[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 12 Dec 2012 23:47:39 +0100
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: office2013-opencl
On 12 Dec, 2012, at 22:08 , magnum <john.magnum@...hmail.com> wrote:
> On 12 Dec, 2012, at 20:59 , Solar Designer <solar@...nwall.com> wrote:
>> Observation: it takes maybe a couple of minutes for --test of this
>> format to complete on GTX 570, but about 8 minutes on 7970. Why?
>
> I know exactly what to do but haven't had the time. All my iterated formats currently auto-tune with the full number of iterations but there is no need for that, so it could be several orders of magnitude faster. Maybe I should give that some prio...
This now done & committed, for all such formats. I think it shaved over 2 minutes from office2013 (which was/is worst), yet it's still over 8 minutes :-(
The reason is now purely the self-test scheme: This unreasonable format take 17 seconds per crypt_all() and the current self-test will do a lot of calls for the keys_per_crypt of 16384 that is chosen, testing only one key per call.
The 570 is much faster because each crypt_all() call is only 7 seconds, and the keys_per_crypt is a mere 2048.
magnum
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.
