[rc5] RISC sppedups

Paul Leskinen paul at csfi.com
Thu Jul 17 10:55:28 EDT 1997


Not to beat a dead horse, but here's my two cents:

1. Sparcs do not have hardware rotate. This is a *huge* disadvantage when
it comes to
   calculating RC5 vs. DES.

2. I don't think there are any Sparc ASM coders working on the Sparc
client. This has 
   been said before, also.  Maybe some will volunteer, but until then,
we're out of luck.

3. I like Sparcs, but this is a case where they're just not optimal for the
job.  That's
   the bottom line.

\=======================================/
|  Paul Leskinen    (paul at csfi.com)     |
|    Consolidated Systems of Florida    |
|     "The Open Systems Solution"       |
/=======================================\

----------
> From: Joshua Weage <weage at mtu.edu>
> To: rc5 at llamas.net
> Subject: Re: [rc5] RISC sppedups
> Date: Thursday, July 17, 1997 8:19 AM
> 
> > > I am running, went from 166K to 220K/sec.  I was quite
> > > impressed, although with deschal each of those machines was
> > > running something like 4 million keys/sec.
> > 
> > I've noticed others comparing the rc5 client with the deschal one...
Don't
> > forget, as http://rc5.distributed.net/ says, ". . . this flexibility in
> > RC5 comes at a cost of greater computational overhead per key than DES,
> > due to the increased complexity of the algorithm." So don't expect to
get
> > anywhere close to the key rate y'all were getting with DES...
> 
> 	I didn't say I was expecting the key rates to be the same
> as DES, just mentioning the VERY large difference between the
> two.  However, some time ago, I thought it was estimated that it
> only took
> about twice as much time for an rc5 key compared to DES, current
> rates are 10 times slower than DES. (220K/sec rc5, 2M/sec DES
> per processor)  That 220K/sec rate isn't even the standard
> bovine client, the standard v2.002 clients only get 160K/sec.
> 	I still think that there can be a substantial improvement
> especially on the 64 bit systems like Sun Ultra's.
> 	Comparing x86 architecture, rc5 is about 4 times slower
> which isn't as bad (and yes I know x86 is better suited for
> rc5 than sparcs.
> 
> Josh
> 
> P.S.  The speed problem is quite important.  If any other
> groups show up with significantly faster clients we WILL
> have people jump ship to switch, and any new participants
> would be more likely to run the faster clients.
> 
> 
> -- 
> - Joshua Weage  weage at mtu.edu  http://www.me.mtu.edu/~weage    -
> - "A well regulated militia, being necessary to the security   -
> -  of a free state, the right of the people to keep and bear   -
> -  arms, shall not be infringed."                              -
> -           Second Amendment U.S. Constitution                 -
> ----
> To unsubscribe, send email to majordomo at llamas.net with 'unsubscribe rc5'
in the body.

----
To unsubscribe, send email to majordomo at llamas.net with 'unsubscribe rc5' in the body.



More information about the rc5 mailing list