NVidia 436.xx and later drivers can cause very long compute times especially on Arecibo VHAR work units

Message boards : Number crunching : NVidia 436.xx and later drivers can cause very long compute times especially on Arecibo VHAR work units
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 17 · 18 · 19 · 20

AuthorMessage
robertmiles
Volunteer tester

Send message
Joined: 16 Jan 12
Posts: 213
Credit: 4,117,756
RAC: 6
United States
Message 2041517 - Posted: 30 Mar 2020, 4:35:30 UTC - in response to Message 2041509.  

How do you use GPU-Z to monitor GPU use? It showed me a lot of information about the GPU, not including whether it was being used.

GTX 1080 445.75 hangs.
GTX 1080 442.19 finishes in a few minutes, but the *-benchMB.txt has a lot of messages about files not found.

It's too late here to download another 442 version of the driver - I'll try tomorrow.
ID: 2041517 · Report as offensive     Reply Quote
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13244
Credit: 208,696,464
RAC: 304
Australia
Message 2041519 - Posted: 30 Mar 2020, 4:37:15 UTC - in response to Message 2041517.  

How do you use GPU-Z to monitor GPU use?
Click on the Sensors tab.
Grant
Darwin NT
ID: 2041519 · Report as offensive     Reply Quote
robertmiles
Volunteer tester

Send message
Joined: 16 Jan 12
Posts: 213
Credit: 4,117,756
RAC: 6
United States
Message 2041607 - Posted: 30 Mar 2020, 13:56:23 UTC

GTX 1080 442.74 finishes in about 3 minutes, but the *-benchMB.txt has a lot of messages about files not found.
The GPU use was about 97%.

The sensors tab of GPU-Z made GPU use obvious AFTER I had observed it both with and without another BOINC project using the GPU.
ID: 2041607 · Report as offensive     Reply Quote
Richard Haselgrove Project Donor
Volunteer tester

Send message
Joined: 4 Jul 99
Posts: 14415
Credit: 200,643,578
RAC: 874
United Kingdom
Message 2041611 - Posted: 30 Mar 2020, 14:20:38 UTC - in response to Message 2041607.  

GTX 1080 442.74 finishes in about 3 minutes, but the *-benchMB.txt has a lot of messages about files not found.
What file is missing? state.sah would be worrying, result.sah would be catastrophic.
ID: 2041611 · Report as offensive     Reply Quote
robertmiles
Volunteer tester

Send message
Joined: 16 Jan 12
Posts: 213
Credit: 4,117,756
RAC: 6
United States
Message 2041616 - Posted: 30 Mar 2020, 14:53:57 UTC

result.sah and state.sah were both present - no messages about them.

I got warnings about several of the MB_clFFTplan_GeForceGTX1080_* files not being found, though.

No error messages in the *-benchMB.txt file.

I'm about to download the 442.75 driver for another test run.
ID: 2041616 · Report as offensive     Reply Quote
Richard Haselgrove Project Donor
Volunteer tester

Send message
Joined: 4 Jul 99
Posts: 14415
Credit: 200,643,578
RAC: 874
United Kingdom
Message 2041618 - Posted: 30 Mar 2020, 15:06:05 UTC - in response to Message 2041616.  

Ah, thanks - panic over. The MB_clFFTplan_GeForceGTX1080_* files are - intentionally - generated by the app on the first run on any given machine, and are disposable: if present, they will be used to optimise future runs; if absent, they'll be re-generated.
ID: 2041618 · Report as offensive     Reply Quote
robertmiles
Volunteer tester

Send message
Joined: 16 Jan 12
Posts: 213
Credit: 4,117,756
RAC: 6
United States
Message 2041880 - Posted: 31 Mar 2020, 4:17:52 UTC

The test for the 442.75 driver also hung for my GTX 1080, with no GPU use.

