Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 02 Apr 2012 21:42:35 +0200
From: magnum <>
Subject: Re: JtR: GPU for slow hashes

On 04/02/2012 07:28 PM, SAYANTAN DATTA wrote:
> However due to huge opencl kernel  code I had to modify the common-opencl.c
> a little bit. I had to changed the "#define SRC_SIZE 1024*16" to "#define
> SRC_SIZE 4096*16" in order to fit the opencl kernel.
> I will reduce the code length as much as possible in the final code and
> also make a large number of optimizations.

Yeah I just saw this the other day. The source buffer should obviously
be allocated dynamically. This is on my to-do list (which unfortunately
only exist in my head, continuosly overflowing) unless someone else
fixes it (but until then, your fix will do of course).


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.