Risk Management Team Helps Keep Frontier’s Launch on Track

May 20, 2021

May 20, 2021 — Jason Hill sometimes jokes he knocks on wood for a living.

“In the past year, I’ve worn a hole in my desk,” he said.

As risk manager for the Oak Ridge Leadership Computing Facility (OLCF), Hill spends his days—and some sleepless nights—pondering not what kind of scientific breakthroughs Oak Ridge National Laboratory’s supercomputers can make possible but what can stand in the way. The countdown to launch for Frontier, the nation’s first exascale supercomputer, increased those concerns—and that was before a viral pandemic shut down the world.

“I definitely didn’t have that on the bingo card,” Hill said. “When we first talked about the coronavirus and what might happen, it was in February 2020, and the virus was still seen as just a problem overseas. Some team members at the time wondered, ‘Why are we dedicating so much time to this?’ But shortly thereafter came the directive to work from home, and now here we are over a year later.”

The planning—and yes, worrying—paid off. The Frontier system remains on track for delivery by late 2021, more than a year into the greatest worldwide disease outbreak in a century and amid shocks to supply lines from Albania to Zimbabwe.

“We got ahead of the problem, if only by a couple of weeks,” Hill said. “That’s why we plan, for the situations we expect and don’t expect. That we’ve been able to stay on track is a huge credit to the design and construction teams who are part of this amazing group of people. My job as the risk manager is to just help them do theirs the best way they can and try to eliminate uncertainty along the way.”

The power of exascale speed, capable of over a quintillion calculations per second—more than 1018, or a billion billion—promises opportunities to help solve some of the greatest challenges in science when the HPE Cray system opens to full user operations in 2022. Teams of scientists will be lined up, waiting to tackle challenges such as screening new cancer treatments, building better nuclear reactors, and probing the origins of the universe.

Hill’s priorities tend to be more immediate. Will the system arrive on time? Will unexpected costs sap the budget? Which parts of the plan could stumble—and which solutions will be effective? And once all the parts that comprise Frontier finally arrive, will they fit together and work as intended when the requisite dignitaries show up to cut the ribbon and flip the switch?

“Even during the pandemic, the greatest risk has been and probably always will be the scale of the system,” Hill said. “The first time it’s ever put together as one machine is when it shows up here at our facility. The application teams can’t fine-tune the codes until we have all the hardware, so until it’s all put together, we don’t have the ability to measure full system performance.”

Constant questions and point-by-point planning can cut down the guesswork. Hill approaches each project like a detective sizing up a case, noting the good and the bad, the known and the unknown.

He and other members of the OLCF team draw on decades of experience in building up and maintaining supercomputer systems from Jaguar to Titan to Summit, the nation’s fastest such machine until Frontier powers up. Hill spent a decade as an on-call system administrator, helping maintain the file systems supporting those computers and answering his share of late-night calls and emails.

“I’ve been one of the people receiving, configuring, and operating computer systems throughout my career, and that experience helps me ask leading questions of the project team that is executing the work but may not speak the same language as the team responsible for creating the project’s performance baseline,” he said. “We start with what project controls call the iron triangle—cost, schedule, and scope—and build out from there. How certain are we on each of these? Where can we find events that will affect the project’s ability to deliver on any of these goals?

“Some people choose to see risk management as a roadblock to their work, but it’s really just about helping achieve the end goal. We look at the risks to the project’s completion, but we also look at opportunities—a risk that can benefit the project, too. As the project moves along, events become more certain, and estimates are fine-tuned as we go. Then we can have multiple risk-mitigation plans locked and ready to go if and when an event occurs.”

Having the team’s full support just makes the process smoother.

“They understand the value that risk management can create,” Hill said. “We have great discussions during our risk meetings, and in other discussions, the team will routinely ask: ‘Is this in our risk register?’ That level of team investment helps improve the ability of the project to meet their deliverables.”

The coronavirus appeared on the risk management team’s radar near the end of February 2020. They had barely a week and a half to prepare before the nationwide shutdown began.

“That day in March when we got the guidance to stay home, it became apparent to everyone this pandemic was going to be something that could really affect the project,” Hill said. “First, if the lab shuts down completely, our construction crews can’t get the work done. Second, if all our staff have to work from home, we introduce lots of potential reliability and stability issues with our electronic infrastructure. We can’t fix an issue with an outside internet service provider’s network, for example. That impacts our team’s ability to collaborate and complete their work on the project.

“Then there’s the additional risk that all the vendors along the supply chain are doing the same thing in terms of remote work and safety protocols. Can they produce at the level to meet the project goals? Can they meet the delivery time promised? And that’s on top of the existing risks we already had to navigate.”

The lead time, though slim, proved to be enough to pivot. Steps that might seem minor on their own—increasing advance orders on materials, shoring up network security, drawing up safety protocols for crews onsite just in case—came together to help keep the project on track.

“Some of them were little things we had no idea would save us later,” Hill said. “We’d created an electronic workflow process early in the project—in 2019—that eliminated the need for hand signatures for approvals of change requests. That turned out to be a necessity in a work-from-home environment. The guidance to work from home created a bubble that allowed the construction crews to keep working safely on-site, similar to what was done for the end of the NBA season in 2020. Our risk management process and discussion of the responses to several scenarios bought us some time. We took advantage of that time, and the result has been this project remaining on schedule.”

The project to bring Frontier online began with more than 100 identified risks. Hill estimates he’s been able to cross out a quarter or more of those as the supercomputer’s arrival date draws closer.

“From the risk-management perspective, the hardest part is over now,” Hill said. “We’re closing out the facility-related work. There are still risks: safety for installation, project staffing—someone could win the lottery tomorrow—that’s why the project team cross-trains and has succession plans. I’m counting down to later this year when the facility transitions to Paul Abston (the OLCF Data Center manager and installation manager for Frontier), to put the system on the floor, connect everything, and turn it on safely.”

The work won’t end with Frontier’s delivery, but Hill hopes the handoff will allow more time to spend with his wife and four children and to jump back into his favorite pastime of running. The clock’s ticking once again: he already signed up for his next marathon.

UT-Battelle LLC manages Oak Ridge National Laboratory for DOE’s Office of Science, the single largest supporter of basic research in the physical sciences in the United States. DOE’s Office of Science is working to address some of the most pressing challenges of our time. For more information, visit https://energy.gov/science.


Source: MATT LAKIN, OLCF

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