概要
- らずぱい３で、aarch64のUnixBenchも、とりたい
-
openSUSEのRPi3向け配布イメージは、aarch64対応している
aarch64# uname -a Linux linux.suse 4.4.49-16-default #1 SMP Sun Feb 19 17:40:35 UTC 2017 (70e9954) aarch64 aarch64 aarch64 GNU/Linux
環境
- Raspberry Pi 3
- openSUSE-Leap42.2-ARM-XFCE-raspberrypi3.aarch64.raw.xz
HCL:Raspberry_Pi3 ページから
> Installing the 64-bit openSUSE Leap image > XFCEイメージ選択- デフォルトログイン > ユーザ: root / パスワード: linux
- UART:115200bpsで、接続するのが、簡単かも。
手順
- いつものツールでmicroSDにやく。
- 起動
- sshでログイン
/etc/sshd/sshd_configをrootでログイン可能+パスワード使用可能、と編集して、systemctl restart sshd - パッケージ導入は、
zypper install ほにゃららで。
BYTE UNIX Benchmarks (Version 5.1.3)
- ここら辺をインストール
zypper install make git-core gcc -
Makefileを編集 (
-march=native -mtune=nativeがあるとエラー出る)diff --git a/UnixBench/Makefile b/UnixBench/Makefile index d6868ba..1dd7e42 100644 --- a/UnixBench/Makefile +++ b/UnixBench/Makefile @@ -87,7 +87,7 @@ OPTON = -O3 -ffast-math OSNAME:=$(shell uname -s) ifeq ($(OSNAME),Linux) -OPTON += -march=native -mtune=native +#OPTON += -march=native -mtune=native endif ifeq ($(OSNAME),Darwin) # (adjust flags or comment out this section for older versions of XCode or OS X)
結果: Benchmark of linux.suse / openSUSE 42.2 (aarch64) on Wed Mar 22 2017
BYTE UNIX Benchmarks (Version 5.1.3)
Test System Information
| System: | linux.suse: openSUSE 42.2 (aarch64) | |
| OS: | GNU/Linux -- 4.4.49-16-default -- #1 SMP Sun Feb 19 17:40:35 UTC 2017 (70e9954) | |
| Machine: | aarch64: aarch64 | |
| Language: | en_US.utf8 (charmap="UTF-8", collate="UTF-8") | |
| Uptime: | 20:08pm up 0:07, 2 users, load average: 1.12, 0.80, 0.42; runlevel 1970-01-01 | |
Benchmark Run: 4 CPUs; 1 parallel process
Time: 20:08:40 - 20:37:56; 29m 16s
System Benchmarks
| Test | Score | Unit | Time | Iters. | Baseline | Index |
|---|---|---|---|---|---|---|
| Dhrystone 2 using register variables | 3379589.7 | lps | 10.0 s | 7 | 116700.0 | 289.6 |
| Double-Precision Whetstone | 610.0 | MWIPS | 12.0 s | 7 | 55.0 | 110.9 |
| Execl Throughput | 1049.4 | lps | 29.6 s | 2 | 43.0 | 244.0 |
| File Copy 1024 bufsize 2000 maxblocks | 109187.0 | KBps | 30.0 s | 2 | 3960.0 | 275.7 |
| File Copy 256 bufsize 500 maxblocks | 39170.3 | KBps | 30.0 s | 2 | 1655.0 | 236.7 |
| File Copy 4096 bufsize 8000 maxblocks | 270879.3 | KBps | 30.0 s | 2 | 5800.0 | 467.0 |
| Pipe Throughput | 212769.9 | lps | 10.0 s | 7 | 12440.0 | 171.0 |
| Pipe-based Context Switching | 57328.4 | lps | 10.0 s | 7 | 4000.0 | 143.3 |
| Process Creation | 2708.7 | lps | 30.0 s | 2 | 126.0 | 215.0 |
| Shell Scripts (1 concurrent) | 1438.3 | lpm | 60.0 s | 2 | 42.4 | 339.2 |
| Shell Scripts (8 concurrent) | 419.0 | lpm | 60.1 s | 2 | 6.0 | 698.3 |
| System Call Overhead | 247097.0 | lps | 10.0 s | 7 | 15000.0 | 164.7 |
| System Benchmarks Index Score: | 246.0 | |||||
Benchmark Run: 4 CPUs; 4 parallel processes
Time: 20:37:56 - 21:06:55; 28m 59s
System Benchmarks
| Test | Score | Unit | Time | Iters. | Baseline | Index |
|---|---|---|---|---|---|---|
| Dhrystone 2 using register variables | 23353355.0 | lps | 10.0 s | 7 | 116700.0 | 2001.1 |
| Double-Precision Whetstone | 4196.7 | MWIPS | 9.9 s | 7 | 55.0 | 763.0 |
| Execl Throughput | 2651.0 | lps | 29.9 s | 2 | 43.0 | 616.5 |
