223 lines
6.7 KiB
ArmAsm
223 lines
6.7 KiB
ArmAsm
/* Copyright (c) 2012-2013, Linaro Limited
|
|
All rights reserved.
|
|
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions are met:
|
|
* Redistributions of source code must retain the above copyright
|
|
notice, this list of conditions and the following disclaimer.
|
|
* Redistributions in binary form must reproduce the above copyright
|
|
notice, this list of conditions and the following disclaimer in the
|
|
documentation and/or other materials provided with the distribution.
|
|
* Neither the name of the Linaro nor the
|
|
names of its contributors may be used to endorse or promote products
|
|
derived from this software without specific prior written permission.
|
|
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */
|
|
|
|
/*
|
|
* Copyright (c) 2015 ARM Ltd
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
* 3. The name of the company may not be used to endorse or promote
|
|
* products derived from this software without specific prior written
|
|
* permission.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY ARM LTD ``AS IS'' AND ANY EXPRESS OR IMPLIED
|
|
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
|
* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
|
* IN NO EVENT SHALL ARM LTD BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
|
|
* TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
|
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
|
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
|
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
|
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
*/
|
|
|
|
/* Assumptions:
|
|
*
|
|
* ARMv8-a, AArch64, unaligned accesses.
|
|
*
|
|
*/
|
|
|
|
#if (defined (__OPTIMIZE_SIZE__) || defined (PREFER_SIZE_OVER_SPEED))
|
|
/* See memcpy-stub.c */
|
|
#else
|
|
|
|
#define dstin x0
|
|
#define src x1
|
|
#define count x2
|
|
#define dst x3
|
|
#define srcend x4
|
|
#define dstend x5
|
|
#define A_l x6
|
|
#define A_lw w6
|
|
#define A_h x7
|
|
#define A_hw w7
|
|
#define B_l x8
|
|
#define B_h x9
|
|
#define C_l x10
|
|
#define C_h x11
|
|
#define D_l x12
|
|
#define D_h x13
|
|
#define E_l src
|
|
#define E_h count
|
|
#define F_l srcend
|
|
#define F_h dst
|
|
#define tmp1 x9
|
|
|
|
#define L(l) .L ## l
|
|
|
|
.macro def_fn f p2align=0
|
|
.text
|
|
.p2align \p2align
|
|
.global \f
|
|
.type \f, %function
|
|
\f:
|
|
.endm
|
|
|
|
/* Copies are split into 3 main cases: small copies of up to 16 bytes,
|
|
medium copies of 17..96 bytes which are fully unrolled. Large copies
|
|
of more than 96 bytes align the destination and use an unrolled loop
|
|
processing 64 bytes per iteration.
|
|
Small and medium copies read all data before writing, allowing any
|
|
kind of overlap, and memmove tailcalls memcpy for these cases as
|
|
well as non-overlapping copies.
