Quantum of Solace: Research Seeks Atomic Keys to Lock Down COVID-19

Anshuman Kumar is sharpening a digital pencil to penetrate the secrets of the coronavirus.

He and colleagues at the University of California at Riverside want to calculate atomic interactions at a scale never before attempted for the virus. If they succeed, they’ll get a glimpse into how a molecule on the virus binds to a molecule of a drug, preventing it from infecting healthy cells.

Kumar is part of a team at UCR taking work in the tiny world of quantum mechanics to a new level. They aim to measure a so-called barrier height, a measure of the energy required to interact with a viral protein that consists of about 5,000 atoms.

That’s more than 10x the state of the art in the field, which to date has calculated forces of molecules with up to a few hundred atoms.

Accelerating Anti-COVID Drug Discovery

Data on how quantum forces determine the likelihood a virus will bind with a neutralizing molecule, called a ligand, could speed work at pharmaceutical companies seeking drugs to prevent COVID-19.

“At the atomic level, Newtonian forces become irrelevant, so you have to use quantum mechanics because that’s the way nature works,” said Bryan Wong, an associate professor of chemical engineering, materials science and physics at UCR who oversees the project. “We aim to make these calculations fast and efficient with NVIDIA GPUs in Microsoft’s Azure cloud to narrow down our path to a solution.”

Researchers started their work in late April using a protein on the coronavirus believed to play a strong role in rapidly infecting healthy cells. They’re now finishing up a series of preliminary calculations that take up to 10 days each.

The next step, discovering the barrier height, involves even more complex and time-consuming calculations. They could take as long as five weeks for a single protein/ligand pair.

Calling on GPUs in the Azure Cloud

To accelerate time to results, the team got a grant from Microsoft’s AI for Health program through the COVID-19 High Performance Computing Consortium. It included high performance computing on Microsoft’s Azure cloud and assistance from NVIDIA.

Kumar implemented a GPU-accelerated version of the scientific program that handles the quantum calculations. It already runs on the university’s NVIDIA GPU-powered cluster on premises, but the team wanted to move it to the cloud where it could run on V100 Tensor Core GPUs.

In less than a day, Kumar was able to migrate the program to Azure with help from NVIDIA solutions architect Scott McMillan using HPC Container Maker, an open source tool created and maintained by NVIDIA. The tool lets users define a container with a few clicks that identify a program and its key components such as a runtime environment and other dependencies.

Anshuman Kumar used an open source program developed by NVIDIA to move UCR’s software to the latest GPUs in the Microsoft Azure cloud.

It was a big move given the researchers had never used containers or cloud services before.

“The process is very smooth once you identify the correct libraries and dependencies — you just write a script and build the code image,” said Kumar. “After doing this, we got 2-10x speedups on GPUs on Azure compared to our local system,” he added.

NVIDIA helped fine-tune the performance by making sure the code used the latest versions of CUDA and the Magma math library. One specialist dug deep in the stack to update a routine that enabled multi-GPU scaling.

New Teammates and a Mascot

The team got some unexpected help recently when it discovered a separate computational biology lab at UCR also won a grant from the HPC consortium to work on COVID. The lab observes the binding process using statistical sampling techniques to make bindings that are otherwise rare occur more often.

“I reached out to them because pairing up makes for a better project,” said Wong. “They can use the GPU code Anshuman implemented for their enhanced sampling work,” he added.

“I’m really proud to be part of this work because it could help the whole world,” said Kumar.

The team also recently got a mascot. A large squirrel, dubbed Billy, now sits daily outside the window of Wong’s home office, a good symbol for the group’s aim to be fast and agile.

Pictured above: Colorful ribbons represent the Mpro protein believed to have an important role in the replication of the coronavirus. Red strands represent a biological molecule that binds to a ligand. (Image courtesy of UCR.)

The post Quantum of Solace: Research Seeks Atomic Keys to Lock Down COVID-19 appeared first on The Official NVIDIA Blog.

Robotics Reaps Rewards at ICRA: NVIDIA’s Dieter Fox Named RAS Pioneer

Thousands of researchers from around the globe will be gathering — virtually — next week for the IEEE International Conference on Robotics and Automation.

As a flagship conference on all things robotics, ICRA has become a renowned forum since its inception in 1984. This year, NVIDIA’s Dieter Fox will receive the RAS Pioneer Award, given by the IEEE Robotics and Automation Society.

Fox is the company’s senior director of robotics research and head of the NVIDIA Robotics Research Lab, in Seattle, as well as a professor at the University of Washington Paul G. Allen School of Computer Science & Engineering and head of the UW Robotics and State Estimation Lab. At the NVIDIA lab, Fox leads over 20 researchers and interns, fostering collaboration with the neighboring UW.

He’s receiving the RAS Pioneer Award “for pioneering contributions to probabilistic state estimation, RGB-D perception, machine learning in robotics, and bridging academic and industrial robotics research.”

“Being recognized with this award by my research colleagues and the IEEE society is an incredible honor,” Fox said. “I’m very grateful for the amazing collaborators and students I had the chance to work with during my career. I also appreciate that IEEE sees the importance of connecting academic and industrial research — I believe that bridging these areas allows us to make faster progress on the problems we really care about.”

Fox will also give a talk at the conference, where a total of 19 papers that investigate a variety of topics in robotics will be presented by researchers from NVIDIA Research.

