The more near the publication date of a new product moves close, the more rumors gives it around this.
This applies particularly to diagram chips, in this case to nVidias coming G80-Chip. Because this will have the ability owing to a revised architecture probably also to accomplish physics computations.
This announced nVidias PR-boss Michael Hara in a shortly appearing interview with the colleagues of Golem.de and provided in such a way for clarity, because in the past days some rumors made in this connection the round. Trip was a press release of the Main board and diagram map manufacturer Asus to the new "P5N32-SLI Premium" - motherboard.
The board for processors from the house Intel has over "nVidias nForce 590" - chip set and altogether three Slots of the type "PCI express x16" for diagram maps. According to the mentioned press release Nvidia's Physics is to find card "place in the third Slot". This sentence gave a fertile soil to rumors, nVidia its own physics acceleration map would develop. Here it concerns however a misunderstanding, as Michael Hara in the discussion with Golem.de explained.
Thus nVidia no own map of this kind develops. One works at present rather on somewhat, into whom one would grow slowly, thus Hara. It continued to implement that with the next and the generation after the next of the GeForce Grafikkarten "the possibilities for physics computations become very good its ". This is to be understood as an allusion on the coming G80-Chip, which will probably come along with physics acceleration abilities.
Michael Hara continued to explain that nVidia about it think, the new "Unified Shader" - architecture, in which pixel and Vertex Shader are summarized, to use also for physics computations. By the unification of these two computation units it is very simple to compute also physics within the GPU. With nVidia one believes firmly in this concept and sees also opposite processors, which will have four cores, an achievement advantage.