john-users - 2 Qs on performance and benchmarking

Openwall Project		/home Owl JtR Pro crypt pam_passwdqc tcb phpass scanlogd popa3d msulogin / Linux BIND / advisories presentations / services donations / wordlists passwords / community lists wiki CVSweb mirrors signatures
bringing security into open environments

This website is powered by Openwall GNU/*/Linux security-enhanced OS

[<prev] [next>] [thread-next>] [month] [year] [list]

Date: Sat, 17 Sep 2005 19:03:14 +0200
From: Christian Karpp <xn@...delbg.ibm.com>
To: john-users@...ts.openwall.com
Subject: 2 Qs on performance and benchmarking

Hi,

in a previous mail I read
 > John's 1M c/s at traditional crypt(3) (on PPC G5 1.8 GHz or P4 3.6
 > GHz) roughly translates to:
 > 1M * 25 * 64 / 3 = 530 Mbps at 3DES

Q1: How does this estimation break down for other CPU types / clock 
speeds? i.e. How will the "1M c/s" number vary?

Q2: Is there some further documentation on john's benchmarking 
available? e.g. What's the difference between real c/s vs. virtual c/s? 
How do the results map to Mbps, etc. And, some info or links for further 
reading about the algorithms bechmarked would be nice as well.

AtDhVaAnNkCsE, Xn.