| File Copy 1024 bufsize 2000 maxblocks | 278507.9 | KBps | 30.0 s | 2 | 3960.0 | 703.3 |
| File Copy 256 bufsize 500 maxblocks | 76708.0 | KBps | 30.0 s | 2 | 1655.0 | 463.5 |
| File Copy 4096 bufsize 8000 maxblocks | 671709.4 | KBps | 30.0 s | 2 | 5800.0 | 1158.1 |
| Pipe Throughput | 1345451.5 | lps | 10.0 s | 7 | 12440.0 | 1081.6 |
| Pipe-based Context Switching | 246604.4 | lps | 10.0 s | 7 | 4000.0 | 616.5 |
| Process Creation | 7088.1 | lps | 30.0 s | 2 | 126.0 | 562.5 |
| Shell Scripts (1 concurrent) | 3253.0 | lpm | 60.1 s | 2 | 42.4 | 767.2 |
| Shell Scripts (8 concurrent) | 440.3 | lpm | 60.3 s | 2 | 6.0 | 733.8 |
| System Call Overhead | 1562405.9 | lps | 10.0 s | 7 | 15000.0 | 1041.6 |
| System Benchmarks Index Score: | 808.6 | |||||
コンソールログ
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
Version 5.1.3 Based on the Byte Magazine Unix Benchmark
Multi-CPU version Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011 johantheghost at yahoo period com
1 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10
1 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10
1 x Execl Throughput 1 2 3
1 x File Copy 1024 bufsize 2000 maxblocks 1 2 3
1 x File Copy 256 bufsize 500 maxblocks 1 2 3
1 x File Copy 4096 bufsize 8000 maxblocks 1 2 3
1 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10
1 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10
1 x Process Creation 1 2 3
1 x System Call Overhead 1 2 3 4 5 6 7 8 9 10
1 x Shell Scripts (1 concurrent) 1 2 3
1 x Shell Scripts (8 concurrent) 1 2 3
4 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10
4 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10
4 x Execl Throughput 1 2 3
4 x File Copy 1024 bufsize 2000 maxblocks 1 2 3
4 x File Copy 256 bufsize 500 maxblocks 1 2 3
4 x File Copy 4096 bufsize 8000 maxblocks 1 2 3
4 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10
4 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10
4 x Process Creation 1 2 3
4 x System Call Overhead 1 2 3 4 5 6 7 8 9 10
4 x Shell Scripts (1 concurrent) 1 2 3
4 x Shell Scripts (8 concurrent) 1 2 3
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: linux.suse: openSUSE 42.2 (aarch64)
OS: GNU/Linux -- 4.4.49-16-default -- #1 SMP Sun Feb 19 17:40:35 UTC 2017 (70e9954)
Machine: aarch64 (aarch64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
20:08pm up 0:07, 2 users, load average: 1.12, 0.80, 0.42; runlevel 1970-01-01
------------------------------------------------------------------------
Benchmark Run: Wed Mar 22 2017 20:08:40 - 20:37:56
4 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 3379589.7 lps (10.0 s, 7 samples)
Double-Precision Whetstone 610.0 MWIPS (12.0 s, 7 samples)
Execl Throughput 1049.4 lps (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 109187.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 39170.3 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 270879.3 KBps (30.0 s, 2 samples)
Pipe Throughput 212769.9 lps (10.0 s, 7 samples)
Pipe-based Context Switching 57328.4 lps (10.0 s, 7 samples)
Process Creation 2708.7 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 1438.3 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 419.0 lpm (60.1 s, 2 samples)
