When scaling your workload is a matter of saving lives

By Werner Vogels, CTO, Amazon.com

April 20, 2020

On March 16, 2020, at 9:26 PM, I received an urgent email from my friend DJ Patil, former White House Chief Data Scientist, Head of Technology for Devoted Health, a Senior Fellow at the Belfer Center at the Harvard Kennedy School, and Advisor to Venrock Partners. You don’t get that many titles after your name unless you’re pretty good at something. For DJ, that “something” is math and computer science.

DJ was writing to me from the California crisis command center. He explained that he was working with governors from across the country to model the potential impact of COVID-19 for scenario planning. He wanted to help them answer critical questions, like “How many hospital beds will we need?” and “Can we reduce the spread if we temporarily close places where people gather?” and “Should we issue a shelter-in-place order and for how long?” While nobody can predict the future, modeling the virus with all the factors they did know was their best shot at helping leaders make informed decisions, which would impact hundreds of thousands of lives.

DJ assembled a team of volunteers that consisted of some of the brightest minds from across Silicon Valley and the country. As though following a call to arms, these professionals came together, in a personal capacity, to fight COVID-19 the best way they knew how: with data.

The good news is that they had a model. And not just any model. DJ and his team have been working with one that had been primarily developed by the world renowned Johns Hopkins Bloomberg School of Public Health (JHSPH). This model, which is an open-source project, uses state or county population numbers along with transportation data to model the number of people who potentially would be exposed, infected, and/or hospitalized. The model also considers virus spread based on a variety of non-pharmaceutical interventions, including shutting down schools and parks and issuing quarantine orders.

However, the model was running on the JHSPH on-premises infrastructure and the model pipeline couldn’t scale to run a large number of scenarios simultaneously or to meet the needs of the country (and potentially the world). It was too slow. To get the required scale and speed, DJ and his team needed to run the model in the cloud—so they moved their on-premises code to AWS. This led to another challenge: The code hadn’t been written initially with the cloud in mind, so it couldn’t fully take advantage of the scale and optimizations possible with AWS. As a result, DJ’s team spent one week porting and running a single scenario for California, which still wasn’t fast enough.

Imagine how long it would take to scale the pipeline for 49 more states. It would require at least months of work. Adding multiple scenarios with different variables would delay it even more. DJ’s team didn’t have that kind of time. In the words of Dr. Anthony Fauci, the director of the National Institute of Allergy and Infectious Diseases, “You don’t make the timeline. The virus makes the timeline.”

DJ’s team needed to be able to onboard the model pipeline and run a full report in hours rather than weeks or months. That’s why DJ reached out to me. He wanted our help optimizing the model pipeline for the cloud. Presented with an opportunity to help my friend and support a project that could save lives, I immediately said “yes.”

When I sounded the alarm internally, something amazing happened. People from across the company volunteered to help because they knew that they had the expertise that the project needed. Nobody asked, “Who is responsible for this customer?” or “Who has the bandwidth to work on this project?” Everyone sprang into action immediately.

We wanted to get that model pipeline running like it had a jet engine. The first thing we had to do was create an architecture that would fuel the model every step of the way. We began by profiling the code and re-compiling key numerical libraries.

Next, we had to help optimize the model pipeline. That’s when our specialist team, including the high performance computing (HPC) group, stepped in. These professionals help organizations solve some of the biggest data-related problems and tame the largest workloads, like in genomics, computational chemistry, machine learning, and autonomous vehicle simulation. They worked with members of DJ’s team, JHSPH, and some state employees non-stop through two weekends to optimize the model pipeline through re-architecture and deployment on AWS.

We contributed to the open-source JHSPH model to enable a Continuous Integration & Deployment (CI/CD) pipeline for container deployments on Amazon Elastic Container Registry. Also, we orchestrated scalable deployment strategies on AWS Elastic Container Service through AWS Batch and integrated several other services, including Amazon S3 and Amazon EC2 Auto Scaling. A high level of coordination with AWS was critical to bringing all these technologies together.

Figure 1: Architecture for the Scalable COVID Scenario Pipeline using AWS Batch

What was the end result?

DJ’s team has reduced the time to on-board the model pipeline and generate a full report from one week for one scenario to under 12 hours for multiple scenarios. Now, the new model created by JHSPH is being rolled out on AWS to all 50 states and internationally to help with making decisions that directly impact the global spread of COVID-19.

But this isn’t where the story ends—it’s where it begins. While the spread of the virus is now global, we have yet to grasp its full impact on human society. As we learn more about the spreading conditions of the virus, iterating over existing models will be crucial. There will be many more sleepless nights for everyone working on this initiative as they continue to scale the model to more states and countries as well as analyze the effect of mitigation strategies.

