Questions and Answers :
Getting started :
Optimized apps: Reliable and accurate?
Message board moderation
Author | Message |
---|---|
Steve Bergman Send message Joined: 20 May 07 Posts: 48 Credit: 292,679 RAC: 0 |
I'm considering running optimized versions of the apps. Q6600, 64 bit, Linux. I don't care about credits, and competing, and teams, and all that sort of thing. But I do care very much about the quality of the science work. How much assurance do I have that down the road, I won't find out about some subtle SSE3 bug or some such that renders my results useless, or of reduced science value? Or worse yet, *not* find out about one that exists but nobody noticed. I'd hate to miss the alien "Wormhole Construction HowTo" due to a silly app bug. -Steve |
John McLeod VII Send message Joined: 15 Jul 99 Posts: 24806 Credit: 790,712 RAC: 0 |
I'm considering running optimized versions of the apps. Q6600, 64 bit, Linux. I don't care about credits, and competing, and teams, and all that sort of thing. But I do care very much about the quality of the science work. How much assurance do I have that down the road, I won't find out about some subtle SSE3 bug or some such that renders my results useless, or of reduced science value? Or worse yet, *not* find out about one that exists but nobody noticed. I'd hate to miss the alien "Wormhole Construction HowTo" due to a silly app bug. SETI does not use homogeneous redundancy. That means that the tasks you do on your computer get compared against tasks done on completely different computers. If disparate computers match, neither of them has a subtle bug in the underlying hardware. If yours is done on SSE3 your wingmates is done on a GPU, and they both match, there is nothing in common in the hardware. BOINC WIKI |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
No one can assure that any program is 100% free of bugs so the corporations sell software which may cost 1000s of $ and at the same time they push you to [Agree] that you get the program "As Is, with all faults"! So far the optimized apps (released to public - not beta) proved to be accurate on results (they validate OK for years against "stock" results). Â - ALF - "Find out what you don't do well ..... then don't do it!" :) Â |
Steve Bergman Send message Joined: 20 May 07 Posts: 48 Credit: 292,679 RAC: 0 |
Thanks for the replies. That sounds like a reasonable assurance. I've installed the latest AK Linux X86_64 SSE3 apps, and multibeam looks to be running 2-1/2 to 3 times faster. -Steve |
©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.