Oil and Gas HPC Workshop Highlights Industry Challenges

By Ted Walker

March 14, 2012

Leaders from the oil and gas industry and the high performance computing and information technology industry, as well as academics and representatives from national laboratories, met at Rice University in Houston, Texas, March 1 for the 5th annual Rice Oil and Gas HPC Workshop.

The oil and gas industry depends heavily on high performance computing to spur meaningful returns on its investments in drilling and production. The huge demands on data and processing in the industry are driven by the services that support geophysical mapping, like seismic imaging and reservoir simulation, to help companies assess reservoirs and place wells.

The workshop’s 300 attendees is a record number for the event, which is organized by the Ken Kennedy Institute for Information Technology at Rice University, heard talks from industry and academic leaders, and participated in workshops that delved into tools and techniques leading the way forward in HPC in the oil and gas industry. More than a conference with formal talks, networking and conversation are at the forefront, and vendors and workshop participants from around the world engaged in dialog about opportunities and challenges.

“The growth of the workshop continues to show the importance of high performance computing as a critical business enabler and differentiator in the oil and gas industry, with a well-understood return on investment,” said Jan Odegard, executive director of the Ken Kennedy Institute. “The energy at this year’s conference is a strong indicator of the desire to attack head-on the challenges in applying computing across the oil and gas industry.”

Interactive talks covered a wide range of topics, from algorithm optimization, performance and programming tools, like HPCToolkit and Loo.py, to programming models and languages, such as Co-array Fortran and OpenCL. The wide range of discussion also covered the challenges for developing and managing HPC facilities and infrastructure, and the open-source software framework IWAVE.

The workshop also featured several keynote addresses on emerging HPC and data center challenges in the oil and gas industry:

Cray CEO Ungaro on Oil & Gas: “We’re Back in the Industry”

Peter Ungaro, President and Chief Executive Officer of Cray Inc., delivered the workshop’s opening keynote address, and he spoke about his company’s foray into oil and gas.

“If I was sitting in your chair right now,” Ungaro said, “I would wonder, ‘What are you doing here, Pete? Cray is a company that mostly goes to national laboratories. Were you trying to get to Oak Ridge last night and you got off in Houston by accident? Well, I would tell you that the same challenges that are happening in building some of the biggest supercomputers in the world are going to hit the oil and gas industry.

“From my perspective,” he continued, “[these challenges] are going to change the kind of machines that we put in production within the oil and gas community, and a lot of the requirements are fundamentally going to shift as we go through these changes in processing. The requirements keep rising. The machines that we’re using today are not the kind of machines that we are going to be using in a few years.”

Ungaro also addressed what he called the compelling business case for HPC in the oil and gas industry.

“When we look at the requirements from a compute and data standpoint, they are huge,” he said. “From data acquisition, through seismic, through reservoir simulation, and to downstream needs, that is a very broad set of applications that stresses many different parts of the machine and many different aspects of processing, not only for petaflop-sized systems for doing state-of-the-art computations, but also on the data side. From that perspective I think it’s a very unique kind of model.

An accurate seismic image has huge returns. A well can cost a lot of money, and restating a reserve has some serious business implications. When the requirements and the returns are huge, the demand for getting it right really goes up.”

As systems increase in complexity and integration, Ungaro also noted the need for increased investment in software technology that supports both scale-up and scale-out architectures, as that takes advantage of accelerators — all of this while hiding the level of complexity on the front end.

“There was a time when there were a lot of Cray computers in the oil and gas industry,” Ungaro concluded. “We’re back in the industry.”

IWAVE, an open-source software framework 

William Symes, Director of The Rice Inversion Project and Professor in Computational and Applied Mathematics at Rice University, gave a detailed introduction to IWAVE, the open-source framework for regular grid finite difference modeling.

The IWAVE package evolved from its beginnings as a QC component of the SEG Advanced Modeling (SEAM) project into a framework that can be used to explore new algorithms, code porting, benchmarking architectures and testing tools and new ideas. As a part of several breakout workshops, Ted Barragy of AMD and Murtaza Ali of Texas Instruments (TI) demonstrated the facility of the IWAVE framework in the oil and gas industry by porting components to AMD’s Fusion APU and the TI’s C66x KeyStone-based multicore DSP.

