Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sun, 21 Dec 2008 04:46:18 +0300
From: Solar Designer <solar@...nwall.com>
To: john-users@...ts.openwall.com
Subject: Re: Bitslice DES fast implementation for AltiVec(PPC)

Hi,

On Wed, Dec 17, 2008 at 04:12:52AM +0900, Dumplinger Boy wrote:
> I tried the method of making Bitslice DES can executed at high speed
> or more in PowerPC.
> VSEL instruction can replace 3 instruction combination(VAND, VANDC, and VOR).

Right.  Is your work in any way based on Marc Bevand's or did you arrive
at this independently?  I am referring to this thread:

	http://www.openwall.com/lists/john-users/2008/10/07/1

(and click "[thread-next>]" to see the follow-ups, including a
discussion of applying the approach to "regular" PowerPC with AltiVec).

What are you using to generate your sboxes-alti.c file?

Would you like your code to be integrated into the official JtR, into
the jumbo patch, or not at all?

For the official JtR, your use of a BSD license is problematic; I'd
prefer public domain or an even more relaxed license, obviously
compatible with both BSD and GPL and not requiring anything extra.
http://www.fsf.org/licensing/licenses/ says that the 2-clause BSD
license is GPL-compatible, yet I think it imposes extra restrictions -
namely, it requires that it be "reproduced" on copies of the software.
So merely including the GNU GPL with the software (or referring to it)
becomes no longer sufficient.

As an option, you could release whatever software you use to generate
your sboxes-alti.c, under a license of your choice, but not have that
license apply to the program's output.

FWIW, your patch appears to do more than it needs to.  It would probably
be sufficient to replace:

#include "DES_bs_a.c"

with:

#include "sboxes-alti.c"

>  As long as I know, scaler-integer and AltiVec instructions can be
> operated parallel in most PowerPC imprementation. Therefore, there is a
> possibility of more performance gain.

Yes.  This idea was commented on in this posting:

	http://www.openwall.com/lists/john-users/2008/10/19/5

Thanks,

-- 
Alexander Peslyak <solar at openwall.com>
GPG key ID: 5B341F15  fp: B3FB 63F4 D7A3 BCCC 6F6E  FC55 A2FC 027C 5B34 1F15
http://www.openwall.com - bringing security into open computing environments

-- 
To unsubscribe, e-mail john-users-unsubscribe@...ts.openwall.com and reply
to the automated confirmation request that will be sent to you.

Powered by blists - more mailing lists

Your e-mail address:

Powered by Openwall GNU/*/Linux - Powered by OpenVZ