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.
Powered by blists - more mailing lists
Powered by Openwall GNU/*/Linux - Powered by OpenVZ