Join us at the International Supercomputing Conference 2023 (ISC 2023) in Hamburg, Germany to see how large-scale, energy-efficient simulations, machine learning, digital twins, and quantum computing are changing the landscape of scientific computing.

Meet our partners at ISC on the showfloor, and join us in sessions and workshops. 

NVIDIA News at ISC22

Top Global Systems Makers Accelerate Adoption of NVIDIA Grace and Grace Hopper

Just announced top global systems makers accelerate adoption of NVIDIA Grace CPU and Grace Hopper Superchips to create the next generation of servers turbocharging AI and HPC workloads for the exascale era.

The Man With 100,000 Brains: AI’s Big Donation to Science

Researchers at King’s College London used transformer models on the Cambridge-1 supercomputer to create medical images they’re releasing freely to accelerate AI in healthcare.

HPC Researchers Seed the Future of In-Network Computing with DPUs

Supercomputing centers in Asia, Europe and the US are taking accelerated computing to the next level with NVIDIA Bluefield DPUs on NVIDIA Quantum InfiniBand networks.

The Road to the Hybrid Quantum Data Center

Dozens of quantum organizations are leveraging NVIDIA cuQuantum with the major quantum software frameworks to accelerate quantum circuit simulations on GPUs, paving the way to build tomorrow’s hybrid quantum systems.

Building Digital Twins in NVIDIA Omniverse to Accelerate Clean Energy Research

The U.K.’s Atomic Energy Authority and University of Manchester are using the digital twin simulation platform to connect distributed design teams and gain a deeper understanding of fusion plasma behavior.

NVIDIA ISC22 Special Address

Watch On-Demand

Accelerating a New Wave of AI Innovation and Scientific Discovery


NVIDIA shares an overview of the latest technologies and innovations transforming the world of AI and computational science, from the data center to the cloud and to the edge. 

Ian Buck, VP and GM of Accelerated Computing, NVIDIA

NVIDIA Special Address

Accelerating a New Wave of AI Innovation and Scientific Discovery

NVIDIA shares an overview of the latest technologies and innovations transforming the world of AI and computational science, from the data center to the cloud and to the edge.

Attendees will get a complimentary code for a free online, self-paced course from NVIDIA Deep Learning Institute.

Ian Buck, VP and GM of Accelerated Computing, NVIDIA

Ian Buck
BMW Group

ISC22 Keynote

Supercomputing: The Key to Unlocking the Next Level of Digital Twins

Today’s technologies have led to a big bang in large-scale virtual world simulation, explore BMW’s virtual production system, and find out how digital twins are enabling the next era of industrial virtualization and AI.

Rev Lebaredian, VP of Omniverse and Simulation Technology, NVIDIA
Michele Melchiorre, Snr VP Production System, Technical Planning, Tool Shop and Plant Construction, BMW Group.

ISC at a Glance

Throughout ISC 2023, explore a range of groundbreaking work in the field of accelerated computing. Take a closer look at this year’s scheduled NVIDIA sessions, demos, and workshops.

  • Sunday 21/05
  • Tuesday 23/05
  • Wednesday 24/05
  • Thursday 25/05

Better Together Reception ISC 2023

May 23, 6:00 p.m. - 10:00 p.m. CEST, Hofbräu Wirtshaus Esplanade

Connect with industry colleagues and partners over refreshments and appetizers at our Better Together Reception, hosted by AWS and NVIDIA. 

Anyone attending ISC 2023 is welcome to join—reserve your place today.

Featured Demos

In a series of demos, explore how NVIDIA technologies are transforming a variety of industries with new capabilities—highlighting the latest breakthroughs in AI, HPC, accelerated data science, healthcare, visualization, and more.

Expanding NVIDIA Omniverse - BMW Group’s Factory of the Future 2.0

BMW’s Factory of the Future uses a digital twin, created in NVIDIA Omniverse, to simulate complex production scenarios, support continuous improvement, speed output, increase agility, and optimize efficiency.

Siemens Maximizes Wind Energy production using Wake Optimization

Using NVIDIA Modulus and NVIDIA Omniverse, Siemens Gamesa Renewable Energy can optimize each wind farm configuration to get the most out of the investment and reduce cost for consumers. The simulation using Omniverse is 4,000X faster than their previous models.

Accelerating Extreme Weather Prediction with FourCastNet

NVIDIA’s FourCastNet, a physics-ML model that emulates the dynamics of global weather patterns, predicts extremes with unprecedented speed and accuracy.

Accelerating Scientific Computing with NVIDIA BlueField

Learn how  BlueField accelerates scientific computing applications up to 26% by offloading collective operations from the CPU and performing the communications in the background.