Here’s a preview of some of the show-stopping NVIDIA research papers that were accepted at ICRA:

Robotics Work a Finalist for Best Paper Awards

6-DOF Grasping for Target-Driven Object Manipulation in Clutter” is a finalist for both the Best Paper Award in Robot Manipulation and the Best Student Paper.

The paper delves into the challenging robotics problem of grasping in cluttered environments, which is a necessity in most real-world scenes, said Adithya Murali, one of the lead researchers and a graduate student at the Robotics Institute at Carnegie Mellon University. Much current research considers only planar grasping, in which a robot grasps from the top down rather than moving in more dimensions.

Arsalan Mousavian, another lead researcher on the paper and a senior research scientist at the NVIDIA Robotics Research Lab, explained that they performed this research in simulation. “We weren’t bound by any physical robot, which is time-consuming and very expensive,” he said.

Mousavian and his colleagues trained their algorithms on NVIDIA V100 Tensor Core GPUs, and then tested on NVIDIA TITAN GPUs. For this particular paper, the training data consisted of simulating 750,000 robot object interactions in less than half a day, and the models were trained in a week. Once trained, the robot was able to robustly manipulate objects in the real world.

Replanning for Success

NVIDIA Research also considered how robots could plan to accomplish a wide variety of tasks in challenging environments, such as grasping an object that isn’t visible, in a paper called “Online Replanning in Belief Space for Partially Observable Task and Motion Problems.”

The approach makes a variety of tasks possible. Caelan Garrett, graduate student at MIT and a lead researcher on the paper, explained, “Our work is quite general in that we deal with tasks that involve not only picking and placing things in the environment, but also pouring things, cooking, trying to open doors and drawers.”

Garrett and his colleagues created an open-source algorithm, SS-Replan, that allows the robot to incorporate observations when making decisions, which it can adjust based on new observations it makes while trying to accomplish its goal.

They tested their work in NVIDIA Isaac Sim, a simulation environment used to develop, test and evaluate virtual robots, and on a real robot.

DexPilot: A Teleoperated Robotic Hand-Arm System

In another paper, NVIDIA researchers confronted the problem that current robotics algorithms don’t yet allow for a robot to complete precise tasks such as pulling a tea bag out of a drawer, removing a dollar bill from a wallet or unscrewing the lid off a jar autonomously.

In “DexPilot: Depth-Based Teleoperation of Dexterous Robotic Hand-Arm System,” NVIDIA researchers present a system in which a human can remotely operate a robotic system. DexPilot observes the human hand using cameras, and then uses neural networks to relay the motion to the robotic hand.

Whereas other systems require expensive equipment such as motion-capture systems, gloves and headsets, DexPilot archives teleoperation through a combination of deep learning and optimization.

It took 15 hours to train on a single GPU once we collected the data, according to NVIDIA researchers Ankur Handa and Karl Van Wyk, two of the authors of the paper. They and their colleagues used the NVIDIA TITAN GPU for their research.

Learn all about these papers and more at ICRA 2020.

The NVIDIA research team has more than 200 scientists around the globe, focused on areas such as AI, computer vision, self-driving cars, robotics and graphics. Learn more at www.nvidia.com/research.

The post Robotics Reaps Rewards at ICRA: NVIDIA’s Dieter Fox Named RAS Pioneer appeared first on The Official NVIDIA Blog.

40 Years on, PAC-MAN Recreated with AI by NVIDIA Researchers

Forty years to the day since PAC-MAN first hit arcades in Japan, and went on to munch a path to global stardom, the retro classic has been reborn, delivered courtesy of AI.

Trained on 50,000 episodes of the game, a powerful new AI model created by NVIDIA Research, called NVIDIA GameGAN, can generate a fully functional version of PAC-MAN — without an underlying game engine. That means that even without understanding a game’s fundamental rules, AI can recreate the game with convincing results.

GameGAN is the first neural network model that mimics a computer game engine by harnessing generative adversarial networks, or GANs. Made up of two competing neural networks, a generator and a discriminator, GAN-based models learn to create new content that’s convincing enough to pass for the original.

“This is the first research to emulate a game engine using GAN-based neural networks,” said Seung-Wook Kim, an NVIDIA researcher and lead author on the project. “We wanted to see whether the AI could learn the rules of an environment just by looking at the screenplay of an agent moving through the game. And it did.”

As an artificial agent plays the GAN-generated game, GameGAN responds to the agent’s actions, generating new frames of the game environment in real time. GameGAN can even generate game layouts it’s never seen before, if trained on screenplays from games with multiple levels or versions.

This capability could be used by game developers to automatically generate layouts for new game levels, as well as by AI researchers to more easily develop simulator systems for training autonomous machines.

“We were blown away when we saw the results, in disbelief that AI could recreate the iconic PAC-MAN experience without a game engine,” said Koichiro Tsutsumi from BANDAI NAMCO Research Inc., the research development company of the game’s publisher BANDAI NAMCO Entertainment Inc., which provided the PAC-MAN data to train GameGAN. “This research presents exciting possibilities to help game developers accelerate the creative process of developing new level layouts, characters and even games.”

We’ll be making our AI tribute to the game available later this year on AI Playground, where anyone can experience our research demos firsthand.

AI Goes Old School

PAC-MAN enthusiasts once had to take their coins to the nearest arcade to play the classic maze chase. Take a left at the pinball machine and continue straight past the air hockey, following the unmistakable soundtrack of PAC-MAN gobbling dots and avoiding ghosts Inky, Pinky, Blinky and Clyde.

