New AstroPulse for GPU ( ATi & NV) released (r1316)


log in

Advanced search

Message boards : Number crunching : New AstroPulse for GPU ( ATi & NV) released (r1316)

Previous · 1 . . . 6 · 7 · 8 · 9 · 10 · 11 · Next
Author Message
Profile [AF>EDLS] Polynesia
Volunteer tester
Avatar
Send message
Joined: 1 Apr 09
Posts: 54
Credit: 4,002,615
RAC: 6,556
France
Message 1263789 - Posted: 23 Jul 2012, 17:42:43 UTC
Last modified: 23 Jul 2012, 17:55:20 UTC

I tell you here when downloading my 2 units GPU is finally completed ...
____________


Alliance Francophone

Profile [AF>EDLS] Polynesia
Volunteer tester
Avatar
Send message
Joined: 1 Apr 09
Posts: 54
Credit: 4,002,615
RAC: 6,556
France
Message 1264024 - Posted: 24 Jul 2012, 10:05:31 UTC

About 1 hour 20 for the operating time on my gtx 470
____________


Alliance Francophone

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 4081
Credit: 111,759,464
RAC: 147,051
United States
Message 1264066 - Posted: 24 Jul 2012, 13:16:44 UTC - in response to Message 1263719.

I've noticed that some WUs are getting low credits, is there a problem somewhere? It's not happening only with the latest app, it also happened with previous versions, not sure when I first noticed it.

http://setiathome.berkeley.edu/results.php?hostid=6442255&offset=0&show_names=0&state=3&appid=12

Do you mean the ones with 0.13 & 0.08 credit? Which are 100% blanked.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

Profile MikeProject donor
Volunteer tester
Avatar
Send message
Joined: 17 Feb 01
Posts: 23816
Credit: 32,633,220
RAC: 23,534
Germany
Message 1264080 - Posted: 24 Jul 2012, 13:55:25 UTC - in response to Message 1264024.

About 1 hour 20 for the operating time on my gtx 470


Both results are looking fine.

____________

JohnDKProject donor
Volunteer tester
Avatar
Send message
Joined: 28 May 00
Posts: 840
Credit: 43,058,020
RAC: 74,347
Denmark
Message 1264102 - Posted: 24 Jul 2012, 14:46:56 UTC - in response to Message 1264066.

I've noticed that some WUs are getting low credits, is there a problem somewhere? It's not happening only with the latest app, it also happened with previous versions, not sure when I first noticed it.

http://setiathome.berkeley.edu/results.php?hostid=6442255&offset=0&show_names=0&state=3&appid=12

Do you mean the ones with 0.13 & 0.08 credit? Which are 100% blanked.

No there's some that only gives around 150-250 and not around 600-800 as normal. Right now there's only one with 140.64 Cr on my finished WUs list, last when I wrote there was 3-4 WUs with the low credit.

Profile Fred J. Verster
Volunteer tester
Send message
Joined: 21 Apr 04
Posts: 3238
Credit: 31,693,345
RAC: 5,965
Netherlands
Message 1264128 - Posted: 24 Jul 2012, 21:50:36 UTC - in response to Message 1262988.

I had an abortion because the download is very long ...

In my preferences I put yes to everything in CPU / GPU


Well, DownLoads are very slow at SETI, comaired to projects with
fewer users and hosts, GPUgrid hits 20MBit, Einstein is also faster.
Milkyway, WCG, etc..
Problem is SETI is constant overloaded/saturated and in too much cases
the cause of a DownLoad Errors as in your case.

How long for a MB (~360KBytes) and AstroPulse (8MBytes) workunit?



____________

JohnDKProject donor
Volunteer tester
Avatar
Send message
Joined: 28 May 00
Posts: 840
Credit: 43,058,020
RAC: 74,347
Denmark
Message 1264139 - Posted: 24 Jul 2012, 22:39:00 UTC - in response to Message 1264102.

I've noticed that some WUs are getting low credits, is there a problem somewhere? It's not happening only with the latest app, it also happened with previous versions, not sure when I first noticed it.

http://setiathome.berkeley.edu/results.php?hostid=6442255&offset=0&show_names=0&state=3&appid=12

Do you mean the ones with 0.13 & 0.08 credit? Which are 100% blanked.

No there's some that only gives around 150-250 and not around 600-800 as normal. Right now there's only one with 140.64 Cr on my finished WUs list, last when I wrote there was 3-4 WUs with the low credit.

Here's one with only 175.27 Cr
http://setiathome.berkeley.edu/result.php?resultid=2525075894

Another one, same blanking, almost same run time, but 697.07 Cr
http://setiathome.berkeley.edu/result.php?resultid=2525071993

Profile [AF>EDLS] Polynesia
Volunteer tester
Avatar
Send message
Joined: 1 Apr 09
Posts: 54
Credit: 4,002,615
RAC: 6,556
France
Message 1264162 - Posted: 25 Jul 2012, 18:53:06 UTC - in response to Message 1264128.
Last modified: 25 Jul 2012, 18:54:04 UTC

I had an abortion because the download is very long ...

