Hello,
I noticed one of my machines is exhibiting a strange phenomena as far as invalids.
In particular, in one of the tasks it completed that were subsequently marked as invalid, this message came up:
[21:17:46][2528][ERROR] Couldn't allocate 36880 bytes of CUDA HS summing memory (error: 715)!
[21:17:46][2528][ERROR] Demodulation failed (error: 1006)!
[21:17:46][2528][WARN ] Sorry, at the moment your system doesn't have enough free CPU/GPU memory to run this task!
------> Returning control to BOINC, delaying next attempt for at least 15 minutes...
------> If this problem persists you should consider aborting this task...
Activated exception handling...
It is for this task: http://einsteinathome.org/task/512544795
and for this computer:
http://einsteinathome.org/host/11896949
Any help? I'm not sure what to suspect, this GPU runs well on SETI@HOME GPU tasks, but it does not like EINSTEIN@HOME for some reason.[/url]
Copyright © 2024 Einstein@Home. All rights reserved.
Weird error message in stderr, help please!
)
How many GPU tasks do you have running at the same time on that host and are you using all 4 cores running CPU tasks at the same time?
The 970's drivers are not all that old but there are about 4 updates since then but probably not the problem.
You were getting valid until the start of August 1st so did you change anything?
You may have already tried but maybe a reboot and try some new Einstein GPU's (or maybe have your Ram tested)
I just had a problem of one of my 7 hosts having Ran problems and I wish it was the first things I checked since I would have saved some hours of trying to figure out what happened.
But I only run GPU's here.
RE: Hello, I noticed one
)
Also are you running more than one task at a time? If so you may want to back that off to one less and see if that frees up enough memory.