Graphics vendor Nvidia, together with its global partners, has announced the availability of its GPU-based Tesla Personal Supercomputer aimed towards the scientific research sector.
The new system dispenses with the traditional need for supercomputing clusters, bringing the equivalent computing power for a fraction of the price and in the form of a desktop computer.
The core of the system is Tesla C1060 GPU Computing Processor, which is based on Nvidia’s CUDA parallel computing architecture, allowing for multi-string processing.
“GPUs have evolved to the point where many real world applications are easily implemented on them and run significantly faster than on multi-core systems,” said the director of the Innovative Computing Laboratory at the University of Tennessee, Prof. Jack Dongarra. “Future computing architectures will be hybrid systems with parallel-core GPUs working in tandem with multi-core CPUs.”