In 1981 alone, Americans inserted billions of quarters to play 75,000 hours of coin-operated games like PAC-MAN. Over the decades since, the hit game has seen versions for PCs, gaming consoles and cell phones.

NVIDIA Researcher Seung-Wook Kim
Game Changer: NVIDIA Researcher Seung-Wook Kim and his collaborators trained GameGAN on 50,000 episodes of PAC-MAN.

The GameGAN edition relies on neural networks, instead of a traditional game engine, to generate PAC-MAN’s environment. The AI keeps track of the virtual world, remembering what’s already been generated to maintain visual consistency from frame to frame.

No matter the game, the GAN can learn its rules simply by ingesting screen recordings and agent keystrokes from past gameplay. Game developers could use such a tool to automatically design new level layouts for existing games, using screenplay from the original levels as training data.

With data from BANDAI NAMCO Research, Kim and his collaborators at the NVIDIA AI Research Lab in Toronto used NVIDIA DGX systems to train the neural networks on the PAC-MAN episodes (a few million frames, in total) paired with data on the keystrokes of an AI agent playing the game.

The trained GameGAN model then generates static elements of the environment, like a consistent maze shape, dots and Power Pellets — plus moving elements like the enemy ghosts and PAC-MAN itself.

It learns key rules of the game, both simple and complex. Just like in the original game, PAC-MAN can’t walk through the maze walls. He eats up dots as he moves around, and when he consumes a Power Pellet, the ghosts turn blue and flee. When PAC-MAN exits the maze from one side, he’s teleported to the opposite end. If he runs into a ghost, the screen flashes and the game ends.

Since the model can disentangle the background from the moving characters, it’s possible to recast the game to take place in an outdoor hedge maze, or swap out PAC-MAN for your favorite emoji. Developers could use this capability to experiment with new character ideas or game themes.

It’s Not Just About Games

Autonomous robots are typically trained in a simulator, where the AI can learn the rules of an environment before interacting with objects in the real world. Creating a simulator is a time-consuming process for developers, who must code rules about how objects interact with one another and how light works within the environment.

Simulators are used to develop autonomous machines of all kinds, such as warehouse robots learning how to grasp and move objects around, or delivery robots that must navigate sidewalks to transport food or medicine.

GameGAN introduces the possibility that the work of writing a simulator for tasks like these could one day be replaced by simply training a neural network.

Suppose you install a camera on a car. It can record what the road environment looks like or what the driver is doing, like turning the steering wheel or hitting the accelerator. This data could be used to train a deep learning model that can predict what would happen in the real world if a human driver — or an autonomous car — took an action like slamming the brakes.

“We could eventually have an AI that can learn to mimic the rules of driving, the laws of physics, just by watching videos and seeing agents take actions in an environment,” said Sanja Fidler, director of NVIDIA’s Toronto research lab. “GameGAN is the first step toward that.”

NVIDIA Research has more than 200 scientists around the globe, focused on areas such as AI, computer vision, self-driving cars, robotics and graphics.

GameGAN is authored by Fidler, Kim, NVIDIA researcher Jonah Philion, University of Toronto student Yuhao Zhou and MIT professor Antonio Torralba. The paper will be presented at the prestigious Conference on Computer Vision and Pattern Recognition in June.

PAC-MANTM & ©BANDAI NAMCO Entertainment Inc.

The post 40 Years on, PAC-MAN Recreated with AI by NVIDIA Researchers appeared first on The Official NVIDIA Blog.

Gut Instinct: Human Microbiome May Reveal COVID-19 Mysteries

Days before a national lockdown in the U.S., Daniel McDonald realized his life’s work had put a unique tool in his hands to fight COVID-19.

The assay kits his team was about to have made by the tens of thousands could be repurposed to help understand the novel coronavirus that causes the disease.

McDonald is scientific director of the American Gut Project and the Microsetta Initiative, part of an emerging field that studies microbiomes, the collections of single-cell creatures that make up much if not most of life in and around us. The assay kits were the first to be able to safely take and ship samples from human feces preserved at room temperature.

The kits originally targeted broad research in microbiology. But McDonald and his colleagues knew they needed to pivot into the pandemic.

With careful screening, samples might reveal patterns of how the mutating coronavirus was spreading. That information would be gold for public health experts trying to slow the growth of new infections.

The team also hopes to gather just enough data from participants to let researchers explore another mystery: Why does the virus make some people very sick while others show no symptoms at all?

“Everybody here is absolutely excited about doing something that could help save lives,” said McDonald, part of the 50-person team in Rob Knight’s lab at the University of California, San Diego.

“We are lucky to work close and collaborate with experts in RNA and other areas applicable for studying this virus,” he added.

Hitting the Accelerator at the Right Time

As the kits were taking shape, the group had another stroke of good fortune.

Igor Sfiligoi, lead scientific software developer at the San Diego Supercomputer Center, ported to NVIDIA GPUs the latest version of the team’s performance-hungry UniFrac software, which is used to analyze microbiomes. The results were stunning.

A genetic analysis of 113,000 samples that would have required 1,300 CPU core-hours on a cluster of servers (or about 900 hours on a single CPU) finished in less than two hours on a single NVIDIA V100 Tensor Core GPU – a 500x speedup. A cluster of eight V100 GPUs would cut that to less than 15 minutes.

The port also enabled individual researchers to run the analysis in nine hours on a workstation equipped with an NVIDIA GeForce RTX 2080 Ti. And a smaller dataset that takes 13 hours on a server CPU now runs in just over one hour on a laptop with an NVIDIA GTX 1050 GPU.

