Advanced search

Message boards : News : acemdlong application 815 updated for Maxwell

Author Message
Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 35741 - Posted: 19 Mar 2014 | 16:59:44 UTC

The cuda60 version of application version 815 is now present on acemdlong for those of you with the latest driver or a Maxwell card.

Matt

TheFiend
Send message
Joined: 26 Aug 11
Posts: 99
Credit: 2,500,112,138
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35751 - Posted: 19 Mar 2014 | 22:44:00 UTC
Last modified: 19 Mar 2014 | 22:47:09 UTC

Getting a lot of failures on app 815(Cuda60)

Jeremy Zimmerman
Send message
Joined: 13 Apr 13
Posts: 61
Credit: 726,605,417
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwat
Message 35791 - Posted: 21 Mar 2014 | 20:45:33 UTC - in response to Message 35741.

Realize the effort and focus of the 8.15 and cuda60 is probably for maxwell, but just wanted to ensure you knew WinXP seems to error out on every one of these tasks while Win7/8 is ok.

See below thread
http://www.gpugrid.net/forum_thread.php?id=3671

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 35795 - Posted: 21 Mar 2014 | 23:22:44 UTC - in response to Message 35791.

Jeremy, Could you try a project reset on the affected XP machines please? The error suggests the application's files haven't downloaded correctly

Matt

Profile skgiven
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35796 - Posted: 21 Mar 2014 | 23:42:55 UTC - in response to Message 35795.

Different security architecture?
____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

GoodFodder
Send message
Joined: 4 Oct 12
Posts: 53
Credit: 333,467,496
RAC: 0
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 35802 - Posted: 22 Mar 2014 | 10:11:09 UTC
Last modified: 22 Mar 2014 | 10:19:24 UTC

Hi,

Just confirmation the new 8.15/cuda60 app on XP x86 with a GTX 650 ti crash with a popup message:
"The procedure entry point GetTickCount64 could not be located in the dynamic link library KERNEL32.dll"
Performed a project as suggested to no avail.

x86 bug?

cuda55 app was working fine.
Until the issue is resolved is there a way of identifying cuda60 tasks by name so I can write a script to abort them immediately?

Thanks

Betting Slip
Send message
Joined: 5 Jan 09
Posts: 670
Credit: 2,498,095,550
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35804 - Posted: 22 Mar 2014 | 10:51:00 UTC - in response to Message 35802.

Downgrade video driver and you won't get Cuda 6

TheFiend
Send message
Joined: 26 Aug 11
Posts: 99
Credit: 2,500,112,138
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35805 - Posted: 22 Mar 2014 | 11:24:46 UTC - in response to Message 35804.

Downgrade video driver and you won't get Cuda 6


That is a way around it but surely there must be a bug in the application that is causing the failures in Windows XP machines. Some participants prefer the performance advantage of XP for crunching GPUGRID.

Jeremy Zimmerman
Send message
Joined: 13 Apr 13
Posts: 61
Credit: 726,605,417
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwat
Message 35807 - Posted: 22 Mar 2014 | 12:24:48 UTC - in response to Message 35795.

Matt,

I reset the project for both machine, and they are both still erroring out on every cuda60 WU. I went through the top 320 performing computers on the volunteer list last night, and did not find a single XP machine with drivers 334 or 335 that completed a cuda60 WU. The other XP machines just did not receive the WU's with the older drivers. Only a handful of the XP machines were on 334/335. The rest were on older drivers and just running the cuda55/42 WU's.

I am changing back to the 331 driver to avoid the cuda60 WU's for now. I can try the 335 driver again later if needed.

Thank you for the feedback and suggestion.

Regards,
Jeremy

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 35808 - Posted: 22 Mar 2014 | 12:26:56 UTC - in response to Message 35807.

Thanks for the error message. Should be enough to track down the problem. I've disabled the acemdlong cuda60 app for the moment.

Matt

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 321,525,386
RAC: 477,412
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35809 - Posted: 22 Mar 2014 | 12:28:57 UTC
Last modified: 22 Mar 2014 | 12:29:32 UTC

Would it be possible to add a checkbox to the 'Run only the selected application' named 'Cuda 6' and one named 'Cuda < 6' ?
Using these choices should solve most probles with these version incompatibilities.

Alexander

Jozef J
Send message
Joined: 7 Jun 12
Posts: 112
Credit: 1,118,845,172
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 35811 - Posted: 22 Mar 2014 | 12:37:44 UTC

I got the first tasks cuda 60 on March 19 and all were Calculate flawlessly. Already about 20 + already completed okay.
Times is about 25000sec, cpu 8500 but it can be for each user due to hw different one..
Good job GPUGRID, cheers

Jim1348
Send message
Joined: 28 Jul 12
Posts: 819
Credit: 1,591,285,971
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35812 - Posted: 22 Mar 2014 | 12:56:32 UTC - in response to Message 35809.

Would it be possible to add a checkbox to the 'Run only the selected application' named 'Cuda 6' and one named 'Cuda < 6' ?
Using these choices should solve most probles with these version incompatibilities.

Alexander

I agree. However, it looks like they want to use CUDA 6.0 on all the new work, so that would be only a temporary solution.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 35813 - Posted: 22 Mar 2014 | 15:59:17 UTC - in response to Message 35812.

Try acemdbeta 812 or acemdshort 813 - these should fix the crash on 32bit Win XP.
Please report here!

Matt

ROBtheLIONHEART
Send message
Joined: 21 Nov 13
Posts: 34
Credit: 636,026,131
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 35814 - Posted: 22 Mar 2014 | 21:32:24 UTC - in response to Message 35813.

Will this also be compatible for WinXP 64bit? From the leader list the top machines are using it.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 35815 - Posted: 22 Mar 2014 | 22:23:44 UTC - in response to Message 35814.

Yep

GoodFodder
Send message
Joined: 4 Oct 12
Posts: 53
Credit: 333,467,496
RAC: 0
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 35818 - Posted: 23 Mar 2014 | 11:27:37 UTC
Last modified: 23 Mar 2014 | 11:40:45 UTC

Hi,

Updated 8.15-cuda60 on the short Q (win XP x86, gtx 650ti) appears to getting further however running very slowly with CPU utilisation <1% (typically 8-10%) (Currently a SANTI_MAR419cap310 after 2hrs 22min is only at 47%)

Ah, noticed I am still getting the error "..GetTickCount64 could not be located in KERNEL32.DLL" msg which pops up as soon as I start the task :(

GoodFodder
Send message
Joined: 4 Oct 12
Posts: 53
Credit: 333,467,496
RAC: 0
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 35825 - Posted: 23 Mar 2014 | 13:40:03 UTC

Update - rebooted and performed a project reset to no avail.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 35827 - Posted: 23 Mar 2014 | 15:13:14 UTC - in response to Message 35825.

Try the new version 820

Jim1348
Send message
Joined: 28 Jul 12
Posts: 819
Credit: 1,591,285,971
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35834 - Posted: 23 Mar 2014 | 19:03:07 UTC

I have just completed my first 8.20 short run on a GTX 660 under WinXP 32-bit.
No problems or restarts at all at 3 hours 7 minutes total elapsed time; good work.
(And please take some time off during the week.)

Name 990x-SANTI_MAR423cap310-45-84-RND7785_1
Workunit 5346410
Created 23 Mar 2014 | 15:20:02 UTC
Sent 23 Mar 2014 | 15:20:14 UTC
Received 23 Mar 2014 | 18:30:08 UTC
Server state Over
Outcome Success
Client state Done
Exit status 0 (0x0)
Computer ID 168614
Report deadline 28 Mar 2014 | 15:20:14 UTC
Run time 11,222.14
CPU time 1,951.00
Validate state Valid
Credit 18,300.00
Application version Short runs (2-3 hours on fastest card) v8.20 (cuda60)

ROBtheLIONHEART
Send message
Joined: 21 Nov 13
Posts: 34
Credit: 636,026,131
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 35841 - Posted: 24 Mar 2014 | 3:03:02 UTC - in response to Message 35827.
Last modified: 24 Mar 2014 | 3:14:06 UTC

I can confirm . 8.20 cuda 6 short run ; ran one each on gtx770 & gtx780 WinXP Pro 64bit with the 335.28 driver all went fine. Only just slightly longer GPU run time than observed with 5.5 and 332.21 driver.



