[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <033d03cc8e8a598bccc222fa4ebac307@smtp.hushmail.com>
Date: Sun, 9 Dec 2012 00:14:47 +0100
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: bitslice DES on GPU
That was exactly my gut feeling. Even if you find it in host addressable memory, it might well be a stale copy of what is residing on the GPU. And if you do get it working on a particular architecture, this does not in any way guarantee it will work on any other architecture. Or even on the same one, another day o.O
magnum
On 9 Dec, 2012, at 0:09 , Milen Rangelov <gat3way@...il.com> wrote:
> I am not sure you can do that at run time. Reason is that the binary is being "transferred" to the GPU at the moment you call clCreateKernel(). Any change in the binary would not have any effect unless you release the kernel and create it again (which would involve a memory transfer again). But that of course involves the transfer costs.
>
> On Fri, Dec 7, 2012 at 10:42 AM, Sayantan Datta <std2048@...il.com> wrote:
>
> On Fri, Dec 7, 2012 at 11:39 AM, Milen Rangelov <gat3way@...il.com> wrote:
> Why would you want to do that via patching (given that they are compile-time constants)?
>
> The so called constants will change with every new salt which is why I need to patch them at runtime.
>
> Regards,
> Sayantan
>
Content of type "text/html" skipped
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.