“That’s game changing for people who don’t have access to high-performance computers,” said McDonald. For example, individual researchers may be able to use UniFrac as a kind of search tool for ad hoc queries, he said.

With the lab’s cluster of six V100 GPUs, it also can begin to tackle analysis of its expanding datasets.

Sfiligoi’s work on 113,000 samples “arguably represents the largest assessment of microbial life to date,” McDonald said. But the lab already has a repository of about 300,000 public samples and “it won’t be much longer before we’re well in excess of a million samples,” he added.

GPUs Speed Up UniFrac Three Ways

Three techniques were key to the speedups. OpenACC accelerated the many tight loops in the Striped UniFrac code, then Sfiligoi applied memory optimizations. Downshifting from 64-bit to 32-bit floating-point math delivered additional speedups without affecting the accuracy the experiments needed.

Sfiligoi of the San Diego Supercomputing Center ported UniFrac to GPUs.

Sfiligoi completed the initial OpenACC port in a matter of days. Other optimizations came in incremental steps over a few weeks as the team got a better understanding of UniFrac’s compute and memory-access needs.

The work came on the heels of landmark effort Sfiligoi described in a session at GTC Digital. He was part of a team that harnessed exascale performance from GPUs on public cloud services for research in astronomy.

NVIDIA is collaborating with Sfiligoi on his next task. He aims to integrate his GPU optimizations on UniFrac into the software microbiologists use daily.

Data Flood Would Swamp CPU-only Systems

Meanwhile, McDonald and his team need to adapt UniFrac to work with viral data. They also face heady challenges turning vast amounts of data they will generate into well organized and error-free datasets they can process.

On the tech front, the group needs lots of storage and compute performance. To analyze what could one day amount a million microbiomes could require 20 petabytes of storage and more than 100 million CPU cycles/year.

“I would love to see a lot of that pushed onto GPUs,” McDonald said.

The work has broad potential given how long the extended family of coronaviruses has been affecting both humans and farm animals.

“Everybody on the planet has felt these impacts on productivity in some way. Now we can start to understand how to better manage this family of viruses that have been with us a long time,” he added.

The efforts in San Diego are part of a broad network of research projects leveraging NVIDIA GPUs and high performance computing to fight COVID-19.

More than 30 supercomputing centers worldwide spanning centers in Asia, Australia, Europe and the United States are engaged in the effort. The COVID-19 High Performance Computing Consortium alone has more than 30 active projects with access to 420 petaflops of power that includes 41,000 GPUs.

Image at top: Rob Knight (left) and Daniel McDonald in the UCSD Knight Lab. Photo courtesy Erik Jepsen/UC San Diego Publications

The post Gut Instinct: Human Microbiome May Reveal COVID-19 Mysteries appeared first on The Official NVIDIA Blog.

NVIDIA Chief Scientist Releases Low-Cost, Open-Source Ventilator Design

NVIDIA Chief Scientist Bill Dally this week released an open-source design for a low-cost, easy-to-assemble mechanical ventilator.

The ventilator, designed in just a few weeks by Dally — whose storied technology career includes key contributions to semiconductors and supercomputers — can be built quickly from just $400 of off-the-shelf parts, Dally says.

Traditional ventilators, by contrast, can cost more than $20,000 — and that’s when the world hasn’t been slammed with demand for the life-saving machines.

“I hope that we don’t get so many people sick that we run out of ventilators,” Dally says, speaking from a spartan home electronics workshop stocked with oscilloscopes, voltmeters and other lab equipment.

“But I want to make sure if we do, something like this is ready,” he adds.

Ventilators and Coronavirus

Ventilators, of course, are urgently needed around the world to address the medical crisis that has gripped the globe.

Check out NVIDIA Chief Scientist Bill Dally’s open-source design for a low-cost, easy-to-assemble ventilator

Of patients that are infected with COVID-19, between 0.3 percent and 0.6 percent develop acute respiratory distress syndrome severe enough to need a mechanical ventilator, Dally explains.

Dally’s aim was to build the “simplest possible” ventilator.

His ventilator is built around just two easily sourced, key components – a proportional solenoid valve and a microcontroller to regulate the flow of gas through the valve to the patient.

Dally holds more than 120 patents. He’s had teaching and research stints at Caltech, MIT and Stanford, where he chaired the computer science department.

He’s led NVIDIA’s research team since 2009. It includes more than 200 scientists from around the globe focused on areas such as AI, computer vision, self-driving cars, robotics and graphics.

Dally began exploring how to make a contribution after NVIDIA CEO Jensen Huang called on company leaders to look for ways to help with the COVID-19 pandemic.

Dally quickly connected on phone calls and in video conferences with leaders across the technology and medical fields.

NVIDIA CEO: “It Works!”

Then, when kayaking on the cool, crystal-clear waters of Lake Tahoe in early April, where he was sheltering in place, inspiration struck.

NVIDIA Chief Scientist Bill Dally built the first prototypes of his design in his home workshop.

Dally went online and ordered a solenoid valve, which uses an electromagnet to squeeze a valve open and shut.

Then he pulled the microcontroller, a cheap, stripped-down computer, out of the home-brewed cooling system he’d built for his wine cellar.

After pulling a couple of late nighters in his home electronics workshop — and cranking out several thousand lines of code — Dally had a working prototype built from common pipe fittings and a few easily obtained valves.