PS: I have this wild dream that one day Nvidia comes out with a new driver and it actually shortens GPU run time ! DARE TO DREAM :)

Jeremy Zimmerman
Send message
Joined: 13 Apr 13
Posts: 61
Credit: 726,605,417
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwat
Message 35849 - Posted: 24 Mar 2014 | 10:39:11 UTC - in response to Message 35827.

Try the new version 820


Moved one of the XP Pro32 machines back to 335.28 last night and it just completed a 8.20 Cuda60 WU this morning. This one was a short on a GTX460.

http://www.gpugrid.net/result.php?resultid=8012977

I'll move the other XP machine back to 335.28 now.

Thank you.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 35851 - Posted: 24 Mar 2014 | 11:02:26 UTC - in response to Message 35841.

PS: I have this wild dream that one day Nvidia comes out with a new driver and it actually shortens GPU run time ! DARE TO DREAM :)


Doesn't really happen with compute applications the way it does with games. I suspect that the larger performance increases boasted about for individual games comes from shipping manually-optimised versions of a game's shader kernels along with the driver.

For compute applications (for ours at least), that's not possible. We'll only get a benefit from the driver if it addresses system-level issues; for example the launch overhead of WDM.

Matt

TheFiend
Send message
Joined: 26 Aug 11
Posts: 99
Credit: 2,500,112,138
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35872 - Posted: 24 Mar 2014 | 22:12:54 UTC

Finally got some of the new 820(CUDA60) units on my XP32 cruncher and they started ok without erroring out :-)

Thanks for sorting out the problem with the app!!!

Jeremy Zimmerman
Send message
Joined: 13 Apr 13
Posts: 61
Credit: 726,605,417
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwat
Message 35874 - Posted: 24 Mar 2014 | 23:42:06 UTC - in response to Message 35849.

Update on 820 Cuda60 on XP Pro32

Computer 1 completed another for 2 good and 0 errors
Computer 2 I switched this morning to 335.28 completed 1, 1 in progress, and 0 errors.

Looks resolved. Again, thanks.

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1576
Credit: 5,517,861,851
RAC: 8,636,022
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35882 - Posted: 25 Mar 2014 | 11:00:44 UTC

I'm still getting the occasional v8.15 allocated to my Maxwell - which is a bit of a waste for all concerned.

Task 8064144

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 35886 - Posted: 25 Mar 2014 | 13:53:24 UTC - in response to Message 35882.


I'm still getting the occasional v8.15 allocated to my Maxwell


Don't know what's going wrong there. Try a project reset?

Matt

Profile FourOh
Send message
Joined: 20 Feb 14
Posts: 3
Credit: 100,000,070
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwat
Message 35887 - Posted: 25 Mar 2014 | 14:04:56 UTC - in response to Message 35886.

Same here: My 750 Ti is getting Cuda55 long work units and they all error out... the short units are Cuda60 and are successful. A few days ago I got some long run Cuda60 units which were also sucessful - but I'm not getting those anymore.

Is there anything I can do to force Cuda 6 long run units?

http://www.gpugrid.net/results.php?hostid=170512

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 35888 - Posted: 25 Mar 2014 | 14:46:19 UTC - in response to Message 35887.

Oh, you are talking about long. The app isn't on acemdlong yet. No until I'm happy with the results I get on short.


Matt

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1576
Credit: 5,517,861,851
RAC: 8,636,022
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35889 - Posted: 25 Mar 2014 | 16:48:05 UTC - in response to Message 35886.

I'm still getting the occasional v8.15 allocated to my Maxwell

Don't know what's going wrong there. Try a project reset?

Matt

I don't see how that would help? I started testing the card with short run tasks, switched to long tasks when the the cuda60 app was made available. Got a long task error when the highest version dropped back to cuda55, so switched to short tasks again.

Mostly, the short tasks have been tagged as cuda60, and have run successfully. It's just that single short task allocated at 10:47 this morning which failed because of the cuda55 tagging: since then, I've completed one cuda60 task without error, and I'm in the middle of another one now.

All tasks for host 170387

Which plan_class a task is allocated to use (cuda42, cuda55, cuda60) isn't something either we or our BOINC clients can control (though some wish....). Currently, it's a server decision only, which is why I drew attention to it.

Referring to Specifying plan classes in XML, it looks as if you may need filter the lower plan_classes (cuda42, cuda55) with

Fields for NVIDIA GPU apps:

<max_nvidia_compcap>0499</max_nvidia_compcap>
maximum compute capability

or something like that - I'm not 100% certain of my translation of "<5.0" into MMmm format.

TheFiend
Send message
Joined: 26 Aug 11
Posts: 99
Credit: 2,500,112,138
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 35890 - Posted: 25 Mar 2014 | 16:49:15 UTC

I've had 6 App820(CUDA60) units successfully complete on my XP32 cruncher... Looking good!!!

GoodFodder
Send message
Joined: 4 Oct 12
Posts: 53
Credit: 333,467,496
RAC: 0
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 35892 - Posted: 25 Mar 2014 | 21:31:13 UTC

Agree; 820 now looking good on win x86 - gtx 650ti

Thanks

funkydude
Send message
Joined: 29 Mar 14
Posts: 5
Credit: 37,067,828
RAC: 0
Level
Val
Scientific publications
watwatwatwat
Message 35980 - Posted: 29 Mar 2014 | 2:55:43 UTC - in response to Message 35882.
Last modified: 29 Mar 2014 | 2:57:50 UTC

I'm still getting the occasional v8.15 allocated to my Maxwell - which is a bit of a waste for all concerned.

Task 8064144


This is still an issue. I only just attached to the project and my first unit was cuda55 which errored. My 2nd unit is cuda60.

Task 8203849

funkydude
Send message
Joined: 29 Mar 14
Posts: 5
Credit: 37,067,828
RAC: 0
Level
Val
Scientific publications
watwatwatwat
Message 36009 - Posted: 30 Mar 2014 | 22:20:37 UTC - in response to Message 35980.

Should we detach until this is fixed? Half my units are erroring due to 8.15.

This poor unit keeps being sent as 8.15 http://www.gpugrid.net/workunit.php?wuid=5508762

funkydude
Send message
Joined: 29 Mar 14
Posts: 5
Credit: 37,067,828
RAC: 0
Level
Val
Scientific publications
watwatwatwat
Message 36062 - Posted: 2 Apr 2014 | 16:23:19 UTC - in response to Message 36009.

I guess no one cares enough. I'll detach, back to PrimeGrid with me.

Profile skgiven
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36063 - Posted: 2 Apr 2014 | 16:47:29 UTC - in response to Message 36062.

I would keep running the WU's, but I would abort any 5.5 I see downloading. The WU's that fail do so very quickly but there is a lot of wasted Internet usage.
____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 321,525,386
RAC: 477,412
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36065 - Posted: 2 Apr 2014 | 18:36:18 UTC - in response to Message 36063.

I would keep running the WU's, but I would abort any 5.5 I see downloading. The WU's that fail do so very quickly but there is a lot of wasted Internet usage.

And, at the moment, there is a lot of idle-time due to slow server ...

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 36067 - Posted: 2 Apr 2014 | 19:37:24 UTC - in response to Message 36063.

It would be incorrect to say I understand why the scheduler is fickle in giving out cuda55 and cuda60 to Maxwell machines, but I think I can see how to stop it happening. Scheduler restart shortly.

