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 19:02:39 +0200
From: Agnieszka Bielec <bielecagnieszka8@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: PHC: Argon2 on GPU

2015-08-14 17:47 GMT+02:00 Agnieszka Bielec <bielecagnieszka8@...il.com>:
> 2015-08-14 17:37 GMT+02:00 Solar Designer <solar@...nwall.com>:
>> On Fri, Aug 14, 2015 at 05:31:07PM +0200, Agnieszka Bielec wrote:
>>> 2015-08-14 17:20 GMT+02:00 Solar Designer <solar@...nwall.com>:
>>> > And just as important: figure out why the speeds are so poor, compared
>>> > to what you're getting on your laptop, as well as to what you had
>>> > reported earlier (IIRC).
>>>
>>> when earlier? I remember only earlier tests when I had another costs
>>
>> Here you reported ~3k c/s at ~1.5 MB on super's Tahiti for Argon2d:
>>
>> http://www.openwall.com/lists/john-dev/2015/08/12/11
>>
>> Now you're reporting ~10x lower speeds for the same GPU.
>
> indeed, this is even the same version that I'm using now. I had a
> situation that I runned tests, runned again and I noticed that speed
> is worse, typed command 'w', super was not idle, there was Kai on
> super so I e-mailed to him, he turned off his job but after that speed
> was the same (worse) I though that this is only problem with my eyes
> or memory but now I see that not, maybe this have nothing common with
> Kai, he said that he didn't touched GPU's.  Solar, can you restart
> super?

ah, In this link is argon2d, it's faster than argon2i because t_cost
for argon2d is equal to 1, 3 for argon2i

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.