The acceleration of game physics, and I use the terms acceleration and physics broadly, is a hot topic for gamers and developers alike. Hardware acceleration of various physics APIs has been demonstrated or promised, Microsoft is undoubtedly pondering a DirectPhysics implementation, and the basic concept of having hardware -- be that CPU, GPU or even a new kind of dedicated physics processing unit (PPU) -- accelerate physics calculations is back at the forefront of discussion.
The concept isn't new, game middleware and sole developers making the physics calculations go faster by multithreading the game engine, letting game physics run on its own, populating the engine with results as they happen.
That most basic acceleration then spawns further acceleration of those calculations on something a bit more capable than a CPU (or so the promise goes), be it GPU or PPU. Havok, a physics middleware developer, announced Havok FX™ recently, which accelerates a class of game physics calculations on a Shader Model 3.0 graphics processor.
As far as PPU acceleration goes, there's only one PPU vendor working that space at the time of writing. And Ageia, a Californian startup fresh from a round of venture capital and new employee hires, not only have a PPU design in production silicon but they're selling it too.
Recently shipping in high-end systems from a range of mostly boutique vendor systems, their PhysX PPU works, has support in a few games and is available for sale. Worth a peek, then?
I've recently spent time with a board and a couple of supported games and there's some data worth sharing with you, the awesome readers of HEXUS.core. First, then, the PhysX PPU itself and what it's capable of.