Matt

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36068 - Posted: 2 Apr 2014 | 19:48:02 UTC

One day, my heterogeneous PC will have: 1 Maxwell GPU, 1 Kepler GTX 660 Ti, and 1 Fermi GTX 460... while running the latest NVIDIA drivers. I hope that, whatever scheduler changes you make, will still allow for heterogeneous scenarios such as mine.

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1576
Credit: 5,517,861,851
RAC: 8,636,022
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36070 - Posted: 2 Apr 2014 | 21:12:40 UTC - in response to Message 36067.

I think the scheduler is written to 'test' sub-optimal plan_classes randomly, to avoid a client getting stuck indefinitely in a one-off rogue allocation.

That means that the periodic 'ping' with cuda55 is deliberate, and has to be actively prevented when, as now, there's an app or two which are incompatible with a certain class of cards or (more commonly) drivers.

Use that max_compute_capability (check the tag name - it's probably not that) on the lower plan classes to prevent them being sent to Maxwell or above.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 36074 - Posted: 3 Apr 2014 | 15:10:19 UTC - in response to Message 36070.

Should be fixed now.

Matt

Profile Mumak
Avatar
Send message
Joined: 7 Dec 12
Posts: 92
Credit: 225,897,225
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36238 - Posted: 11 Apr 2014 | 21:44:30 UTC

I don't receive any long tasks on my 750 Ti. Should I be getting them ?
Win7 x64, driver 337.50

Jozef J
Send message
Joined: 7 Jun 12
Posts: 112
Credit: 1,118,845,172
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36239 - Posted: 11 Apr 2014 | 21:54:38 UTC - in response to Message 35889.
Last modified: 11 Apr 2014 | 22:05:12 UTC

short and long..

Peter_M
Send message
Joined: 25 Feb 14
Posts: 15
Credit: 23,570,837
RAC: 0
Level
Pro
Scientific publications
watwatwatwatwat
Message 36262 - Posted: 13 Apr 2014 | 14:55:46 UTC - in response to Message 36238.

@Mumak, I dont get any either (Ubuntu 12.04.4, GTX750Ti) since about two days, but the server status says always only 15, 21, 27 are available, so I ***guess*** there are simply much less long runs available than there is demand.

Profile Beyond
Avatar
Send message
Joined: 23 Nov 08
Posts: 1112
Credit: 6,162,416,256
RAC: 0
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36389 - Posted: 18 Apr 2014 | 15:32:17 UTC

Doesn't seem that long cuda60 WUs are being sent out any more. Any particular reason? Has the bug with the cuda55 app that causes WU crashes when a machine is rebooted or BOINC is restarted been fixed?

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36402 - Posted: 18 Apr 2014 | 21:37:55 UTC - in response to Message 36389.
Last modified: 18 Apr 2014 | 21:41:02 UTC

My research indicates that I am still being given 8.15 apps that still infuriatingly crash. It seems that they never updated the non-cuda6 applications to the fixed 8.20 version :(

I continue to lose massive amounts of work every 3 days or so, as my computer usage habits require that I shutdown BOINC for a couple hours, and then the 8.15 tasks fail. It sucks.

TJ
Send message
Joined: 26 Jun 09
Posts: 815
Credit: 1,470,385,294
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36436 - Posted: 19 Apr 2014 | 14:54:37 UTC - in response to Message 36402.

Please try to suspend all work first and to then the reboot. That works for me, no errors when I start all projects again after booting. I am only getting 8.15 apps as I don't upgrade my 331.82 drivers yet.
____________
Greetings from TJ

GPUGRID Role account
Send message
Joined: 15 Feb 07
Posts: 134
Credit: 1,349,535,983
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36437 - Posted: 19 Apr 2014 | 15:30:54 UTC - in response to Message 36389.
Last modified: 19 Apr 2014 | 15:31:06 UTC


Doesn't seem that long cuda60 WUs are being sent out any more. Any particular reason?


That's correct for Linux. Too many clients were not correctly reporting the Nvidia driver version, which makes correct scheduling difficult.

Matt

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36443 - Posted: 19 Apr 2014 | 16:37:52 UTC - in response to Message 36437.

For Windows, I am still regularly getting 8.15 tasks. It's almost as if the non-cuda60 app versions were not rebuilt for 8.20. Any hopes of seeing it get fixed (since the 8.15's have the restart/resume bug?)

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1576
Credit: 5,517,861,851
RAC: 8,636,022
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36447 - Posted: 19 Apr 2014 | 17:12:44 UTC - in response to Message 36443.

For Windows, I am still regularly getting 8.15 tasks. It's almost as if the non-cuda60 app versions were not rebuilt for 8.20. Any hopes of seeing it get fixed (since the 8.15's have the restart/resume bug?)

You can always check the current build status on the applications page.

We do appear to be in a transitional state at the moment, with a number of imbalances between the long and short queues again.

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36448 - Posted: 19 Apr 2014 | 17:21:34 UTC - in response to Message 36447.
Last modified: 19 Apr 2014 | 17:22:53 UTC

To clarify what I meant: There was an 8.20 cuda60 app on the Long Queue (proof pasted below), but now that app is gone, leaving only the buggy 8.15 apps. The applications page doesn't even indicate 8.20 on Long at all, and is a bit misleading.

I don't know what's going on, really. I just know that 8.20 seems more stable, yet I'm still being given 8.15's on the Long Queue, and they end up wasting work. :(

Yes, we appear to be in a transitional state. It just doesn't make sense why we are.

Proof:
Name I1100R11-SDOERR_BARNA-3-4-RND7766_0
Workunit 6406602
Created 9 Apr 2014 | 11:43:56 UTC
Sent 9 Apr 2014 | 14:54:40 UTC
Received 10 Apr 2014 | 8:49:06 UTC
Server state Over
Outcome Success
Client state Done
Exit status 0 (0x0)
Computer ID 153764
Report deadline 14 Apr 2014 | 14:54:40 UTC
Run time 48,792.57
CPU time 7,842.47
Validate state Valid
Credit 137,700.00
Application version Long runs (8-12 hours on fastest card) v8.20 (cuda60)

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36449 - Posted: 19 Apr 2014 | 17:24:04 UTC
Last modified: 19 Apr 2014 | 17:24:43 UTC

Worse yet, I think I had managed to, at some point, get an 8.20 task to error out with the "The file exists. (0x50) - exit code 80 (0x50)" error I had been seeing with the 8.15's. Saddening and maddenning.

Name e5s7_e3s9f68-GIANNI_trypben1MCavg09-0-1-RND4755_1
Workunit 6406263
Created 9 Apr 2014 | 10:04:32 UTC
Sent 9 Apr 2014 | 12:34:36 UTC
Received 9 Apr 2014 | 14:53:42 UTC
Server state Over
Outcome Computation error
Client state Compute error
Exit status 80 (0x50) Unknown error number
Computer ID 153764
Report deadline 14 Apr 2014 | 12:34:36 UTC
Run time 7,386.87
CPU time 1,743.23
Validate state Invalid
Credit 0.00
Application version Long runs (8-12 hours on fastest card) v8.20 (cuda60)
Stderr output