In another workshop talk, John Mellor-Crummey, Professor of Computer Science at Rice University, used IWAVE as an example for how HPCToolkit can be used to gain insight into performance optimization.

Envisioning Exascale

Addressing the issue of the transition from petascale to exascale computing, Intel’s General Manager of the Technical Computing Group, Rajeeb Hazra, looked ahead to the journey towards exascale.

“Why do we care about getting to exascale?” he asked. “Scientists either have more to do, or they need to do the same thing much quicker.” Accepting the assumption that there is a continual need for more performance in HPC, Hazra called attention to the costs of the pace of improvement we’ve already experienced. With the increase in performance, power usage has increased alongside.

“Exascale is not about one computer,” Hazra continued. “Exascale is a statement that means you have hundreds of computers that are a petaflop at half a rack. That’s the promise of exascale. You should look at it as a supply chain that has suddenly been enabled at a much higher level, not just that the top of the supply chain has the biggest computer to run on.

“We’ve gone from a few Kilowatts for the largest computing systems, to the largest system in existence, which is the K computer in Japan, taking 10 megawatts per ten petaflops. So it looks wonderful, but we’ve done this by scaling out systems faster than Moore’s Law. We have not done what we need to do, which is to change the performance density.

“You have to now approach this problem from a systems perspective,” Hazra continued. “My message to programmers: your mindset needs to change. The more sequential you are, the more problems you are creating for yourself. You are thinking about performance and results in an old paradigm. Whether it’s domain-specific languages or particular pragmas or a library-based approach to getting parallel, you have to be able to express it. Parallelism with no locality, and locality with no parallelism are extremes you have to avoid.” 

He also stressed hardware and software co-design, with a feedback loop between the two parties. “Co-design has to be something that changes what you are doing and what I was going to do in a concerted way,” he said. “It’s not requirements gathering. It’s a tough problem. It can be like trying to get the Congress to work together, but it has to be done.”

The Power Challenge

Los Alamos National Laboratory (LANL) engineers Richard Rivera and Farhad Banisadr discussed the increased demand for data center power, and the engineering practices to meet those needs. Rivera stressed the importance of engineering efficiency into data center management. “We try to be proactive,” he said. “Power is one of the commodities that technology is demanding. We have to put some engineering practices in place to gain efficiencies where we can.”

Careful planning marks the approach for Rivera and Banisadr, who use modeling software to maximize efficiency, and to anticipate HPC needs years ahead of installation. Networked sensors at the LANL data center profile temperatures, humidity and air pressure under the data center floors at any point. These sensors allow engineers to analyze the efficiency of their cooling systems and to tune the facility to optimize efficiency.

Another trend points to liquid cooling. “With the power densities [in data centers] going up towards 100 kilowatts per rack,” said Banisadr, “we see the trend moving towards liquid cooling. With the existing air-handling units, a 41-ton air-handling unit uses roughly 15 to 18 percent of its own capacity to remove the heat from its own electric motors.”

At LANL, the amount of power to cool these less efficient units translates to around 2 megawatts of power at a roughly 19 Megawatt facility. This is not sustainable if we project towards exascale by end of the decade.

Ideas in development to increase efficiency include advanced machine scheduling to maximize capabilities, modular and customizable power center technology and more cooperation and integration between facilities, power, cooling and IT teams.

The long-term future of data center power is clear, even if the path to that future is not. “We have a plan,” said Rivera, “and that is to bring in more power.”

—– 

The 2012 Rice Oil and Gas HPC Workshop was, as it has been in the past, organized by a team that includes Henri Calandra of Total, Keith Gray of BP, David Judson of WesternGeco, Bill Menger of Weinman Geoscience, Scott Morton of Hess Corp., Chap Wong of Chevron, and Jan E. Odegard of Rice University.

Presentations and archived webcasts will shortly be available at og-hpc.org.

Next year’s Oil and Gas HPC Workshop will take place at Rice University on Thursday, February 28, 2013.

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!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues 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 power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion 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…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen 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…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. 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…

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…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a 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…

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…

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…

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…

Leading Solution Providers

Contributors

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…

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…

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…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer 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…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire