UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/arch/loongarch/lib/memset.S

92 lines
1.4 KiB
ArmAsm
Raw Normal View History

LoongArch: Use alternative to optimize libraries Use the alternative to optimize common libraries according whether CPU has UAL (hardware unaligned access support) feature, including memset(), memcopy(), memmove(), copy_user() and clear_user(). We have tested UnixBench on a Loongson-3A5000 quad-core machine (1.6GHz): 1, One copy, before patch: System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 9566582.0 819.8 Double-Precision Whetstone 55.0 2805.3 510.1 Execl Throughput 43.0 2120.0 493.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 209833.0 529.9 File Copy 256 bufsize 500 maxblocks 1655.0 89400.0 540.2 File Copy 4096 bufsize 8000 maxblocks 5800.0 320036.0 551.8 Pipe Throughput 12440.0 340624.0 273.8 Pipe-based Context Switching 4000.0 109939.1 274.8 Process Creation 126.0 4728.7 375.3 Shell Scripts (1 concurrent) 42.4 2223.1 524.3 Shell Scripts (8 concurrent) 6.0 883.1 1471.9 System Call Overhead 15000.0 518639.1 345.8 ======== System Benchmarks Index Score 500.2 2, One copy, after patch: System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 9567674.7 819.9 Double-Precision Whetstone 55.0 2805.5 510.1 Execl Throughput 43.0 2392.7 556.4 File Copy 1024 bufsize 2000 maxblocks 3960.0 417804.0 1055.1 File Copy 256 bufsize 500 maxblocks 1655.0 112909.5 682.2 File Copy 4096 bufsize 8000 maxblocks 5800.0 1255207.4 2164.2 Pipe Throughput 12440.0 555712.0 446.7 Pipe-based Context Switching 4000.0 99964.5 249.9 Process Creation 126.0 5192.5 412.1 Shell Scripts (1 concurrent) 42.4 2302.4 543.0 Shell Scripts (8 concurrent) 6.0 919.6 1532.6 System Call Overhead 15000.0 511159.3 340.8 ======== System Benchmarks Index Score 640.1 3, Four copies, before patch: System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 38268610.5 3279.2 Double-Precision Whetstone 55.0 11222.2 2040.4 Execl Throughput 43.0 7892.0 1835.3 File Copy 1024 bufsize 2000 maxblocks 3960.0 235149.6 593.8 File Copy 256 bufsize 500 maxblocks 1655.0 74959.6 452.9 File Copy 4096 bufsize 8000 maxblocks 5800.0 545048.5 939.7 Pipe Throughput 12440.0 1337359.0 1075.0 Pipe-based Context Switching 4000.0 473663.9 1184.2 Process Creation 126.0 17491.2 1388.2 Shell Scripts (1 concurrent) 42.4 6865.7 1619.3 Shell Scripts (8 concurrent) 6.0 1015.9 1693.1 System Call Overhead 15000.0 1899535.2 1266.4 ======== System Benchmarks Index Score 1278.3 4, Four copies, after patch: System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 38272815.5 3279.6 Double-Precision Whetstone 55.0 11222.8 2040.5 Execl Throughput 43.0 8839.2 2055.6 File Copy 1024 bufsize 2000 maxblocks 3960.0 313912.9 792.7 File Copy 256 bufsize 500 maxblocks 1655.0 80976.1 489.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 1176594.3 2028.6 Pipe Throughput 12440.0 2100941.9 1688.9 Pipe-based Context Switching 4000.0 476696.4 1191.7 Process Creation 126.0 18394.7 1459.9 Shell Scripts (1 concurrent) 42.4 7172.2 1691.6 Shell Scripts (8 concurrent) 6.0 1058.3 1763.9 System Call Overhead 15000.0 1874714.7 1249.8 ======== System Benchmarks Index Score 1488.8 Signed-off-by: Jun Yi <yijun@loongson.cn> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
2022-12-10 22:39:59 +08:00
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2020-2022 Loongson Technology Corporation Limited
*/
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/asmmacro.h>
#include <asm/cpu.h>
#include <asm/export.h>
#include <asm/regdef.h>
.macro fill_to_64 r0
bstrins.d \r0, \r0, 15, 8
bstrins.d \r0, \r0, 31, 16
bstrins.d \r0, \r0, 63, 32
.endm
SYM_FUNC_START(memset)
/*
* Some CPUs support hardware unaligned access
*/
ALTERNATIVE "b __memset_generic", \
"b __memset_fast", CPU_FEATURE_UAL
SYM_FUNC_END(memset)
EXPORT_SYMBOL(memset)
/*
* void *__memset_generic(void *s, int c, size_t n)
*
* a0: s
* a1: c
* a2: n
*/
SYM_FUNC_START(__memset_generic)
move a3, a0
beqz a2, 2f
1: st.b a1, a0, 0
addi.d a0, a0, 1
addi.d a2, a2, -1
bgt a2, zero, 1b
2: move a0, a3
jr ra
SYM_FUNC_END(__memset_generic)
/*
* void *__memset_fast(void *s, int c, size_t n)
*
* a0: s
* a1: c
* a2: n
*/
SYM_FUNC_START(__memset_fast)
move a3, a0
beqz a2, 3f
ori a4, zero, 64
blt a2, a4, 2f
/* fill a1 to 64 bits */
fill_to_64 a1
/* set 64 bytes at a time */
1: st.d a1, a0, 0
st.d a1, a0, 8
st.d a1, a0, 16
st.d a1, a0, 24
st.d a1, a0, 32
st.d a1, a0, 40
st.d a1, a0, 48
st.d a1, a0, 56
addi.d a0, a0, 64
addi.d a2, a2, -64
bge a2, a4, 1b
beqz a2, 3f
/* set the remaining bytes */
2: st.b a1, a0, 0
addi.d a0, a0, 1
addi.d a2, a2, -1
bgt a2, zero, 2b
/* return */
3: move a0, a3
jr ra
SYM_FUNC_END(__memset_fast)