Message boards :
Number crunching :
Where o where has the CUDA gone????
Message board moderation
Author | Message |
---|---|
Cliff Harding Send message Joined: 18 Aug 99 Posts: 1432 Credit: 110,967,840 RAC: 67 |
Since 7/21, one machine A-SYS running 6.13.1 & Lunatics _x39e, keeps asking for CUDA work and the server says no joy. While the B-SYS running 6.12.33 & Lunatics _x38g is sucking up CUDA work like a vacumn cleaner on steroids. In the mean time the other machine is sucking up MB 6.03 & AP WUs with the same steroids. Any suggestions? I don't buy computers, I build them!! |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
Luck of the draw? Out of my 20 some odd machines some get 0 tasks when they ask and other get work every time they ask. Just seems to be the state of the feeder at the exact moment they ask. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
Darren Wright Send message Joined: 15 Jan 00 Posts: 92 Credit: 17,556,032 RAC: 0 |
why not reschedule units over to the GPU? |
Josef W. Segur Send message Joined: 30 Oct 99 Posts: 4504 Credit: 1,414,761 RAC: 0 |
Since 7/21, one machine A-SYS running 6.13.1 & Lunatics _x39e, keeps asking for CUDA work and the server says no joy. While the B-SYS running 6.12.33 & Lunatics _x38g is sucking up CUDA work like a vacumn cleaner on steroids. In the mean time the other machine is sucking up MB 6.03 & AP WUs with the same steroids. Any suggestions? Report your alpha testing observations for 6.13.1 to the developers. That totally new work fetch approach will obviously operate differently. So you send back the logs with the recommended log flags set, and the developers can analyze and fix it for 6.13.2 or later. Joe |
Cliff Harding Send message Joined: 18 Aug 99 Posts: 1432 Credit: 110,967,840 RAC: 67 |
Since 7/21, one machine A-SYS running 6.13.1 & Lunatics _x39e, keeps asking for CUDA work and the server says no joy. While the B-SYS running 6.12.33 & Lunatics _x38g is sucking up CUDA work like a vacumn cleaner on steroids. In the mean time the other machine is sucking up MB 6.03 & AP WUs with the same steroids. Any suggestions? I don't think that the version of Lunatics is the problem, it has been running perfectly up until the 21st. I even uninstalled and regressed to v.037 and still nojoy, before going back to _x39e. I just think the servers are being stingy with which machines it is sending CUDA to, but I would like it to make up its mind and send me some. I don't buy computers, I build them!! |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14654 Credit: 200,643,578 RAC: 874 |
Since 7/21, one machine A-SYS running 6.13.1 & Lunatics _x39e, keeps asking for CUDA work and the server says no joy. While the B-SYS running 6.12.33 & Lunatics _x38g is sucking up CUDA work like a vacumn cleaner on steroids. In the mean time the other machine is sucking up MB 6.03 & AP WUs with the same steroids. Any suggestions? Joe isn't commenting on your version of Lunatics, he's commenting on your version of BOINC. Read him again - he's right. Do that. |
Cliff Harding Send message Joined: 18 Aug 99 Posts: 1432 Credit: 110,967,840 RAC: 67 |
Since 7/21, one machine A-SYS running 6.13.1 & Lunatics _x39e, keeps asking for CUDA work and the server says no joy. While the B-SYS running 6.12.33 & Lunatics _x38g is sucking up CUDA work like a vacumn cleaner on steroids. In the mean time the other machine is sucking up MB 6.03 & AP WUs with the same steroids. Any suggestions? I apologize for any misunderstanding on Joe's post. Here are my settings for the cc_config.xml file, which one(s) do I turn on? Sched_ops has been turned on for several days, but I see no increase in the log because of it. <cc_config> <log_flags> <task>0</task> <file_xfer>0</file_xfer> <sched_ops>1</sched_ops> <coproc_debug>0</coproc_debug> <cpu_sched>0</cpu_sched> <cpu_sched_debug>0</cpu_sched_debug> <dcf_debug>0</dcf_debug> <sched_op_debug>0</sched_op_debug> <state_debug>0</state_debug> <http_debug>0</http_debug> <http_xfer_debug>0</http_xfer_debug> </log_flags> <options> <use_all_gpus>1</use_all_gpus> </options> </cc_config> I don't buy computers, I build them!! |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14654 Credit: 200,643,578 RAC: 874 |
I apologize for any misunderstanding on Joe's post. Here are my settings for the cc_config.xml file, which one(s) do I turn on? Sched_ops has been turned on for several days, but I see no increase in the log because of it. As in the Alpha Test Announcement |
©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.