[Beowulf] coprocessor to do "physics calculations"
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Geoff Jacobs gdjacobs at gmail.comSat May 6 12:16:18 PDT 2006
- Previous message: [Beowulf] coprocessor to do "physics calculations"
- Next message: [Beowulf] p4_error: net_recv read: probable EOF on socket: 1
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Joe Landman wrote: <snip> > Likely it has a linearized version of an ODE solver. Nothing > spectacular. Shouldn't be that hard to code a simple Runge-Kutta or > even a Simpson's rule in hardware ... Indeed, but it probably only accelerates specific functions in the Ageia engine. Here is what the competition (Havoc, used in Half-Life 2 for those familiar) does: http://www.havok.com/content/view/17/30/ I suspect it's like original Geforce cards were - very much a fixed function device. > Likely it has "game physics" and the major question is how do game > physics map against the real world physics. It likely has a subset (that which needed accelerating) of the Ageia physics engine. It is also likely not tuned for accuracy. > Thats not the only reason ... Dedicated hardware, well designed to the > task, can absolutely wipe the floor with general purpose hardware. GPU > vs CPU is a great example of this. > -- Geoffrey D. Jacobs MORE CORE AVAILABLE, BUT NONE FOR YOU. \-----------------------------------------------------\ Please update your address book to gdjacobs at gmail.org. \-----------------------------------------------------\
- Previous message: [Beowulf] coprocessor to do "physics calculations"
- Next message: [Beowulf] p4_error: net_recv read: probable EOF on socket: 1
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
