Unveiled yesterday at the Annual Meeting of National High Performance Computing (HPC China 2010) in Beijing, Tianhe-1A is now the world’s fastest supercomputer with a performance record of 2.507 petaflops, as measured by the LINPACK benchmark.
Designed by the National University of Defense Technology (NUDT) in China, it epitomizes modern heterogeneous computing by coupling massively parallel GPUs with multi-core CPUs, enabling significant achievements in performance, size and power. The system uses 7,168 NVIDIA® Tesla™ M2050 GPUs and 14,336 Intel Xeon CPUs; it would require more than 50,000 CPUs and twice as much floor space to deliver the same performance using CPUs alone.
It cost $88 million; its 103 cabinets weigh 155 tons, and the entire system consumes 4.04 megawatts of electricity & it is already fully operational.
Tianhe-1A ousted the previous record holder, Cray XT5 Jaguar, which is used by the U.S. National Center for Computational Sciences at Oak Ridge National Laboratories. It is powered by 224,162 Opteron CPUs and achieves a performance record of 1.75 petaflops.
According to Nvidia, Tianhe-1A will be operated as an open access system to use for large scale scientific computations.
Note: NVIDIA Tesla GPUs, based on the CUDA™ parallel computing architecture, are designed specifically for high performance computing (HPC) environments and deliver transformative performance increases across a wide range of HPC fields, including drug discovery, hurricane and tsunami modeling, cancer research, car design, even studying the formation of galaxies.