Optimize strcat/strcpy, small tweaks to strlen. DO NOT MERGE
Create one version of strcat/strcpy/strlen for cortex-a15/krait and another
version for cortex-a9.
Tested with the libc_test strcat/strcpy/strlen tests.
Including new tests that verify that the src for strcat/strcpy do not
overread across page boundaries.
NOTE: The handling of unaligned strcpy (same code in strcat) could probably
be optimized further such that the src is read 64 bits at a time instead of
the partial reads occurring now.
strlen improves slightly since it was recently optimized.
Performance improvements for strcpy and strcat (using an empty dest string):
cortex-a9
- Small copies vary from about 5% to 20% as the size gets above 10 bytes.
- Copies >= 1024, about a 60% improvement.
- Unaligned copies, from about 40% improvement.
cortex-a15
- Most small copies exhibit a 100% improvement, a few copies only
improve by 20%.
- Copies >= 1024, about 150% improvement.
- Unaligned copies, about 100% improvement.
krait
- Most small copies vary widely, but on average 20% improvement, then
the performance gets better, hitting about a 100% improvement when
copies 64 bytes of data.
- Copies >= 1024, about 100% improvement.
- When coping MBs of data, about 50% improvement.
- Unaligned copies, about 90% improvement.
As strcat destination strings get larger in size:
cortex-a9
- about 40% improvement for small dst strings (>= 32).
- about 250% improvement for dst strings >= 1024.
cortex-a15
- about 200% improvement for small dst strings (>=32).
- about 250% improvement for dst strings >= 1024.
krait
- about 25% improvement for small dst strings (>=32).
- about 100% improvement for dst strings >=1024.
Merge from internal master.
(cherry-picked from d119b7b6f48fe507088cfb98bcafa99b320fd884)
Change-Id: I296463b251ef9fab004ee4dded2793feca5b547a
2013-07-15 19:49:26 +00:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2013 The Android Open Source Project
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
* 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 OWNER 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) 2013 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.
|
|
|
|
*/
|
|
|
|
|
2014-02-20 00:53:20 +00:00
|
|
|
#include <private/bionic_asm.h>
|
Optimize strcat/strcpy, small tweaks to strlen. DO NOT MERGE
Create one version of strcat/strcpy/strlen for cortex-a15/krait and another
version for cortex-a9.
Tested with the libc_test strcat/strcpy/strlen tests.
Including new tests that verify that the src for strcat/strcpy do not
overread across page boundaries.
NOTE: The handling of unaligned strcpy (same code in strcat) could probably
be optimized further such that the src is read 64 bits at a time instead of
the partial reads occurring now.
strlen improves slightly since it was recently optimized.
Performance improvements for strcpy and strcat (using an empty dest string):
cortex-a9
- Small copies vary from about 5% to 20% as the size gets above 10 bytes.
- Copies >= 1024, about a 60% improvement.
- Unaligned copies, from about 40% improvement.
cortex-a15
- Most small copies exhibit a 100% improvement, a few copies only
improve by 20%.
- Copies >= 1024, about 150% improvement.
- Unaligned copies, about 100% improvement.
krait
- Most small copies vary widely, but on average 20% improvement, then
the performance gets better, hitting about a 100% improvement when
copies 64 bytes of data.
- Copies >= 1024, about 100% improvement.
- When coping MBs of data, about 50% improvement.
- Unaligned copies, about 90% improvement.
As strcat destination strings get larger in size:
cortex-a9
- about 40% improvement for small dst strings (>= 32).
- about 250% improvement for dst strings >= 1024.
cortex-a15
- about 200% improvement for small dst strings (>=32).
- about 250% improvement for dst strings >= 1024.
krait
- about 25% improvement for small dst strings (>=32).
- about 100% improvement for dst strings >=1024.
Merge from internal master.
