It seems Nvidia has the Ageia PhysX engine it purchased a few months ago almost ready for use with CUDA (Compute Unified Device Architecture) which will allow programmers to utilize the graphics card's physics processor to calculate "complex computation-intensive challenges" of all kinds. All of Nvidia's 8000 series video cards can make use of this new feature.

Nvidia told analysts that the conversion of Ageia's physics application interface to CUDA is almost complete. To demonstrate the technology’s horsepower, Nvidia ran a particle demo similar to what have been showcased by Intel on Nehalem – at more than 10 times the speed.

In order to demonstrate the physics horsepower of the GeForce 8800/9800 series, Hegde took aim at Intel's eight-core Nehalem particle demo, which can be seen in one of our IDF articles. Back in Shanghai for IDF Spring 2008, our own Humphrey Cheung filmed Intel's demo and a statement from Intel's engineer, who talked about the fact that CPUs could soon be strong enough so that you wouldn’t need a GPU in the future. While Intel told us later on that the engineer’s remarks did not reflect the company’s opinion, the statement made waves at Nvidia and prompted the company to create a physics demo with 65,000 simulated particles.

While Intel's Nehalem demo had 50,000-60,000 particles and ran at 15-20 fps (without a GPU), the particle demo on a GeForce 9800 card resulted in 300 fps. If the very likely event that Nvidia’s next-gen parts (G100: GT100/200) will double their shader units, this number could top 600 fps, meaning that Nehalem at 2.53 GHz is lagging 20-40x behind 2006/2007/2008 high-end GPU hardware. However, you can’t ignore the fact that Nehalem in fact can run physics.

Read more @ TGDaily

Comments (0)