variables. */
#define data1 x3
#define data1w w3
#define data1h x4
#define data2 x5
#define data2w w5
#define data2h x6
#define tmp1 x7
#define tmp2 x8
ENTRY (memcmp)
PTR_ARG (0)
PTR_ARG (1)
SIZE_ARG (2)
subs limit, limit, 8
b.lo L(less8)
ldr data1, [src1], 8
ldr data2, [src2], 8
cmp data1, data2
b.ne L(return)
subs limit, limit, 8
b.gt L(more16)
ldr data1, [src1, limit]
ldr data2, [src2, limit]
b L(return)
L(more16):
ldr data1, [src1], 8
ldr data2, [src2], 8
cmp data1, data2
bne L(return)
/* Jump directly to comparing the last 16 bytes for 32 byte (or less)
strings. */
subs limit, limit, 16
b.ls L(last_bytes)
/* We overlap loads between 0-32 bytes at either side of SRC1 when we
try to align, so limit it only to strings larger than 128 bytes. */
cmp limit, 96
b.ls L(loop16)
/* Align src1 and adjust src2 with bytes not yet done. */
and tmp1, src1, 15
add limit, limit, tmp1
sub src1, src1, tmp1
sub src2, src2, tmp1
/* Loop performing 16 bytes per iteration using aligned src1.
Limit is pre-decremented by 16 and must be larger than zero.
Exit if <= 16 bytes left to do or if the data is not equal. */
.p2align 4
L(loop16):
ldp data1, data1h, [src1], 16
ldp data2, data2h, [src2], 16
subs limit, limit, 16
ccmp data1, data2, 0, hi
ccmp data1h, data2h, 0, eq
b.eq L(loop16)
cmp data1, data2
bne L(return)
mov data1, data1h
mov data2, data2h
cmp data1, data2
bne L(return)
/* Compare last 1-16 bytes using unaligned access. */
L(last_bytes):
add src1, src1, limit
add src2, src2, limit
ldp data1, data1h, [src1]
ldp data2, data2h, [src2]
cmp data1, data2
bne L(return)
mov data1, data1h
mov data2, data2h
cmp data1, data2
/* Compare data bytes and set return value to 0, -1 or 1. */
L(return):
#ifndef __AARCH64EB__
rev data1, data1
rev data2, data2
#endif
cmp data1, data2
L(ret_eq):
cset result, ne
cneg result, result, lo
ret
.p2align 4
/* Compare up to 8 bytes. Limit is [-8..-1]. */
L(less8):
adds limit, limit, 4
b.lo L(less4)
ldr data1w, [src1], 4
ldr data2w, [src2], 4
cmp data1w, data2w
b.ne L(return)
sub limit, limit, 4
L(less4):
adds limit, limit, 4
beq L(ret_eq)
L(byte_loop):
ldrb data1w, [src1], 1
ldrb data2w, [src2], 1
subs limit, limit, 1
ccmp data1w, data2w, 0, ne /* NZCV = 0b0000. */
b.eq L(byte_loop)
sub result, data1w, data2w
ret
END (memcmp)