Message boards :
Number crunching :
Thank you to all of those who....
Message board moderation
Author | Message |
---|---|
Dorsai Send message Joined: 7 Sep 04 Posts: 474 Credit: 4,504,838 RAC: 0 |
Spent their time and effort making the 'optimised' Boinc and S@H app's. I downloaded the seti-p3.zip from a link in one of the threads discussing the creation of the optimised code. Carfully reading the various threads, I installed the new code, and after 2 days can report that: 1. My claimed credit now matches my granted credit to a much greater degree. I averaged a granted credit of 30, and now claim about 32, instead of 42. 2. My cunch time has falled by 25%, From 15,000ish (4 hours) to 11,500ish (3 hours). 3. My benchmark only 'improved' by about 10%, hence the fall in credit claimed. It is my understanding that a WU should claim about 30 anyway, so i lose nothing. 4. All result from the optimized versionhave passed validation so far. So to all of those numerious programmers out there who's hard work made this possible, Thank You. As a point that may be of interest, I notice that now a WU will get 50% done in one hour, and then the remaining 50% will take two hours. I assume this is because the first 50% of processing is 'relativly easy' while the second half of the math is 'harder'? Perhpas the next target, to speed up the second hhlaf of the processing?? Foamy is "Lord and Master". (Oh, + some Classic WUs too.) |
ampoliros Send message Joined: 24 Sep 99 Posts: 152 Credit: 3,542,579 RAC: 5 |
|
HokieForever Send message Joined: 9 Mar 02 Posts: 18 Credit: 4,497,208 RAC: 0 |
I agree thanks to all of you who optimized BOINC and SETI especially for Windows/Intel. HokieForever |
©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.