platform_bionic/libc/arch-arm64/generic/bionic/memcpy_base.S
Jake Weinstein 372f19e9e2 libc: ARM64: update memset/strlen/memcpy/memmove to newlib/cortex-strings
* Bionic benchmarks results at the bottom

* This is a squash of the following commits:

libc: ARM64: optimize memset.

 This is an optimized memset for AArch64.  Memset is split into 4 main
 cases: small sets of up to 16 bytes, medium of 16..96 bytes which are
 fully unrolled.  Large memsets of more than 96 bytes align the
 destination and use an unrolled loop processing 64 bytes per
 iteration.  Memsets of zero of more than 256 use the dc zva
 instruction, and there are faster versions for the common ZVA sizes 64
 or 128.  STP of Q registers is used to reduce codesize without loss of
 performance.

Change-Id: I0c5b5ec5ab8a1fd0f23eee8fbacada0be08e841f

libc: ARM64: improve performance in strlen

Change-Id: Ic20f93a0052a49bd76cd6795f51e8606ccfbf11c

libc: ARM64: Optimize memcpy.

 This is an optimized memcpy for AArch64.  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.  In order to share code with memmove, small and medium
 copies read all data before writing, allowing any kind of overlap.  On
 a random copy test memcpy is 40.8% faster on A57 and 28.4% on A53.

Change-Id: Ibb9483e45bbc0e8ca3d5ce98a31c55dfd8a5ac28

libc: AArch64: Tune memcpy

* Further tuning for performance.

Change-Id: Id08eaab885f9743fa7575077924a947c1b88e4ff

libc: ARM64: optimize memmove for Cortex-A53

* Sadly does not work on Denver or Kryo, so can't go to generic

 This is an optimized memmove for AArch64.  All copies of up to 96
 bytes and all backward copies are done by the new memcpy.  The only
 remaining case is large forward copies which are done in the same way
 as the memcpy loop, but copying from the end rather than the start.

Tested on the Nextbit Robin with MSM8992 (Snapdragon 808):

Before
BM_string_memcmp/8                          1000k         27    0.286 GiB/s
BM_string_memcmp/64                           50M         20    3.053 GiB/s
BM_string_memcmp/512                          20M        126    4.060 GiB/s
BM_string_memcmp/1024                         10M        234    4.372 GiB/s
BM_string_memcmp/8Ki                        1000k       1726    4.745 GiB/s
BM_string_memcmp/16Ki                        500k       3711    4.415 GiB/s
BM_string_memcmp/32Ki                        200k       8276    3.959 GiB/s
BM_string_memcmp/64Ki                        100k      16351    4.008 GiB/s
BM_string_memcpy/8                          1000k         13    0.612 GiB/s
BM_string_memcpy/64                         1000k          8    7.187 GiB/s
BM_string_memcpy/512                          50M         38   13.311 GiB/s
BM_string_memcpy/1024                         20M         86   11.858 GiB/s
BM_string_memcpy/8Ki                           5M        620   13.203 GiB/s
BM_string_memcpy/16Ki                       1000k       1265   12.950 GiB/s
BM_string_memcpy/32Ki                        500k       2977   11.004 GiB/s
BM_string_memcpy/64Ki                        500k       8003    8.188 GiB/s
BM_string_memmove/8                         1000k         11    0.684 GiB/s
BM_string_memmove/64                        1000k         16    3.855 GiB/s
BM_string_memmove/512                         50M         57    8.915 GiB/s
BM_string_memmove/1024                        20M        117    8.720 GiB/s
BM_string_memmove/8Ki                          2M        853    9.594 GiB/s
BM_string_memmove/16Ki                      1000k       1731    9.462 GiB/s
BM_string_memmove/32Ki                       500k       3566    9.189 GiB/s
BM_string_memmove/64Ki                       500k       7708    8.501 GiB/s
BM_string_memset/8                          1000k         16    0.487 GiB/s
BM_string_memset/64                         1000k         16    3.995 GiB/s
BM_string_memset/512                          50M         37   13.489 GiB/s
BM_string_memset/1024                         50M         58   17.405 GiB/s
BM_string_memset/8Ki                           5M        451   18.160 GiB/s
BM_string_memset/16Ki                          2M        883   18.554 GiB/s
BM_string_memset/32Ki                       1000k       2181   15.022 GiB/s
BM_string_memset/64Ki                        500k       4563   14.362 GiB/s
BM_string_strlen/8                          1000k          8    0.965 GiB/s
BM_string_strlen/64                         1000k         16    3.855 GiB/s
BM_string_strlen/512                          20M         92    5.540 GiB/s
BM_string_strlen/1024                         10M        167    6.111 GiB/s
BM_string_strlen/8Ki                        1000k       1237    6.620 GiB/s
BM_string_strlen/16Ki                       1000k       2765    5.923 GiB/s
BM_string_strlen/32Ki                        500k       6135    5.341 GiB/s
BM_string_strlen/64Ki                        200k      13168    4.977 GiB/s

