Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CABob6ip1MNsoHRMP+uY_eML4zHaJJoNqUP2JJcSo5Vtu1FCOrg@mail.gmail.com>
Date: Mon, 25 Jun 2012 00:13:39 +0200
From: Lukas Odzioba <lukas.odzioba@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: async key transfers to GPU

2012/6/24 Solar Designer <solar@...nwall.com>:
> Yes, I did not suggest to use multiple streams.  I am not familiar with
> this, but Lukas was able to have data transfers to GPU overlap with
> computation on GPU by interleaving these inside crypt_all().

myrice: we're talking about that:
http://developer.download.nvidia.com/compute/DevZone/docs/html/C/doc/CUDA_C_Best_Practices_Guide.pdf
page 26+


Lukas

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.