From: Jim McCoy <mccoy@ccwf.cc.utexas.edu>
Date: Wed, 18 Aug 93 15:30:43 PDT
To: honey@citi.umich.edu (peter honeyman)
Subject: Re: World record in password checking
In-Reply-To: <9308182116.AA14986@toad.com>
Message-ID: <199308182228.AA22350@tramp.cc.utexas.edu>
MIME-Version: 1.0
Content-Type: text


> why doesn't this impress me?  i'll tell you why.  with
[use a bunch of PCs running some freenix to do it]
>
> now give me a "1,024 node" machine made of of these -- admittedly
> unwieldy, but no doubt a hell of a lot cheaper than a 1,024 node CM/5
> (and a hell of a lot more useful, imho) -- and i can run at three times
> the "world record" rate.

Perhaps because internal communication between those 1024 machines will be
significantly more difficult than running on a machine that is optimized
for parallel operations, RPC just doesn't cut it.  You would probably lose
a number of your hosts off the top just to coordinate the activity of the
remaining machines. Besides, if you really want to do this spend your
one or two million (approx cost of your 1000PC site) on seriously dedicated
DES-cracking parallel hardware.  Do the cracking in hardware, not software.

Either way, I could think of more fun things to do with those 1024 PCs :)

jim