On April 4 Dally shared a video, shot in his garage by his wife, of the device slowly inflating and deflating a rubber glove, with his NVIDIA colleagues.

Jensen’s reaction: “It works!”

Gathering Expert Advice

To continue moving the project forward, Dally dipped into the expertise of contacts across a wide range of disciplines.

He turned to Paul Karplus, a former student, noted for his work in autonomous vehicles and robotics, for the mechanical engineering of key parts.

He also relied on Emma Tran, a fourth-year medical student, to make a number of other connections in the medical field.

Dally quickly gathered input from Dr. Andrew Moore, a chief resident at the Stanford University School of Medicine, Dr. Bryant Lin, a prominent medical devices expert and founder of two companies, and anesthesiologist Dr. Ruth Fanning.

Dally turned to Dr. David Gaba a top expert in immersive and simulation-based learning, to test the device’s capabilities.

On Friday, April 17, Dr. Gaba tested a prototype on a sophisticated lung simulator, modeling normal and two levels of COVID-19 lung disease with a wide variety of ventilator settings.

It worked as expected, Dally reports.

Read NVIDIA Chief Scientist Bill Dally’s paper detailing his open-source design for a low-cost, easy-to-assemble ventilator. 

From Parts to Functional Ventilator in 5 Minutes

Yet the latest prototype of Dally’s device, which he assembled in his home workshop, remains simple and reliable.

Dally reports he can bolt the device’s pneumatic components together in 5 minutes. The entire ventilator can be attached to a simple display and slid into a compact Pelican carrying case.

It provides better care than “bag squeezer” emergency ventilators because it precisely regulates flow, pressure, and volume, Dally says. It also uses fewer parts and less power, and it’s lower cost.

It includes sensors that accurately meter airflow, compensate for valve inaccuracy, control maximum pressure, enable patient-initiated breathing, and monitor for alarm conditions, among other features.

Dally’s now in the process of navigating the paperwork needed for emergency use authorization from the U.S. Food and Drug Administration.

After that, the next step will be to find a way to start building these.

To learn more about innovative projects like this, visit Research at NVIDIA.

The post NVIDIA Chief Scientist Releases Low-Cost, Open-Source Ventilator Design appeared first on The Official NVIDIA Blog.

Calling AI: Researchers Dial in Machine Learning for 5G

5G researchers from three top institutions have joined NVIDIA in bringing AI to telecom.

The Heinrich Hertz Institute (HHI), the Technical University in Berlin (TU Berlin) and Virginia Tech are collaborating with NVIDIA to harness the power of GPUs for next-generation cellular networks.

The journey began in October at MWC Los Angeles, where NVIDIA and partners announced plans to enable virtual radio access networks (vRANs) for 5G with GPUs.

NVIDIA also debuted Aerial, a software development kit for accelerating vRANs. And partners Ericsson, Microsoft and Red Hat are working with us to deliver 5G at the edge of the network powered by GPUs.

These vRANs will bring cellular network operators the kind of operational efficiencies that cloud service providers already enjoy. Carriers will program network functions in high-level software languages, easing the work of adding new capabilities and deploying capacity where and when it’s needed.

Forging Wireless Ties

Our new research partnerships with HHI, TU Berlin and Virginia Tech will explore multiple ways to accelerate 5G with AI.

They’ll define novel techniques leveraging GPUs that help wireless networks use precious spectrum more efficiently. The work will span research in reinforcement learning and other techniques that build on the product plans announced in October.

HHI is part of Germany’s Fraunhofer Society, a research group founded in 1928 that has a history of pioneering technologies in mobile and optical networking as well as video compression. The collaboration with TU Berlin includes a new 5G test bed with participation from a number of wireless companies in Germany.

“I want to redesign many algorithms in radio access networks (RAN) so we can perform tasks in parallel, and the GPU is a good architecture for this because it exploits massive parallelism,” said Slawomir Stanczak, a professor at TU Berlin and head of HHI’s wireless networking department.

Stanczak’s teams will explore use cases such as adapting AI to deliver improved 5G receivers. “If we are successful, they could offer a breakthrough in dramatically increasing performance and improving spectral efficiency, which is important because spectrum is very expensive,” he said.

In a session for GTC Digital, Stanczak recently described ways to apply AI to the private 5G campus networks which he believes will be market drivers for vRANs. Stanczak chairs a focus group on the use of AI in 5G for the ITU, a leading communications standards group. He’s also author of a widely cited text on the math behind optimizing wireless networks.

Hitting 5G’s Tight Timing Targets

Work at Virginia Tech is led by Tom Hou, a professor of computer engineering whose team specializes in solving some of the most complex and challenging problems in telecom.

His Ph.D. student, Yan Huang, described in a 2018 paper how he used an NVIDIA Quadro P6000 GPU to solve a complex scheduling problem in a tight 100-microsecond window set by the 5G standard. His latest effort cut the time to 60 microseconds using an NVIDIA Tensor Core V100 GPU.

The work “got an enormous response because at that time people using traditional computational techniques would hit roadblocks — no one in the world could solve such a complex problem in 100 microseconds,” said Hou.

“Using GPUs transformed our research group, now we are looking at AI techniques on top of our newly acquired parallel techniques,” he added.

Specifically, Virginia Tech researchers will explore how AI can automatically find and solve in real time thorny problems optimizing 5G networks. For instance, AI could uncover new ways to weave multiple services on a single frequency band, making much better use of spectrum.