If you have relevant skills in technology, communications, and/or operations, please consider joining the U.S. Digital Response team. It’s a volunteer-run, non-partisan effort to help federal, state, and local government with technology, data, design, operations, communications, project management, and other needs during the COVID-19 crisis. https://www.usdigitalresponse.org/

 

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Intel’s Silicon Brain System a Blueprint for Future AI Computing Architectures

April 24, 2024

Intel is releasing a whole arsenal of AI chips and systems hoping something will stick in the market. Its latest entry is a neuromorphic system called Hala Point. The system includes Intel's research chip called Loihi 2, Read more…

Anders Dam Jensen on HPC Sovereignty, Sustainability, and JU Progress

April 23, 2024

The recent 2024 EuroHPC Summit meeting took place in Antwerp, with attendance substantially up since 2023 to 750 participants. HPCwire asked Intersect360 Research senior analyst Steve Conway, who closely tracks HPC, AI, Read more…

AI Saves the Planet this Earth Day

April 22, 2024

Earth Day was originally conceived as a day of reflection. Our planet’s life-sustaining properties are unlike any other celestial body that we’ve observed, and this day of contemplation is meant to provide all of us Read more…

Intel Announces Hala Point – World’s Largest Neuromorphic System for Sustainable AI

April 22, 2024

As we find ourselves on the brink of a technological revolution, the need for efficient and sustainable computing solutions has never been more critical.  A computer system that can mimic the way humans process and s Read more…

Empowering High-Performance Computing for Artificial Intelligence

April 19, 2024

Artificial intelligence (AI) presents some of the most challenging demands in information technology, especially concerning computing power and data movement. As a result of these challenges, high-performance computing Read more…

Kathy Yelick on Post-Exascale Challenges

April 18, 2024

With the exascale era underway, the HPC community is already turning its attention to zettascale computing, the next of the 1,000-fold performance leaps that have occurred about once a decade. With this in mind, the ISC Read more…

Intel’s Silicon Brain System a Blueprint for Future AI Computing Architectures

April 24, 2024

Intel is releasing a whole arsenal of AI chips and systems hoping something will stick in the market. Its latest entry is a neuromorphic system called Hala Poin Read more…

Anders Dam Jensen on HPC Sovereignty, Sustainability, and JU Progress

April 23, 2024

The recent 2024 EuroHPC Summit meeting took place in Antwerp, with attendance substantially up since 2023 to 750 participants. HPCwire asked Intersect360 Resear Read more…

AI Saves the Planet this Earth Day

April 22, 2024

Earth Day was originally conceived as a day of reflection. Our planet’s life-sustaining properties are unlike any other celestial body that we’ve observed, Read more…

Kathy Yelick on Post-Exascale Challenges

April 18, 2024

With the exascale era underway, the HPC community is already turning its attention to zettascale computing, the next of the 1,000-fold performance leaps that ha Read more…

Software Specialist Horizon Quantum to Build First-of-a-Kind Hardware Testbed

April 18, 2024

Horizon Quantum Computing, a Singapore-based quantum software start-up, announced today it would build its own testbed of quantum computers, starting with use o Read more…

MLCommons Launches New AI Safety Benchmark Initiative

April 16, 2024

MLCommons, organizer of the popular MLPerf benchmarking exercises (training and inference), is starting a new effort to benchmark AI Safety, one of the most pre Read more…

Exciting Updates From Stanford HAI’s Seventh Annual AI Index Report

April 15, 2024

As the AI revolution marches on, it is vital to continually reassess how this technology is reshaping our world. To that end, researchers at Stanford’s Instit Read more…

Intel’s Vision Advantage: Chips Are Available Off-the-Shelf

April 11, 2024

The chip market is facing a crisis: chip development is now concentrated in the hands of the few. A confluence of events this week reminded us how few chips Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Leading Solution Providers

Contributors

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Eyes on the Quantum Prize – D-Wave Says its Time is Now

January 30, 2024

Early quantum computing pioneer D-Wave again asserted – that at least for D-Wave – the commercial quantum era has begun. Speaking at its first in-person Ana Read more…

GenAI Having Major Impact on Data Culture, Survey Says

February 21, 2024

While 2023 was the year of GenAI, the adoption rates for GenAI did not match expectations. Most organizations are continuing to invest in GenAI but are yet to Read more…

The GenAI Datacenter Squeeze Is Here

February 1, 2024

The immediate effect of the GenAI GPU Squeeze was to reduce availability, either direct purchase or cloud access, increase cost, and push demand through the roof. A secondary issue has been developing over the last several years. Even though your organization secured several racks... Read more…

Intel’s Xeon General Manager Talks about Server Chips 

January 2, 2024

Intel is talking data-center growth and is done digging graves for its dead enterprise products, including GPUs, storage, and networking products, which fell to Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire