[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CA+TsHUD1ZoU7tkxvxXOcVDbmX0dc=WX0g-rHQvad4zOhckSu8A@mail.gmail.com>
Date: Fri, 13 Apr 2012 16:16:45 +0530
From: SAYANTAN DATTA <std2048@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: OpenCL tests on GTX 570
On Fri, Apr 13, 2012 at 3:39 PM, Solar Designer <solar@...nwall.com> wrote:
> I think not intentionally, but it is common for OpenCL implementations
> to be slower than CUDA implementations of the same things.
>
May or may not, because I just read at one of hascat's wiki page that a
well optimized ocl code for nv gpus runs 15% slower than the cuda
implementation.
http://hashcat.net/wiki/oclhashcat_catalyst_forceware
Yes, or at least some tuning will be needed to get this to run faster.
>
> With Lukas' CUDA code, I actually get similar speed to the above without
> tuning, but it increases to 29k c/s with very minor tuning (THREADS and
> BLOCKS settings, target architecture setting for the compiler).
>
No doubt it would require some nv specific optimizations but in my last
performance update I have made some optimizations that are common to both
nv and AMD. Hope it runs well on both architecture.
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.