“We have found that for some very hard telecom problems, there’s no math formulation, but AI can learn the problem models automatically, enhancing our GPU-based parallel solutions” said Huang.

Groundswell Starts in AI for 5G

Other researchers, including two who presented papers at GTC Digital, are starting to explore the potential for AI in 5G.

Addressing one of 5G’s top challenges, researchers at Arizona State University showed a new method for directing millimeter wave beams, leveraging AI and the ray-tracing features in NVIDIA Turing GPUs.

And Professor Terng-Yin Hsu described a campus network at Taiwan’s National Chiao Tung University that ran a software-defined cellular base station on NVIDIA GPUs.

“We are very much at the beginning, especially in AI for vRAN,” said Stanczak. “In the end, I think we will use hybrid solutions that are driven both by data and domain knowledge.”

Compared to 4G LTE, 5G targets a much broader set of use cases with a much more complex air interface. “AI methods such as machine learning are promising solutions to tackle these challenges,” said Hou of Virginia Tech.

NVIDIA GPUs bring the programming flexibility of CUDA and cuDNN environments and the scalability of multiple GPUs connected on NVLink. That makes them the platform of choice for AI on 5G, he said.

Today we stand at a pivot point in the history of telecom. The traditional principles of wireless signal processing are based on decades-old algorithms. AI and deep learning promise a revolutionary new approach, and NVIDIA’s GPUs are at the heart of it.

The post Calling AI: Researchers Dial in Machine Learning for 5G appeared first on The Official NVIDIA Blog.

Speeding Recovery: GPUs Put Genomics on Faster Pathways

Days after giving an online talk on how GPUs reduce the time to understand diseases, Margaret Linan felt sick, and awoke at 3am gasping for air.

“It was quite frightening,” said Linan, a computational research scientist at Mount Sinai’s Icahn School of Medicine, in New York. With help from first responders, she got her breath back in about 20 minutes.

Her symptoms diminished over a few days, but for a time, it was unsettlingly strange.

“I’m pretty sure it was a minor version of the coronavirus,” said Linan, who had been sheltering at home.

It was a poignant reminder of the value of her work. Linan develops and tests software that accelerates the discovery of mutations in human genomes, used to identify treatments for diseases such as cancer.

At GTC Digital, she presented her latest results, showing dramatic speedups in genomics using a mix of GPUs and CPUs. Her analysis showed how NVIDIA’s RAPIDS software for accelerating data science on GPUs eased the transition from today’s mainly CPU-based programs.

6x Speedups and More in Genomics

Processing and analyzing genome samples can take months on a CPU. Doctors with cancer patients sometimes depend on such studies for life-saving treatments.

In Linan’s experiments, GPUs accelerated one genomic analysis by more than 6x. Another job delivered even greater savings due to the high number of number of runs it required.

A system running a CPU with 10-40 cores and an NVIDIA GPU (green) beat a CPU-only system (purple) in five test runs of the accuracy of a GATK Haplotype Caller.

A server with a single GPU in her lab handled initial tests. More mature experiments ran on Mount Sinai’s Minerva system that packs 48 NVIDIA V100 Tensor Core GPUs, up to four available for a single job. Advanced tests that used eight V100 GPUs were sent to the AWS cloud.

Comparisons of six GPU software frameworks favored RAPIDS. Bioinformatics specialists familiar with Python programs it supports find it easiest to use.

“You feed in an object, and it does what you expect it will,” she said.

Open Source GPU Code on the Way

Mount Sinai’s researchers increasingly tap into GPUs on the Minerva system or in the cloud to handle their toughest jobs, Linan reported.

That’s one reason why she aims to create a suite of open source programs to accelerate genomics in GPUs. She’s almost done creating a GPU-accelerated version of the Genome Analysis Toolkit, one of about five key tools in the field, and has made progress on two others.

“By the end of the year, I hope to have beta versions available for our investigators to test,” Linan said.

Use cases for AI are growing among researchers at the New York hospital.

Late next year, Mount Sinai plans to open a $100 million research center for AI in healthcare. It will extend the mission of its existing Institute for Genomic Health that leverages AI.

Deep Patient, another project at the medical school, uses neural networks to predict which patients are at most risk of developing diabetes or certain cancers. In addition, Mount Sinai has spawned two startups in healthcare AI. RenalytixAI designs clinical diagnostics for kidney disease; Sema4 uses AI to develop personalized cancer care programs.

“GPUs will be leveraged on many large-scale research projects for many years to come,” she said.

The post Speeding Recovery: GPUs Put Genomics on Faster Pathways appeared first on The Official NVIDIA Blog.

Mixing It Up: Saudi Researchers Accelerate Environmental Models with Mixed Precision

Scientists studying environmental variables — like sea surface temperature or wind speed — must strike a balance between the number of data points in their statistical models and the time it takes to run them.

A team of researchers at Saudi Arabia’s King Abdullah University of Science and Technology, known as KAUST, is using NVIDIA GPUs to strike a win-win deal for statisticians: large-scale, high-resolution regional models that run twice as fast. They presented their work, which helps scientists develop more detailed predictions, in a session at GTC Digital.

The software package they developed, ExaGeoStat, can handle data from millions of locations. It’s also accessible in the programming language R through the package ExaGeoStatR, making it easy for scientists using R to take advantage of GPU acceleration.

“Statisticians rely heavily on R, but previous software packages could only process limited data sizes, making it impractical to analyze large environmental datasets,” said Sameh Abdulah, a research scientist at the university. “Our goal is to enable scientists to run GPU-accelerated experiments from R, without needing a deep understanding of the underlying CUDA framework.”

