[RC5] Die SETI die !

Rolu rolu at bigfoot.com
Sun Jul 25 13:25:37 EDT 1999




| 
| On Sun, 18 Jul 1999 23:05:25 +0100
| Matthew Toseland <Matthew.Toseland at btinternet.com> wrote:
| 
| > Visit their stats Totals page and do the math... <groan> EIGHTEEN
| > TERAFLOPS (sorry for shouting, and it's just an order-of-magnitude thing,
| > assuming 200MFlop/CPU) !  I'm pulling in my other recently-disemboweled machine
| > Total CPU time
| >                    263728038 hr 04 min 27.9 sec 
| >                    (30105.94 years)
| 
| CPU time is actually a lousy power meter. It can show how devoted people
| are to the given project, but not the power, since a 386SX/16
| contributes the same amount of time as an 500MHz Alpha, but the Alpha
| crunches a few orders of magnitude more data than the 386. The same
| applies for low priority operation of the seti client. I had 33 hours of
| CPU time reported on a PII/300 with only 1% of the WU done. >850K users
| however seem pretty impressive.
| 
| Attila Csipa
| Team Prometheus coordinator
| Distributed.net regional representative for Yugoslavia

For CPU time to be a fair thing to compare with, you have to report the CPU time in such a way that it is the same for everyone. For example, the number of seconds a P100 would have needed to get your results. If a 386SX/16 and a 500MHz Alpha would have done the same amount of keys, they would also have the same amount of P100-seconds.

Rolu

--
To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
rc5-digest subscribers replace rc5 with rc5-digest



More information about the rc5 mailing list