[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20130809084545.GC29195@openwall.com>
Date: Fri, 9 Aug 2013 12:45:45 +0400
From: Solar Designer <solar@...nwall.com>
To: john-dev@...ts.openwall.com
Subject: Re: ZedBoard / Parallella: bcrypt
Katja,
On Fri, Aug 09, 2013 at 02:10:42AM +0200, Katja Malvoni wrote:
> Because of that I plan to do bcrypt implementation in following steps:
> - get working simulation of sbox transfers to and from custom peripheral
> (in this case custom peripheral will just store sbox) (in case I won't be
> able to do BFM simulation I'll skip this step)
> - implement those transfers between ARM core and FPGA on Parallella board
> - implement bcrypt's most costly loop as separate IP block and test it in
> ISim (without communication, just logic)
> - when I get working simulation test IP block with AXI BFM
> - merge with Parallella prototype
>
> Does this sound reasonable?
It does, although I'm not familiar with the simulation tools involved.
We also still have the task of getting a regenerated bitstream working
right on ZedBoard / Parallella board - with no new features, but also
not breaking any of the existing functionality, right? Is this also
(still) on your priorities list (just not exactly a bcrypt topic, so not
mentioned in this specific posting of yours)?
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.