Abdulah and his colleagues use a variety of NVIDIA data center GPUs, most recently adopting NVIDIA V100 Tensor Core GPUs to further speed up weather simulations using mixed-precision computing.

Predicting Weather, Come Rain or Shine 

Climate and weather models are complex and incredibly time-consuming simulations, taking up significant computational resources on supercomputers worldwide. ExaGeoStat helps statisticians find insights from these large datasets faster.

The application predicts measurements like temperature, soil moisture levels or wind speed for different locations within a region. For example, if the dataset shows that the temperature in Riyadh is 21 degrees Celsius, the application would provide a likely estimation of the temperature at that same point in time further east in, say, Abu Dhabi.

Abdulah and his colleagues are working to extend these predictions to not just different locations in a region, but also to different points in time — for instance, predicting the wind speed in Philadelphia next week based on data from New York City today.

The software reduces the system memory required to run predictions from large-scale simulations, enabling scientists to work with much larger meteorological datasets than previously possible. Larger datasets allow researchers to make estimations about more locations, increasing the geographic scope of their simulations.

The team runs models with data for a couple million locations, primarily focusing on datasets in the Middle East. They’ve also applied ExaGeoStat to soil moisture data from the Mississippi River Basin, and plan to model more environmental data for regions in the U.S.

Compared to using a CPU, the researchers saw a nearly 10x speedup — from 400 seconds to 45 —  running one iteration of the model on a single NVIDIA GPU. It takes about 175 iterations to converge a full simulation.

“Now, with V100 GPUs in our computing center, we’ll be able to accelerate our application even further,” Abdulah said. “While so far we’ve been using double precision and single precision, with Tensor Cores we can also start using half precision.”

Besides higher performance and faster completion times, mixed-precision algorithms also save energy, Abdulah says, by decreasing the amount of time and power consumption required to run the models.

Using a combination of single and double precision, the researchers achieve, on average, a 1.9x speedup of their algorithm on a system with an NVIDIA V100 GPU. He and his colleagues next plan to evaluate how much half-precision computing using NVIDIA Tensor Cores will further accelerate their application. To do so, they’ll use V100 GPUs at their university as well as on Oak Ridge National Laboratory’s Summit system, the world’s fastest supercomputer.

To learn more about Abdulah’s work, watch the full on-demand talk. His collaborators are Hatem Ltaief, David Keyes, Marc Genton and Ying Sun from the Extreme Computing Research Center and the statistics program at King Abdullah University of Science and Technology.

Main image shows wind speed data over the Middle East and the Arabian Sea. 

The post Mixing It Up: Saudi Researchers Accelerate Environmental Models with Mixed Precision appeared first on The Official NVIDIA Blog.

Supercomputers Get the Hard Cell: Researchers Use GPUs to Discover Molecular Design Principles of Photosynthesis

Energy efficiency isn’t just a concern for vehicle design or the power grid — it’s a calculation occurring at a microscopic level in every living cell.

Whether it feeds on light or glucose, every cell works around the clock to generate enough energy to survive in its environment. The more efficient this energy transfer is, the more productive that cell can be.

Researchers at the University of Illinois at Urbana-Champaign and Arizona State University are simulating photosynthetic organisms to understand how they capture energy — and how they could be made even more productive.

Applied to agriculture, this kind of optimization would mean a bigger crop yield. In healthcare, it could mean improving the delivery of antibodies and peptides in precision medicine, or even extending the lifespan of cells. And in the energy industry, it could improve the efficiency of biofuels.

“Any given plant wants to be able to live anywhere, so it will optimize its underlying machinery to survive in a range of environmental conditions,” said Abhishek Singharoy, assistant professor in the School of Molecular Sciences at ASU. “As scientists and engineers, we can make a more productive variant of that plant to get more energy out of it for us.”

Singharoy and his collaborators run their molecular dynamics simulations on NVIDIA GPU-accelerated supercomputers, including the world’s fastest system, Oak Ridge National Laboratory’s Summit. They presented their work in one of more than 150 online talks at GTC Digital.

Throwing Light on Photosynthesis’ Efficiency

Green plants photosynthesize, converting sunlight into food. But in many organisms, less than 10 percent of the solar energy absorbed is turned into usable nutrients. To understand why, the researchers used a GPU-accelerated simulation of a purple bacteria’s photosynthetic apparatus.

The atomic-scale simulation can model 136 million atoms and their movements for 500 nanoseconds, or half a microsecond, on the Summit supercomputer.

By moving to the Summit supercomputer from its predecessor, Oak Ridge National Laboratory’s Titan system, the team saw a 6x speedup in run time. They used, on average, 922 nodes on the system to run their simulation. Each node contains six NVIDIA V100 Tensor Core GPUs.

“It’s useful to build the entire thing at atomic resolution to make sure you have a realistic model,” said Jim Phillips, senior research programmer at the University of Illinois. “To run a dynamic model of that size fast enough, you need GPU parallelization.”

However, to capture the process of light turning to energy during photosynthesis, the researchers needed to run a longer simulation of a few dozen milliseconds. So rather than simulating each atom individually, they introduced approximations to simplify the cell into rigid domains — getting them to the 30-millisecond mark.

From there, the team extended their predictions to determine how long the cell would take to reproduce under different light conditions. They found that the bacteria thrives best in low-light conditions — an adaptation to its muddy water habitat.

