whole serie of data blocks failing with SoG

Message boards : Number crunching : whole serie of data blocks failing with SoG
Message board moderation

To post messages, you must log in.

Previous · 1 · 2

AuthorMessage
Profile IntenseGuy

Send message
Joined: 25 Sep 00
Posts: 190
Credit: 23,498,825
RAC: 9
United States
Message 2011594 - Posted: 11 Sep 2019, 15:32:14 UTC

Trying the new drivers now.

SOG seem to be running correctly now. Will test longer.
ID: 2011594 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13164
Credit: 1,160,866,277
RAC: 1,873
United States
Message 2011601 - Posted: 11 Sep 2019, 17:41:56 UTC - in response to Message 2011594.  
Last modified: 11 Sep 2019, 17:43:03 UTC

Trying the new drivers now.

SOG seem to be running correctly now. Will test longer.

You need to find some tasks that are the corner case for the failures. The tasks that failed were Arecibo VHARs of AR=2.7. So you need to wait until a new Arecibo file gets loaded and hope for some VHAR tasks. Or wait for some of the inevitable resends from those early failures. Or use the card and drivers on some of the other projects that had failures too like Einstein.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 2011601 · Report as offensive
rob smith Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer moderator
Volunteer tester

Send message
Joined: 7 Mar 03
Posts: 22775
Credit: 416,307,556
RAC: 380
United Kingdom
Message 2011604 - Posted: 11 Sep 2019, 18:01:58 UTC - in response to Message 2011601.  

Those VHAR task look like data that was collected while the telescope was sweeping from one target to another, so probably not a lot of use in them anyway.
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 2011604 · Report as offensive
Jeff

Send message
Joined: 8 May 99
Posts: 5
Credit: 98,361,983
RAC: 150
United States
Message 2011656 - Posted: 11 Sep 2019, 23:55:02 UTC - in response to Message 2011554.  

Version 436.30 is out today. I wonder if nVidia fixed things....
Be the guinea pig and report back.
No mention of it being fixed in the release notes, but there's also no mention of it in the existing issues notes either.


Patiently awaiting the guinea pig report.
Definitely not wanting to try downgrading those drivers yet again.
436.02 started the issue, 436.15 was no better. Not holding my breath with 436.30.
Until I hear that it is finally working properly for CUDA processing I am sticking with 431.60.
ID: 2011656 · Report as offensive
Profile IntenseGuy

Send message
Joined: 25 Sep 00
Posts: 190
Credit: 23,498,825
RAC: 9
United States
Message 2011983 - Posted: 15 Sep 2019, 0:08:35 UTC

Still getting errors with nVidia driver 436.30
ID: 2011983 · Report as offensive
jdzukley Project Donor

Send message
Joined: 6 Apr 11
Posts: 19
Credit: 26,357,809
RAC: 74
United States
Message 2012378 - Posted: 18 Sep 2019, 3:25:35 UTC

I am getting errors too, please reference computer # 7433824 and look at the tasks that errored out. I have 1070 cards, and while I aborted 3 tasks that have not advanced more than 0.6% after many minutes - I had yet to see any task take more than 10 minutes to complete. There are other tasks in the error list that have run times over 4000 seconds before they errored out. All are Arecibo tasks from different dates, and but many other tasks from the same date group have finish successfully...

I look foreword to any and all suggestions.

jdzukley
ID: 2012378 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13164
Credit: 1,160,866,277
RAC: 1,873
United States
Message 2012383 - Posted: 18 Sep 2019, 4:02:11 UTC - in response to Message 2012378.  

I am getting errors too, please reference computer # 7433824 and look at the tasks that errored out. I have 1070 cards, and while I aborted 3 tasks that have not advanced more than 0.6% after many minutes - I had yet to see any task take more than 10 minutes to complete. There are other tasks in the error list that have run times over 4000 seconds before they errored out. All are Arecibo tasks from different dates, and but many other tasks from the same date group have finish successfully...

I look foreword to any and all suggestions.

jdzukley

Depends on whether the Arecibo tasks have a high angle range. Those tasks will error out on the 436 drivers.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 2012383 · Report as offensive
Previous · 1 · 2

Message boards : Number crunching : whole serie of data blocks failing with SoG


 
©2025 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.