- 追加された行はこの色です。
- 削除された行はこの色です。
#author("2020-11-30T11:20:51+09:00","default:honma","honma")
#author("2020-11-30T14:17:48+09:00","default:honma","honma")
* UnixBench [#l0c6c656]
Unix系OSで昔から使われる定番のベンチマークツール。~
「Sun SPARCstation 20 SM61」という、1995年頃のコンピューターの値を10としたときの比較値。
** インストール [#jda5e976]
pi@raspberrypi:~ $ git clone https://github.com/kdlucas/byte-unixbench.git
** 実行 [#wa0366eb]
pi@raspberrypi:~ $ cd byte-unixbench/UnixBench
pi@raspberrypi:~/byte-unixbench/UnixBench $ ./Run
** 結果 [#g5aaad98]
Rasberry PI 3b+(1CPU) の結果
raspberry pi 3b+ の結果
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: raspberrypi: GNU/Linux
OS: GNU/Linux -- 5.4.75-v7+ -- #1 SMP Wed Nov 11 05:50:19 GMT 2020
Machine: armv7l (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: ARMv7 Processor rev 4 (v7l) (0.0 bogomips)
CPU 1: ARMv7 Processor rev 4 (v7l) (0.0 bogomips)
CPU 2: ARMv7 Processor rev 4 (v7l) (0.0 bogomips)
CPU 3: ARMv7 Processor rev 4 (v7l) (0.0 bogomips)
04:14:57 up 2 min, 3 users, load average: 0.22, 0.25, 0.10; runlevel Nov
------------------------------------------------------------------------
Benchmark Run: Mon Nov 30 2020 01:03:33 - 01:31:36
Benchmark Run: Mon Nov 30 2020 04:14:57 - 04:43:14
4 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 2327768.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 835.8 MWIPS (8.9 s, 7 samples)
Execl Throughput 394.8 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 65461.9 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 17712.4 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 185379.1 KBps (30.0 s, 2 samples)
Pipe Throughput 112648.8 lps (10.0 s, 7 samples)
Pipe-based Context Switching 19829.4 lps (10.0 s, 7 samples)
Process Creation 895.9 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 1042.4 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 300.1 lpm (60.1 s, 2 samples)
System Call Overhead 376537.2 lps (10.0 s, 7 samples)
Dhrystone 2 using register variables 2226539.7 lps (10.0 s, 7 samples)
Double-Precision Whetstone 609.8 MWIPS (10.0 s, 7 samples)
Execl Throughput 383.8 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 59366.3 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 16395.3 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 179096.8 KBps (30.0 s, 2 samples)
Pipe Throughput 91524.1 lps (10.0 s, 7 samples)
Pipe-based Context Switching 17886.8 lps (10.0 s, 7 samples)
Process Creation 856.6 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 1011.0 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 292.5 lpm (60.1 s, 2 samples)
System Call Overhead 295593.3 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 2327768.5 199.5
Double-Precision Whetstone 55.0 835.8 152.0
Execl Throughput 43.0 394.8 91.8
File Copy 1024 bufsize 2000 maxblocks 3960.0 65461.9 165.3
File Copy 256 bufsize 500 maxblocks 1655.0 17712.4 107.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 185379.1 319.6
Pipe Throughput 12440.0 112648.8 90.6
Pipe-based Context Switching 4000.0 19829.4 49.6
Process Creation 126.0 895.9 71.1
Shell Scripts (1 concurrent) 42.4 1042.4 245.8
Shell Scripts (8 concurrent) 6.0 300.1 500.2
System Call Overhead 15000.0 376537.2 251.0
Dhrystone 2 using register variables 116700.0 2226539.7 190.8
Double-Precision Whetstone 55.0 609.8 110.9
Execl Throughput 43.0 383.8 89.3
File Copy 1024 bufsize 2000 maxblocks 3960.0 59366.3 149.9
File Copy 256 bufsize 500 maxblocks 1655.0 16395.3 99.1
File Copy 4096 bufsize 8000 maxblocks 5800.0 179096.8 308.8
Pipe Throughput 12440.0 91524.1 73.6
Pipe-based Context Switching 4000.0 17886.8 44.7
Process Creation 126.0 856.6 68.0
Shell Scripts (1 concurrent) 42.4 1011.0 238.4
Shell Scripts (8 concurrent) 6.0 292.5 487.5
System Call Overhead 15000.0 295593.3 197.1
========
System Benchmarks Index Score 152.2
Rasberry PI 3b+(4CPU) の結果
System Benchmarks Index Score 137.2
------------------------------------------------------------------------
Benchmark Run: Mon Nov 30 2020 01:31:36 - 01:59:53
Benchmark Run: Mon Nov 30 2020 04:43:14 - 05:11:34
4 CPUs in system; running 4 parallel copies of tests
Dhrystone 2 using register variables 9114804.7 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2514.0 MWIPS (9.6 s, 7 samples)
Execl Throughput 1091.5 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 101986.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 27446.8 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 318205.8 KBps (30.0 s, 2 samples)
