Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 16 Jan 2012 22:33:50 +0400
From: Solar Designer <>
Subject: Re: Windows cracker benchmark comparison script

On Mon, Jan 16, 2012 at 10:03:12AM -0800, Alain Espinosa wrote:
> On 1/16/12, Solar Designer <> wrote:
> > Also, I guess you already have some benchmark results to post?
> Together with the scripts there is a 'sample_out_all_parsed.csv' to
> know how the output looks like. As the output is formatted in Comma
> Separated Values format i do not post here and i recommend open the
> output file with a spreadsheet program.

Thanks, I took a look.

For MSCash (which is salted), I think it will make more sense to report
raw hashing speed rather than passwords tested per second.  Then you'll
be able to reasonably show how it scales up to 1M hashes and beyond.

Also, I think testing on longer passwords (8 characters or so, 7 for LM)
will be of more practical relevance.  I understand that your choice of
length 5 might be related to JtR's shortcoming where you can't easily
get incremental mode to terminate early by other means, except with an
external mode which would introduce overhead.  I got to introduce a fast
built-in mask mode or the like.


Powered by blists - more mailing lists

Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.