forked from OSchip/llvm-project
52 lines
1.2 KiB
ArmAsm
52 lines
1.2 KiB
ArmAsm
/*
|
|
* memcmp - compare memory
|
|
*
|
|
* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
* See https://llvm.org/LICENSE.txt for license information.
|
|
* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
*/
|
|
|
|
#if __ARM_FEATURE_SVE
|
|
/* Assumptions:
|
|
*
|
|
* ARMv8-a, AArch64
|
|
* SVE Available.
|
|
*/
|
|
|
|
.arch armv8-a+sve
|
|
.text
|
|
|
|
.globl __memcmp_aarch64_sve
|
|
.type __memcmp_aarch64_sve, %function
|
|
.p2align 4
|
|
__memcmp_aarch64_sve:
|
|
mov x3, 0 /* initialize off */
|
|
|
|
0: whilelo p0.b, x3, x2 /* while off < max */
|
|
b.none 9f
|
|
|
|
ld1b z0.b, p0/z, [x0, x3] /* read vectors bounded by max. */
|
|
ld1b z1.b, p0/z, [x1, x3]
|
|
|
|
/* Increment for a whole vector, even if we've only read a partial.
|
|
This is significantly cheaper than INCP, and since OFF is not
|
|
used after the loop it is ok to increment OFF past MAX. */
|
|
incb x3
|
|
|
|
cmpne p1.b, p0/z, z0.b, z1.b /* while no inequalities */
|
|
b.none 0b
|
|
|
|
/* Found inequality. */
|
|
1: brkb p1.b, p0/z, p1.b /* find first such */
|
|
lasta w0, p1, z0.b /* extract each byte */
|
|
lasta w1, p1, z1.b
|
|
sub x0, x0, x1 /* return comparison */
|
|
ret
|
|
|
|
/* Found end-of-count. */
|
|
9: mov x0, 0 /* return equality */
|
|
ret
|
|
|
|
.size __memcmp_aarch64_sve, . - __memcmp_aarch64_sve
|
|
#endif
|