Questions and Answers :
Wish list :
Another setting instead of Additional work buffer
Message board moderation
Author | Message |
---|---|
JohnDK Send message Joined: 28 May 00 Posts: 1222 Credit: 451,243,443 RAC: 1,127 |
What I do when the CUDA completion time is way out is to change the <flops></flops> number in the app_info.xml file. When I started my flops was 3.000.000.000, but since BOINC keeps recalculate the completion time I now have it set to 10.000.000.000 flops after I have changed it several times. The finishing time isn't that important I think, problem is that the additional work buffer setting gets affected. I've always wondered why when a CPU WU finishes and BOINC recalculate the completion time, it also changes the GPU completion time, same when a GPU WU finishes, it changes the CPU completion time, what's the idea with that? Anyway, I would like an option of either stopping BOINC recalculating the completion time when I want or an option where instead of the additional work buffer I can say who many of each different WUs I want in the cache. |
John McLeod VII Send message Joined: 15 Jul 99 Posts: 24806 Credit: 790,712 RAC: 0 |
What I do when the CUDA completion time is way out is to change the <flops></flops> number in the app_info.xml file. When I started my flops was 3.000.000.000, but since BOINC keeps recalculate the completion time I now have it set to 10.000.000.000 flops after I have changed it several times. The finishing time isn't that important I think, problem is that the additional work buffer setting gets affected. Because there is only one duration_correction_factor per project. The plan is to (eventually) make it one DCF per application. BOINC WIKI |
©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.