[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <aea21943b4a470e955f8af722a96c9ce@smtp.hushmail.com>
Date: Sat, 26 Jan 2013 18:20:42 +0100
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: Proposed optimizations to pwsafe
On 01/26/2013 04:49 PM, Claudio André wrote:
> Em 26-01-2013 07:28, magnum escreveu:
>> Bleeding has experimental multi-device support added, and possibly
>> some initial performane regression from that (that we hopefully can fix).
>>
>> magnum
>
> This is not expected.
> - if OpenCL is not enabled, none of this opencl multi-gpu is executed.
> - at common-cuda, and i saw no reason for regression (but i know nothing
> about CUDA).
I meant the pwsafe-cuda format itself. It's the first and so far only
CUDA format that can use multiple devices. Our shared code currently
doesn't let you select multiple CUDA devices though.
magnum
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.
