I'm cool with OpenCL when it achieves the maturity that Cuda already has... Patience...
-----Original Message-----
From: amber-bounces.ambermd.org [mailto:amber-bounces.ambermd.org] On Behalf Of Alan
Sent: Thursday, May 13, 2010 07:52
To: AMBER Mailing List
Subject: Re: [AMBER] AMBER SUPPORT FOR ATI GPUs ?
I do hope in a not distant future to have AMBER running in OpenCL. This
would sort several issues in my opinion starting with the annoying fact the
nvcc doesn't work with gcc > 4.3, no 64 bits runtime lib in Mac, no ATI
support (believing they would comply with opencl) etc. Bottom line, getting
rid of proprietary solutions.
Well I may not being fair since coding for OpenCL would be a new demanding
and likely huge task as well, let alone the maturity of Cuda versus OpenCL.
Don't get me wrong here. Having Cuda is simply fantastic. I just hope that
we can have OpenCL on board as well.
Alan
On Thu, May 13, 2010 at 15:10, Jason Swails <jason.swails.gmail.com> wrote:
> 2010/5/13 Marek Maly <marek.maly.ujep.cz>
>
> > Dear all,
> >
> > if I understood well, at present only NVIDIA GPUs are supported
> > for Amber 11 calculations.
> >
> > Is there any hope that in close future also support for ATI GPUs will be
> > implemented ?
> >
>
> Probably not... The current GPU implementation uses CUDA, which is an
> NVidia-proprietary software that they have written for their GPUs. As far
> as I know, ATI has not released or developed an API to facilitate this kind
> of development on their GPUs.
>
> Furthermore, scientists/engineers from NVidia itself have had a hand in
> helping the development of pmemd.cuda (Dr. Scott Le Grand).
>
> If this is not the case, Ross may chime in here and surprise me, but I
> believe it will be NVidia-exclusive for awhile.
>
> All the best,
> Jason
>
>
> > Best,
> >
> > Marek
> >
> > _______________________________________________
> > AMBER mailing list
> > AMBER.ambermd.org
> > http://lists.ambermd.org/mailman/listinfo/amber
> >
>
>
>
> --
> Jason M. Swails
> Quantum Theory Project,
> University of Florida
> Ph.D. Graduate Student
> 352-392-4032
> _______________________________________________
> AMBER mailing list
> AMBER.ambermd.org
> http://lists.ambermd.org/mailman/listinfo/amber
>
--
Alan Wilter S. da Silva, D.Sc. - CCPN Research Associate
Department of Biochemistry, University of Cambridge.
80 Tennis Court Road, Cambridge CB2 1GA, UK.
>>http://www.bio.cam.ac.uk/~awd28<<
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
-----------------------------------------------------------------------------------
This email message is for the sole use of the intended recipient(s) and may contain
confidential information. Any unauthorized review, use, disclosure or distribution
is prohibited. If you are not the intended recipient, please contact the sender by
reply email and destroy all copies of the original message.
-----------------------------------------------------------------------------------
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Thu May 13 2010 - 12:00:06 PDT