<core_client_version>7.3.15</core_client_version>
<![CDATA[
<message>
The file exists.
(0x50) - exit code 80 (0x50)
</message>
<stderr_txt>
# GPU [GeForce GTX 460] Platform [Windows] Rev [3301M] VERSION [60]
# SWAN Device 1 :
# Name : GeForce GTX 460
# ECC : Disabled
# Global mem : 1024MB
# Capability : 2.1
# PCI ID : 0000:08:00.0
# Device clock : 1526MHz
# Memory clock : 1900MHz
# Memory width : 256bit
# Driver version : r337_00 : 33750
# GPU 0 : 67C
# GPU 1 : 57C
# GPU 2 : 74C
# GPU 0 : 68C
# GPU 1 : 60C
# GPU 0 : 69C
# GPU 1 : 63C
# GPU 1 : 65C
# GPU 0 : 70C
# GPU 1 : 66C
# GPU 0 : 71C
# GPU 1 : 68C
# GPU 1 : 69C
# GPU 0 : 72C
# GPU 1 : 70C
# GPU 1 : 71C
# GPU 2 : 75C
# GPU 1 : 72C
# GPU 2 : 76C
# GPU 2 : 77C
# BOINC suspending at user request (exit)
# GPU [GeForce GTX 460] Platform [Windows] Rev [3301M] VERSION [60]
# SWAN Device 1 :
# Name : GeForce GTX 460
# ECC : Disabled
# Global mem : 1024MB
# Capability : 2.1
# PCI ID : 0000:08:00.0
# Device clock : 1526MHz
# Memory clock : 1900MHz
# Memory width : 256bit
# Driver version : r337_00 : 33750
# GPU 0 : 66C
# GPU 1 : 58C
# GPU 2 : 70C
# GPU 0 : 67C
# GPU 1 : 61C
# GPU 2 : 72C
# GPU 0 : 68C
# GPU 1 : 63C
# GPU 2 : 73C
# BOINC suspending at user request (exit)

</stderr_txt>
]]>

Profile skgiven
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36458 - Posted: 20 Apr 2014 | 10:29:47 UTC - in response to Message 36447.

At present the demand for all types of WU outstrips supply, server status. The projects current GigaFLOPs is 1,359,099. With 3450 GPU WU's in the wild, and a maximum of 2/GPU that means there is over 1725 GPU's attached to the project. A mere 1,401 CPU WU's is even more limiting. Clearly the project is struggling to maintain WU supply, never mind honing the apps, developing new research models and introducing server side fixes.

On the 22 Mar the CUDA6 Long app was suspended/removed. Matt later said he doesn’t want to put it on the Long queue until he’s happy with the results from the short queue. This makes sense as it's primarily there to support Maxwell's, which are entry level for GPUGrid (the top GPU's are 2.4 times faster).

max_compute_capability was applied a while ago, to override the scheduler (which tests other apps). Presumably this was only done for the short queue CUDA6 apps.

If all the apps need to be rebuilt (for this and other reasons) it will take time...
____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

Peter_M
Send message
Joined: 25 Feb 14
Posts: 15
Credit: 23,570,837
RAC: 0
Level
Pro
Scientific publications
watwatwatwatwat
Message 36464 - Posted: 20 Apr 2014 | 16:52:32 UTC

Thanks skgiven,
finally I know why I dont get any long WU's anymore :)

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 36466 - Posted: 20 Apr 2014 | 21:55:41 UTC - in response to Message 36402.

jacob,

There will be an update for the older versions of the windows application coming tomorrow.

Matt

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36468 - Posted: 20 Apr 2014 | 22:56:28 UTC - in response to Message 36466.
Last modified: 20 Apr 2014 | 22:56:43 UTC

Hurray!! Thanks!! [I'll be sure to test the normal scenarios of exiting/restarting BOINC, and suspending/resuming tasks without restarting... as I rely on those scenarios all of the time!]

Profile Beyond
Avatar
Send message
Joined: 23 Nov 08
Posts: 1112
Credit: 6,162,416,256
RAC: 0
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36485 - Posted: 21 Apr 2014 | 16:26:22 UTC - in response to Message 36466.

There will be an update for the older versions of the windows application coming tomorrow.

Matt

Received one GERRARD cuda60 long WU about 4 hours ago. Hopeful that the app results will be good. The Maxwells will be happy and so will the rest of us :-)

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 36488 - Posted: 21 Apr 2014 | 16:37:09 UTC - in response to Message 36468.

cuda-42 and cuda-55 are updated now.

As an aside, I'll be deprecating cuda-55 soon. Since we've had to deploy a cuda-60 app for the Maxwells, there's not much point keeping it around: it doesn't offer any performance benefit over cuda-42[1], and there are still plenty of hosts that need the older version.

Matt

[1] Any performance benefit you think you've seen is actually from using a more modern driver.

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36490 - Posted: 21 Apr 2014 | 16:41:58 UTC - in response to Message 36488.

Thank you so much Matt. I know this will help to improve stability, although I think there is still some lingering issue, even in 8.20. :) I'm glad we are moving forward. Is there any way you would consider including additional debug in the stderr.txt, especially during suspends/resumes, especially so we might be better able to figure out why a task might abruptly just quit/exit with an error?

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 36491 - Posted: 21 Apr 2014 | 16:51:13 UTC - in response to Message 36490.
Last modified: 21 Apr 2014 | 16:51:52 UTC

Jacob,

It's on the todo list! I'm going to leave 820 to settle for a week or so to get some good failure stats, before making any more changes.

Right now I am doing work on the CPU app, and also on our internal infrastructure, improving the tools that the researchers here in the lab use to put work on GPUGRID.

The latter's relevant to you guys as it should i) reduce the number of bad WUs we put out and ii) reduce the variation in WU runtime and credit allocation.

Matt

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 36492 - Posted: 21 Apr 2014 | 16:57:02 UTC - in response to Message 36490.

Actually, I have to put out another revision, as I inadvertently missed out G80 support in version 820 (yes, there are still enough GTX280s out there to care!).
So, tell me what you want in the next 10 minutes, and you might well get it.

Matt

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36495 - Posted: 21 Apr 2014 | 17:03:38 UTC - in response to Message 36493.

I'd want anything that would indicate WHY a task ended prematurely. I'd want it printed in stderr.txt.

Profile skgiven
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36498 - Posted: 21 Apr 2014 | 17:30:35 UTC - in response to Message 36493.
Last modified: 21 Apr 2014 | 17:38:32 UTC

Actually, I have to put out another revision, as I inadvertently missed out G80 support in version 820 (yes, there are still enough GTX280s out there to care!).
So, tell me what you want in the next 10 minutes, and you might well get it.

Matt

I know what you mean but to be precise the G80's (CC1.0) are no longer supported. Ditto for the next incarnations G92... (CC1.1).
It's predominantly the GT200 (and mostly 55nm) models of the high end GF200 range that still just about, occasionally work (CC1.3).
Even the CC1.2 cards no longer work AFAIK.
____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 36501 - Posted: 21 Apr 2014 | 17:47:38 UTC - in response to Message 36498.
Last modified: 21 Apr 2014 | 17:52:52 UTC

Quite right, G2xx/sm13 is what I meant.

Checking now, I see sm13 cards now amount to <2% of compute capacity.

I shouldn't have bothered.

Matt

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 36502 - Posted: 21 Apr 2014 | 17:49:10 UTC - in response to Message 36501.

Apps updated to fix some numbering discrepencies and reintroduce (pointless) sm13 support. Version # is now 840 across all Windows applications.

Matt

Profile skgiven
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36504 - Posted: 21 Apr 2014 | 18:01:33 UTC - in response to Message 36502.

Matt, thanks for the support and effort you put in, it's much appreciated.
____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

Trotador
Send message
Joined: 25 Mar 12
Posts: 103
Credit: 9,769,314,893
RAC: 87,581
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36507 - Posted: 21 Apr 2014 | 18:27:01 UTC - in response to Message 36501.

Quite right, G2xx/sm13 is what I meant.

Checking now, I see sm13 cards now amount to <2% of compute capacity.

I shouldn't have bothered.

Matt


Every little contribution should be appreciatted. This user for example will have surely suffered a bit :)

http://www.gpugrid.net/hosts_user.php?userid=67028

No pun intended, your continuos dedication to the volunteers is very much appreciated and in my view unequalled in the distributed projects world.