Pipe Throughput 365794.6 lps (10.0 s, 7 samples)
Pipe-based Context Switching 72573.8 lps (10.0 s, 7 samples)
Process Creation 2300.5 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2337.5 lpm (60.1 s, 2 samples)
Shell Scripts (8 concurrent) 310.6 lpm (60.4 s, 2 samples)
System Call Overhead 1134848.6 lps (10.0 s, 7 samples)
Dhrystone 2 using register variables 8888103.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2437.1 MWIPS (10.0 s, 7 samples)
Execl Throughput 1090.6 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 101772.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 27435.4 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 320594.0 KBps (30.0 s, 2 samples)
Pipe Throughput 365514.9 lps (10.0 s, 7 samples)
Pipe-based Context Switching 71226.7 lps (10.0 s, 7 samples)
Process Creation 2315.5 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2344.8 lpm (60.1 s, 2 samples)
Shell Scripts (8 concurrent) 311.6 lpm (60.4 s, 2 samples)
System Call Overhead 1140603.4 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 9114804.7 781.0
Double-Precision Whetstone 55.0 2514.0 457.1
Execl Throughput 43.0 1091.5 253.8
File Copy 1024 bufsize 2000 maxblocks 3960.0 101986.0 257.5
File Copy 256 bufsize 500 maxblocks 1655.0 27446.8 165.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 318205.8 548.6
Pipe Throughput 12440.0 365794.6 294.0
Pipe-based Context Switching 4000.0 72573.8 181.4
Process Creation 126.0 2300.5 182.6
Shell Scripts (1 concurrent) 42.4 2337.5 551.3
Shell Scripts (8 concurrent) 6.0 310.6 517.7
System Call Overhead 15000.0 1134848.6 756.6
Dhrystone 2 using register variables 116700.0 8888103.1 761.6
Double-Precision Whetstone 55.0 2437.1 443.1
Execl Throughput 43.0 1090.6 253.6
File Copy 1024 bufsize 2000 maxblocks 3960.0 101772.0 257.0
File Copy 256 bufsize 500 maxblocks 1655.0 27435.4 165.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 320594.0 552.7
Pipe Throughput 12440.0 365514.9 293.8
Pipe-based Context Switching 4000.0 71226.7 178.1
Process Creation 126.0 2315.5 183.8
Shell Scripts (1 concurrent) 42.4 2344.8 553.0
Shell Scripts (8 concurrent) 6.0 311.6 519.4
System Call Overhead 15000.0 1140603.4 760.4
========
System Benchmarks Index Score 358.2
System Benchmarks Index Score 356.6
自宅サーバーの結果
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: *****.chobits.com: GNU/Linux
OS: GNU/Linux -- 4.9.0-9-686 -- #1 SMP Debian 4.9.168-1+deb9u2 (2019-05-13)
Machine: i586 (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: Geode(TM) Integrated Processor by National Semi (796.9 bogomips)
MMX, AMD MMX
11:37:04 up 559 days, 11:58, 1 user, load average: 1.68, 0.79, 0.57; runlevel May
------------------------------------------------------------------------
Benchmark Run: 月 11月 30 2020 11:37:04 - 12:05:41
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 413312.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 179.8 MWIPS (9.3 s, 7 samples)
Execl Throughput 174.9 lps (29.5 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 14033.1 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 3893.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 39558.0 KBps (30.0 s, 2 samples)
Pipe Throughput 42795.9 lps (10.0 s, 7 samples)
Pipe-based Context Switching 4677.5 lps (10.0 s, 7 samples)
Process Creation 424.7 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 258.4 lpm (60.1 s, 2 samples)
Shell Scripts (8 concurrent) 26.1 lpm (60.9 s, 2 samples)
System Call Overhead 113513.7 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 413312.1 35.4
Double-Precision Whetstone 55.0 179.8 32.7
Execl Throughput 43.0 174.9 40.7
File Copy 1024 bufsize 2000 maxblocks 3960.0 14033.1 35.4
File Copy 256 bufsize 500 maxblocks 1655.0 3893.0 23.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 39558.0 68.2
Pipe Throughput 12440.0 42795.9 34.4
Pipe-based Context Switching 4000.0 4677.5 11.7
Process Creation 126.0 424.7 33.7
Shell Scripts (1 concurrent) 42.4 258.4 61.0
Shell Scripts (8 concurrent) 6.0 26.1 43.5
System Call Overhead 15000.0 113513.7 75.7
========
System Benchmarks Index Score 37.3
自宅サーバーの結果
自宅サーバよりラズパイ3B+の方が10倍近く高速だけど、WordPressが稼働中w
#htmlinsert(amazon_pc.html);
![[PukiWiki]](image/gbook_orange_80x80.png "[PukiWiki]")
