Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Fri, 14 Aug 2015 18:17:35 +0300
From: Solar Designer <solar@...nwall.com>
To: john-dev@...ts.openwall.com
Subject: Re: PHC: Argon2 on GPU

On Fri, Aug 14, 2015 at 04:37:06PM +0200, Agnieszka Bielec wrote:
> cracking mode on my laptop on argon2d showed that at the beginning
> speed is the same to this showed during computing gws, after some time
> I am getting speed closest to showed during --test but it's not
> exactly the same.

Please use either only wordlist mode, or incremental mode locked to a
fixed length for such tests.  When you run with no cracking mode
specified, this eventually proceeds to incremental mode (pass 3/3) with
length switching, and that length switching is rather slow initially (so
may significantly reduce the speeds during the first few minutes).
Anyway, I think your runs are long enough to mostly compensate for this
effect.

> Speed for cost 1 (t) of 1, cost 2 (m) of 1500, cost 3 (l) of 1
> Many salts:     4114 c/s real, 4077 c/s virtual
> Only one salt:  4114 c/s real, 4114 c/s virtual
> 
> I don't have big differences with argon2i on my laptop
> 
> on super:
[...]
> Speed for cost 1 (t) of 3, cost 2 (m) of 1500, cost 3 (l) of 1
> Many salts:     390 c/s real, 102400 c/s virtual
> Only one salt:  390 c/s real, 102400 c/s virtual

Is super like 10x slower than your laptop at this now?  Why is that?

> so speeds reported by main --test are good

Yes, it seems so, but your benchmarks above also show a GPU on super
performing much slower than in your laptop, and this makes no sense.

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.