From owner-freebsd-chat Fri Feb 28 20:35:37 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id UAA08818 for chat-outgoing; Fri, 28 Feb 1997 20:35:37 -0800 (PST) Received: from alpha.risc.org (taob@trt-on1-06.netcom.ca [207.181.81.70]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id UAA08813 for ; Fri, 28 Feb 1997 20:35:34 -0800 (PST) Received: from localhost (taob@localhost) by alpha.risc.org (8.8.4/8.8.4) with SMTP id XAA08080; Fri, 28 Feb 1997 23:34:41 -0500 (EST) Date: Fri, 28 Feb 1997 23:34:40 -0500 (EST) From: Brian Tao Reply-To: Brian Tao To: "Kenneth D. Merry" cc: Amancio Hasty , FREEBSD-CHAT-L Subject: Re: RSA 56-bit key challenge In-Reply-To: <199703010400.XAA01541@r74h25.res.gatech.edu> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-chat@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Fri, 28 Feb 1997, Kenneth D. Merry wrote: > > I think that is correct. Here's what I got, dual PPRO 200, 256K > cache. (so I assume I could get about twice this if I ran two > copies) Yes, it seems to scale quite linearly with the number of CPU's. csm@sgi.com is running an SGI Origin2000 with 128 CPU's and 2GB of RAM. He's benchmarked it at over 20 million keys/sec, but he can't dedicate the whole machine to it (luckily for the rest of us ;-)). > {r74h118:/usr/home/ken/dl:23:0} uname -a > FreeBSD r74h118.res.gatech.edu 3.0-SMP FreeBSD 3.0-SMP #0: Mon Jan 27 01:27:38 EST 1997 ken@r74h118.res.gatech.edu:/usr/src/sys-SMP/compile/panzer i386 > {r74h118:/usr/home/ken/dl:24:0} ./rc5-client-freebsd -m > rc5-56-client: Performance testing with 1000000 crypts > rc5-56-client: Complete in 3.300 seconds. (303063.36 keys/sec) Well... I guess I'll make this an open invite: anyone not already affiliated with a team is more than welcome to join our little grassroots effort at rsacrack@vex.net (http://www.vex.net/~rasmus/rsa/). We've got everything from PPro200's down to a wee Sun 3/60 that takes almost 2 days to complete a single keyblock, and we don't favour one particular OS over another. :) -- Brian Tao (BT300, taob@risc.org) "Though this be madness, yet there is method in't"