Posts by Sitarow

\n studio-striking\n
1) Questions and Answers : Windows : Multi-GPU task takes longer than single-gpu task (Message 246)
Posted 12 May 2011 by Sitarow
Post:
Okay, I finally had time to run the -bench test. Here are the results for the two machines in question:

Dual 5870:


[May 12 01:57:38 UTC] RC5-72: using core #0 (IL 4-pipe c).
[May 12 01:57:46 UTC] RC5-72: Benchmark for core #0 (IL 4-pipe c)
0.00:00:05.75 [755,039,695 keys/sec]
[May 12 01:57:46 UTC] RC5-72: using core #1 (IL 4-pipe c alt).
[May 12 01:57:52 UTC] RC5-72: Benchmark for core #1 (IL 4-pipe c alt)
0.00:00:03.71 [1,173,790,362 keys/sec]
[May 12 01:57:52 UTC] RC5-72: using core #2 (IL 4-pipe 2 threads).
[May 12 01:57:58 UTC] RC5-72: Benchmark for core #2 (IL 4-pipe 2 threads)
0.00:00:03.34 [1,306,783,130 keys/sec]
[May 12 01:57:58 UTC] RC5-72: using core #3 (IL 4-pipe cs-1).
[May 12 01:58:03 UTC] RC5-72: Benchmark for core #3 (IL 4-pipe cs-1)
0.00:00:02.17 [2,044,294,794 keys/sec]
[May 12 01:58:03 UTC] RC5-72 benchmark summary :
Default core : #0 (IL 4-pipe c)
Fastest core : #3 (IL 4-pipe cs-1)
[May 12 01:58:03 UTC] Core #3 is significantly faster than the default core.


If core 0 is slow then setting core use to 3 will help with speed but pay attention to the credit granted.

With the dual setup the wrapper on your bench will use core 0 for its base and if you set the core to 3 you will get lower credit because it thinks it was a mini rather then full task.

Also I run all my dual + with out crossfire / sli.
At least that is what I have found.
2) Questions and Answers : Windows : Multi-GPU task takes longer than single-gpu task (Message 243)
Posted 11 May 2011 by Sitarow
Post:
Sounds good. And yes it would run hot OC'ed :) I notice that OC of the card is not as important as the OC of the CPU for this project.
3) Questions and Answers : Windows : Multi-GPU task takes longer than single-gpu task (Message 241)
Posted 11 May 2011 by Sitarow
Post:
Ok, I figured it out. I did the check for core performance. It came back saying core 3 was best. I tried changing the config using the local app, but that didn't work. When I set my core 3 in my Moo Wrapper preferences, my times for dual 5870s went to 9 minutes.

Thanks,

Dan



Sounds like its working.

Now the only question I have is what are the points you are getting awarded for each task?
4) Questions and Answers : Preferences : benchmarks (Message 238)
Posted 11 May 2011 by Sitarow
Post:
It's "dnetc518-win32-x86-cuda31.exe" for you.


how I run this benchmark, I did not understand


if your running windows 7 / vista do this.

hold down windows key + r You should get a popup window.

Now paste the following line including the "

"C:\Users\All Users\BOINC\projects\moowrap.net\dnetc518-win32-x86-cuda31.exe" -bench

that file your running is located in the following default directory

C:\Users\All Users\BOINC\projects\moowrap.net



Here is something similar that should come up on the window.

Computer ID 405 CPU IDLE

http://www.moowrap.net/results.php?hostid=405&offset=0&show_names=0&state=3&appid=

Intel I7 920@2.66 HT Disabled Windows 7 Enterprise 64
ATI 5850 1.4.1353 Drivers 11.4 Boinc Client 6.10.60



[May 11 20:45:39 UTC] RC5-72: using core #0 (IL 4-pipe c).
[May 11 20:45:54 UTC] RC5-72: Benchmark for core #0 (IL 4-pipe c)
0.00:00:11.46 [381,036,501 keys/sec]
[May 11 20:45:54 UTC] RC5-72: using core #1 (IL 4-pipe c alt).
[May 11 20:46:01 UTC] RC5-72: Benchmark for core #1 (IL 4-pipe c alt)
0.00:00:04.77 [926,568,859 keys/sec]
[May 11 20:46:01 UTC] RC5-72: using core #2 (IL 4-pipe 2 threads).
[May 11 20:46:07 UTC] RC5-72: Benchmark for core #2 (IL 4-pipe 2 threads)
0.00:00:03.51 [1,296,465,069 keys/sec]
[May 11 20:46:07 UTC] RC5-72: using core #3 (IL 4-pipe cs-1).
[May 11 20:46:12 UTC] RC5-72: Benchmark for core #3 (IL 4-pipe cs-1)
0.00:00:02.77 [1,617,546,052 keys/sec]
[May 11 20:46:13 UTC] RC5-72 benchmark summary :
Default core : #0 (IL 4-pipe c)
Fastest core : #3 (IL 4-pipe cs-1)
[May 11 20:46:13 UTC] Core #3 is significantly faster than the default core.
The GPU core selection has been made as a tradeoff be ...
and responsiveness of the graphical desktop.


