[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20130105042612.GA13252@openwall.com>
Date: Sat, 5 Jan 2013 08:26:12 +0400
From: Solar Designer <solar@...nwall.com>
To: john-dev@...ts.openwall.com
Subject: Re: BLAKE2 (was: New plugin load order magic)
On Sat, Jan 05, 2013 at 09:15:05AM +0530, Dhiru Kholia wrote:
> On Sat, Jan 5, 2013 at 6:58 AM, Solar Designer <solar@...nwall.com> wrote:
> > Then, Dhiru included the slow reference implementation of BLAKE2b
> > instead of the SIMD implementations. I think we should include all SIMD
> > implementations that are available from BLAKE2 team, plus the reference
> > implementations for non-x86 and for older x86 CPUs.
>
> I can try doing this but I am not familiar with SIMD business.
With BLAKE2, it is very different from and much easier than the SIMD
business we have elsewhere in JtR. BLAKE2 uses up to 128-bit SIMD
vectors on its own - you just need to pick the right implementation.
There's further room for optimization (cracking-specific), but that's a
possible next step.
> Speed is not that bad on 64-bit machines.
Yes. It's similar to SHA-512's, but it is supposed to be better (with
SIMD code).
Thanks!
Alexander
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.
