Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date: Sun, 13 Sep 2015 00:51:21 +0300
From: Solar Designer <>
Subject: Judy array

Sayantan, all -

I just had a very interesting e-mail conversation with Fred Wang, the
author of MDXfind:

MDXfind has very impressive performance when targeting large lists of
saltless hashes (such as tens of million or more), beating JtR and
*hashcat, while also using less RAM.  MDXfind also has many unique
features such as matching against partial or rotated hash encodings,
as prompted by this thread:

Fred suggested that we look into using Judy, which he uses in MDXfind,
along with a Bloom filter ("but Judy is the key", in his words).

Fred also confirmed my understanding that while needing exactly two
lookups with perfect hash tables is very nice, it's just not good enough
on its own for this application - we (also) have to optimize for the
common case of a miss, and thus achieve a little higher than one lookup
per hash computed on average (MDXfind does).


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.