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 16,606
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36512 - Posted: 21 Apr 2014 | 22:39:25 UTC
Last modified: 21 Apr 2014 | 22:47:10 UTC

Mayday mayday mayday
The 8.40 CUDA5.5 app isn't working on my hosts.
GTX 680 / WinXPx64
GTX 780Ti / WinXPx64

EDIT: it's not working on any Windows host I've checked

EDIT2: I've suspended requesting new work, as I don't want my hosts get banned.

petebe
Send message
Joined: 19 Nov 12
Posts: 31
Credit: 1,549,545,867
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36513 - Posted: 21 Apr 2014 | 22:56:05 UTC

Same here - I have churned out 2 pages of failed v8.20's and 8.40's. Looks like it started with units sent around 1140 UTC. Wingmen are also erroring out.


XP Pro 332.21 GTX780ti and Titan

klepel
Send message
Joined: 23 Dec 09
Posts: 189
Credit: 4,181,686,293
RAC: 1,793,796
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36514 - Posted: 21 Apr 2014 | 23:00:59 UTC

Same here! 8.40 does not work on w7 and driver 332.21.

Jeremy Zimmerman
Send message
Joined: 13 Apr 13
Posts: 61
Credit: 726,605,417
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwat
Message 36516 - Posted: 21 Apr 2014 | 23:29:50 UTC - in response to Message 36514.

Same here. All 8.40 failing on Win7-64 with driver 331.82.

http://www.gpugrid.net/results.php?hostid=165832&offset=0&show_names=1&state=0&appid=

I see that there is a recommended driver for the new app of 334.21 or newer.
http://www.gpugrid.net/forum_thread.php?id=3733#36505

I think I will go ahead and update this pc when I get a chance to see if it will work.

In the mean time, it may be best to not send 8.40 WU's to at least Win7-64 331.82 drivers. Not sure if that is possible.

My WinXP machines are currently crunching on the new WU's without errors. I see a 8.40 Cuda55 on a GTX460 and a 8.40 Cuda60 on a GTX680 on http://www.gpugrid.net/results.php?hostid=149863&offset=0&show_names=1&state=0&appid=.

My other WinXP machine, a 8.40 Cuda60 is on a GTX680 with no issues so far. This is on http://www.gpugrid.net/results.php?hostid=158717&offset=0&show_names=1&state=0&appid=

Both WinXP systems are on driver 335.28.

GPUGRID Role account
Send message
Joined: 15 Feb 07
Posts: 134
Credit: 1,349,535,983
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36517 - Posted: 21 Apr 2014 | 23:37:32 UTC - in response to Message 36516.

Yes, don't know what's gone wrong here. I've reverted back to 815 for now.

Matt.

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 16,606
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36518 - Posted: 21 Apr 2014 | 23:56:35 UTC - in response to Message 36517.

Yes, don't know what's gone wrong here. I've reverted back to 815 for now.

I'm still receiving the 8.40 Cuda 5.5 app.

GPUGRID Role account
Send message
Joined: 15 Feb 07
Posts: 134
Credit: 1,349,535,983
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36519 - Posted: 22 Apr 2014 | 0:04:56 UTC - in response to Message 36518.

See if you can get a new 841.

klepel
Send message
Joined: 23 Dec 09
Posts: 189
Credit: 4,181,686,293
RAC: 1,793,796
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36520 - Posted: 22 Apr 2014 | 0:05:49 UTC
Last modified: 22 Apr 2014 | 0:18:09 UTC

Me too! now as a Cuda 4.2.

[Edit] Started in this very moment with version 8.40 and Cuda 4.2. 2 minutes working without problems. [Edit]

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 16,606
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36522 - Posted: 22 Apr 2014 | 0:09:18 UTC - in response to Message 36519.

See if you can get a new 841.

I got a 8.15, and then a 8.41 on my another host.

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 16,606
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36524 - Posted: 22 Apr 2014 | 0:12:54 UTC - in response to Message 36522.

See if you can get a new 841.

I got a 8.15, and then a 8.41 on my another host.

The 8.41 is working on my GTX 680.

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36525 - Posted: 22 Apr 2014 | 0:22:06 UTC

Is 8.41 the same as 8.15?

Or is 8.41 the same as 8.40 with a fix? If so, what was the fix?

Jeremy Zimmerman
Send message
Joined: 13 Apr 13
Posts: 61
Credit: 726,605,417
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwat
Message 36526 - Posted: 22 Apr 2014 | 0:23:16 UTC - in response to Message 36524.

I put the 335.23 driver on my Win7-64 machine, and it is now crunching the 8.40 Cuda55 tasks. They are short and not long, but now crunching and not getting errors. Will leave this driver on for a while. I had a soft spot for the 331.82 driver. Was able to get the better utilization with 331.82 according to Precision as compared to the 335.23.

GPUGRID Role account
Send message
Joined: 15 Feb 07
Posts: 134
Credit: 1,349,535,983
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36527 - Posted: 22 Apr 2014 | 0:28:37 UTC - in response to Message 36525.

841, 840 and 820 are all the same code, I'd just made a mistake in the deployment (calling a cuda60 version cuda55), which only showed up when it hit hosts that weren't cuda 6 capable.

To summarise the current app version: cuda42 and cuda55 are version 841, cuda60 is 840. These are all the same code, just for different cuda revisions, and all include with the fix that prompted this all.

Hohum.

Matt

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36528 - Posted: 22 Apr 2014 | 0:30:28 UTC - in response to Message 36527.

Hang in there, Matt. Thanks for the prompt response, for keeping us informed, and for moving forward with the apps. Much respect.

GPUGRID Role account
Send message
Joined: 15 Feb 07
Posts: 134
Credit: 1,349,535,983
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36529 - Posted: 22 Apr 2014 | 0:33:49 UTC - in response to Message 36526.


I put the 335.23 driver on my Win7-64 machine, and it is now crunching the 8.40 Cuda55 tasks. They are short and not long, but now crunching and not getting errors. Will leave this driver on for a while. I had a soft spot for the 331.82 driver. Was able to get the better utilization with 331.82 according to Precision as compared to the 335.23.


Remember SWAN_SYNC? Next time I rev the app, I'll introduce the ability to force busy waiting, which ought to give best performance, at the cost of CPU.

Matt

ExtraTerrestrial Apes
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 17 Aug 08
Posts: 2705
Credit: 1,311,122,549
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36531 - Posted: 22 Apr 2014 | 10:35:27 UTC - in response to Message 36529.

Remember SWAN_SYNC? Next time I rev the app, I'll introduce the ability to force busy waiting, which ought to give best performance, at the cost of CPU.

All thumbs up for providing it as an option, for those who really want or need it!

MrS
____________
Scanning for our furry friends since Jan 2002

ExtraTerrestrial Apes
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 17 Aug 08
Posts: 2705
Credit: 1,311,122,549
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36558 - Posted: 22 Apr 2014 | 21:12:13 UTC - in response to Message 36529.

Remember SWAN_SYNC? Next time I rev the app, I'll introduce the ability to force busy waiting, which ought to give best performance, at the cost of CPU.

In the other thread you said 8.41 would already have it. I have such a CUDA 6 WU running under Win 8.1. I created a user or system environment variable called SWAN_SYNC, set it to 0 and rebooted. However, CPU usage remains at 1.4 - 1.8% (8 threads), so it's obviously not working yet. Did I do anything wrong?

MrS
____________
Scanning for our furry friends since Jan 2002

Profile skgiven
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36564 - Posted: 22 Apr 2014 | 22:24:44 UTC - in response to Message 36558.

Try setting SWAN_SYNC to 1.
I can't test that yet because I'm running two 8.40 WU's. Maybe tomorrow I'll get some 8.41 WU's...
____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

TJ
Send message
Joined: 26 Jun 09
Posts: 815
Credit: 1,470,385,294
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36566 - Posted: 22 Apr 2014 | 22:54:49 UTC - in response to Message 36558.
Last modified: 22 Apr 2014 | 23:01:33 UTC

Remember SWAN_SYNC? Next time I rev the app, I'll introduce the ability to force busy waiting, which ought to give best performance, at the cost of CPU.

