Supercomputing Crucial to Clean Energy Production

By Tiffany Trader

February 13, 2013

The Office of Fossil Energy’s National Energy Technology Laboratory (NETL) is the proud owner of a brand new SGI supercomputer. Named High-Performance Computer for Energy and the Environment, or HPCEE for short, the 500 teraflops machine will help NETL scientists undertake a broad range of energy and environmental research, with a focus on coal, natural gas and oil.

Growing concern over climate change has led many to reconsider our relationship with fossil fuels, which comprise nearly 60 percent of human-generated CO2 emissions. The reality is that for now, traditional energy sources continue to dominate US energy policy, but there are signs of change. The US Department of Energy (DOE) under the direction of outgoing-Secretary Steven Chu has pushed for an environmentally-sound, sustainable energy portfolio that includes alternative energy sources. It was Chu who set the stage for some of NETL’s most prominent programs, for example the Simulation-Based Engineering User Center (SBEUC) and the Carbon Capture Simulation Initiative (CCSI).

As a Department of Energy lab, NETL supports the DOE’s mission to advance the national, economic, and energy security of the United States, mainly through a focus on fossil fuel resources. A glance at the lab’s key mandates – which include clean power, climate change mitigation, energy-efficiency and renewable energy – reveals an expanded awareness of today’s energy-related challenges. One of the ways that NETL contributes to climate change mitigation is by developing new methods for monitoring, capturing and sequestering greenhouse gases as directed by the President’s Global Climate Change Initiative. High-performance computing is essential to carrying out this research.

HPCwire spoke with Chris Guenther, director of NETL’s Computational Science Division to find out more about the new system. Mr. Guenther is responsible for the day-to-day management of NETL’s Simulation-Based Engineering User Center – where HPCEE is housed.

“Within the division what we try to do is develop physics-based models and methods and tools to accelerate the development and deployment of advanced technology to utilize our fossil energy resources,” says Guenther.

His team undertakes a wide range of modeling and simulation work at various scales, from molecules to devices to entire power plants.

HPCEE was commissioned to support the computational fluid dynamics and computational chemistry efforts underway at NETL. The SGI Rackable machine contains 24,192 2.6 gHz Intel Xeon E5-2670 cores with 48,384 GB of system memory in 1,512 computational nodes connected via Mellanox InfiniBand QDR. The architecture achieved 413.5 teraflops Rmax (Linpack) out of 503.2 teraflops peak, for an impressive theoretical efficiency of 82 percent.

NETL characterizes HPCEE as one of the most energy-efficient systems of its kind in the world, but that statement merits closer inspection. The half-petaflop supercomputer placed a respectable 55th on the latest TOP500 list. But on the Green500 list, which ranks top systems based on FLOPS per watt, the system finished in 403rd place – not exactly boast-worthy.

Where NETL can claim some green bragging rights is on the datacenter-side. HPCEE resides inside an SGI ICE Cube Air datacenter, which provides cooling and power with a PUE in the 1.03 to 1.06 range. It does so “out-of-the-box” – no special modifications were made to achieve this level of performance.

This low PUE reading means that only one percent of total electrical consumption goes toward cooling the equipment. NETL notes that the increased efficiency translates into an average annual savings of $450,000.

“The SGI Modular Data Center consists of a 1.1 MW transformer and utility/power center supporting two equipment aisles of 20 racks each,” says Guenther. “Three racks of storage and utility equipment, three racks of Mellanox trunk switches and 21 racks of compute nodes fill 27 of the available racks.”

Asked what the impetus was for a modular datacenter as opposed to a custom-built site, Guenther referenced a site study which showed that the external modular datacenter approach was more cost effective and quicker in terms of providing compute cycles to the Fossil Energy research staff. The purchase decision was based on a scoring system which put an emphasis on performance and efficiency, he reported.

Next >>

This 500-teraflops machine is a really big deal for NETL researchers and their partners. Up to now, the laboratory has gotten by with using many small computer clusters, but there were many days when users simply could not find available cores to do their work, notes Guenther. With an order of magnitude more computing power, scientists will have more cores available to them and they’ll be able to model extremely difficult problems, such as coal jet penetration into a gasifier.

NETL HPCEE supercomputerAs HPCEE comes online, they will start shutting down the other clusters except for one or two, adding to the overall energy savings.

