Nvidia Tesla M2050 GPUs, the fastest speeds to date is now powering China's Tianhe-1A supercomputer. "Tianhe-1A" has hit 2.507 petaflops, beating a system at Tennessee-based Oak Ridge National Laboratories.
China's Tianhe-1A supercomputer uses 7,168 Nvidia Tesla M2050 GPUs and 14,336 Intel Xeon CPUs.
The new system would top another Chinese supercomputer also using Nvidia chips called Nebulae, rated at 1.271 petaflops (one petaflop is one thousand trillion operations per second). Both Nebulae and Tianhe-1A performance ratings are based on Linpack benchmark. Nebulae is currently rated No. 2 in the world based on the Top500 June list. The Oak Ridge system is rated fastest at 1.75 petaflops, according to Top500 June list. Tianhe-1A will top the supercomputer list at a Chinese conference.
Tianhe-1A combines 7,168 Nvidia Tesla M2050 GPUs with 14,336 Intel Xeon CPUs. Nvidia isn't only claiming the performance crown but a greener supercomputer, as well. The machine consumes only 4.04 megawatts, making it three times more power efficient than a CPU-only system, Nvidia said in a statement.