[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAKtfLcuscxQXr36-g40aPSeLQOcy==orpzj+m6CzCjo_nj1kdQ@mail.gmail.com>
Date: Thu, 22 Mar 2012 09:09:42 -0700
From: Alain Espinosa <alainesp@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: Research ideas.
On 3/18/12, Solar Designer <solar@...nwall.com> wrote:
>> S-BOX related stuff from gsoc ideas page looks interesting,
>
> Yes, but be prepared that it may be difficult. Roman's current
> implementation is a 60 KB C source file with no comments, and it
> implements some non-trivial algorithms. He will likely be willing to
> answer specific questions on it, but you'd need to know what exactly to
> ask and be able to interpret the answer - meaning that you'd need to
> figure out at least half of it yourself first. ;-)
I was trying to implement and S-box assembly code generator. The new
s-box are amazing but there is other optimization as well. Solar
counts gates but in s-box functions ~30% of code are implementation
specific, like mov instructions. The s-box can be represented by a
directed acyclic graph and develop an algotithm to generate code with
the less instructions. I have done this manually i get ~20% better
than Microsoft C compiler for SSE2 assembly and i think and automatic
way speed up things more. There is also the fact that roman generate
various possibles variants of each s-box.
> Another related project would be producing a bitslice implementation of
> the Lotus5 hashing...
Is possible a bit-slice implementation of AES? I think is possible.
saludos,
alain
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.
