Message boards :
Number crunching :
Completion Time?
Message board moderation
Author | Message |
---|---|
JAF Send message Joined: 9 Aug 00 Posts: 289 Credit: 168,721 RAC: 0 |
I got to wondering, is the "to completion" data really necessary/useful? For the project to have to "tune" the software to estimate completion time, with new processors, different L2 cache sizes, and more intense crunching on (larger?) WU's in the future, is it really worth the effort? The database already has a CPU time for each completed WU and the number of WU's credited/pending credit. It wouldn't seem an easy calculation to give a user an "average crunch time per machine" and maybe a second "last ten WU's average CPU time". To me, it just doesn't seem to be worth the effort to estimate completion time. Or am I missing something? |
Keck_Komputers Send message Joined: 4 Jul 99 Posts: 1575 Credit: 4,152,111 RAC: 1 |
The estimated completion time effects when more work is downloaded. On most of my computers this was not an issue just an annoyance, however on my slowest computer it was a real problem. That computer had problems meeting the deadlines to begin with. When the first half was running very fast that computer would sometimes download a second workunit when it shouldn't have. That second workunit would have no chance of finishing before the deadline. BOINC WIKI BOINCing since 2002/12/8 |
©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.