(cherry-picked from d119b7b6f48fe507088cfb98bcafa99b320fd884)
Change-Id: I296463b251ef9fab004ee4dded2793feca5b547a
2013-07-15 19:49:26 +00:00
|
|
|
|
|
|
|
.syntax unified
|
|
|
|
|
|
|
|
.thumb
|
|
|
|
.thumb_func
|
|
|
|
|
|
|
|
ENTRY(strlen)
|
|
|
|
pld [r0, #0]
|
|
|
|
mov r1, r0
|
|
|
|
|
|
|
|
ands r3, r0, #7
|
|
|
|
bne align_src
|
|
|
|
|
|
|
|
.p2align 2
|
|
|
|
mainloop:
|
|
|
|
ldmia r1!, {r2, r3}
|
|
|
|
|
|
|
|
pld [r1, #64]
|
|
|
|
|
|
|
|
sub ip, r2, #0x01010101
|
|
|
|
bic ip, ip, r2
|
|
|
|
ands ip, ip, #0x80808080
|
|
|
|
bne zero_in_first_register
|
|
|
|
|
|
|
|
sub ip, r3, #0x01010101
|
|
|
|
bic ip, ip, r3
|
|
|
|
ands ip, ip, #0x80808080
|
|
|
|
bne zero_in_second_register
|
|
|
|
b mainloop
|
|
|
|
|
|
|
|
zero_in_first_register:
|
|
|
|
sub r0, r1, r0
|
|
|
|
// Check for zero in byte 0.
|
|
|
|
lsls r2, ip, #17
|
|
|
|
beq check_byte1_reg1
|
|
|
|
|
|
|
|
sub r0, r0, #8
|
|
|
|
bx lr
|
|
|
|
|
|
|
|
check_byte1_reg1:
|
|
|
|
bcc check_byte2_reg1
|
|
|
|
|
|
|
|
sub r0, r0, #7
|
|
|
|
bx lr
|
|
|
|
|
|
|
|
check_byte2_reg1:
|
|
|
|
// Check for zero in byte 2.
|
|
|
|
tst ip, #0x800000
|
|
|
|
itt ne
|
|
|
|
subne r0, r0, #6
|
|
|
|
bxne lr
|
|
|
|
sub r0, r0, #5
|
|
|
|
bx lr
|
|
|
|
|
|
|
|
zero_in_second_register:
|
|
|
|
sub r0, r1, r0
|
|
|
|
// Check for zero in byte 0.
|
|
|
|
lsls r2, ip, #17
|
|
|
|
beq check_byte1_reg2
|
|
|
|
|
|
|
|
sub r0, r0, #4
|
|
|
|
bx lr
|
|
|
|
|
|
|
|
check_byte1_reg2:
|
|
|
|
bcc check_byte2_reg2
|
|
|
|
|
|
|
|
sub r0, r0, #3
|
|
|
|
bx lr
|
|
|
|
|
|
|
|
check_byte2_reg2:
|
|
|
|
// Check for zero in byte 2.
|
|
|
|
tst ip, #0x800000
|
|
|
|
itt ne
|
|
|
|
subne r0, r0, #2
|
|
|
|
bxne lr
|
|
|
|
sub r0, r0, #1
|
|
|
|
bx lr
|
|
|
|
|
|
|
|
align_src:
|
|
|
|
// Align to a double word (64 bits).
|
|
|
|
rsb r3, r3, #8
|
|
|
|
lsls ip, r3, #31
|
|
|
|
beq align_to_32
|
|
|
|
|
|
|
|
ldrb r2, [r1], #1
|
|
|
|
cbz r2, done
|
|
|
|
|
|
|
|
align_to_32:
|
|
|
|
bcc align_to_64
|
|
|
|
|
|
|
|
ldrb r2, [r1], #1
|
|
|
|
cbz r2, done
|
|
|
|
ldrb r2, [r1], #1
|
|
|
|
cbz r2, done
|
|
|
|
|
|
|
|
align_to_64:
|
|
|
|
tst r3, #4
|
|
|
|
beq mainloop
|
|
|
|
ldr r2, [r1], #4
|
|
|
|
|
|
|
|
sub ip, r2, #0x01010101
|
|
|
|
bic ip, ip, r2
|
|
|
|
ands ip, ip, #0x80808080
|
|
|
|
bne zero_in_second_register
|
|
|
|
b mainloop
|
|
|
|
|
|
|
|
done:
|
|
|
|
sub r0, r1, r0
|
|
|
|
sub r0, r0, #1
|
|
|
|
bx lr
|
|
|
|
END(strlen)
|