[RC5] performance

chandler sobel-sörenson scar at fugazi.engr.arizona.edu
Sat Sep 13 18:06:49 EDT 2003


yes i suppose you're right.  the whole 4 processors being detected threw me
off.  and also, i was thinking 1.6 GHz when i typed the 1.6 Mkeys/s, the
rate iwas getting on the 1.6 GHz was 2.2 Mkeys/s, so this works out
mathematically almost perfectly to 7.2 Mkeys/s for 2x2.80 GHz, if you
account that not 100% of my cpu is being used.  however, i think i will try
turning the htt off next time i reboot and see what that does.  thanks for
the links marty.
----- Original Message ----- 
From: "Dave Huang" <khym at azeotrope.org>
To: "D.net Discussion" <rc5 at lists.distributed.net>
Sent: Saturday, September 13, 2003 3:28 PM
Subject: Re: [RC5] performance


> On Sat, Sep 13, 2003 at 01:54:38PM -0700, chandler sobel-sörenson wrote:
> > i am not satisfied with this 3.8 Mkeys/s., i am thinking i should be
getting
> > ~20 Mkeys/s.  now, when i change the "numbert of crunchers to run
> > simultaneously" to 2 my rate jumps up to like 7.2 Mkeys/s.  i have not
yet
>
> I think you're being too optimistic if you're expecting 20Mkeys/s. If
> one P4 1.60GHz gets 1.6Mkeys/s, you'd expect a P4 2.80GHz to get
> around 2.8Mkeys/s. Two of them would give you 5.6Mkeys/s. So
> 7.2Mkeys/s sounds very good to me! Why do you think you should get
> 20Mkeys/s?
> -- 
> Name: Dave Huang         |  Mammal, mammal / their names are called /
> INet: khym at azeotrope.org |  they raise a paw / the bat, the cat /
> FurryMUCK: Dahan         |  dolphin and dog / koala bear and hog -- TMBG
> Dahan: Hani G Y+C 27 Y++ L+++ W- C++ T++ A+ E+ S++ V++ F- Q+++ P+ B+ PA+
PL++
> _______________________________________________
> rc5 mailing list
> rc5 at lists.distributed.net
> http://lists.distributed.net/mailman/listinfo/rc5



More information about the rc5 mailing list