In the other thread you said 8.41 would already have it. I have such a CUDA 6 WU running under Win 8.1. I created a user or system environment variable called SWAN_SYNC, set it to 0 and rebooted. However, CPU usage remains at 1.4 - 1.8% (8 threads), so it's obviously not working yet. Did I do anything wrong?

MrS

How can we do that set the environment variable for SWAN_SYNC? If that helps performance I might try updating to latest beta driver and see how the 780Ti will perform then.

Edit: Sorry for spamming, I found it here: http://www.gpugrid.net/forum_thread.php?id=2123&nowrap=true#16463
Did a search in the forum, but did not find, did a search in Google and there is the answer.
____________
Greetings from TJ

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36569 - Posted: 23 Apr 2014 | 3:28:14 UTC - in response to Message 36558.
Last modified: 23 Apr 2014 | 3:45:40 UTC

Remember SWAN_SYNC? Next time I rev the app, I'll introduce the ability to force busy waiting, which ought to give best performance, at the cost of CPU.

In the other thread you said 8.41 would already have it. I have such a CUDA 6 WU running under Win 8.1. I created a user or system environment variable called SWAN_SYNC, set it to 0 and rebooted. However, CPU usage remains at 1.4 - 1.8% (8 threads), so it's obviously not working yet. Did I do anything wrong?

MrS


It is working for me, sort of, on my GTX 660 Ti, using the 8.41 cuda60 app. But it seems it is bugged - read on.

Note: You don't have to restart Windows in order to make this work. I'm using Process Explorer to monitor the CPU usage.

- If I close BOINC, go to Control Panel -> System -> Advanced -> Environment Variables, set a System variable SWAN_SYNC set to value 0, restart BOINC, I see the process use a full core.
- If I close BOINC, go to Control Panel -> System -> Advanced -> Environment Variables, set a System variable SWAN_SYNC set to value 1, restart BOINC, I see the process use a full core.
- If I close BOINC, remove the System variable SWAN_SYNC, restart BOINC, I see the process use a partial (approximately 1/12th of a) core.

This leads me to believe the feature is bugged. I would have thought the application would have acted differently, when setting the variable to 1 vs setting it to 0. It's only acting differently based on the EXISTENCE of the variable, not the SETTING of the variable. Bug?

Now I get to stay up all night, contemplating whether I want to actually use this. Sigh. Thanks for making in an option at least. We appreciate options, we really do.

Trotador
Send message
Joined: 25 Mar 12
Posts: 103
Credit: 9,769,314,893
RAC: 87,581
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36570 - Posted: 23 Apr 2014 | 4:18:13 UTC

I was so happy receiving just cuda55/cuda42 wus for the GTX660Ti and now I'm receiving cuda60 units that are all failing since my driver is old but was perfect for my cards and ubuntu system.

Peter_M
Send message
Joined: 25 Feb 14
Posts: 15
Credit: 23,570,837
RAC: 0
Level
Pro
Scientific publications
watwatwatwatwat
Message 36571 - Posted: 23 Apr 2014 | 5:29:16 UTC

Hello guys,

there is also something wrong with some long WU's on Maxwell cards,

I'm on GTX750Ti here, Driver 334.21, Ubuntu 12.04.4 64 bit.

I have a A2ART4Ex04x21-GERARD_A2ART4E-1-14-RND8074_3 task, cuda 60 8.21 and after half an hour its at 0.2% done, CPU is at almost 100% while GPU is almost idle.

Profile skgiven
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36573 - Posted: 23 Apr 2014 | 7:41:44 UTC - in response to Message 36571.
Last modified: 23 Apr 2014 | 7:44:05 UTC

I had SWAN_SYNC=0 set as a User Variable, from way back, and it worked as soon as I used the 8.41 app version. It was the case that it should be set as an environmental variable and should be set to 0, but it use to work when set to other numbers including 1. However, I remember Gianni or Toni wasn't happy with it being set to other numbers - don't know why?

I found that the GPU usage rose by ~2% (to 92% and 94%) on my one W7 system (770 and 670; GK104 cards), but I am using more than 50% of the CPU's (100% now). At 50%, for me, I saw no significant difference from the drivers (actually newer drivers were slightly faster), but others found that their GK110 cards were slightly slower with the newer drivers. I wonder if that is still the case?

Is SWAN_SYNC available for Linux?

Peter_M, you completed other work with the 8.21 app, so it's probably not an app issue. It sounds like the WU is/was just running very slow. Check the GPU clocks in NVidia X server and if need be restart the application, system or even abort the WU. Are you running CPU tasks as well as GPU tasks? It doesn't look like it but if you are try to suspend the CPU work.
____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

GPUGRID Role account
Send message
Joined: 15 Feb 07
Posts: 134
Credit: 1,349,535,983
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36575 - Posted: 23 Apr 2014 | 7:59:57 UTC - in response to Message 36573.

skgiven,

SWAN_SYNC it has different meaning now - it merely needs to be present (set to any value at all, including 0) to have an effect.

Matt

ExtraTerrestrial Apes
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 17 Aug 08
Posts: 2705
Credit: 1,311,122,549
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36580 - Posted: 23 Apr 2014 | 8:45:09 UTC - in response to Message 36558.
Last modified: 23 Apr 2014 | 8:56:53 UTC

In the other thread you said 8.41 would already have it. I have such a CUDA 6 WU running under Win 8.1. I created a user or system environment variable called SWAN_SYNC, set it to 0 and rebooted. However, CPU usage remains at 1.4 - 1.8% (8 threads), so it's obviously not working yet. Did I do anything wrong?

Guys, sorry for the confusion. After sleeping over it I changed nothing and came back just to find SWAN_SYNC working, making the app use a full core again. Can't quantify any performance gains yet, though.

Edit: for a statistically insufficient sample size of "1" I saw no change in performance (GTX660Ti, 335.23, Win 8.1, CPU not completely saturated). Which makes sense since otherwise I would have sticked to earlier drivers.

MrS
____________
Scanning for our furry friends since Jan 2002

Jeremy Zimmerman
Send message
Joined: 13 Apr 13
Posts: 61
Credit: 726,605,417
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwat
Message 36588 - Posted: 23 Apr 2014 | 13:04:51 UTC - in response to Message 36580.

Have had SWAN_SYNC set to 0 on all my machines. Also running with the <cpu_usage>1.0</cpu_usage> line in my app_config. Woke up today to see each machine has completed tasks on the 335 driver (XP and Win7) where CPU time is nearly equal to GPU time.

Each thread given to a GPUGrid task is now actually using the whole thread now. Yup, it is working. Thanks.

Trotador
Send message
Joined: 25 Mar 12
Posts: 103
Credit: 9,769,314,893
RAC: 87,581
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36595 - Posted: 23 Apr 2014 | 20:01:12 UTC

All tasks v8.21(cuda60) are failing in my Linux host with driver 304.88. My cards are GTx 660Ti.

What have I to change to run them properly?

Thanks for your help.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 36596 - Posted: 23 Apr 2014 | 20:09:05 UTC - in response to Message 36595.

See the "Important new for Linux crunchers" post in the News.

Trotador
Send message
Joined: 25 Mar 12
Posts: 103
Credit: 9,769,314,893
RAC: 87,581
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36599 - Posted: 23 Apr 2014 | 20:17:47 UTC

Thanks, major issue I see. no time for it now.

Peter_M
Send message
Joined: 25 Feb 14
Posts: 15
Credit: 23,570,837
RAC: 0
Level
Pro
Scientific publications
watwatwatwatwat
Message 36602 - Posted: 24 Apr 2014 | 6:14:53 UTC - in response to Message 36573.

