[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CABob6iqWNmYCEmON+mVJ2fSYmT8uCR4OKnd=qEma5xxUYh3RUw@mail.gmail.com>
Date: Mon, 27 May 2013 02:34:07 +0200
From: Lukas Odzioba <lukas.odzioba@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: new dev box wishes (was: Contest)
2013/5/26 Solar Designer <solar@...nwall.com>:
> Before we care about multi-GPU with CUDA (rather than only with OpenCL),
> shouldn't our formats reach decent speeds with CUDA? Right now, they're
> often slower than their OpenCL counterparts and they lack auto-tuning.
First we should make a decision whether we want to develop CUDA
formats in the future, or just move all to OpenCL with nv optimized
kernels.
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.
