Questions and Answers :
GPU applications :
Cuda owned by CPU ?!?
Message board moderation
Author | Message |
---|---|
Maik Send message Joined: 15 May 99 Posts: 163 Credit: 9,208,555 RAC: 0 |
http://setiathome.berkeley.edu/workunit.php?wuid=391996729 | result both: Spike count: 1 1115527821 | 4358149 | 7 Jan 2009 13:22:07 UTC | 7 Jan 2009 23:57:22 UTC | Over | Success | Done | 121.70 | 59.29 | 43.30 1115527822 | 4687279 | 7 Jan 2009 13:22:07 UTC | 7 Jan 2009 21:40:12 UTC | Over | Success | Done | 27,917.66 | 43.30 | 43.30 http://setiathome.berkeley.edu/workunit.php?wuid=391996735 | result both: Spike count: 20 1115527823 | 3237238 | 7 Jan 2009 13:22:07 UTC | 7 Jan 2009 23:12:43 UTC | Over | Success | Done | 25,601.66 | 43.33 | 43.33 1115527824 | 4358149 | 7 Jan 2009 13:22:07 UTC | 7 Jan 2009 23:57:22 UTC | Over | Success | Done | 133.09 | 59.27 | 43.33 ... or just some miscalculation of claimed credits for cuda ? |
Geek@Play Send message Joined: 31 Jul 01 Posts: 2467 Credit: 86,146,931 RAC: 0 |
Cuda consistantly overclaims on credit. When validated the servers select the lowest claimed credit and award that amount. Boinc....Boinc....Boinc....Boinc.... |
mr.kjellen Send message Joined: 4 Jan 01 Posts: 195 Credit: 71,324,196 RAC: 0 |
Well not totally consistently...at least not for all ARs I've seen the ~2.7 (14 Credit) WUs with identical claim, but at AR ~0.43 the claim differs (~59 compared to ~43) I wonder why is there such a difference related to the AR of the WU? |
popandbob Send message Joined: 19 Mar 05 Posts: 551 Credit: 4,673,015 RAC: 0 |
The difference is the Flops count... Cuda takes more Flops to do a larger wu it appears. Hence the over claim. Do you Good Search for Seti@Home? http://www.goodsearch.com/?charityid=888957 Or Good Shop? http://www.goodshop.com/?charityid=888957 |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
It is 'counting' more flops [Well more correctly fpops anyway] for the same processing. This would not be tolerated in a third party app. I will have to determine if this is an intentional modification to the stock op count regime, so build new AK_v8 builds to match, if it continues. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
©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.