NVIDIA has released its Tesla personal supercomputer that delivers 250 times the processing power of a conventional PC.
A majority of today’s scientific research is carried out on supercomputing clusters, which is a resource shared by several researchers. The GPU-based Tesla provides the equivalent computing power of a cluster, but at a fraction of the price and in the form of a standard desktop workstation.
“We’ve all heard ‘desktop supercomputer’ claims in the past, but this time it’s for real,” said Burton Smith, a certified Microsoft Technical Fellow. “NVIDIA and its partners will be delivering outstanding performance and broad applicability to the mainstream marketplace. Heterogeneous computing, where GPUs work in tandem with CPUs, is what makes such a breakthrough possible.”
Leading institutions including MIT, Cambridge University and others are already advancing their research using GPU-based personal supercomputers.
At the core of the GPU-based Tesla Personal Supercomputer is the Tesla C1060 GPU processor based on NVIDIA’s CUDA parallel computing architecture.
Yesterday, Tokyo Institute of Technology’s TSUBAME became the first supercomputer to achieve a ranking in the world’s top supercomputers with an NVIDIA Tesla GPU-based cluster. Ranked 29 out of 500, TSUBAME now delivers 170 teraFLOPS of performance through its addition of 170 Tesla S1070 1U systems.