In my preferences I put yes to everything in CPU / GPU


Well, DownLoads are very slow at SETI, comaired to projects with
fewer users and hosts, GPUgrid hits 20MBit, Einstein is also faster.
Milkyway, WCG, etc..
Problem is SETI is constant overloaded/saturated and in too much cases
the cause of a DownLoad Errors as in your case.

How long for a MB (~360KBytes) and AstroPulse (8MBytes) workunit?




FFor astro: more than 3 hours in download time but I have caused to manually restart the download dozens of times

For the rest, I can not remember ...
____________


Alliance Francophone

Wedge009
Volunteer tester
Avatar
Send message
Joined: 3 Apr 99
Posts: 317
Credit: 138,271,531
RAC: 244,461
Australia
Message 1265643 - Posted: 29 Jul 2012, 21:52:46 UTC
Last modified: 29 Jul 2012, 21:53:39 UTC

Just some more feedback for Raistmer and any other AP OpenCL developers:

Getting a lot of invalid results on my old HD 4670, mostly due to 30 single pulses, 30 repeating pulses, or both. This seems to happen regardless of what combination of parameters I try. The confusing thing is that, sporadically, I still get the occasional valid result.

I think I'll have to revert to r555 even though it has much lower performance (especially with regards to CPU usage), it's still bound to be much better than CPU-only processing on the ancient machine it's on. There were still invalid results, but they were limited to 30 repeating pulses and there were far more valid results than invalid ones. I put all this down to the 'beta-level' OpenCL support on the HD 4000 series - I ceased all GPU processing on my HD 4850 a long time ago because of similar issues presumably arising from this.

Other GPUs (HD 5000 series and later, as well as GeForce cards) continue to work very well on r1316. I'm aware there is a r1363 release, but I don't understand the parameters enough to try it. Doesn't seem as though there's as large a performance increase either.
____________
Soli Deo Gloria

Profile MikeProject donor
Volunteer tester
Avatar
Send message
Joined: 17 Feb 01
Posts: 23816
Credit: 32,633,220
RAC: 23,534
Germany
Message 1265647 - Posted: 29 Jul 2012, 22:14:24 UTC


Have you tried lower unroll ?

I´d suggest -unroll 4 -ffa_block 2048 -ffa_block_fetch 1024

Mike

____________

Wedge009
Volunteer tester
Avatar
Send message
Joined: 3 Apr 99
Posts: 317
Credit: 138,271,531
RAC: 244,461
Australia
Message 1265675 - Posted: 29 Jul 2012, 23:16:46 UTC

Yes. As I mentioned, the both valid and invalid results occur for all manner of parameters. I've tried unroll of 4, 8, 10 with r1316. With r555, unroll of 4 always resulted in invalid results, whereas 10 was the only one that consistently returned valid results.
____________
Soli Deo Gloria

Profile Jim Holly
Volunteer tester
Send message
Joined: 14 May 99
Posts: 11
Credit: 3,363,801
RAC: 0
United States
Message 1265960 - Posted: 30 Jul 2012, 18:51:26 UTC

I would be delighted to just download some AstroPulse files that would run! Every one shows completion in the Transfers tab, but the Tasks list always says 'Download failed'.

Running all other WU's in Seti and Einstein with no problems.

Windows 7 Pro 64-bit; i7-2600 quad core with 8 Gb RAM.
____________

Profile BilBg
Volunteer tester
Avatar
Send message
Joined: 27 May 07
Posts: 2644
Credit: 6,006,007
RAC: 4,448
Bulgaria
Message 1266045 - Posted: 31 Jul 2012, 2:17:50 UTC - in response to Message 1265960.


Your problem is with the file ap_graphics_6.01_windows_intelx86.exe
http://setiathome.berkeley.edu/result.php?resultid=2544369687

Very probably your antivirus is interfering:
http://setiathome.berkeley.edu/forum_thread.php?id=68629&postid=1257824#1257824

Get the file manually:
http://boinc2.ssl.berkeley.edu/sah/download_fanout/ap_graphics_6.01_windows_intelx86.exe

(Probably your antivirus will say something nasty and wrong. If it does: complain to the antivirus company)


If you can get the file from the above link (I can, I get the file just now and the file is the same as the one I have):
put it in the ....\BOINC\projects\setiathome.berkeley.edu\ and then start BOINC

In your case of Windows 7 the exact path is most likely:
C:\ProgramData\BOINC\projects\setiathome.berkeley.edu\


____________



- ALF - "Find out what you don't do well ..... then don't do it!" :)

Profile Raistmer
Volunteer developer
Volunteer tester
Avatar
Send message
Joined: 16 Jun 01
Posts: 3399
Credit: 46,366,390
RAC: 9,836
Russia
Message 1266127 - Posted: 31 Jul 2012, 9:25:40 UTC - in response to Message 1265643.
Last modified: 31 Jul 2012, 9:26:03 UTC

Just some more feedback for Raistmer and any other AP OpenCL developers:

Getting a lot of invalid results on my old HD 4670, mostly due to 30 single pulses, 30 repeating pulses, or both. This seems to happen regardless of what combination of parameters I try. The confusing thing is that, sporadically, I still get the occasional valid result.

