The Tianhe-1A supercomputer in Tianjin uses 7,168 Nvidia Tesla M2050 GPUs and 14,336 CPUs
The Tianhe-1A, a Nvidia-powered supercomputer that made its debut at the Annual Meeting of National High Performance Computing (HPC China 2010) in Beijing, set a performance record of 2.51 petaflops, as measured by the Linpack benchmark. A petaflop is a measure of a computer’s processing speed and can be expressed as a thousand-trillion floating point operations per second.
This performance record makes the Tianhe-1A the fastest system in the world today, based on performance data submitted for the June 2010 Top500 list. On that list, the nearest GPU-based competitor stands at number three. It is called Nebulae, built from a Dawning TC3600 Blade system with Intel X5650 processors and Nvidia Tesla C2050 GPUs (graphics processing units), took the title of world’s fastest supercomputer. Its Linpack rating is 1.0 petaflops.
The previous fastest supercomputer was named Jaguar, located at the Department of Energy’s Oak Ridge Leadership Computing Facility, with its record 1.76 petaflops performance, running the Linpack benchmark. Jaguar has a theoretical peak capability of 2.3 petaflop/s and nearly a quarter of a million cores.
The Tianhe-1A was designed by the National University of Defense Technology in China. Nvidia reported the system is housed at National Supercomputer Centre in Tianjin and is already fully operational. According to the Nvidia press statement, the Tianhe-1A will be operated as an open-access system for use in large-scale scientific computations.
The supercomputer couples massively parallel GPUs with multi-core CPUs and the system uses 7,168 Nvidia Tesla M2050 GPUs and 14,336 CPUs. Nvidia claimed it would require more than 50,000 CPUs and twice as much floor space to deliver the same performance using CPUs alone. A 2.51 petaflop system built entirely with CPUs would consume more than 12 megawatts.
Not Exactly Green But Uses Less Energy
Nvidia’s Tesla GPUs, based on the company’s Compute Unified Device Architecture, parallel computing architecture, are designed specifically for high-performance computing (HPC) environments and are designed to deliver performance increases across a range of HPC fields, including drug discovery, hurricane and tsunami modelling, cancer research, car design or studying the formation of galaxies.
“GPUs are redefining high-performance computing,” said Jen-Hsun Huang, president and CEO of Nvidia. “With the Tianhe-1A, GPUs now power two of the top three fastest computers in the world today. These GPU supercomputers are essential tools for scientists looking to turbocharge their rate of discovery. “Thanks to the use of GPUs in a heterogeneous computing environment, Tianhe-1A consumes only 4.04 megawatts, making it three times more power-efficient; the difference in power consumption is enough to provide electricity to over 5,000 homes for a year,” the company said in a statement.
“The performance and efficiency of Tianhe-1A was simply not possible without GPUs,” said Guangming Liu, chief of National Supercomputer Center in Tianjin, China. “The scientific research that is now possible with a system of this scale is almost without limits; we could not be more pleased with the results.”