Building a Fusion Reactor Digital Twin in NVIDIA Omniverse

The U.K.’s Atomic Energy Authority (UKAEA) and researchers at University of Manchester are using the NVIDIA Omniverse simulation platform to accelerate the design and development of a full scale fusion reactor.

NVIDIA Self-Healing Network Technology Enables Unbreakable Data Centers

The self-healing network capabilities of NVIDIA Quantum InfiniBand switches speeds up fault recovery by 1,000X to overcome link failures, enabling network recovery much faster than any other software-based solution.

Maximize Performance for Distributed Deep Learning with NVIDIA SHARP

Learn how SHARP and HGX A100 working together deliver performance gains of up to 2.5X for the most common message sizes used with deep learning.

Partner Ecosystem

We are excited to work with our partners, supercomputing centers hosting supercomputers like Isambard 3, Alps, Berzelius, Leonardo, and Marenostrum 5, and developers to showcase our continued commitment to scientific computing.

Be sure to visit our esteemed partners and witness firsthand how we are collectively propelling the boundaries of high-performance computing across diverse industries and creating a better tomorrow.

Altair Logo
AsrockRACK Logo
Atos Logo
AWS Logo
Boston Logo
DDN Logo
Dell Logo
Equinix Logo
Google Cloud Logo
Gigabyte Logo
HPE Logo
Lenovo Logo
Megware Logo
Pure Storage Logo
Quanta Logo
Run:ai Logo
Supermicro Logo
Vast Logo
Weka Logo
xFusion Logo

Virtual Theater

Hear from industry leaders, scientists, and researchers as they explain their groundbreaking work utilizing GPU and high performance computing technologies. Tune in during the week of 28th June to watch short, on-demand talks at your own pace.

Hear from industry leaders, scientists, and researchers at your own place
NVIDIA technologies are transforming a variety of industries with new capabilities

Featured Demos

In a series of live and recorded demos, explore how NVIDIA technologies are transforming a variety of industries with new capabilities— highlighting the latest breakthroughs in accelerated computing technologies and developer tools, and how they're being utilized across industries from agriculture to weather and climate.

Watch Live: NVIDIA DPU Acceleration

HPC and AI communication frameworks and libraries are latency/bandwidth-sensitive, and they play a critical role in determining application performance. 

Join this live demo session to interact with MVAPICH2-DPU MPI library developers and learn how to accelerate MPI-based scientific applications on clusters with NVIDIA BlueField DPUs.

NVIDIA DPU Acceleration

Watch NVIDIA CEO Jensen Huang’s Teratec Keynote

The Industrial HPC Revolution

Industrial high performance computing is at its tipping point.
Learn how this industrial HPC revolution will sweep through data centers, public and hybrid clouds and edge networks, and revolutionize every industry - from product manufacturing to aerospace and drug discovery.


NVIDIA Developer Program

NVIDIA Developer Program

Developers, researchers, professors and students can get access to 600+ SDKs, AI models, community forums, tech blogs and technical resources to advance education and research by joining our Developer Program.

NVIDIA Inception for Startups

NVIDIA Inception for Startups

Inception provides 14,000 cutting-edge startups worldwide with critical go-to-market support, technical expertise, training, and introductions to funding opportunities to accelerate their business. See how program members in higher education, research and other industries are using computer vision to create innovative products.

NVIDIA Training

Get Hands-On Training in Accelerated Computing, Accelerated Data Science and AI

Elevate your HPC expertise with our technical training program that offers hands-on experience building and deploying accelerated applications. Get access to a fully configured, GPU-accelerated server in the cloud, gain practical skills for your work, and take advantage of opportunities to earn certificates of subject matter competency.

Catch all the Brilliant GTC Sessions

See how NVIDIA’s computing platforms, advances, and breakthroughs in virtual collaboration are transforming HPC.

Technologies & Resources for HPC & AI

  • Technologies
  • Resources

NVIDIA Hopper GPU Architecture

The NVIDIA Hopper™ architecture is powering the next generation of accelerated computing with unprecedented performance, scalability, and security for every data center. With the ability to securely scale diverse workloads—from small enterprise to exascale HPC and trillion-parameter AI—Hopper enables brilliant innovators to fulfill their life's work at the fastest pace in human history.


NVIDIA Grace™ CPU delivers high performance, power efficiency, and high-bandwidth connectivity that can be used for HPC & AI applications. NVIDIA Grace Hopper Superchip is a breakthrough integrated CPU+GPU for giant scale AI and HPC applications. For CPU only HPC applications, NVIDIA Grace CPU Superchip provides the highest performance, memory bandwidth and energy-efficiency compared to today’s leading server chips.

NVIDIA BlueField data processing units (DPUs)

Providing powerful computing, high-speed InfiniBand networking, and highly programmable engines, the NVIDIA BlueField DPU ignites unprecedented innovation and performance for modern scientific computing applications.

