[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20110705004525.GA12598@openwall.com>
Date: Tue, 5 Jul 2011 04:45:25 +0400
From: Solar Designer <solar@...nwall.com>
To: crypt-dev@...ts.openwall.com
Subject: Re: Yuri's Status Report - #8 of 15
Hi Yuri,
Thank you for the status report, as usual. It helps.
On Mon, Jul 04, 2011 at 09:36:11PM -0300, Yuri Gonzaga wrote:
> - Accomplishments:
> - Eksblowfish's inner loop interface
> - Communication to host PC successfully done.
> - Code and hardware result uploaded to wiki page (
> http://openwall.info/wiki/crypt-dev/files)
> - Based on version called "eksblowfish-loop-2"
> - The same test case was employed to compare results in host
> software side
Sounds good.
> - This was executed 10 times sequentially and waste 234.938 seconds
> of execution time
> - The hardware worked properly
Any info on the performance? This is one Eksblowfish core running in
the FPGA right? If so, it got to be several times slower than native
(compiled) code on the CPU, right?
> - Priorities:
> - Integrate eksblowfish-loop to crypt_blowfish package
No, integrate into JtR. Initially integrate interface to one core, then
expand to multiple cores.
crypt_blowfish has interfaces limited to computing one hash at a time,
so you wouldn't be able to expand to more than one core. On the other
hand, JtR readily supports multiple hash computations per crypt_all().
One of your/our objectives here is to learn to synthesize and interface
to multiple crypto cores in an FPGA. Of course, this is nothing new,
but we lack experience with it. So we need to gain such experience.
On our tiny team, David has such experience, though. Please ask him
specific questions on this when you have any.
Please let me know if you have any questions or comments.
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.
