Today Nvidia CEO Jen-Hsun Huang revealed that the company will bring its CUDA programming language to "any computer, or any server in the world," with the help of the Portland Group. Nvidia's dip into the x86 market means that systems without Nvidia GPUs will be able to process CUDA code, allowing the company to better compete against DirectCompute and OpenCL in the high-performance computing (HPC) market, says Ars Technica.
The CUDA x86 will be demonstrated at the SC10 Supercomputing conference in November, reports DriversHQ.com. The availability of the new compiler has not yet been announced.
Nvidia also announced the names and dates of its next-generation GPUs. Code-named Kepler and Maxwell, the GPUs will be made available in 2011 and 2013, respectively, according to PCMag.com.