Nvidia has taken a step towards creating what it calls "personal supercomputers" with the unveiling of a graphics processing unit (GPU) designed for scientists and engineers.

The Tesla GPUs are designed for high-performance computing fields such as geoscience, molecular biology and medical diagnostics.

Nvidia's offerings span from PCs to large-scale server clusters and include the Tesla GPU Computing Processor, a dedicated computing board that scales multiple Tesla GPUs inside a single PC or workstation.

The board can support 128 parallel processors and up to 518 gigaflops of parallel computation.

The range also includes the Tesla Deskside Supercomputer, a system that includes two Nvidia Tesla GPUs and attaches to a PC or workstation, and the Tesla GPU Computing Server, a 1U server housing up to eight Tesla GPUs.

"Today's science is no longer confined to the laboratory, and scientists employ computer simulations before a single physical experiment is performed," said Jen-Hsun Huang, president and chief executive at Nvidia.

"This fundamental transition to computational methods is forging a new path for discoveries in science and engineering."

John Stone, senior research programmer at the University of Illinois at Urbana-Champaign, added: "Many of the molecular structures we analyse are so large that they can take weeks of processing time to run the calculations required for their physical simulation.

"Nvidia's GPU computing technology has given us a 100-fold increase in some of our programs, and this is on desktop machines where previously we would have had to run these calculations to a cluster."