I wrote a rather long set of instructions for running the test and sent it to Nvidia, as an addon to to the problem report
I sent them about a week ago.
ID: 2041880 · Report as offensive     Reply Quote
Jacob Klein
Volunteer tester

Send message
Joined: 15 Apr 11
Posts: 149
Credit: 9,783,406
RAC: 9
United States
Message 2041882 - Posted: 31 Mar 2020, 5:11:05 UTC - in response to Message 2041880.  
Last modified: 31 Mar 2020, 5:13:38 UTC

You mean 445.75, right?? This is a Release 445 driver, a major release from the prior ones.
ID: 2041882 · Report as offensive     Reply Quote
robertmiles
Volunteer tester

Send message
Joined: 16 Jan 12
Posts: 213
Credit: 4,117,756
RAC: 6
United States
Message 2041957 - Posted: 31 Mar 2020, 12:36:45 UTC - in response to Message 2041882.  

You mean 445.75, right?? This is a Release 445 driver, a major release from the prior ones.

Yes. Sorry about the mistake.
ID: 2041957 · Report as offensive     Reply Quote
Jacob Klein
Volunteer tester

Send message
Joined: 15 Apr 11
Posts: 149
Credit: 9,783,406
RAC: 9
United States
Message 2041960 - Posted: 31 Mar 2020, 13:08:14 UTC - in response to Message 2041957.  

I'm glad you also have a repro of the issue, and I thank you for reporting it to NVIDIA via the Driver Feedback Form.
ID: 2041960 · Report as offensive     Reply Quote
Ian&Steve C.
Avatar

Send message
Joined: 28 Sep 99
Posts: 4126
Credit: 1,282,604,591
RAC: 6,640
United States
Message 2041994 - Posted: 31 Mar 2020, 15:02:49 UTC

<24hrs of project life remaining. it'll be over before it hits any desk at Nvidia.
Seti@Home classic workunits: 29,492 CPU time: 134,419 hours

ID: 2041994 · Report as offensive     Reply Quote
Jacob Klein
Volunteer tester

Send message
Joined: 15 Apr 11
Posts: 149
Credit: 9,783,406
RAC: 9
United States
Message 2042156 - Posted: 1 Apr 2020, 2:26:18 UTC

I have confirmation from NVIDIA, that the changes that fixed this issue in R440 driver 442.19, were accidentally removed from the R445 branch.
NVIDIA is looking into next steps.
ID: 2042156 · Report as offensive     Reply Quote
Jacob Klein
Volunteer tester

Send message
Joined: 15 Apr 11
Posts: 149
Credit: 9,783,406
RAC: 9
United States
Message 2045919 - Posted: 20 Apr 2020, 0:47:00 UTC
Last modified: 20 Apr 2020, 0:49:05 UTC

I have re-tested, using the 445.87 driver (from 4/15/2020), and they have again fixed the issue. So ..
445.87 has the fix, for Release 445 Drivers.

Thanks,
Jacob Klein
ID: 2045919 · Report as offensive     Reply Quote
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13244
Credit: 208,696,464
RAC: 304
Australia
Message 2045921 - Posted: 20 Apr 2020, 0:50:47 UTC - in response to Message 2045919.  

I have re-tested, using the 445.87 driver (from 4/15/2020), and they have again fixed the issue. So ..
445.87 has the fix, for Release 445 Drivers.

Thanks,
Jacob Klein
Thanks again for your efforts.
Grant
Darwin NT
ID: 2045921 · Report as offensive     Reply Quote
Jacob Klein
Volunteer tester

Send message
Joined: 15 Apr 11
Posts: 149
Credit: 9,783,406
RAC: 9
United States
Message 2045922 - Posted: 20 Apr 2020, 0:51:21 UTC - in response to Message 2045921.  

You're welcome :)
ID: 2045922 · Report as offensive     Reply Quote
Previous · 1 . . . 17 · 18 · 19 · 20

Message boards : Number crunching : NVidia 436.xx and later drivers can cause very long compute times especially on Arecibo VHAR work units


 
©2021 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.