I think I'll have to revert to r555 even though it has much lower performance (especially with regards to CPU usage), it's still bound to be much better than CPU-only processing on the ancient machine it's on. There were still invalid results, but they were limited to 30 repeating pulses and there were far more valid results than invalid ones. I put all this down to the 'beta-level' OpenCL support on the HD 4000 series - I ceased all GPU processing on my HD 4850 a long time ago because of similar issues presumably arising from this.

Other GPUs (HD 5000 series and later, as well as GeForce cards) continue to work very well on r1316. I'm aware there is a r1363 release, but I don't understand the parameters enough to try it. Doesn't seem as though there's as large a performance increase either.


Actually I'm trying to maintain compatibility with HD4xxx though has no hardware installed now. But HD46xx low-end ones AFAIK and have some different issues.
Special LHD4 build for them still in debugging. From the other side I would not expect same failures on HD4850. Can you replace HD46xx with HD48xx on that host ?

Profile Jim Holly
Volunteer tester
Send message
Joined: 14 May 99
Posts: 11
Credit: 3,363,801
RAC: 0
United States
Message 1266310 - Posted: 1 Aug 2012, 0:29:17 UTC

Thanks BilBg. Trend did try to block it, and I placed it on the 'approved' list. I replaced the one in the folder which was only 9kB. Time will tell, once I get another AP download.
____________

Wedge009
Volunteer tester
Avatar
Send message
Joined: 3 Apr 99
Posts: 317
Credit: 138,271,531
RAC: 244,461
Australia
Message 1266319 - Posted: 1 Aug 2012, 1:41:28 UTC - in response to Message 1266127.
Last modified: 1 Aug 2012, 1:45:54 UTC

Special LHD4 build for them still in debugging. From the other side I would not expect same failures on HD4850. Can you replace HD46xx with HD48xx on that host ?

Sorry, no, the HD 4850 I put in the machine for my brother and besides, HD 4850 is PCIe, HD 4670 is AGP. For HD 4850's issues, I think it's driver issues more than anything else.

After getting yet another 30 single pulses result on the HD 4670, I reverted to r555 and re-processed the task. Hasn't validated yet, but it seems to be giving more reasonable results again.

As mentioned previously, the puzzling thing is that there are still some valid results produced with r1316. These two were validated recently, so they're still present in the database at time of writing:

2543227294

Oops, no, scratch that. Second one just got purged as I was writing...

Edit: If you want a tester for your special HD 4000 build, I'm willing to help. Will just take a while as 0% blanking AP WUs take about 7.5 hours with r1316, just under 10 hours with r555.
____________
Soli Deo Gloria

Profile Raistmer
Volunteer developer
Volunteer tester
Avatar
Send message
Joined: 16 Jun 01
Posts: 3399
Credit: 46,366,390
RAC: 9,836
Russia
Message 1266353 - Posted: 1 Aug 2012, 6:21:40 UTC - in response to Message 1266319.


Edit: If you want a tester for your special HD 4000 build, I'm willing to help.

Currently I'm busy with MultiBeam, but will keep your proposal for future, thanks.

Wedge009
Volunteer tester
Avatar
Send message
Joined: 3 Apr 99
Posts: 317
Credit: 138,271,531
RAC: 244,461
Australia
Message 1266365 - Posted: 1 Aug 2012, 6:54:07 UTC
Last modified: 1 Aug 2012, 6:54:36 UTC

I'm in no hurry, I only offered because you mentioned developing a special build.

Best wishes for MB development.
____________
Soli Deo Gloria

Profile Jim Holly
Volunteer tester
Send message
Joined: 14 May 99
Posts: 11
Credit: 3,363,801
RAC: 0
United States
Message 1266502 - Posted: 1 Aug 2012, 19:59:23 UTC

AstroPulse WU's are running fine again. :)
____________

Profile dskagcommunity
Volunteer tester
Avatar
Send message
Joined: 24 Feb 11
Posts: 43
Credit: 2,041,597
RAC: 0
Austria
Message 1266716 - Posted: 2 Aug 2012, 15:10:42 UTC

Only as Info, Application runs without errors on a low low lowest end HD4350 ^^ ~24h for 1 WU
____________

Previous · 1 . . . 6 · 7 · 8 · 9 · 10 · 11 · Next

Message boards : Number crunching : New AstroPulse for GPU ( ATi & NV) released (r1316)

Copyright © 2014 University of California