Welcome to MilkyWay@home

Auto-aborted GPU WU when changing video cards

Message boards : Number crunching : Auto-aborted GPU WU when changing video cards
Message board moderation

To post messages, you must log in.

AuthorMessage
10esseeTony

Send message
Joined: 31 Aug 11
Posts: 20
Credit: 528,670,571
RAC: 0
Message 63104 - Posted: 6 Feb 2015, 5:03:35 UTC

Hello all, I have a number of Windows boxes, and I've recently acquired a few more video cards, ATI HD4850's and 280X's.

I've been a bit undecided as to which cards should go into which machines, due to PCIe slots, case size, PSU limitations, etc.

My problem is that when changing from a 4850 to a 280X or vice versa, (and uninstalling and reinstalling the correct drivers), BOINC automatically aborts any and all incoming GPU workunits.

I go to my account, and the computer shows the correct video card is recognized by the server. I uninstall and reinstall BOINC, and STILL get auto-aborted workunits.

Other than "QUIT SWAPPING CARDS!" does anyone have any advice? :)
ID: 63104 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
10esseeTony

Send message
Joined: 31 Aug 11
Posts: 20
Credit: 528,670,571
RAC: 0
Message 63105 - Posted: 6 Feb 2015, 6:49:50 UTC - in response to Message 63104.  
Last modified: 6 Feb 2015, 6:50:36 UTC

Well, going from a hd4850 to a 280x it fixed itself within an hour.

My other machine going from a 280x down to a hd4850 is still aborting after 2 days.

I've uninstalled BOINC and the drivers half a dozen times and reinstalled. :-/
ID: 63105 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile mikey
Avatar

Send message
Joined: 8 May 09
Posts: 3315
Credit: 519,941,778
RAC: 22,440
Message 63110 - Posted: 6 Feb 2015, 11:44:37 UTC - in response to Message 63105.  

Well, going from a hd4850 to a 280x it fixed itself within an hour.

My other machine going from a 280x down to a hd4850 is still aborting after 2 days.

I've uninstalled BOINC and the drivers half a dozen times and reinstalled. :-/


Your pc's are hidden so I can't even look at the error messages.
ID: 63110 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
10esseeTony

Send message
Joined: 31 Aug 11
Posts: 20
Credit: 528,670,571
RAC: 0
Message 63112 - Posted: 6 Feb 2015, 20:55:30 UTC - in response to Message 63110.  

http://milkyway.cs.rpi.edu/milkyway/results.php?hostid=594815

http://milkyway.cs.rpi.edu/milkyway/show_host_detail.php?hostid=594815
ID: 63112 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile mikey
Avatar

Send message
Joined: 8 May 09
Posts: 3315
Credit: 519,941,778
RAC: 22,440
Message 63116 - Posted: 7 Feb 2015, 12:39:55 UTC - in response to Message 63112.  

http://milkyway.cs.rpi.edu/milkyway/results.php?hostid=594815

http://milkyway.cs.rpi.edu/milkyway/show_host_detail.php?hostid=594815


The error message is: Exit status 201 (0xc9) EXIT_MISSING_COPROC

Meaning it can't find your gpu so it's auto aborting the units. Are you sharing the pc with someone else and you each have your own login? I see your gpu also only supports OpenCL 1.0, most projects are going to only version 1.02 and above and you could be caught up in that, I don't remember if MW is one of those or not. Another option is what else is your pc doing while trying to crunch? If it is something that is using the gpu, ie gaming, photoshopping, anything graphics intensive, your gpu may not be available to Boinc when Boinc wants it so the units get aborted. In your settings do you have the box checked to 'use the gpu while the pc is in use'?
ID: 63116 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
10esseeTony

Send message
Joined: 31 Aug 11
Posts: 20
Credit: 528,670,571
RAC: 0
Message 63120 - Posted: 7 Feb 2015, 23:07:44 UTC - in response to Message 63116.  

Thanks for looking into it mikey. Milkyway is the last holdout that I'm aware of that still allows the HD4850, which is a shame, because at 200GFLOPS double precision and 110watts max, it's one heck of a performer that can be picked up on ebay for only $30 or less. It's a great option for old dual core PC's with wimpy power supplies.

To answer most of your questions with a single response, I got it working again by formatting and installing Windows 10 beta. When that expires in April it will be time to turn off the 'heaters' anyway. :)

The PC is only for crunching, although it's located in my daughters room (as a heater), she only uses it when her Macbook isn't yet unpacked for her weekend visit, or the Mac is just a few inches further away than she feels like reaching. :)

It's odd that the link to that machine shows it has the card installed, I was given the option to use the GPU in the BOINC Manager, but the error msg says it's missing the coprocessor.

I used to think it was a server-side error, sending OpenCL 1.02 tasks, that just took some time to correct, thus I let it run (CPU crunching) for a few days and yet it did not self repair. Not the first time I had the problem, the other times it self corrected in a fair amount of time.

Thanks again for trying.
ID: 63120 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile mikey
Avatar

Send message
Joined: 8 May 09
Posts: 3315
Credit: 519,941,778
RAC: 22,440
Message 63123 - Posted: 8 Feb 2015, 12:20:22 UTC - in response to Message 63120.  

Thanks for looking into it mikey. Milkyway is the last holdout that I'm aware of that still allows the HD4850, which is a shame, because at 200GFLOPS double precision and 110watts max, it's one heck of a performer that can be picked up on ebay for only $30 or less. It's a great option for old dual core PC's with wimpy power supplies.

To answer most of your questions with a single response, I got it working again by formatting and installing Windows 10 beta. When that expires in April it will be time to turn off the 'heaters' anyway. :)

The PC is only for crunching, although it's located in my daughters room (as a heater), she only uses it when her Macbook isn't yet unpacked for her weekend visit, or the Mac is just a few inches further away than she feels like reaching. :)

It's odd that the link to that machine shows it has the card installed, I was given the option to use the GPU in the BOINC Manager, but the error msg says it's missing the coprocessor.

I used to think it was a server-side error, sending OpenCL 1.02 tasks, that just took some time to correct, thus I let it run (CPU crunching) for a few days and yet it did not self repair. Not the first time I had the problem, the other times it self corrected in a fair amount of time.

Thanks again for trying.


Have you tried Collatz yet, I think they can take some OLD cards still.
http://boinc.thesonntags.com/collatz/

I use Collatz as my backup project on my pc's, meaning I run it when the other projects are down or they are giving me troubles, or even when my teammates are being too slow in their own crunching. He is working thru an intermittent problem though, so he does go down for a day or so here and there.
ID: 63123 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote

Message boards : Number crunching : Auto-aborted GPU WU when changing video cards

©2024 Astroinformatics Group