Files
clang-p2996/libc/AOR_v20.02/string/aarch64/memset.S
Kristof Beyls 0928368f62 [libc] Provide Arm Optimized Routines for the LLVM libc project.
This adds the Arm Optimized Routines (see
https://github.com/ARM-software/optimized-routines) source code under the
the LLVM license. The version of the code provided in this patch is v20.02
of the Arm Optimized Routines project.

This entire contribution is being committed as is even though it does
not currently fit the LLVM libc model and does not follow the LLVM
coding style. In the near future, implementations from this patch will be
moved over to their right place in the LLVM-libc tree. This will be done
over many small patches, all of which will go through the normal LLVM code
review process. See this libc-dev post for the plan:
http://lists.llvm.org/pipermail/libc-dev/2020-March/000044.html

Differential revision of the original upload: https://reviews.llvm.org/D75355
2020-03-16 12:19:31 -07:00

116 lines
2.2 KiB
ArmAsm

/*
* memset - fill memory with a constant byte
*
* 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
*/
/* Assumptions:
*
* ARMv8-a, AArch64, Advanced SIMD, unaligned accesses.
*
*/
#include "../asmdefs.h"
#define dstin x0
#define val x1
#define valw w1
#define count x2
#define dst x3
#define dstend x4
#define zva_val x5
ENTRY (__memset_aarch64)
dup v0.16B, valw
add dstend, dstin, count
cmp count, 96
b.hi L(set_long)
cmp count, 16
b.hs L(set_medium)
mov val, v0.D[0]
/* Set 0..15 bytes. */
tbz count, 3, 1f
str val, [dstin]
str val, [dstend, -8]
ret
nop
1: tbz count, 2, 2f
str valw, [dstin]
str valw, [dstend, -4]
ret
2: cbz count, 3f
strb valw, [dstin]
tbz count, 1, 3f
strh valw, [dstend, -2]
3: ret
/* Set 17..96 bytes. */
L(set_medium):
str q0, [dstin]
tbnz count, 6, L(set96)
str q0, [dstend, -16]
tbz count, 5, 1f
str q0, [dstin, 16]
str q0, [dstend, -32]
1: ret
.p2align 4
/* Set 64..96 bytes. Write 64 bytes from the start and
32 bytes from the end. */
L(set96):
str q0, [dstin, 16]
stp q0, q0, [dstin, 32]
stp q0, q0, [dstend, -32]
ret
.p2align 4
L(set_long):
and valw, valw, 255
bic dst, dstin, 15
str q0, [dstin]
cmp count, 160
ccmp valw, 0, 0, hs
b.ne L(no_zva)
#ifndef SKIP_ZVA_CHECK
mrs zva_val, dczid_el0
and zva_val, zva_val, 31
cmp zva_val, 4 /* ZVA size is 64 bytes. */
b.ne L(no_zva)
#endif
str q0, [dst, 16]
stp q0, q0, [dst, 32]
bic dst, dst, 63
sub count, dstend, dst /* Count is now 64 too large. */
sub count, count, 128 /* Adjust count and bias for loop. */
.p2align 4
L(zva_loop):
add dst, dst, 64
dc zva, dst
subs count, count, 64
b.hi L(zva_loop)
stp q0, q0, [dstend, -64]
stp q0, q0, [dstend, -32]
ret
L(no_zva):
sub count, dstend, dst /* Count is 16 too large. */
sub dst, dst, 16 /* Dst is biased by -32. */
sub count, count, 64 + 16 /* Adjust count and bias for loop. */
L(no_zva_loop):
stp q0, q0, [dst, 32]
stp q0, q0, [dst, 64]!
subs count, count, 64
b.hi L(no_zva_loop)
stp q0, q0, [dstend, -64]
stp q0, q0, [dstend, -32]
ret
END (__memset_aarch64)