Getting wu's that run up to 20.946% and stall

Questions and Answers : GPU applications : Getting wu's that run up to 20.946% and stall
Message board moderation

To post messages, you must log in.

AuthorMessage
Profile Christine&Rusty
Avatar

Send message
Joined: 28 Nov 03
Posts: 11
Credit: 38,321,501
RAC: 0
United States
Message 1603389 - Posted: 21 Nov 2014, 2:24:36 UTC

I've been getting a lot of these and each group stalls at a different % in each group. Currently am working on this one (opencl_ati5_cat132) and decided to use the "task_debug" thing. Yeah, here again, like I know what I am doing, right. but it did go down through and check each work unit and check them all with some results like this:
    11/20/2014 5:18:58 PM | | log flags: file_xfer, sched_ops, task, task_debug
    11/20/2014 5:26:09 PM | SETI@home | [task] task_state=QUIT_PENDING for 13oc08ab.11968.130514.438086664199.12.90_0 from request_exit()
    11/20/2014 5:26:10 PM | SETI@home | [task] Process for 13oc08ab.11968.130514.438086664199.12.90_0 exited, exit code 0, task state 8
    11/20/2014 5:26:10 PM | SETI@home | [task] task_state=UNINITIALIZED for 13oc08ab.11968.130514.438086664199.12.90_0 from handle_exited_app
    11/20/2014 5:26:10 PM | SETI@home | [task] task_state=EXECUTING for 13oc08ab.11968.130514.438086664199.12.12_0 from start
    11/20/2014 5:30:17 PM | SETI@home | task 13oc08ab.11968.130514.438086664199.12.12_0 suspended by user
    11/20/2014 5:30:18 PM | SETI@home | [task] task_state=QUIT_PENDING for 13oc08ab.11968.130514.438086664199.12.12_0 from request_exit()
    11/20/2014 5:30:34 PM | SETI@home | [task] quit request timed out, killing task 13oc08ab.11968.130514.438086664199.12.12_0
    11/20/2014 5:30:35 PM | SETI@home | [task] Process for 13oc08ab.11968.130514.438086664199.12.12_0 exited, exit code 0, task state 8
    11/20/2014 5:30:35 PM | SETI@home | [task] task_state=UNINITIALIZED for 13oc08ab.11968.130514.438086664199.12.12_0 from handle_exited_app
    11/20/2014 5:30:35 PM | SETI@home | [task] task_state=EXECUTING for 13oc08ab.11968.130514.438086664199.12.90_0 from start


So, remember, like I really know what I am doing, I don't want to just abort them like I did 83 or less others without letting some one know. The computer's ID# is 7419064. This is my Astropulse eating and loving them, the hardest working PC (but not as fast as ID# 7284568), then started coming strange one's I had not seen, "sse" "see3" some with "nocal_100" or something like that and I see some go and some fail/error, computation error, etc. I have been trying to run 2 screens and put SETI on one and Netflix on the big screen but even with hydravision I have not quiet yet got it-I have to do it myself to learn how instead of being told it's "this easy" so bear with me. That's all I guess. Can't fix it, not a quitter, but wasted GPU time is just that-unless it helps solve a problem. And yes, everything is up to date . It's updated into next week sometime, and yes, it's probably a little old, but not near as old as ID #'s 7096043 & 7095613.
Maybe somebody out there knows who to forward this to or it has already been talked about and I flat just missed it looking for other stuff.
Thanks a lot
Happy Hunting
Rusty and Christine


"It don't really hurt 'till the bone shows...."

"SAEPE EXPERTUS, SEMPER FIDELIS, FRATRES AETERNI"
ID: 1603389 · Report as offensive

Questions and Answers : GPU applications : Getting wu's that run up to 20.946% and stall


 
©2024 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.