NVIDIA Quantum-2 Networking Platform

NVIDIA Quantum-2 InifiniBand Networking empowers the world’s leading supercomputing data centers with software-defined networking, In-Network Computing, performance isolation, advanced acceleration engines, remote direct-memory access (RDMA), and the fastest speeds and feeds up to 400 Gb/s.

NVIDIA Modulus

NVIDIA Modulus is an open-source framework for building, training, and fine-tuning physics-machine learning models with a simple Python interface. NVIDIA Modulus enables engineers to build high-fidelity digital twins that blend the causality of physics with simulation data from CAE solvers or observed data and feature near-real-time latency.

NVIDIA Quantum Computing

NVIDIA offers a suite of quantum computing solutions include NVIDIA cuQuantum, an SDK of optimized libraries and tools for accelerating quantum computing workflows, NVIDIA CUDA Quantum, an open QPU-agnostic development platform for hybrid quantum-classical computing, and NVIDIA DGX Quantum, a reference architecture which combines the NVIDIA Grace Hopper Superchip and the Quantum Machines OPX control system to create a powerful hybrid quantum-classical system.


The NVIDIA HPC SDK is a comprehensive suite of compilers, libraries, and tools essential to maximizing developer productivity and the performance and portability of HPC applications.


NVIDIA Magnum IO™ is the architecture for parallel, intelligent data center IO. It maximizes storage, network, and multi-node, multi-GPU communications for the world’s most important applications, using large language models, recommender systems, imaging, simulation, and scientific research.

NVIDIA Grace Hopper Superchip Whitepaper and Data Sheet

The NVIDIA® Grace Hopper architecture brings together the groundbreaking performance of the NVIDIA Hopper GPU with the versatility of the NVIDIA Grace™ CPU, connected with a high bandwidth and memory coherent NVIDIA NVLink Chip-2-Chip (C2C)® interconnect in a single Superchip, and support for the new NVIDIA NVLink Switch System.

NVIDIA Grace CPU Superchip Whitepaper and Data Sheet

The NVIDIA® Grace CPU architecture brings together two high-performance and power efficient NVIDIA Grace CPUs with server-class LPDDR5X memory connected with NVIDIA NVLInk Chip-2-chip (C2C) interconnect to deliver flagship two socket server performance in a single Grace CPU Superchip. Learn more from this deep dive into the NVIDIA Grace CPU Superchip Architecture Whitepaper.

DPU Power Efficiency Whitepaper

NVIDIA® BlueField® DPUs can reduce power consumption by 30%, saving $56 million for large data centers. Find all of NVIDIA’s test results on the power consumption of various DPUs.

NVIDIA Quantum-2 InfiniBand Platform

The NVIDIA® Quantum-2 InfiniBand platform provides AI developers and scientific researchers with the highest networking performance available to take on the world’s most challenging problems. Innovative NVIDIA In-Network Computing acceleration engines provide ultra-low latency and double the data throughput, while delivering the scalability and feature-rich capabilities required for supercomputers and artificial intelligence.

NVIDIA Modulus Webinar

Physics-informed machine learning, otherwise known as physics-ML, is enabling real-time digital twin use cases ranging from climate science to industrial manufacturing. Learn how to use physics-ML for engineering problems with NVIDIA Modulus.

NVIDIA Quantum-Classical Computing Press Release

NVIDIA unveiled a new system built with Quantum Machines that provides a revolutionary new architecture for researchers working in high-performance and low-latency quantum-classical computing.


Take a deep dive into the latest developments in NVIDIA software for HPC applications, including a comprehensive look at what’s new in programming models, compilers, libraries, and tools.

NVIDIA Magnum IO Blog

Improve HPC network performance using NVIDIA Magnum IO NVSHMEM and GPUDirect Async.

Earth-2 for Carbon Capture and Storage Blog

Learn how using digital twins built with NVIDIA Earth-2 for carbon capture and storage can reduce the cost and time needed for industrial net-zero strategies.

Student Cluster Competition

The annual Student Cluster Competition returns as an in-person event at ISC 2023. Student teams design state-of-the-art systems that must be capable of achieving both the highest performance across a series of standard HPC/AI benchmarks and challenges, while adhering to the competition’s strict power constraints. They learn scientific applications, optimize their cloud configurations, and compete in a 72-hour challenge to complete a set of benchmarks and real-world scientific workloads. Student teams will design and build clusters by leveraging the NVIDIA Quantum InfiniBand Platform and NVIDIA GPUs. 

The intensive competition culminates during the conference’s closing plenary with teams taking center stage for a live award ceremony, where they are recognized and celebrated by an audience of thousands of HPC luminaries.

Sign up to receive the latest news from NVIDIA