Chinese supercomputer is world’s fastest at 2.5 petaflops

October 28, 2010

The Tianhe-1A Supercomputer, located at National Supercomputer Center, Tianjin (NVIDIA)

Tianhe-1A, a new supercomputer revealed today at HPC 2010 China, has set a new performance record of 2.507 petaflops (quadrillion floating point operations per second), as measured by the LINPACK benchmark, making it the fastest system in China and in the world today, according to an NVIDIA statement.

The supercomputer operates 50% faster than the world’s current top supercomputer, the Cray XT5-HE Jaquar at Oak Ridge National Laboratory, which can deliver 1.76 petaflops of sustained performance. The Tianhe-1A operates at one-third the power and at one half the size of the Jagquar, according to NVIDIA.

Tesla GPU computing module (NVIDIA)

The system uses 7,168 NVIDIA Tesla M2050 massively parallel graphics processing units (GPUs) and 14,336 multi-core central processing units (CPUs). It would require more than 50,000 CPUs and twice as much floor space to deliver the same performance using CPUs alone. the company says.

Tianhe-1A was designed by the National University of Defense Technology (NUDT) in China. The system is housed at National Supercomputer Center in Tianjin and is already fully operational. It will be operated as an open access system to use for large scale scientific computations.

The Tianhe-1A was announced two weeks before the release of the next Top500 list.