[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20120619074806.GA7123@cmpxchg8b.com>
Date: Tue, 19 Jun 2012 09:48:06 +0200
From: Tavis Ormandy <taviso@...xchg8b.com>
To: john-dev@...ts.openwall.com
Subject: Re: Re: [patch] optional new raw sha1 implemetation
On Sun, Jun 17, 2012 at 04:45:59PM +0200, Tavis Ormandy wrote:
> On Sun, Jun 17, 2012 at 04:24:43PM +0200, magnum wrote:
> > Nice, you boosted it by 13% on my core2 laptop.
>
> Great news! I'll experiment with a few other ideas.
>
I noticed that one of the problems with setting it too high was that
John calls cmp_one for every hash after a successful cmp_all. cmp_one
really hurts, so if max_keys_per_crypt is too high, I lose some of the
benefit to the overhead when there is a partial match.
I noticed an easy way to fix it is just to check if get_hash() ==
binary_hash() first, I sent you a pull request to add that. But would
that work in general for all the other hashes?
It might matter in the cases where you have high max_keys_per_crypt, and
very fast hashes. I didn't check if anyone else is doing that, but maybe
they will in future :-)
Tavis.
--
-------------------------------------
taviso@...xchg8b.com | pgp encrypted mail preferred
-------------------------------------------------------
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.
