From: Bill Stewart <stewarts@ix.netcom.com>
Date: Wed, 24 Jul 1996 20:25:00 +0800
To: cypherpunks@toad.com
Subject: RE: Distributed DES crack
Message-ID: <199607240927.CAA18805@toad.com>
MIME-Version: 1.0
Content-Type: text/plain


At 03:40 PM 7/23/96 PDT, koontz@netapp.com (Dave Koontz) wrote:
>  >   I'd like to see a very general hardware processing power equivalence
table.
>  >   For example, 1 MasPar equals how many Pentiums.
>
>One MasPar MP2 (4K processors) could run 300,000 crypt(3) crack attempts
>per second (a password checker).  That should give you 6 or 7 million 
>brute force key attempts per second.

Interesting - thanks for the result.  Do you know how tightly tuned
the crack implementation was (e.g. straight C with MasPar optimizer,
hand-tuned assembler, etc.)?  Since the MasPar has a large number of
very small processors, I'd expect it to be better at bit-twiddling
than conventional processors.

#				Thanks;  Bill
# Bill Stewart +1-415-442-2215 stewarts@ix.netcom.com
# http://www.idiom.com/~wcs
#				Confuse Authority!