From: Axel Kohlmeyer (akohlmey_at_gmail.com)
Date: Thu Dec 12 2013 - 00:04:44 CST

On Wed, Dec 11, 2013 at 6:31 PM, Jrme Hnin <jerome.henin_at_ibpc.fr> wrote:
> Hi everyone,
>
> Traditionally I used to favor nvidia GPUs over AMD for running VMD under Linux, because the drivers were "better" (that is, they ran with some glitches, but ran nonetheless). The landscape seems to be evolving these days, and nvidia has notoriously antagonized the Linus crowd (or was that Linux?) for its lack of cooperation, while AMD has been more forthcoming. That was mostly a problem with open source support, but I wonder if that also reflects in the quality of the proprietary drivers.

while nvidia engineers do on and off things that irritate the hard
core open source people, their proprietary drivers are way ahead of
the corresponding amd offerings. that is in terms of features,
configurability, consistency and performance.

that doesn't mean that there is not the occasional setback (aka bug)
and the on-and-off issue with features being a bit too aggressive
(often based on the desire to achieve higher performance for CUDA
applications). very obviously, amd simply has not the financial
resources that they can dedicate to linux drivers to have a
competitive offering (despite having competitive or even superior
hardware).

the most annoying part about nvidia's proprietary drivers is that they
often have limitations that are solely due to choices of the engineers
(based on a "we know better what you want" attitude) and thus can
require very ugly hacks and workarounds to circumvent them. but those
are almost always corner cases that do not apply to regular use and
the restrictions are less enforced on consumer grade desktop hardware,
but rather on the "professional" offerings.

axel.

> So, it would be great to hear about the recent experiences of some VMD/Linux users with AMD and nvidia support - both in terms of features and performance.
>
> Thanks,
> Jerome

-- 
Dr. Axel Kohlmeyer  akohlmey_at_gmail.com  http://goo.gl/1wk0
International Centre for Theoretical Physics, Trieste. Italy.