After
BM_string_memcmp/8                          1000k         21    0.369 GiB/s
BM_string_memcmp/64                         1000k         28    2.272 GiB/s
BM_string_memcmp/512                          20M        128    3.983 GiB/s
BM_string_memcmp/1024                         10M        234    4.375 GiB/s
BM_string_memcmp/8Ki                        1000k       1732    4.728 GiB/s
BM_string_memcmp/16Ki                        500k       3485    4.701 GiB/s
BM_string_memcmp/32Ki                        500k       7031    4.660 GiB/s
BM_string_memcmp/64Ki                        200k      14296    4.584 GiB/s
BM_string_memcpy/8                          1000k          5    1.458 GiB/s
BM_string_memcpy/64                         1000k          7    8.952 GiB/s
BM_string_memcpy/512                          50M         36   13.907 GiB/s
BM_string_memcpy/1024                         20M         80   12.750 GiB/s
BM_string_memcpy/8Ki                           5M        572   14.307 GiB/s
BM_string_memcpy/16Ki                       1000k       1165   14.053 GiB/s
BM_string_memcpy/32Ki                        500k       3141   10.430 GiB/s
BM_string_memcpy/64Ki                        500k       7008    9.351 GiB/s
BM_string_memmove/8                           50M          7    1.074 GiB/s
BM_string_memmove/64                        1000k          9    6.593 GiB/s
BM_string_memmove/512                         50M         37   13.502 GiB/s
BM_string_memmove/1024                        20M         80   12.656 GiB/s
BM_string_memmove/8Ki                          5M        573   14.281 GiB/s
BM_string_memmove/16Ki                      1000k       1168   14.018 GiB/s
BM_string_memmove/32Ki                      1000k       2825   11.599 GiB/s
BM_string_memmove/64Ki                       500k       6548   10.008 GiB/s
BM_string_memset/8                          1000k          7    1.038 GiB/s
BM_string_memset/64                         1000k          8    7.151 GiB/s
BM_string_memset/512                        1000k         29   17.272 GiB/s
BM_string_memset/1024                         50M         53   18.969 GiB/s
BM_string_memset/8Ki                           5M        424   19.300 GiB/s
BM_string_memset/16Ki                          2M        846   19.350 GiB/s
BM_string_memset/32Ki                       1000k       2028   16.156 GiB/s
BM_string_memset/64Ki                        500k       4514   14.517 GiB/s
BM_string_strlen/8                          1000k          7    1.120 GiB/s
BM_string_strlen/64                         1000k         16    3.918 GiB/s
BM_string_strlen/512                          50M         64    7.894 GiB/s
BM_string_strlen/1024                         20M        104    9.815 GiB/s
BM_string_strlen/8Ki                           5M        664   12.337 GiB/s
BM_string_strlen/16Ki                       1000k       1291   12.682 GiB/s
BM_string_strlen/32Ki                       1000k       2940   11.143 GiB/s
BM_string_strlen/64Ki                        500k       6440   10.175 GiB/s

Change-Id: I635bd2798a755256f748b2af19b1a56fb85a40c6
2016-11-28 19:35:12 +00:00

217 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.
*
*/
#include <private/bionic_asm.h>
#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_lw w8
#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
/* 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.
*/
prfm PLDL1KEEP, [src]
add srcend, src, count
add dstend, dstin, count
cmp count, 16
b.ls L(copy16)
cmp count, 96
b.hi L(copy_long)
/* Medium copies: 17..96 bytes. */
sub tmp1, count, 1
ldp A_l, A_h, [src]
tbnz tmp1, 6, L(copy96)
ldp D_l, D_h, [srcend, -16]
tbz tmp1, 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
/* Small copies: 0..16 bytes. */
L(copy16):
cmp count, 8
b.lo 1f
ldr A_l, [src]
ldr A_h, [srcend, -8]
str A_l, [dstin]
str A_h, [dstend, -8]
ret
.p2align 4
1:
tbz count, 2, 1f
ldr A_lw, [src]
ldr A_hw, [srcend, -4]
str A_lw, [dstin]
str A_hw, [dstend, -4]
ret
/* Copy 0..3 bytes. Use a branchless sequence that copies the same
byte 3 times if count==1, or the 2nd byte twice if count==2. */
1:
cbz count, 2f
lsr tmp1, count, 1
ldrb A_lw, [src]
ldrb A_hw, [srcend, -1]
ldrb B_lw, [src, tmp1]
strb A_lw, [dstin]
strb B_lw, [dstin, tmp1]
strb A_hw, [dstend, -1]
2: 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