While most of NETL’s funding and work is to support the Office of Fossil Energy, Guenther emphasizes an R&D portfolio that is “weighted heavily toward technology that is much more environmentally-friendly as well as the optimization of existing fossil energy devices.”

“Fossil energy gets a bad rap, but just about everything that we are doing is focusing on the environmental aspect of fossil energy,” he adds.

Underscoring this point, Guenther cites the innovative work of the Carbon Capture Simulation Initiative (CSSI), tasked with accelerating the development and deployment of sorbent-based CO2 capture. This NETL-led project just rolled out a suite of 21 computational tools and models aimed at new carbon capture technologies.

“Programs like this are the reason we have HPCEE,” says Guenther. “The high fidelity computational fluid dynamic modeling work that is part of the Carbon Capture Simulation Initiative will be done exclusively on this new system.”

sorbent pellets
Sorbent pellets developed by NETL prepared by Pressure Chemical Company

“There’s no commercial-scale sorbent-based carbon capture systems out there,” he continues. “We’re developing our own sorbents here at NETL from the ground up. We’re testing those; we’re modeling them in small reactors; we’re gaining confidence in our models that will allow us then to scale up these models, to actually look at the ability in the virtual world to do commercial-scale sorbent-based CO2 capture.”

For industry, sophisticated models like these are critical for reducing the risks associated with commercialization.

Combining innovative technology with an effective industry transfer mechanism is a winning strategy. NETL was just recognized by R&D Magazine for its work with sorbent pellets. The magazine considers this novel carbon capture technology among the 100 most technologically significant products to enter the marketplace within the past year.

The CCSI also helps quantify the uncertainty associated with a model’s prediction. “In this initiative, they’re conducting models at different length and time scales,” says Guenther. “At one end they’re doing process-level modeling, or the overall power-plant type modeling. At the other end, they’re doing very high-fidelity, kinetic models and CFD models that are very small length of time scales, and they’re coupling those different models together in a consistent fashion and they are propagating the uncertainty through these different length and time scales.”

NETL projects span the entire gamut of research stages. “We work with industry and other people on brand-new technology that has not hit the ground as well as technology that’s already out there that we are trying to optimize and/or improve,” says Guenther.

As an example of the former, the lab is exploring promising new technologies like chemical-looping, which offers the potential to generate electricity from coal with significantly less pollution and less cost. To do this, researchers are building models and gaining insight from a fundamental level using small experiments to help guide them.

And at the other end of the spectrum, NETL scientists are doing work with coal gasification, a technology that is more mature and which they have more experience with. This is an area where they are applying their models toward industry transfer and commercialization.

The HPCEE support staff are currently in the process of migrating over data, software and all the necessary tools for performing day-to-day simulations. They anticipate that the system will be production-ready by early Spring.

When HPCEE goes live, researchers from the five universities that are part of the NETL-Regional University Alliance – Carnegie Mellon, Penn State, the University of Pittsburgh, West Virginia University, and Virginia Tech – will also be able to access the supercomputer.


Related Articles

Steven Chu’s DOE Legacy: Big Science, Grand Challenges and Solyndra

New Computational Tools Help Carbon Capture Technologies

Clean Energy Conundrum: In Europe, Regulations Have Helped Create a “Golden Age Of Coal”

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!

Slide Shows Samsung May be Developing a RISC-V CPU for In-memory AI Chip

June 19, 2024

Samsung may have unintentionally revealed its intent to develop a RISC-V CPU, which a presentation slide showed may be used in an AI chip. The company plans to release an AI accelerator with heavy in-memory processing Read more…

ASC24 Student Cluster Competition: Who Won and Why?

June 18, 2024

As is our tradition, we’re going to take a detailed look back at the recently concluded the ASC24 Student Cluster Competition (Asia Supercomputer Community) to see not only who won the various awards, but to figure out Read more…

Qubits 2024: D-Wave’s Steady March to Quantum Success

June 18, 2024

In his opening keynote at D-Wave’s annual Qubits 2024 user meeting, being held in Boston, yesterday and today, CEO Alan Baratz again made the compelling pitch that D-Wave’s brand of analog quantum computing (quantum Read more…

Apple Using Google Cloud Infrastructure to Train and Serve AI

June 18, 2024

Apple has built a new AI infrastructure to deliver AI features introduced in its devices and is utilizing resources available in Google's cloud infrastructure.  Apple's new AI backend includes: A homegrown foun Read more…

