NVIDIA, the world chief in accelerated computing, is driving a elementary shift within the high-performance laptop (HPC) business. This week NVIDIA detailed how its AI chips are accelerating innovation for AI-powered programs for superior supercomputing and scientific discovery.
The chipmaker introduced on the ISC Excessive Efficiency occasion in Hamburg that new supercomputers across the globe are utilizing NVIDIA Grace Hopper Superchips (GH200). This contains supercomputer JUPITER on the Jülich Supercomputing Centre in Germany, CEA on the French Different Energies and Atomic Power Fee, and Alps on the Swiss Nationwide Supercomputing Centre from Hewlett-Packard Enterprise (HPE).
Based on NVIDIA, the supercomputing programs utilizing Grace Hopper chips signify a mixed whole of 200 exaflops of computational AI processing energy. That is equal to a staggering 200 quintillion calculations per second.
“AI is accelerating analysis into local weather change, dashing drug discovery, and resulting in breakthroughs in dozens of different fields,” stated Ian Buck, vice chairman of hyperscale and HPC at NVIDIA. “NVIDIA Grace Hopper-powered programs have gotten a vital a part of HPC for his or her means to rework industries whereas driving higher power effectivity.”
NVIDIA has additionally introduced its objective to speed up its quantum computing efforts, which embody the set up of the open-source NVIDIA CUDA-Q platforms at a number of worldwide websites.
CUDA-Q is an open-source accelerated computing platform that powers quantum processing items (QPUs), specialised and designed to carry out quantum computations which are too computationally intensive for classical computing.
QPUs allow researchers to carry out advanced quantum simulations and optimization duties. As well as, it permits them to leverage quantum parallelism for speedy computations and improve machine studying algorithms to speed up scientific discovery and innovation.
“Helpful quantum computing might be enabled by the tight integration of quantum with GPU supercomputing,” stated Tim Costa, director of quantum and HPC at NVIDIA, in a press release. “NVIDIA’s quantum computing platform equips pioneers corresponding to AIST, JSC, and PSNC to push the boundaries of scientific discovery and advance the cutting-edge in quantum-integrated supercomputing.”
In March this 12 months, NVIDIA launched the Earth-2 platform for predicting world local weather utilizing simulation by AI supercomputers. The platform, which is a part of NVIDIA CUDA-X microservices software program, has the potential to offer extremely correct insights into climate fluctuations and supply well timed warnings to mitigate the rising menace of local weather disasters across the globe.
The ability and effectivity of NVIDIA GPUs are additionally being utilized at Argonne Nationwide Laboratory, a multidisciplinary science and engineering analysis heart in Illinois, to generate gene sequences that assist them higher perceive the virus behind COVID-19 and speed up medical discoveries.
Earlier this 12 months, Microsoft expanded its partnership with NVIDIA with highly effective new integrations with NVIDIA applied sciences to advance AI infrastructure and speed up analysis in healthcare and life sciences.
The technological developments enabled by NVIDIA are busting bottlenecks in AI supercomputing, HPC analysis, and scientific discoveries. From predicting world local weather change patterns to the invention of latest supplies, the contributions of NVIDIA applied sciences to the scientific neighborhood are profound. As NVIDIA continues to roll out extra superior applied sciences, we are able to anticipate the chipmaker to play a key function within the subsequent wave of scientific breakthroughs and transformative improvements.
Associated Gadgets
How AI Will Influence the Drug Discovery Pipeline
Scientists Use Machine Studying To Show The Existence of a Uncommon Part Of Matter
Stanford HAI AI Index Report: Science and Medication
Associated