System Call Overhead 247097.0 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 3379589.7 289.6
Double-Precision Whetstone 55.0 610.0 110.9
Execl Throughput 43.0 1049.4 244.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 109187.0 275.7
File Copy 256 bufsize 500 maxblocks 1655.0 39170.3 236.7
File Copy 4096 bufsize 8000 maxblocks 5800.0 270879.3 467.0
Pipe Throughput 12440.0 212769.9 171.0
Pipe-based Context Switching 4000.0 57328.4 143.3
Process Creation 126.0 2708.7 215.0
Shell Scripts (1 concurrent) 42.4 1438.3 339.2
Shell Scripts (8 concurrent) 6.0 419.0 698.3
System Call Overhead 15000.0 247097.0 164.7
========
System Benchmarks Index Score 246.0
------------------------------------------------------------------------
Benchmark Run: Wed Mar 22 2017 20:37:56 - 21:06:55
4 CPUs in system; running 4 parallel copies of tests
Dhrystone 2 using register variables 23353355.0 lps (10.0 s, 7 samples)
Double-Precision Whetstone 4196.7 MWIPS (9.9 s, 7 samples)
Execl Throughput 2651.0 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 278507.9 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 76708.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 671709.4 KBps (30.0 s, 2 samples)
Pipe Throughput 1345451.5 lps (10.0 s, 7 samples)
Pipe-based Context Switching 246604.4 lps (10.0 s, 7 samples)
Process Creation 7088.1 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 3253.0 lpm (60.1 s, 2 samples)
Shell Scripts (8 concurrent) 440.3 lpm (60.3 s, 2 samples)
System Call Overhead 1562405.9 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 23353355.0 2001.1
Double-Precision Whetstone 55.0 4196.7 763.0
Execl Throughput 43.0 2651.0 616.5
File Copy 1024 bufsize 2000 maxblocks 3960.0 278507.9 703.3
File Copy 256 bufsize 500 maxblocks 1655.0 76708.0 463.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 671709.4 1158.1
Pipe Throughput 12440.0 1345451.5 1081.6
Pipe-based Context Switching 4000.0 246604.4 616.5
Process Creation 126.0 7088.1 562.5
Shell Scripts (1 concurrent) 42.4 3253.0 767.2
Shell Scripts (8 concurrent) 6.0 440.3 733.8
System Call Overhead 15000.0 1562405.9 1041.6
========
System Benchmarks Index Score 808.6
linux:~/byte-unixbench/UnixBench # uname -a
Linux linux.suse 4.4.49-16-default #1 SMP Sun Feb 19 17:40:35 UTC 2017 (70e9954) aarch64 aarch64 aarch64 GNU/Linux
linux:~/byte-unixbench/UnixBench # cat /etc/issue
Welcome to openSUSE Leap 42.2 - Kernel \r (\l).
linux:~/byte-unixbench/UnixBench # cat /proc/cpuinfo
processor : 0
BogoMIPS : 38.40
Features : fp asimd evtstrm crc32
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x0
CPU part : 0xd03
CPU revision : 4
processor : 1
BogoMIPS : 38.40
Features : fp asimd evtstrm crc32
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x0
CPU part : 0xd03
CPU revision : 4
processor : 2
BogoMIPS : 38.40
Features : fp asimd evtstrm crc32
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x0
CPU part : 0xd03
CPU revision : 4
processor : 3
BogoMIPS : 38.40
Features : fp asimd evtstrm crc32
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x0
CPU part : 0xd03
CPU revision : 4
linux:~/byte-unixbench/UnixBench #