手头有f1c100s,f1c200s,v3s,zerow。本次测试了v3s和zerow(sysbench),v3s比zerow稍微慢了点,频率都是1G,可能和v3s的ram太小有关,v3s的ram是64m,zerow是512m,差太多了。
v3s:
root@LicheePi:~# sysbench --test=cpu --cpu-max-prime=20000 run
sysbench 0.4.12: multi-threaded system evaluation benchmark
Running the test with following options:
Number of threads: 1
Doing CPU performance benchmark
Threads started!
Done.
Maximum prime number checked in CPU test: 20000
Test execution summary:
total time: 730.7818s
total number of events: 10000
total time taken by event execution: 730.7642
per-request statistics:
min: 72.70ms
avg: 73.08ms
max: 79.48ms
approx. 95 percentile: 74.25ms
Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 730.7642/0.00
zerow
pi@raspberrypi:~/go/src/test $ sysbench --test=cpu --cpu-max-prime=20000 run
sysbench 0.4.12: multi-threaded system evaluation benchmark
Running the test with following options:
Number of threads: 1
Doing CPU performance benchmark
Threads started!
Done.
Maximum prime number checked in CPU test: 20000
Test execution summary:
total time: 596.4347s
total number of events: 10000
total time taken by event execution: 596.4006
per-request statistics:
min: 59.52ms
avg: 59.64ms
max: 157.06ms
approx. 95 percentile: 59.71ms
Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 596.4006/0.00
最近编辑记录 kekemuyu (2019-11-04 21:38:43)
离线
zerow是什么?荔枝派zero?树莓派zero?
能否和imx6ull对比下?
离线
zerow是什么?荔枝派zero?树莓派zero?
能否和imx6ull对比下?
树莓派zerow,没有i.mx6ull。欢迎有i.mx6ull的朋友比拼
离线
应该有问题吧。zero是arm11,同频能比arm a7还快?
离线
应该有问题吧。zero是arm11,同频能比arm a7还快?
实测就是这样,可能和linux版本不同有关。pizerow是4.19,licheepizero是4.13
最近编辑记录 kekemuyu (2019-11-05 20:31:46)
离线
f1c200s的700m测试:
root@antbian:~/tool# sysbench --test=cpu --cpu-max-prime=20000 run
sysbench 0.4.12: multi-threaded system evaluation benchmark
Running the test with following options:
Number of threads: 1
Doing CPU performance benchmark
Threads started!
Done.
Maximum prime number checked in CPU test: 20000
Test execution summary:
total time: 2553.1847s
total number of events: 10000
total time taken by event execution: 2553.0733
per-request statistics:
min: 254.73ms
avg: 255.31ms
max: 574.51ms
approx. 95 percentile: 255.38ms
Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 2553.0733/0.00
最近编辑记录 kekemuyu (2019-11-10 15:32:25)
离线
f1c200s比v3s满了三倍
离线
我来发一个PC机上的测试数据,配置为R7 2700的KVM虚拟机,分配了8核和8G内存。不考虑sysbench的版本的话,速度是V3s的70倍。
sysbench --test=cpu --cpu-max-prime=20000 run
WARNING: the --test option is deprecated. You can pass a script name or path on the command line without any options.
sysbench 1.0.15 (using system LuaJIT 2.0.5)
Running the test with following options:
Number of threads: 1
Initializing random number generator from current time
Prime numbers limit: 20000
Initializing worker threads...
Threads started!
CPU speed:
events per second: 686.40
General statistics:
total time: 10.0002s
total number of events: 6865
Latency (ms):
min: 1.31
avg: 1.45
max: 1.85
95th percentile: 1.52
sum: 9947.28
Threads fairness:
events (avg/stddev): 6865.0000/0.00
execution time (avg/stddev): 9.9473/0.00
离线