Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 13 Jul 2015 20:28:08 +0200
From: Agnieszka Bielec <bielecagnieszka8@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: PHC: Lyra2 on GPU

2015-07-13 19:31 GMT+02:00 Solar Designer <solar@...nwall.com>:
>> and I discovered now that the best number of lws also differ for
>> various costs but it isn't autotuned
>
> Why isn't it auto-tuned?

Do john support lws auto tuning? We only have get_default_workgroup()
function which is called somewhere.

>
>> >> I said that I'm using local memory but I wanted to say __private ,
>> >> sorry if caused confusion
>> >
>> > OK.  I guess you're putting the current row (24 KB) in there?  And when
>> > you were using global memory before, you had the current row fetched
>> > from and sent to global memory each time?
>>
>> it's not 24KB. I wrote that there are very small chunks an when I
>> tried 2x, 3x, 5x bigger - speed decreased.
>> but I'm sceptic about so huge cache in local memory because we have
>> e.g. 32KB for all lws number of threads and speed will decrease after
>> only if I change lws from 64 to 1
>
> You're right indeed.

lastly I discovered that optimal lws is 4 or 8 depends on costs

and there is no synchronization between threads where these numbers
differs by more than lws number

> So how much private memory are you using per Lyra2 instance?

http://www.openwall.com/lists/john-dev/2015/07/04/5 <- but these
tables are per one function

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.