[RC5] keyrate stabilizing?

Paul 'Moose' Gentle moose at distributed.net
Tue Oct 16 12:43:04 EDT 2001


There is a P4 core curently. We have actually improved the speed somewhat
over the PIII core it originally used, but not a whole lot. The P4 has a
slow rotl instruction that has proven to be rather disappointing. 4 clock
latency on rotl makes for a slow rc5. Feel free to download the source and
try and improve on the P4 core. Our current attemts to improve it in house
have slowed and any help others could give to trying to improve the core
would be welcome.

Thanks
moose

----- Original Message -----
From: "Andreas D. Landmark" <andreas.landmark at noxtension.com>
To: <rc5 at lists.distributed.net>
Sent: Tuesday, October 16, 2001 10:44 AM
Subject: Re: [RC5] keyrate stabilizing?


> At 16.10.2001 10:15, TD - Sales International Holland B.V. wrote:
>
> >There is a optimized p4 core far as i know, the reason the p4 scores so
bad
> >is because it's missing a hardware instruction called rotate. For some
reason
> >the people at intel suddenly decided that their cpu didn't need the x86
> >standard's rotate instruction anymore....... anyways, now they have to
> >emulate the instruction which is much slower. if you want high rc5 scores
you
> >better get an amd
>
> Or even better a G4 (better rates wrt clockspeed)...
>
> IIRC there isn't a p4 core, there was talk about one, but I'm pretty sure
> it wasn't
> completed and I'm reasonably sure that it didn't make it into a
> dnetc-release...
>
>
> --
> Andreas D Landmark / noXtension
> Real Time, adj.:
>          Here and now, as opposed to fake time, which only occurs there
> and then.
>
> --
> 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