kernel_optimize_test/arch/powerpc/lib/copypage_64.S
Mark Nelson 57dda6ef5b powerpc: New copy_4K_page()
This new copy_4K_page() function was originally tuned for the best
performance on the Cell processor, but after testing on more 64bit
powerpc chips it was found that with a small modification it either
matched the performance offered by the current mainline version or
bettered it by a small amount.

It was found that on a Cell-based QS22 blade the amount of system
time measured when compiling a 2.6.26 pseries_defconfig decreased
by 4%. Using the same test, a 4-way 970MP machine saw a decrease of
2% in system time. No noticeable change was seen on Power4, Power5
or Power6.

The 4096 byte page is copied in thirty-two 128 byte strides. An
initial setup loop executes dcbt instructions for the whole source
page and dcbz instructions for the whole destination page. To do
this, the cache line size is retrieved from ppc64_caches.

A new CPU feature bit, CPU_FTR_CP_USE_DCBTZ, (introduced in the
previous patch) is used to make the modification to this new copy
routine - on Power4, 970 and Cell the feature bit is set so the
setup loop is executed, but on all other 64bit chips the setup
loop is nop'ed out.

Signed-off-by: Mark Nelson <markn@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-09-15 11:07:42 -07:00

108 lines
2.0 KiB
ArmAsm

/*
* Copyright (C) 2008 Mark Nelson, IBM Corp.
*
* 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/processor.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
.section ".toc","aw"
PPC64_CACHES:
.tc ppc64_caches[TC],ppc64_caches
.section ".text"
_GLOBAL(copy_4K_page)
li r5,4096 /* 4K page size */
BEGIN_FTR_SECTION
ld r10,PPC64_CACHES@toc(r2)
lwz r11,DCACHEL1LOGLINESIZE(r10) /* log2 of cache line size */
lwz r12,DCACHEL1LINESIZE(r10) /* get cache line size */
li r9,0
srd r8,r5,r11
mtctr r8
setup:
dcbt r9,r4
dcbz r9,r3
add r9,r9,r12
bdnz setup
END_FTR_SECTION_IFSET(CPU_FTR_CP_USE_DCBTZ)
addi r3,r3,-8
srdi r8,r5,7 /* page is copied in 128 byte strides */
addi r8,r8,-1 /* one stride copied outside loop */
mtctr r8
ld r5,0(r4)
ld r6,8(r4)
ld r7,16(r4)
ldu r8,24(r4)
1: std r5,8(r3)
ld r9,8(r4)
std r6,16(r3)
ld r10,16(r4)
std r7,24(r3)
ld r11,24(r4)
std r8,32(r3)
ld r12,32(r4)
std r9,40(r3)
ld r5,40(r4)
std r10,48(r3)
ld r6,48(r4)
std r11,56(r3)
ld r7,56(r4)
std r12,64(r3)
ld r8,64(r4)
std r5,72(r3)
ld r9,72(r4)
std r6,80(r3)
ld r10,80(r4)
std r7,88(r3)
ld r11,88(r4)
std r8,96(r3)
ld r12,96(r4)
std r9,104(r3)
ld r5,104(r4)
std r10,112(r3)
ld r6,112(r4)
std r11,120(r3)
ld r7,120(r4)
stdu r12,128(r3)
ldu r8,128(r4)
bdnz 1b
std r5,8(r3)
ld r9,8(r4)
std r6,16(r3)
ld r10,16(r4)
std r7,24(r3)
ld r11,24(r4)
std r8,32(r3)
ld r12,32(r4)
std r9,40(r3)
ld r5,40(r4)
std r10,48(r3)
ld r6,48(r4)
std r11,56(r3)
ld r7,56(r4)
std r12,64(r3)
ld r8,64(r4)
std r5,72(r3)
ld r9,72(r4)
std r6,80(r3)
ld r10,80(r4)
std r7,88(r3)
ld r11,88(r4)
std r8,96(r3)
ld r12,96(r4)
std r9,104(r3)
std r10,112(r3)
std r11,120(r3)
std r12,128(r3)
blr