NVidia Announces Second-Generation Maximus

The NVidia Maximus platform gives users the ability to perform complex analysis and visualization simultaneously on a single machine. According to the announcement, in the new platform, compute work is assigned to run on the new NVidia Tesla K20 GPU computing accelerator, freeing up the new NVidia Quadro K5000 GPU to handle graphics functions. Maximus unified technology automatically assigns visualization and simulation or rendering work to the appropriate processor.
The NVidia Tesla K20 GPU features dynamic parallelism and Hyper-Q GPU technologies for simplified parallel programming and faster performance.
The NVidia Quadro K5000 GPU features bindless textures that allow users to reference more than 1 million textures directly in memory while reducing CPU overhead. Other features include film-style anti-aliasing technologies for outstanding image quality, increased frame buffer capacity of 4GB, and an all-new display engine capable of driving up to four displays simultaneously with a single K5000.
According to the company, NVidia Maximus-powered desktop workstations featuring the new NVidia Quadro K5000 (US$ 2,249) and the new NVidia Tesla K20 GPU (US$ 3,199) will be available in December 2012. NVidia Quadro K5000 will be available as a separate discrete desktop GPU starting in October 2012.