[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20120922053953.GA3890@openwall.com>
Date: Sat, 22 Sep 2012 09:39:53 +0400
From: Solar Designer <solar@...nwall.com>
To: john-dev@...ts.openwall.com
Subject: Re: bitslice DES on GPU
On Sat, Sep 22, 2012 at 10:58:50AM +0530, Sayantan Datta wrote:
> I gave it a detailed thought to your calculations. In fact doubling the
> work items shouldn't affect the speeds anyway. for example:
>
> H c/s = W/(O+C) : where W = no. of work items
> O = time spent on overhead.
> C = time spent on actual
> (non-overhead) hashing.
> H = actual real world speed.
> So if W is doubled , O and C should get doubled automatically as both O and
> C are proportional to W.
This sounds right to me.
> What happened is that I manged to reduce the overhead (using different
> code) while slowing down the actual hashing(using different kernel).
OK.
> Anyway I managed to improve the non-overhead speeds to 59M c/s using
> nvidia s-boxes and putting B[] in private register space on 7970.
Good. We're getting somewhere.
> AMD s-boxes aren't working .
In what way are they non-working?
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.
