Nvidia is the leading GPU manufacturer in the GPU market. However, Nvidia has also spread itself outside the GPU market like machine learning AI and now Nvidia has announced during International Supercomputing Conference that world’s best AI Supercomputers are powered by NVIDIA Tensor Core GPUs.
World’s 500 fastest systems list showcase Nvidia taking the top spots with SuperComputer being powered by NVIDIA Tensor Core GPUs.
Not only that, Supercomputers taking the #1 and #3 spot are powered by NVIDIA Tensor Core GPUs namely Summit and Sierra.
Furthermore, Japan’s fastest AI Supercomputer is also powered by Nvidia Tensor. Other Nvidia Tensor Core GPUs powered Supercomputers include:
- No. 3: Sierra, based at the Lawrence Livermore National Laboratory, delivers 71 petaflops of performance using 17,280 GPUs.
- No. 5: ABCI, Japan’s fastest system, delivers 19.6 petaflops of performance using 4,352 GPUs.
- No. 6: Piz Daint, Europe’s fastest system, delivers 19.5 petaflops of performance using 5,320 GPUs.
- No. 7: Titan, operated by the U.S. Energy Department, delivers 17.6 petaflops of performance using 18,688 GPUs.
The new TOP500 list clearly shows that GPUs are the path forward for supercomputing in an era when Moore’s Law has ended. With the invention of our Volta Tensor Core GPU, we can now combine simulation with the power of AI to advance science, find cures for disease and develop new forms of energy. These new AI supercomputers will redefine the future of computing.
The TOP500 list also reveals the shift towards the GPU powered Supercomputers and 5 out of 7 world’s best Supercomputers are powered by GPUs.
Not only that, 17 out of 20 most energy efficient Supercomputers are powered by GPUs according to GREEN500 list. According to Jack Dongarra, professor at the University of Tennessee and Oak Ridge National Laboratory:
This year’s TOP500 list represents a clear shift toward systems that support both HPC and AI computing. Accelerators, such as GPUs, are critical to deliver this capability at the performance and efficiency targets demanded by the supercomputing community.
Speaking of Nvidia, Nvidia’s next-gen GPUs reportedly have been delayed due to 300,000 GPUs being returned to Nvidia by a major OEM partner.
What do you think of GPUs powering world’s best AI Supercomputers? Let us know in the comments.