Disabling HT on the CPU did not help the core 0 speed however it did help core 3 speed.
5) Questions and Answers : Preferences : benchmarks (Message 235)
Posted 11 May 2011 by Sitarow
Post:
Sitarow,
exact, like you can see, core #3 is MUCH more faster then core #0.
Sadly, this is a bug in the d.net client, not in the wrapper.


Thanks..

The next question would be how can I set the performance for the system bassed on core 3?
6) Questions and Answers : Preferences : benchmarks (Message 231)
Posted 11 May 2011 by Sitarow
Post:
"C:\Users\All Users\BOINC\projects\moowrap.net\dnetc518-win32-x86-stream.exe" -bench

Computer ID 405 CPU IDLE

http://www.moowrap.net/results.php?hostid=405&offset=0&show_names=0&state=3&appid=

Intel I7 920@2.66 HT enabled Windows 7 Enterprise 64
ATI 5850 1.4.1353 Drivers 11.4 Boinc Client 6.10.60

[May 11 17:00:50 UTC] RC5-72: using core #0 (IL 4-pipe c).
[May 11 17:00:58 UTC] RC5-72: Benchmark for core #0 (IL 4-pipe c)
0.00:00:05.80 [759,575,045 keys/sec]
[May 11 17:00:58 UTC] RC5-72: using core #1 (IL 4-pipe c alt).
[May 11 17:01:06 UTC] RC5-72: Benchmark for core #1 (IL 4-pipe c alt)
0.00:00:05.07 [872,034,219 keys/sec]
[May 11 17:01:06 UTC] RC5-72: using core #2 (IL 4-pipe 2 threads).
[May 11 17:01:12 UTC] RC5-72: Benchmark for core #2 (IL 4-pipe 2 threads)
0.00:00:04.01 [1,107,936,912 keys/sec]
[May 11 17:01:12 UTC] RC5-72: using core #3 (IL 4-pipe cs-1).
[May 11 17:01:18 UTC] RC5-72: Benchmark for core #3 (IL 4-pipe cs-1)
0.00:00:02.93 [1,514,639,503 keys/sec]
[May 11 17:01:18 UTC] RC5-72 benchmark summary :
Default core : #0 (IL 4-pipe c)
Fastest core : #3 (IL 4-pipe cs-1)
[May 11 17:01:18 UTC] Core #3 is significantly faster than the default core.
The GPU core selection has been made as a tradeoff be ...
and responsiveness of the graphical desktop.


I can speculate that this may be the a primary cause for low points granted. The Boinc side client does its bench on core 0. After setting the core to 3 via the project settings it completes the task faster and therefore awards the points for the lesser work done.
7) Questions and Answers : Windows : Multi-GPU task takes longer than single-gpu task (Message 224)
Posted 10 May 2011 by Sitarow
Post:
P.S. I did update the CF profile (11.4) from ATI and saw my GPU go from ~5000 seconds to 3,000 seconds and my CPU drop to 1,600 seconds.


I will try that and see if it gives me a similar diffrence.

The only problem is that now the project will not give the proper reward for work done because of the reduced time it take to complete the project.

I may have to reinstall the boinc client on that computer and get a new ID for the computer on this project to get that issue resolved.


Edit: These are the computers that you can check to see about the reduced time and lower points granted.

Computer ID 255
http://www.moowrap.net/results.php?hostid=255&offset=0&show_names=0&state=3&appid=

Computer ID 252
http://www.moowrap.net/results.php?hostid=252&offset=0&show_names=0&state=3&appid=

Computer ID 405
http://www.moowrap.net/results.php?hostid=405&offset=0&show_names=0&state=3&appid=
8) Questions and Answers : Windows : Multi-GPU task takes longer than single-gpu task (Message 222)
Posted 10 May 2011 by Sitarow
Post:
I have done a bit of testing on some of the computers that I have setup for this project.

I took the advice posted here on running a benchmark test on each computer I am running this project on.

What I found was that the computers that performed at a normal rate were using there best core 0 of the 4 options.

After taking the suggestions of the above posts. I found that some would perform great on core 0 and others would perform best on core 3.

I set those computers into diffrent groups and it helped bring the 1.2hr job down to 22mins on a ATI 5850 computer running stock speeds on both CPU and GPU.

I found that with an ATI 5870 we would have to speed up the CPU clock speeds in order to get the added performance.

The drawback was that the normal reward for the task at 1.2hrs would be about 9k points but because of the auto balancing of points the next tasks that finished in 22mins would only be awarded 2400 points.

My next question is how long will it take before it "normalizes" on the points rewarded?

Oh to run the benchmark application found on a windows 7/vista box at the following directory..

default install

"C:\Users\All Users\BOINC\projects\moowrap.net\dnetc518-win32-x86-stream.exe" -bench

P.S.

I ran this bench on an AMD 6 core and an Intel 6 core and both would only do 0 - 3 it would not do the final 2.





 
Copyright © 2011-2024 Moo! Wrapper Project