|
|
*/
|
|
|
|
def_fn memcpy p2align=6
|
|
add srcend, src, count
|
|
add dstend, dstin, count
|
|
cmp count, 96
|
|
b.hi L(copy_long)
|
|
cmp count, 16
|
|
b.hs L(copy_medium)
|
|
|
|
/* Small copies: 0..16 bytes. */
|
|
L(copy16):
|
|
tbz count, 3, 1f
|
|
ldr A_l, [src]
|
|
ldr A_h, [srcend, -8]
|
|
str A_l, [dstin]
|
|
str A_h, [dstend, -8]
|
|
ret
|
|
1:
|
|
tbz count, 2, 1f
|
|
ldr A_lw, [src]
|
|
ldr A_hw, [srcend, -4]
|
|
str A_lw, [dstin]
|
|
str A_hw, [dstend, -4]
|
|
ret
|
|
.p2align 4
|
|
1:
|
|
cbz count, 2f
|
|
ldrb A_lw, [src]
|
|
tbz count, 1, 1f
|
|
ldrh A_hw, [srcend, -2]
|
|
strh A_hw, [dstend, -2]
|
|
1: strb A_lw, [dstin]
|
|
2: ret
|
|
|
|
.p2align 4
|
|
/* Medium copies: 17..96 bytes. */
|
|
L(copy_medium):
|
|
ldp A_l, A_h, [src]
|
|
tbnz count, 6, L(copy96)
|
|
ldp D_l, D_h, [srcend, -16]
|
|
tbz count, 5, 1f
|
|
ldp B_l, B_h, [src, 16]
|
|
ldp C_l, C_h, [srcend, -32]
|
|
stp B_l, B_h, [dstin, 16]
|
|
stp C_l, C_h, [dstend, -32]
|
|
1:
|
|
stp A_l, A_h, [dstin]
|
|
stp D_l, D_h, [dstend, -16]
|
|
ret
|
|
|
|
.p2align 4
|
|
/* Copy 64..96 bytes. Copy 64 bytes from the start and
|
|
32 bytes from the end. */
|
|
L(copy96):
|
|
ldp B_l, B_h, [src, 16]
|
|
ldp C_l, C_h, [src, 32]
|
|
ldp D_l, D_h, [src, 48]
|
|
ldp E_l, E_h, [srcend, -32]
|
|
ldp F_l, F_h, [srcend, -16]
|
|
stp A_l, A_h, [dstin]
|
|
stp B_l, B_h, [dstin, 16]
|
|
stp C_l, C_h, [dstin, 32]
|
|
stp D_l, D_h, [dstin, 48]
|
|
stp E_l, E_h, [dstend, -32]
|
|
stp F_l, F_h, [dstend, -16]
|
|
ret
|
|
|
|
/* Align DST to 16 byte alignment so that we don't cross cache line
|
|
boundaries on both loads and stores. There are at least 96 bytes
|
|
to copy, so copy 16 bytes unaligned and then align. The loop
|
|
copies 64 bytes per iteration and prefetches one iteration ahead. */
|
|
|
|
.p2align 4
|
|
L(copy_long):
|
|
and tmp1, dstin, 15
|
|
bic dst, dstin, 15
|
|
ldp D_l, D_h, [src]
|
|
sub src, src, tmp1
|
|
add count, count, tmp1 /* Count is now 16 too large. */
|
|
ldp A_l, A_h, [src, 16]
|
|
stp D_l, D_h, [dstin]
|
|
ldp B_l, B_h, [src, 32]
|
|
ldp C_l, C_h, [src, 48]
|
|
ldp D_l, D_h, [src, 64]!
|
|
subs count, count, 128 + 16 /* Test and readjust count. */
|
|
b.ls 2f
|
|
1:
|
|
stp A_l, A_h, [dst, 16]
|
|
ldp A_l, A_h, [src, 16]
|
|
stp B_l, B_h, [dst, 32]
|
|
ldp B_l, B_h, [src, 32]
|
|
stp C_l, C_h, [dst, 48]
|
|
ldp C_l, C_h, [src, 48]
|
|
stp D_l, D_h, [dst, 64]!
|
|
ldp D_l, D_h, [src, 64]!
|
|
subs count, count, 64
|
|
b.hi 1b
|
|
|
|
/* Write the last full set of 64 bytes. The remainder is at most 64
|
|
bytes, so it is safe to always copy 64 bytes from the end even if
|
|
there is just 1 byte left. */
|
|
2:
|
|
ldp E_l, E_h, [srcend, -64]
|
|
stp A_l, A_h, [dst, 16]
|
|
ldp A_l, A_h, [srcend, -48]
|
|
stp B_l, B_h, [dst, 32]
|
|
ldp B_l, B_h, [srcend, -32]
|
|
stp C_l, C_h, [dst, 48]
|
|
ldp C_l, C_h, [srcend, -16]
|
|
stp D_l, D_h, [dst, 64]
|
|
stp E_l, E_h, [dstend, -64]
|
|
stp A_l, A_h, [dstend, -48]
|
|
stp B_l, B_h, [dstend, -32]
|
|
stp C_l, C_h, [dstend, -16]
|
|
ret
|
|
|
|
.size memcpy, . - memcpy
|
|
#endif
|