Thank you skgiven,
it seemed to have been a one time issue, other longs are doing well, will report if I encounter it again. And I run tasks on CPU but have a core reserved for GPUGrid always.


Peter_M, you completed other work with the 8.21 app, so it's probably not an app issue. It sounds like the WU is/was just running very slow. Check the GPU clocks in NVidia X server and if need be restart the application, system or even abort the WU. Are you running CPU tasks as well as GPU tasks? It doesn't look like it but if you are try to suspend the CPU work.

Profile Beyond
Avatar
Send message
Joined: 23 Nov 08
Posts: 1112
Credit: 6,162,416,256
RAC: 0
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36608 - Posted: 24 Apr 2014 | 13:17:38 UTC

So now it seems established that SWAN_SYNC reserves a whole CPU core. But is it any faster? If so, how much?

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36610 - Posted: 24 Apr 2014 | 13:20:06 UTC - in response to Message 36608.
Last modified: 24 Apr 2014 | 13:21:29 UTC

It's very easy to test, just close BOINC, create or remove the System Variable, and restart BOINC.

On one of my tests, where I temporarily suspended all projects except GPUGrid (such that no CPU tasks were interfering), I showed GPU Usage go from 93% without SWAN_SYNC, to 96% with SWAN_SYNC. So, that's ~3% speedup, for that sample, which should translate into a similar amount of task completion throughput. But since I run other CPU projects, I have decided to not use SWAN_SYNC.

Profile Beyond
Avatar
Send message
Joined: 23 Nov 08
Posts: 1112
Credit: 6,162,416,256
RAC: 0
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36612 - Posted: 24 Apr 2014 | 14:24:36 UTC - in response to Message 36610.

It's very easy to test, just close BOINC, create or remove the System Variable, and restart BOINC.

On one of my tests, where I temporarily suspended all projects except GPUGrid (such that no CPU tasks were interfering), I showed GPU Usage go from 93% without SWAN_SYNC, to 96% with SWAN_SYNC. So, that's ~3% speedup, for that sample, which should translate into a similar amount of task completion throughput. But since I run other CPU projects, I have decided to not use SWAN_SYNC.

Thanks for the reply. I try to load the CPUs up to the point just before GPU performance starts degrading. At the moment the CPU tasks I'm running have long periods between checkpoints so restarting BOINC is not something I want to do. A 3% speedup doesn't sound like much if sacrificing a CPU task is the result. Since WU types show large differences in GPU usage, I wonder if SWAN_SYNC would have widely varying results?

ExtraTerrestrial Apes
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 17 Aug 08
Posts: 2705
Credit: 1,311,122,549
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36614 - Posted: 24 Apr 2014 | 15:14:47 UTC - in response to Message 36608.

So now it seems established that SWAN_SYNC reserves a whole CPU core. But is it any faster? If so, how much?

In my case (GTX660Ti, 335.23, Win 8.1, CPU not completely saturated) I am not seeing any performance increase due to setting SWAN_SYNC, whereas something like 3% should have been visible during the 4 WUs I've crunched with this setting now. Switching back.

Generally the benefit should increase if CPU interaction is needed more often, which happens for smaller molecules / systems and for faster cards. If anyone profits from this it's going to be high-end GK110 users first.

MrS
____________
Scanning for our furry friends since Jan 2002

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 16,606
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36651 - Posted: 25 Apr 2014 | 19:15:37 UTC - in response to Message 36608.

So now it seems established that SWAN_SYNC reserves a whole CPU core. But is it any faster? If so, how much?

I've experienced with some settings, and it seems that the latest drivers, and CUDA 6.0 tasks are pretty fast without SWAN_SYNC set.
The gain depends on many factors:
1. The GPU: high-end GPUs (GTX 660Ti, 670, 680, 760, 770, 780, 780Ti, Tinans) can gain a little, lesser GPUs can gain less.
2. Operating system: Windows XP is faster than other versions of Windows, but it still can be up to 3% faster with SWAN_SYNC set.
3. The type of the workunit: there are such workunits which use more CPU, they utilize the GPU less, and can gain more by setting SWAN_SYNC (I'm using WinXPx64)
4. The speed and saturation of the CPU cores: The less the CPU usage, the more the GPU utilization. It also depends the CPU app. It is good to know that hyperthreading means that 1 core can handle 2 threads, but these 2 threads won't detain the other only while they don't try to access simultaneously the same resource (FPU) of the core they running on.
5. The CPU affinity of the tasks: the GPUGrid application can gain up to 3% if it runs on the same thread of the CPU all the time (and no other application using the same core).

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36652 - Posted: 25 Apr 2014 | 19:23:05 UTC - in response to Message 36651.

So, would you say that the following is true, regarding GPUGrid SWAN_SYNC:
- If you are after absolute maximum GPUGrid throughput, then use it
- If you are only working on the GPUGrid project, then use it
- If you are also working on other CPU projects, then do not use it

Those are the guidelines I'd recommend, at least.

Profile skgiven
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36653 - Posted: 25 Apr 2014 | 19:43:35 UTC - in response to Message 36652.

It really depends on what you want to prioritise and your system. The number of GPU's you have is important as it will apply to them all, and of course what type they are.
Using SWAN_SYNC means one full CPU thread (or core on AMD's) will be allocated to each GPUGrid app, so if you have 3 low end GPU's and a high end CPU then you could be losing most of 3 threads. If you don't want this then just don't use the Variable. Conversely if you have 3 high end cards then you probably want to get the best out of them.
At least we get to decide!
____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 16,606
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36655 - Posted: 25 Apr 2014 | 22:48:42 UTC - in response to Message 36652.

So, would you say that the following is true, regarding GPUGrid SWAN_SYNC:
- If you are after absolute maximum GPUGrid throughput, then use it

Yes.

- If you are only working on the GPUGrid project, then use it

Yes.

- If you are also working on other CPU projects, then do not use it

I would say you can use it, if you reduce the number of usable CPUs at least by the number of the GPUs in the system.

Those are the guidelines I'd recommend, at least.

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36656 - Posted: 25 Apr 2014 | 22:58:27 UTC - in response to Message 36655.
Last modified: 25 Apr 2014 | 23:01:12 UTC

- If you are also working on other CPU projects, then do not use it

I would say you can use it, if you reduce the number of usable CPUs at least by the number of the GPUs in the system.


I've always hated that advice, because if GPUGrid runs out of work, then you're hopefully working on some other GPU project, but now you've unnecessarily taken out one or more CPUs.

It's much better (in my opinion) to define an appropriate <cpu_usage> value in a GPUGrid app_config.xml file, instead of changing the "X% of the processors" setting (which is admittedly easier).

To each their own. Options are indeed good.

Your approach is good, though -- if you are going to use SWAN_SYNC, then you should somehow make sure that, for each GPUGrid task that is actively running, you "budget" a full core to it. :)

Jeremy Zimmerman
Send message
Joined: 13 Apr 13
Posts: 61
Credit: 726,605,417
RAC: 0
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwat
Message 36682 - Posted: 26 Apr 2014 | 22:32:16 UTC - in response to Message 36656.

Waited until I had a couple different WU's to compare the SWAN_SYNC impact. Wanted a low and high utilization WU to review. Image scales

Did the testing the same as http://www.gpugrid.net/forum_thread.php?id=3634&nowrap=true#35730 To fill the additional threads, SETI and Einstein units were running on the CPU. No reboots between tests in this test were needed. Only had to stop BONIC, change the environment variable, and restart.

These were running under the 8.41 Application Cuda60.

Below is the delta average percentage of SWAN_SYNC Yes - No. So depending on the WU and the number of threads, it will vary. GPU1 was running one of the more intense Nathan_RPS1 while GPU2 was on a lower utilization GERARD_A2ART4E.

