Forum

Please consider registering
guest

Log In Register

Register | Lost password?
Advanced Search

— Forum Scope —

  

— Match —

   

— Forum Options —

   

Minimum search word length is 4 characters - maximum search word length is 84 characters

Topic RSS
SysBench performance test on 86Duino
2015 年 02 月 05 日
00:48:58
Android_Lin
Moderator
Forum Posts: 211
Member Since:
2014 年 04 月 01 日
Offline

86Duino One at 400Mhz and run SysBench under Lubuntu 10.04, the result is:
=====================================================
$sysbench --test=cpu --cpu-max-prime=2000 run
sysbench 0.4.10: 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: 2000

Test execution summary:
total time: 40.1097s
total number of events: 10000
total time taken by event execution: 40.0823
per-request statistics:
min: 3.94ms
avg: 4.01ms
max: 24.80ms
approx. 95 percentile: 4.17ms

Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 40.0823/0.00
=====================================================

The following is the same test on raspberry pi:
=====================================================
$sysbench --test=cpu --cpu-max-prime=2000 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: 2000

Test execution summary:
total time: 55.4093s
total number of events: 10000
total time taken by event execution: 55.3722
per-request statistics:
min: 5.40ms
avg: 5.54ms
max: 15.76ms
approx. 95 percentile: 5.60ms

Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 55.3722/0.00
=====================================================

2015 年 02 月 11 日
04:51:01
pongraczi
Hungary
Moderator
Forum Posts: 20
Member Since:
2015 年 02 月 11 日
Offline

=====================================================
Same test on Vortex86DX som modul (cpuinfo at the bottom)
=====================================================

# sysbench --test=cpu --cpu-max-prime=2000 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: 2000

Test execution summary:
total time: 37.4602s
total number of events: 10000
total time taken by event execution: 37.4243
per-request statistics:
min: 3.68ms
avg: 3.74ms
max: 5.99ms
approx. 95 percentile: 3.85ms

Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 37.4243/0.00

=====================================================
CPU info
=====================================================

# cat /proc/cpuinfo
processor : 0
vendor_id : Vortex86 SoC
cpu family : 5
model : 2
model name : 05/02
stepping : 2
cpu MHz : 799.866
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 1
wp : yes
flags : fpu tsc cx8
bogomips : 1599.73
clflush size : 32
cache_alignment : 32
address sizes : 32 bits physical, 32 bits virtual
power management:

2015 年 02 月 12 日
23:38:13
pongraczi
Hungary
Moderator
Forum Posts: 20
Member Since:
2015 年 02 月 11 日
Offline

86Duino One at 300Mhz and run SysBench under Debian 7, the result is:
========================================================

# sysbench --test=cpu --cpu-max-prime=2000 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: 2000

Test execution summary:
total time: 55.7911s
total number of events: 10000
total time taken by event execution: 55.7539
per-request statistics:
min: 5.56ms
avg: 5.58ms
max: 7.47ms
approx. 95 percentile: 5.58ms

Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 55.7539/0.00

============================================================
Personal opinion: this board is pretty cool.
I just picked up a debian based controlling system on microSD card and I put it into the ONE.
It just started and everything started, even the graphical interface.
Due to that, our system expects more RAM (256MB) and we use fsprotect, we will have to adjust the system to work with low ram, but again, this board is really cool. :)

2015 年 02 月 13 日
16:50:30
roboard
Admin
Forum Posts: 135
Member Since:
2013 年 10 月 05 日
Offline

Overclock 86Duino to 400MHz can be done using the SysImage tool: http://www.86duino.com/index.php?p=7780 Cool
in general, 86Duino at 400MHz will work stably provided that you supply enough power (overclock would increase the power consumption).

2015 年 02 月 13 日
20:21:05
Glaux
Moderator
Forum Posts: 70
Member Since:
2013 年 10 月 11 日
Offline

roboard said
in general, 86Duino at 400MHz will work stably provided that you supply enough power (overclock would increase the power consumption).

But even @300MHz the heatsink gets quite hot. I'm little bit afraid that it might posibly shorten a lifetime because of used ROHS soldering that is more fragile to heat cycles (esp. on the BGA package with tiny balls).
BTW is there a possibility to change CPU clock dynamically from the user program (O'C on demand)? Or is there some reason that it needs to reboot. The clock speed setting is stored somewhere in SPI flash?

2015 年 02 月 16 日
12:31:55
roboard
Admin
Forum Posts: 135
Member Since:
2013 年 10 月 05 日
Offline

BTW is there a possibility to change CPU clock dynamically from the user program (O'C on demand)? Or is there some reason that it needs to reboot. The clock speed setting is stored somewhere in SPI flash?

The clock speed setting must be stored in SPI flash as hardware strapping, and cannot be changed in runtime. The CPU module (Vortex86EX SOM-128) of 86Duino is manufactured to work in -40~70ºC at 300MHz for industrial use; if you use 86Duino only in a 0-40ºC environment, may get it a try at 400MHz. :)

(For comparison, here is a measure of Vortex86EX @444MHz at 24C ambient temperature: http://www.roboard.com/temp/86.....rature.jpg)

Forum Timezone: Asia/Taipei

Most Users Ever Online: 66

Currently Online:
1 Guest(s)

Currently Browsing this Page:
1 Guest(s)

Top Posters:

Dinosaur: 27

leutenecker: 13

mrZagg: 10

lukeross: 8

tomka: 8

smeezekitty: 8

hippy: 8

Ekkehard: 8

UIdahoCIT: 8

blaxxun: 7

Member Stats:

Guest Posters: 0

Members: 1520

Moderators: 14

Admins: 5

Forum Stats:

Groups: 2

Forums: 10

Topics: 239

Posts: 1082

Newest Members: Olegeffep, bradfang, markjensen, carryjhn, garfpinpsivenste, sragdoterlesscu, uledthapeton, srelesponreuterf, prinriaquochilddist, cobdor7

Moderators: Glaux: 70, uaa: 11, guigra: 17, asian55: 22, Android_Lin: 211, bcarroll: 12, cucubutter: 84, recycled-air: 12, stevemork: 16, zerozaber: 52, pongraczi: 20, George Andrews III: 56, poto: 11, garpastym: 20

Administrators: eveshih: 1, anthony: 31, viky6: 0, roboard: 135, hcl: 0