Special address at ISC 2022 shows future of HPC

Researchers grappling with today’s major challenges are gaining traction with accelerated computingas shown on ISCEurope’s annual meeting of supercomputing experts.

Some are building digital twins to simulate new energy sources. Some use AI+HPC to look deep into the human brain.

Others take HPC to the edge with highly sensitive instruments or accelerate simulations on hybrid quantum systems, said Ian Buck, vice president of accelerated computing at NVIDIA, at a special ISC address in Hamburg.

Delivering 10 AI Exaflops

For example, a new supercomputer at Los Alamos National Laboratory (LANL), called Venado, will deliver 10 exaflops of AI performance to advance work in areas such as materials science and renewable energy.

LANL researchers are targeting 30x accelerations in their computational multi-physics applications with NVIDIA GPUs, CPUs and DPUs in the system, named after a peak in northern New Mexico.

LANL's Venado Uses NVIDIA Grace, Grace Hopper, and BlueField DPUs

Venado will use NVIDIA Grace Hopper Super chips to run workloads up to 3x faster than previous GPUs. It also packs NVIDIA Grace CPU Superchips to deliver twice the performance per watt of traditional CPUs on a long tail of unaccelerated applications.

BlueField gathers momentum

The LANL system is one of: the newest of many around the world to embrace NVIDIA BlueField DPUs to offload and speed up communication and storage tasks from host CPUs.

Similarly, the Texas Advanced Computing Center is adding BlueField-2 DPUs to the NVIDIA Quantum InfiniBand network on Lonestar6. It will be a development platform for cloud native supercomputinghosting multiple users and applications with bare-metal performance while securely isolating workloads.

“That’s the architecture of choice for the next generation of supercomputing and HPC clouds,” Buck says.

Exascale in Europe

In Europe, NVIDIA and SiPearl are teaming up to expand the ecosystem of developers building exascale computing on Arm. The work will help users in the region transition applications to systems using SiPearl’s Rhea and future Arm-based CPUs, along with NVIDIA accelerated computing and networking technologies.

Japan’s Center for Computational Sciences, at Tsukuba University, Joins forces NVIDIA H100 Tensor Core GPUs and x86 CPUs on an NVIDIA Quantum-2 InfiniBand platform. The new supercomputer will tackle jobs in climatology, astrophysics, big data, AI and more.

The new system joins the 71% on the latest TOP500 list of supercomputers that have adopted NVIDIA technologies. In addition, 80% of the new systems on the list also use NVIDIA GPUs, networks, or both, and NVIDIA’s network platform is the most popular interconnect for TOP500 systems.

HPC users leverage NVIDIA technologies because they deliver the highest application performance for established supercomputing workloads — simulation, machine learning, real-time edge processing — as well as emerging workloads such as quantum simulations and digital twins.

Start up with Omniverse

To show what these systems can do, Buck played a demo of a virtual fusion plant what researchers from the UK Atomic Energy Authority and the University of Manchester are building NVIDIA Omniverse† The digital twin wants to simulate the entire power station, its robotic components – even the behavior of the nuclear fusion plasma in real time.

NVIDIA Omniverse, a 3D design collaboration and world simulation platform, allows remote researchers to collaborate on the project in real time while using different 3D applications. They want to improve their work with: NVIDIA Modulusa framework for creating physics-informed AI models.

“It’s incredibly intricate work that is paving the way for tomorrow’s clean renewables,” Buck says.

AI for medical imaging

Separately, Buck described how researchers created a library of 100,000 synthetic images of the human brain NVIDIA Cambridge-1a supercomputer dedicated to healthcare advancements with AI.

A team from King’s College London used MONAan AI framework for medical imaging, to generate lifelike images that can help researchers see how diseases like Parkinson’s develop.

“This is a great example of how HPC+AI is making a real contribution to the scientific and research community,” Buck said.

HPC on the edge

The HPC work continues to extend beyond the supercomputing center. Observatories, satellites and new types of laboratory instruments need to stream and visualize data in real time.

For example, work in lightsheet microscopy at Lawrence Berkeley National Lab uses: NVIDIA Clara Holoscan to see life in real time at the nanometer scale, work that would take several days on CPUs.

To take supercomputing to the edge, NVIDIA is developing Holoscan for HPC, a highly scalable version of our imaging software to accelerate scientific discovery. It will run on accelerated platforms from Jetson AGX modules and devices to quad A100 servers.

“We can’t wait to see what researchers do with this software,” Buck says.

Speeding Quantum Simulations

In yet another vector of supercomputing, Buck reported on the rapid adoption of NVIDIA cuQuantuma software development kit to speed up quantum circuit simulations on GPUs.

Dozens of organizations are already using it in research in many fields. It is integrated into major quantum software frameworks, allowing users to access GPU acceleration without additional coding.

Most recently, AWS announced the availability of: cuQuantum in its Braket service† And it showed how cuQuantum can deliver up to 900x acceleration on quantum machine learning workloads while reducing costs by 3.5x.

“Quantum computing has enormous potential, and simulating quantum computing on GPU supercomputers is essential to bring us closer to valuable quantum computing,” Buck said. “We are very excited to be at the forefront of this work,” he added.

To learn more about accelerated computing for HPC, watch the full talk below.

Leave a Comment

Your email address will not be published.