Num_Threads GPU1 GPU2 2 2.0 6.1 3 2.3 5.3 4 2.6 5.4 5 2.9 4.4 6 3.1 5.1 7 2.7 3.7 8 2.3 2.5


I was surprised to see higher variation and larger impacts to utilization with a WU which starts with a much lower utilization.

ExtraTerrestrial Apes
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 17 Aug 08
Posts: 2705
Credit: 1,311,122,549
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36685 - Posted: 27 Apr 2014 | 11:40:40 UTC
Last modified: 27 Apr 2014 | 11:42:06 UTC

Thanks, Jeremy!

For beasts such as GTX780Ti anyone should set SWAN_SYNC. For smaller cards it IMO depends on GPU speed, CPU speed and personal preference (as Jacob said). Assuming at least a half-decent CPU I'd recommend the following:

Always use SWAN_SYNC on GTX780Ti or higher
Don't use SWAN_SYNC on GT640 or slower
The transition point between these clear cases should be somewhere between GTX660 and GTX680/770 - depending on CPU speed and personal preference

Edit: a 2.x% higher GPU utilization sounds very good on fast cards, if it translates into equally faster completion times. Do we have any further measurements on this yet?

MrS
____________
Scanning for our furry friends since Jan 2002

TJ
Send message
Joined: 26 Jun 09
Posts: 815
Credit: 1,470,385,294
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36692 - Posted: 27 Apr 2014 | 15:28:38 UTC - in response to Message 36685.

SWAN_SYNC on means setting it to 1?
____________
Greetings from TJ

GPUGRID Role account
Send message
Joined: 15 Feb 07
Posts: 134
Credit: 1,349,535,983
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 36694 - Posted: 27 Apr 2014 | 15:45:29 UTC - in response to Message 36692.

Doesn't matter what it is set to. It just needs to be set.

Matt

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36695 - Posted: 27 Apr 2014 | 15:59:18 UTC - in response to Message 36694.
Last modified: 27 Apr 2014 | 15:59:51 UTC

What Matt means is: It doesn't matter what value it has; it only matters that the variable exists. To use it, just create a system variable called SWAN_SYNC, set it to some value (like 1, doesn't matter, may not even need a value, but just set it to 1 to be sure), then restart BOINC.

Profile skgiven
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36701 - Posted: 27 Apr 2014 | 18:31:08 UTC - in response to Message 36695.

Jeremy Zimmerman, more good work.
Actual runtimes will probably reflect your finding, but may enhance/augment them.
Thanks,
____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

Profile Beyond
Avatar
Send message
Joined: 23 Nov 08
Posts: 1112
Credit: 6,162,416,256
RAC: 0
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36741 - Posted: 30 Apr 2014 | 15:13:55 UTC - in response to Message 36651.
Last modified: 30 Apr 2014 | 15:48:56 UTC

1. The GPU: high-end GPUs (GTX 660Ti, 670, 680, 760, 770, 780, 780Ti, Tinans) can gain a little, lesser GPUs can gain less.

I tried SWAN_SYNC on a couple slower cards with a 128-bit memory bus: a 650TI and a 750TI. No noticeable difference in WU completion time even though the GPU utilization increased by a percent or so. The only real world difference on those cards in Win7-64 was that they now grabbed a whole CPU core so that one less CPU WU could be run. SWAN_SYNC was a losing proposition at least on those GPUs and Win7-64.

Edit: Decided to try SWAN_SYNC on a box with a 750Ti in a PCI 2.0 X4 slot. Will report back with results.

Profile Beyond
Avatar
Send message
Joined: 23 Nov 08
Posts: 1112
Credit: 6,162,416,256
RAC: 0
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36882 - Posted: 21 May 2014 | 14:33:47 UTC - in response to Message 36741.

1. The GPU: high-end GPUs (GTX 660Ti, 670, 680, 760, 770, 780, 780Ti, Tinans) can gain a little, lesser GPUs can gain less.

I tried SWAN_SYNC on a couple slower cards with a 128-bit memory bus: a 650TI and a 750TI. No noticeable difference in WU completion time even though the GPU utilization increased by a percent or so. The only real world difference on those cards in Win7-64 was that they now grabbed a whole CPU core so that one less CPU WU could be run. SWAN_SYNC was a losing proposition at least on those GPUs and Win7-64.

Edit: Decided to try SWAN_SYNC on a box with a 750Ti in a PCI 2.0 X4 slot. Will report back with results.

Did an extended SWAN_SYNC test on 3 machines. Two showed no improvement and one yielded a 1 to 1.5% decrease in run time. All machines also are running an AMD GPU in PCIe slot 0 and 3-4 CPU WUs on Phenom X6 CPUs. SWAN_SYNC at least on these machines is definitely a waste of resources IMO.

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 16,606
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 36887 - Posted: 21 May 2014 | 20:13:42 UTC - in response to Message 36882.

Did an extended SWAN_SYNC test on 3 machines. Two showed no improvement and one yielded a 1 to 1.5% decrease in run time. All machines also are running an AMD GPU in PCIe slot 0 and 3-4 CPU WUs on Phenom X6 CPUs. SWAN_SYNC at least on these machines is definitely a waste of resources IMO.

I do agree.
SWAN_SYNC can make the crunching a little bit faster only under Windows XP. (My previous post wasn't that straightforward about this.)
I assume you did your tests on your computers under Windows 7 (x64). It is known that the more recent OSes than Windows XP have a new Windows Display Driver Model which makes the OS more stable, but it comes with an overhead, which makes the crunching slower on the GPU, and this overhead makes the gain from SWAN_SYNC negligible. However the recent Windows 7 (8, Vista) drivers are faster than the older (CUDA 3.1) versions.

One of my hosts (using Windows XP x64) did (does) an unintended testing of the SWAN_SYNC, as this host sometimes receives CUDA4.2 tasks, which don't use the SWAN_SYNC. This comparison is not fully adequate as I'm comparing CUDA6.0 tasks to CUDA4.2 tasks, and the CUDA 6.0 app is a little bit faster of its own.
This host have two GTX780Ti's:
the faster one (3500MHz RAM clock) is in a PCIe3.0x16 slot, and
the slower one (2700MHz RAM clock) is in a PCIe2.0x4 slot.

NOELIA_BI_3 workunits:
Faster GPU:
without SWAN_SYNC:17.353, 17.243 +5.26%
.....with SWAN_SYNC: 16.483, 16.384
Slower GPU:
without SWAN_SYNC:18.435, 18.426, 18.382, 18.373 +8.56%
.....with SWAN_SYNC: 16.992, 16.958, 16.925, 16.935

SDOERR_BARNA5 workunits
Faster GPU:
without SWAN_SYNC:16.041, 16.060 +6.5%
.....with SWAN_SYNC: 15.104, 15.045
Slower GPU:
without SWAN_SYNC:16.980, 16.975 +9.2%
.....with SWAN_SYNC: 15.545, 15.550

GERARD_A2ARNUL_adapt3 workunits:
Slower GPU:
without SWAN_SYNC:15.685,

GERARD_A2ART4E_adapt workunits:
Faster GPU:
without SWAN_SYNC: 10.977, 10.966 +6.2%
.....with SWAN_SYNC: 10.328, 10.324

SANTI_marsalWTbound2 workunits:
Slower GPU:
without SWAN_SYNC: 18.686 +11.3%
.....with SWAN_SYNC: 16.781
Faster GPU:
.....with SWAN_SYNC: 15.586

NATHAN_RPS1_adapt5 workunits:
Slower GPU:
without SWAN_SYNC: 14.415 +6.9%
.....with SWAN_SYNC: 13.484
Faster GPU:
without SWAN_SYNC: 13.387 +4%
.....with SWAN_SYNC: 12.862

Post to thread

Message boards : News : acemdlong application 815 updated for Maxwell

//