. home.aspx



NVIDIA Unveils World's Most Powerful AI Supercomputer, Leonardo

October 16, 2020 / Globenewswire

NVIDIA today reported that the Italian between college consortium CINECA — one of the world's most significant supercomputing focuses — will utilize the organization's quickened figuring stage to fabricate the world's quickest AI supercomputer.

The new "Leonardo" framework, worked with Atos, is relied upon to convey 10 exaflops of FP16 AI execution to empower progressed AI and HPC united application use cases. Including almost 14,000 NVIDIA Ampere engineering based GPUs and NVIDIA® Mellanox® HDR 200Gb/s InfiniBand organizing, Leonardo will push Italy as the worldwide pioneer in AI and elite registering exploration and advancement.

Leonardo is obtained by EuroHPC, a cooperation between public governments and the European Union to build up a top notch supercomputing environment and exascale supercomputing in Europe, and supported by the European Commission through the Italian Ministry of University and Research.

“The EuroHPC technology roadmap for exascale in Europe is opening doors for rapid growth and innovation in HPC and AI,” said Marc Hamilton, vice president of solutions architecture and engineering at NVIDIA. “We’re working with CINECA and Atos to accelerate scientific discovery across a broad range of application domains, providing a platform to usher in the era of exascale computing.”

Current logical processing requires elite recreation, information examination, AI and AI, and representation. NVIDIA's registering stage quickens these remaining tasks at hand while giving very high throughput and low force utilization, making it ideal for logical figuring. Instances of exploration utilizing this methodology remember work for such regions as:

Medication disclosure: Using genomic examination to distinguish promising proteins that can be focused with a particular medication to battle COVID-19 and different maladies.

Space investigation and examination: Harnessing the apparatuses of multi-courier astronomy — which consolidates information from wide-running sources, for example, electromagnetic waves, gravitational waves and neutrinos — to more readily comprehend the universe.

Climate displaying: Predicting extraordinary climate conditions with more noteworthy exactness and speed.

The Leonardo supercomputer will help unravel logical difficulties across numerous orders, from material sciences to high-energy material science to environmental change. Researchers and analysts will be quickly gainful on the new framework as it will run in no way different CUDA® programming as CINECA's current NVIDIA-fueled framework, at present the quickest advanced education research supercomputer in Europe.

“CINECA plays a critical part in evolving both the research and industrial community in accelerated HPC application development,” said Sanzio Bassini, director of the HPC department at CINECA. “The Leonardo supercomputer is the result of our long-term commitment to pushing the boundaries of what a modern exascale supercomputer can be.”

“The call for accessibility in HPC, and the expansion of AI in research and industries, have dramatically increased the requirements for more flexibility, and simplicity, in how the world’s leading supercomputers are built,” said Giuseppe di Franco, CEO of Italy at Atos. ”As Europe’s leading supercomputer maker, Atos has made a commitment to embracing these modern-day standards and is raising the bar in further democratizing the world of supercomputing.”

Leonardo will be worked from Atos' BullSequana XH2000 supercomputer hubs, each with four NVIDIA Tensor Core GPUs and a solitary Intel CPU. It will likewise utilize NVIDIA Mellanox HDR 200Gb/s InfiniBand availability, with savvy in-network registering quickening motors that empower very low inertness and high information throughput to give the most elevated AI and HPC application execution and adaptability.

NVIDIA Ampere engineering GPUs can quicken more than 1,800 HPC applications, for example, Quantum Espresso for material science, SPECFEM3D for geoscience and MILC for quantum physical science by up to 70x, making past large test reproductions practically constant assignments.


NVIDIA’s (NASDAQ: NVDA) invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined modern computer graphics and revolutionized parallel computing. More recently, GPU deep learning ignited modern AI — the next era of computing — with the GPU acting as the brain of computers, robots and self-driving cars that can perceive and understand the world. More information at http://nvidianews.nvidia.com/.