[RC5] CSC Clients Picking Wrong Cores?

Albert Zvara Albert.Zvara at colesmyer.com.au
Tue Nov 23 09:21:04 EST 1999


Andy,

I also have a PII 350 and find that as the first process (a) completes, it
is recorded at 408kk/s.  Then when the other process (b) completes (also at
~~408kk/s) the overall rate of my PC goes to ~810kk/s.  That would explain
you increasing rate.  (Wouldn't it be nice if it were 'ever' increasing
though *smile*)

Alby

-----Original Message-----
From: Andy Mucho [mailto:andy at software-superstars.com]
Sent: Tuesday, 23 November 1999 02:56
To: rc5 at lists.distributed.net
Subject: RE: [RC5] CSC Clients Picking Wrong Cores?


> -----Original Message-----
> From: owner-rc5 at lists.distributed.net
> [mailto:owner-rc5 at lists.distributed.net]On Behalf Of
> Claude.Saam at alcatel.fr
> Sent: Friday, November 19, 1999 11:43 AM
> To: rc5 at lists.distributed.net
> Subject: Re: [RC5] CSC Clients Picking Wrong Cores?
> ARG ! Client coders, please do something :)
>
> PS : the client works fine on "normal" pentium clients, and on a
> Sparc Solaris Unix box - only ppro seem to be bugged

Works fine on a P2 as well..
*EXCEPT*
My only question is that I get an ever increasing key-rate as the day rolls
on.. On a dual P2-350 the key-rate starts of at 340kk/s but 4 hours later
the keyrate is typically up to around 700kk/s, eventually topping out after
about 14 hours at 770kk/s..
What's up? The machine recieves a pretty steady amount of free time during
the day, and this morning has hardly been used, yet exhibits the same kind
of ramping up of kk/s..
The Benchmark clocks in at 500kk/s..
RC5 on the same machine, experiencing the same useage used to sit pretty
much around its benchmark speed all the time..

Not worrying, but puzzling nonetheless.

AndyM




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

--
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