“We knew that the bacteria is found in muddy water, but were able to figure out why it survives in that environment,” Singharoy said. “Its underlying structure is built such that it cannot produce more energy in conditions with more sunlight. So it would rather stay in a zone with less light.”

Purple bacteria is just the start. It’s a relatively simple organism where data was available for all protein structures that needed to be simulated. As datasets are released for more complex photosynthetic organisms, such as spinach plants, the researchers aim to simulate those, informing efforts to develop more productive variants of the plant.

The researchers also hope to use the current simulation to train a neural network that can make predictions about cell behavior based on machine learning, instead of molecular dynamics.

To learn more about this research, watch the GTC Digital talk by Singharoy and Phillips.

The post Supercomputers Get the Hard Cell: Researchers Use GPUs to Discover Molecular Design Principles of Photosynthesis appeared first on The Official NVIDIA Blog.

Virus War Goes Viral: Folding@Home Gets 1.5 Exaflops to Fight COVID-19

The tweet party started on Wednesday, March 25, at 1:55pm.

That’s when the research network that Folding@Home manages had arguably become the world’s most powerful supercomputer. Its call to help fight the coronavirus on March 15 had amassed enough donations of spare cycles on home computers to create a crowd-sourced exascale supercomputer.

In just 10 days, supporters had downloaded the group’s software on hundreds of thousands of home PCs to help crack the code on COVID-19.

“It’s been a pretty amazing experience,” said Greg Bowman, director of Folding@Home, an all-volunteer team of researchers. Bowman’s also an associate professor at the Washington University School of Medicine, in St. Louis, home to one of 11 labs worldwide that keep the Folding@Home network humming.

“It’s exciting to have the chance to try everything we can think of in parallel to maximize the chances of having an impact on the current pandemic,” he said.

Folding@Home celebrated breaking the exaflop barrier on Twitter.

Supporters sheltering at home posted a virtual party of animations in response to the tweet that announced the news. Schoolkids in video clips danced on their desks, Top Gun heroes slapped high-fives, the Cookie Monster gobbled goodies, and a small army of Star Trek, Star Wars and anime characters whooped it up. Even an animated Simon Cowell offered a thumbs up.

At Folding@Home, the leaderboard continues to rise. More than a million computers are now on the network that started the year with just 30,000.

Bowman estimates performance has surpassed 1.5 exaflops, fueled in part by more than 356,000 NVIDIA GPUs. The group’s blog site will share more news soon, he said.

Sneak Peak of a COVID-19 Spike

Even before it broke the exaflop barrier, researchers were posting eye-popping work. An animation of a coronavirus protein that infects healthy cells could suggest molecular targets for an anti-COVID drug or vaccine (see the image above).

The effort builds on the group’s earlier experiments on the Ebola virus. It’s part of its broad work exploring how proteins – a basic ingredient of living things including viruses – fold into 3D shapes to perform various functions.

The first snapshot of a coronavirus protein couldn’t be captured with a simple smartphone selfie. Such scientific visualizations demand massive compute power to simulate near-atomic-level interactions.

Flipping on an Exaflop

These days, computer scientists stack computer rooms the size of a couple tennis courts with servers to gnaw on big questions of science. The Summit system at Oak Ridge National Laboratory, currently the world’s largest supercomputer, packs 27,648 NVIDIA Tensor Core GPUs to deliver 148.6 petaflops on the HPL benchmark. The second-ranked Sierra system at Lawrence Livermore National Laboratory also uses NVIDIA GPUs to crank out 94.6 petaflops.

The U.S. Department of Energy, which runs both systems, aims to switch on its first exascale system sometime in 2021. Arguably, the exascale era has already begun. Summit has racked up a handful milestones, including a 3.3 exaflops score running mixed-precision AI tasks.

That said, Folding@Home gets kudos as the first crowd-sourced effort to assemble exascale horsepower.

It’s a heady achievement. Imagine a billion people, each holding a billion calculators. If they all hit the equal sign at the same time, they’d execute in one second a quintillion calculations. That’s one exaflop.

Many Ways You Can Help

Trying to ride the tsunami of donations, Bowman told supporters over Twitter that researchers briefly scrambled for more servers to keep all the connected PCs fed.

“I hope I can speak for most people when I say this has given me something that I can contribute and has had a positive effect on my mental state,” replied one backer.

“Folding has on and off heated the top floor of my house,” quipped a computer specialist in the U.K.

The group continues to encourage users to donate time on their PCs with software they can download here. In turn, Folding@Home makes data from its experiments publicly available on open general research sites and ones devoted to areas such as biology.

To accelerate its efforts, Folding@Home recently announced a new batch of small molecule screening simulations that will help prioritize which molecules will be synthesized and assayed by the COVID Moonshot.

Folding@Home is one of many technology efforts formed to fight coronavirus.

The U.S. Department of Energy created the COVID-19 High Performance Computing Consortium with support from many tech companies and universities. The group will pool 16 supercomputers to deliver a combined 330 petaflops in part with help from more than 36,000 NVIDIA GPUs.

Separately, developers are already coding up projects in the #BuildforCOVID19 hackathon. Highlighted projects will be announced April 10.

For its part, NVIDIA is offering researchers a free 90-day license to its Parabricks software to accelerate the analysis of the coronavirus’ genetic code.

The post Virus War Goes Viral: Folding@Home Gets 1.5 Exaflops to Fight COVID-19 appeared first on The Official NVIDIA Blog.