Nvidia to port PhysX to its GPUs

Nvidia has announced that it plans to port the PhysX physics engine to work on its GPUs – something we predicted in our analysis on the deal last week.

Speaking in the conference call following their fourth-quarter results, Nvidia CEO Jen-Hsun Huang said: "We’re working toward the physics-engine-to-CUDA port as we speak. And we intend to throw a lot of resources at it. Every single GPU that is CUDA-enabled will be able to run the physics engine when it comes."

CUDA – the Compute Unified Device Architecture – is Nvidia’s attempt to get more general purpose computing happening on its GPUs, and exposes the GPU to the developer as a massive array of processors optimised for certain tasks.

The only problem that is seen with the concept of physics sharing a GPU is that not many developers will be willing to syphon off GPU cycles away from graphics tasks.

On this topic, Huang said: "Our expectation is that this is gonna encourage people to buy even better GPUs. It might—and probably will—encourage people to buy a second GPU for their SLI slot. And for the highest-end gamer, it will encourage them to buy three GPUs. Potentially two for graphics and one for physics, or one for graphics and two for physics."

Finally, speaking on developer reaction to the news, Huang said that developers are excited about the news, saying: "Finally they’re able to get a physics engine accelerated into a very large population of gamers."

Do you think that there will be many PC gamers willing to buy a second – or even a third – graphics card so that they can dedicate resources to physics? Or is it aiming too high for an industry that some are saying is in decline? Tell us your thoughts in the comment box below.