3 times longer runtimes under Win 11?

Questions and Answers : Windows : 3 times longer runtimes under Win 11?
Message board moderation

To post messages, you must log in.

AuthorMessage
newman

Send message
Joined: 20 Jul 20
Posts: 3
Credit: 1,305,656
RAC: 0
Message 1399 - Posted: 24 Oct 2021, 16:55:29 UTC

Hi there,
I have just updated to Win 11. The chip driver which should patch the AMD issues is also installed. However my runtime for GPU tasks are now more than 3 times longer as under Win 10:

Win 10: always around 4000 sec
Win 11: 14:000 sec https://www.mlcathome.org/mlcathome/workunit.php?wuid=5755061

Has anybody else made the same experience?

Greetings
Marcus
ID: 1399 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
pianoman [MLC@Home Admin]
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 30 Jun 20
Posts: 462
Credit: 21,406,548
RAC: 0
Message 1400 - Posted: 24 Oct 2021, 17:51:16 UTC - in response to Message 1399.  

Thanks for reporting. We haven't tested on Windows 11, much less cuda on windows 11.

We'll add it to the list, but I suspect this is a windows 11/cuda driver maturity issue.

Have you seen similar slowdowns with other projects' WUs?
ID: 1400 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
bozz4science

Send message
Joined: 9 Jul 20
Posts: 142
Credit: 11,536,204
RAC: 3
Message 1401 - Posted: 24 Oct 2021, 17:56:01 UTC - in response to Message 1399.  
Last modified: 24 Oct 2021, 18:00:40 UTC

As far as I can tell, the slowdown of your runtimes are not (only) connected to your Win11 upgrade.

Just take a look at your stderr file output of your slower task vs. faster ones prior to your upgrade:

Prior to upgrade (Quick task)

[2021-10-23 18:12:53	                main:574]	:	INFO	:	Epoch 1556 | loss: 0.0311986 | val_loss: 0.0312002 | Time: 1904.55 ms
[2021-10-23 18:12:55	                main:574]	:	INFO	:	Epoch 1557 | loss: 0.0311993 | val_loss: 0.0312003 | Time: 1928.85 ms
[2021-10-23 18:12:57	                main:574]	:	INFO	:	Epoch 1558 | loss: 0.0311996 | val_loss: 0.0312058 | Time: 1899.59 ms
[2021-10-23 18:12:59	                main:574]	:	INFO	:	Epoch 1559 | loss: 0.0312017 | val_loss: 0.0312017 | Time: 1945.45 ms
[2021-10-23 18:13:01	                main:574]	:	INFO	:	Epoch 1560 | loss: 0.0311992 | val_loss: 0.0312004 | Time: 1947.02 ms
[2021-10-23 18:13:03	                main:574]	:	INFO	:	Epoch 1561 | loss: 0.0312008 | val_loss: 0.0312009 | Time: 1929.72 ms

Runtime: 4,057 sec & CPU time: 3,881 sec

After upgrade (Slow task)
[2021-10-24 15:38:04	                main:574]	:	INFO	:	Epoch 1546 | loss: 0.0310213 | val_loss: 0.0312575 | Time: 8615.13 ms
[2021-10-24 15:38:12	                main:574]	:	INFO	:	Epoch 1547 | loss: 0.0310251 | val_loss: 0.0312677 | Time: 7332.4 ms
[2021-10-24 15:38:22	                main:574]	:	INFO	:	Epoch 1548 | loss: 0.0310204 | val_loss: 0.0312522 | Time: 9820.51 ms
[2021-10-24 15:38:30	                main:574]	:	INFO	:	Epoch 1549 | loss: 0.0310245 | val_loss: 0.0312602 | Time: 8587.51 ms
[2021-10-24 15:38:37	                main:574]	:	INFO	:	Epoch 1550 | loss: 0.0310288 | val_loss: 0.031248 | Time: 6888.06 ms

Runtime: 14,101 sec & CPU time: 10,746 sec

The variation in computing time per epoch should be marginal only, but in the slow task, it does vary considerably with ∆(deviation) approaching max ~4sec or almost 58%. That combined with the larger gap between runtime and CPU time stays to show that some other system process is infringing the computing process. It seems that your CPU is overcommitted, maybe even through some Win11 upgrade related background processes. And while you're at it, it wouldn't hurt to upgrade your GPU driver. Currently you have installed version 456.71. According to NVIDIA's driver page, the latest version is 496.13. :)

Hope that helps!
ID: 1401 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
newman

Send message
Joined: 20 Jul 20
Posts: 3
Credit: 1,305,656
RAC: 0
Message 1402 - Posted: 24 Oct 2021, 20:36:35 UTC - in response to Message 1401.  

updating the driver was my fist reaction. But this does not help. WU still need about 4 hours. The GPU is showing around 5 % usage in the task manger. So it seems also not over-committed but the other way round. I have never checked GPU usage for MLC but for example milkyway has about 85 % GPU usage.
ID: 1402 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
kotenok2000

Send message
Joined: 17 Jul 20
Posts: 12
Credit: 7,473,347
RAC: 65
Message 1403 - Posted: 24 Oct 2021, 23:00:12 UTC

Try to increase mlds-gpu_9.75_windows-x86_64__cuda10200 priority to realtime.
ID: 1403 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
swiftmallard
Avatar

Send message
Joined: 23 Sep 20
Posts: 24
Credit: 15,318,198
RAC: 1,992
Message 1404 - Posted: 25 Oct 2021, 13:06:02 UTC - in response to Message 1401.  

It seems that your CPU is overcommitted, maybe even through some Win11 upgrade related background processes.


I noticed an almost 20% run time increase working CPU units using Windows 11. That's why I switched back to Windows 10.
ID: 1404 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
newman

Send message
Joined: 20 Jul 20
Posts: 3
Credit: 1,305,656
RAC: 0
Message 1405 - Posted: 25 Oct 2021, 17:49:29 UTC - in response to Message 1404.  

Try to increase mlds-gpu_9.75_windows-x86_64__cuda10200 priority to realtime.


How?
ID: 1405 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote

Questions and Answers : Windows : 3 times longer runtimes under Win 11?

©2022 MLC@Home Team
A project of the Cognition, Robotics, and Learning (CORAL) Lab at the University of Maryland, Baltimore County (UMBC)