mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-26 21:15:11 +07:00
2676b89eb8
At the time being, memcmp() compares two chunks of memory
byte per byte.
This patch optimises the comparison by comparing word by word.
On the same way as commit 15c2d45d17 ("powerpc: Add 64bit
optimised memcmp"), this patch moves memcmp() into a dedicated
file named memcmp_32.S
A small benchmark performed on an 8xx comparing two chuncks
of 512 bytes performed 100000 times gives:
Before : 5852274 TB ticks
After: 1488638 TB ticks
This is almost 4 times faster
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
70 lines
1.4 KiB
ArmAsm
70 lines
1.4 KiB
ArmAsm
/*
|
|
* String handling functions for PowerPC.
|
|
*
|
|
* Copyright (C) 1996 Paul Mackerras.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
#include <asm/ppc_asm.h>
|
|
#include <asm/export.h>
|
|
#include <asm/cache.h>
|
|
|
|
.text
|
|
|
|
/* This clears out any unused part of the destination buffer,
|
|
just as the libc version does. -- paulus */
|
|
_GLOBAL(strncpy)
|
|
PPC_LCMPI 0,r5,0
|
|
beqlr
|
|
mtctr r5
|
|
addi r6,r3,-1
|
|
addi r4,r4,-1
|
|
.balign IFETCH_ALIGN_BYTES
|
|
1: lbzu r0,1(r4)
|
|
cmpwi 0,r0,0
|
|
stbu r0,1(r6)
|
|
bdnzf 2,1b /* dec ctr, branch if ctr != 0 && !cr0.eq */
|
|
bnelr /* if we didn't hit a null char, we're done */
|
|
mfctr r5
|
|
PPC_LCMPI 0,r5,0 /* any space left in destination buffer? */
|
|
beqlr /* we know r0 == 0 here */
|
|
2: stbu r0,1(r6) /* clear it out if so */
|
|
bdnz 2b
|
|
blr
|
|
EXPORT_SYMBOL(strncpy)
|
|
|
|
_GLOBAL(strncmp)
|
|
PPC_LCMPI 0,r5,0
|
|
beq- 2f
|
|
mtctr r5
|
|
addi r5,r3,-1
|
|
addi r4,r4,-1
|
|
.balign IFETCH_ALIGN_BYTES
|
|
1: lbzu r3,1(r5)
|
|
cmpwi 1,r3,0
|
|
lbzu r0,1(r4)
|
|
subf. r3,r0,r3
|
|
beqlr 1
|
|
bdnzt eq,1b
|
|
blr
|
|
2: li r3,0
|
|
blr
|
|
EXPORT_SYMBOL(strncmp)
|
|
|
|
_GLOBAL(memchr)
|
|
PPC_LCMPI 0,r5,0
|
|
beq- 2f
|
|
mtctr r5
|
|
addi r3,r3,-1
|
|
.balign IFETCH_ALIGN_BYTES
|
|
1: lbzu r0,1(r3)
|
|
cmpw 0,r0,r4
|
|
bdnzf 2,1b
|
|
beqlr
|
|
2: li r3,0
|
|
blr
|
|
EXPORT_SYMBOL(memchr)
|