Argonne’s Rick Stevens on Energy, AI, and a New Kind of Science

June 17, 2024

The world is currently experiencing two of the largest societal upheavals since the beginning of the Industrial Revolution. One is the rapid improvement and implementation of artificial intelligence (AI) tools, while the Read more…

Under The Wire: Nearly HPC News (June 13, 2024)

June 13, 2024

As managing editor of the major global HPC news source, the term "news fire hose" is often mentioned. The analogy is quite correct. In any given week, there are many interesting stories, and only a few ever become headli Read more…

Slide Shows Samsung May be Developing a RISC-V CPU for In-memory AI Chip

June 19, 2024

Samsung may have unintentionally revealed its intent to develop a RISC-V CPU, which a presentation slide showed may be used in an AI chip. The company plans Read more…

Qubits 2024: D-Wave’s Steady March to Quantum Success

June 18, 2024

In his opening keynote at D-Wave’s annual Qubits 2024 user meeting, being held in Boston, yesterday and today, CEO Alan Baratz again made the compelling pitch Read more…

Shutterstock_666139696

Argonne’s Rick Stevens on Energy, AI, and a New Kind of Science

June 17, 2024

The world is currently experiencing two of the largest societal upheavals since the beginning of the Industrial Revolution. One is the rapid improvement and imp Read more…

Under The Wire: Nearly HPC News (June 13, 2024)

June 13, 2024

As managing editor of the major global HPC news source, the term "news fire hose" is often mentioned. The analogy is quite correct. In any given week, there are Read more…

Labs Keep Supercomputers Alive for Ten Years as Vendors Pull Support Early

June 12, 2024

Laboratories are running supercomputers for much longer, beyond the typical lifespan, as vendors prematurely deprecate the hardware and stop providing support. Read more…

MLPerf Training 4.0 – Nvidia Still King; Power and LLM Fine Tuning Added

June 12, 2024

There are really two stories packaged in the most recent MLPerf  Training 4.0 results, released today. The first, of course, is the results. Nvidia (currently Read more…

Highlights from GlobusWorld 2024: The Conference for Reimagining Research IT

June 11, 2024

The Globus user conference, now in its 22nd year, brought together over 180 researchers, system administrators, developers, and IT leaders from 55 top research Read more…

Nvidia Shipped 3.76 Million Data-center GPUs in 2023, According to Study

June 10, 2024

Nvidia had an explosive 2023 in data-center GPU shipments, which totaled roughly 3.76 million units, according to a study conducted by semiconductor analyst fir Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. 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…

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…

Everyone Except Nvidia Forms Ultra Accelerator Link (UALink) Consortium

May 30, 2024

Consider the GPU. An island of SIMD greatness that makes light work of matrix math. Originally designed to rapidly paint dots on a computer monitor, it was then 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…

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…

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…

Some Reasons Why Aurora Didn’t Take First Place in the Top500 List

May 15, 2024

The makers of the Aurora supercomputer, which is housed at the Argonne National Laboratory, gave some reasons why the system didn't make the top spot on the Top Read more…

Leading Solution Providers

Contributors

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…

The NASA Black Hole Plunge

May 7, 2024

We have all thought about it. No one has done it, but now, thanks to HPC, we see what it looks like. Hold on to your feet because NASA has released videos of wh Read more…

Google Announces Sixth-generation AI Chip, a TPU Called Trillium

May 17, 2024

On Tuesday May 14th, Google announced its sixth-generation TPU (tensor processing unit) called Trillium.  The chip, essentially a TPU v6, is the company's l Read more…

Intel’s Next-gen Falcon Shores Coming Out in Late 2025 

April 30, 2024

It's a long wait for customers hanging on for Intel's next-generation GPU, Falcon Shores, which will be released in late 2025.  "Then we have a rich, a very Read more…

Nvidia Shipped 3.76 Million Data-center GPUs in 2023, According to Study

June 10, 2024

Nvidia had an explosive 2023 in data-center GPU shipments, which totaled roughly 3.76 million units, according to a study conducted by semiconductor analyst fir Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po 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…

A Big Memory Nvidia GH200 Next to Your Desk: Closer Than You Think

February 22, 2024

Students of the microprocessor may recall that the original 8086/8088 processors did not have floating point units. The motherboard often had an extra socket fo Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire