[Beowulf] Nvidia, cuda, tesla and... where's my double floating point?
rreis at aero.ist.utl.pt
Sun May 4 13:11:16 PDT 2008
On Sun, 4 May 2008, Mikhail Kuzminsky wrote:
> "Next generation Tesla", but I don't know when. Or use AMD FireStream 9170
> instead :-)
I've read somewhere that double precision performance from AMD wasn't very
good and their programming model goes more towards assembly... Besides,
AMD/ATI still have to convince on their linux drivers.
Unless... do you have any experience with that hardware you could share?
PhD student @ Lasef
Computational Fluid Dynamics, High Performance Computing, Turbulence
Cultural Instigator @ Rádio Zero
More information about the Beowulf