DOE Under Secretary for Science Paul Dabbar Interviewed at SC18

By Tiffany Trader

November 21, 2018

During the 30th annual SC conference in Dallas last week, SC18 hosted U.S. Department of Energy Under Secretary for Science Paul M. Dabbar. In attendance Nov. 13-14, Dabbar delivered remarks at the Top500 panel, met with a number of industry stakeholders and toured the show floor. He also met with HPCwire for an interview, where we discussed the role of the DOE in advancing leadership computing.

Dabbar serves as the Department’s principal advisor on fundamental scientific research in high energy and nuclear physics; advanced computing; fusion; biological and environmental research; and has direct management over many of DOE’s national labs that run data-intensive experiments.

HPCwire: We’re here at SC18, which marks the 30th anniversary of the Supercomputing Conference since it started in 1988, with Under Secretary for Science Paul Dabbar — what prompted this level of involvement and participation?

Paul Dabbar: Supercomputing is at the high end of our focus at the Department of Energy in terms of asking for and getting increased dollars to invest. Since the leadership team’s been in place here for a couple of years, our budget for advanced computing is up 45 percent. The whole Office of Science is up almost 25 percent, and there’s a broad theme of investment in the sciences. As a part of that very broad-based increase in construction on all sorts of of user facilities, whether it’s in high-energy particle physics, nuclear physics, genomics and biology and so on, a common theme is that we are building capabilities in which for us to optimize, and frankly for the amount of data that we’re going to be creating across the whole of the science complex for us to be able to get great use of that. And not only for us, but the work that we do internationally with CERN and all the other big science user facilities. For us to innovate and identify the problems in the universe to go attack requires increasingly higher levels of of computing power.

As we looked at what’s a common thread of facilities and capabilities that we need across all of those particular science areas, HPC and the whole computing area is a common thread for us to optimize across everything. So that’s been our big push. Obviously it’s been based on the backs of a number of people here at the department who have been working on this for decades and we were lucky as a leadership team to come in and for that groundwork to be there for us to accelerate the growth of building out the groundwork of those capabilities.

HPCwire: You spoke at the Top500 panel on Tuesday night, which discusses major trends in leadership computing, and stated this is a critical and exciting time for science and supercomputing, what’s behind that statement?

Dabbar: We’ve seen from a broader science point of view we’re at the crux of a number of particularly exciting areas in science. I think if we could apply the right amount of capital and the right brain power we can make some really material moves in science across the world. The world is at the cusp of making dramatic moves in artificial intelligence and machine learning, quantum information science, space exploration, advanced and sustainable energy, advanced mobility and genomics. So when you think about the areas of the sciences broadly speaking, we are very excited about those opportunities.

We are very blessed that there is a consensus that increased investment is needed and as I mentioned the Office of Science is up almost 25 percent this year in terms of spending but the National Institutes of Health are up about 20 percent, the National Science Foundation is up about 10 percent. There’s been broad support for increased federal dollars against it because the opportunity is there and people see that this is a place for driving the country and driving the world and innovation. How does HPC factor into that? Clearly when you think about all those different sciences, data and optimizing data is a big part of each and every one of those. So once again it’s a common thread across all the sciences and so it’s very important for us. It’s also important for us economically for the United States. We know that effectively we are the pointy end of a spear. We are the seed money that moves things along. So us as not only as a basic researcher in many areas associated with materials and characterization that are applicable to microelectronics.

We know also that we are the high-end consumer of the products. We helped drive the industry. We drive it for our own purposes, effectively from a science and research point of view. But we know as we seed the whole industry to develop HPC to the next cutting-edge point we know that we are seeding the whole country and a whole of the industry that has applications far beyond our particular area.

HPCwire: The biannual list of the world’s fastest computers was just announced with DOE labs Oak Ridge and Livermore operating the top two systems Summit and Sierra, and five of the top ten machines. What is the significance of having these very powerful computers within a global context, where we see other nations are also making significant advances in computing?

Dabbar: We focus a little bit less on exact rankings versus capabilities. Clearly being at the front end of capabilities means that everything I’ve been discussing regarding all of our needs means that we have the capability of basically leading and using all of the data that we create across the science complex. That’s the first and foremost aspect. I do think there’s an important secondary aspect to it which is at the end of the day, when we build large user facilities we are a beacon to the science world. And one of the things that is really unique about the United States and how we run the science complex and National Labs is that we are an open transnational, merit-based, proposal-based use of our facilities, and whether it’s a light source or it’s a computing facility, people propose based on merit from anywhere in the world. The U.S. is only five percent of the world’s population and we have a great history of having people coming to this country, including vast amounts of our lab complex, from our friends all around the world who are very open to open access and cooperative access to science and research. So having the best in the world draws the best in the world from here in the United States from all over the world to drive science and research are in the United States. I think that’s an important aspect to us having these capabilities.

HPCwire: With CORAL-2, the second procurement project for the Collaboration of Oak Ridge Argonne and Livermore, the U.S. has declared its intention to spend up to $1.8 billion on two or potentially three exascale supercomputers. What is the status of this project?

Dabbar: Clearly as we look at CORAL-2, that’s the next solicitation of the two machines [at Oak Ridge and Livermore] and possibly an upgrade at Argonne [editor’s note: i.e., an upgrade to Aurora 2021]. So that process is moving along well. We’ve received proposals and we’re looking at finalizing our decision. We are going to be making a decision and we are going to be moving forward. The exact architecture and the exact suppliers have not been finalized yet but we are getting very close on that as we took proposals on that several months ago.

Clearly we have the dollars as I was commenting from a budget point of view for us to go and execute and we received great proposals so we have no problems with that. We are very much heading down the road of securing those.

HPCwire: What is the role of the government in funding these large projects?

Dabbar: I spend a lot of time with our partners who help us with our labs or work on various other kinds of grant programs at MIT and Caltech and Stanford and Princeton. The reality is when you think about having very large user facilities that can have broad based access with all sort of researchers, from not only inside our labs but from universities all over the U.S. and all over the world, someone has to build them. And notwithstanding the wonderful endowments of Princeton and MIT and Harvard and Stanford, the resources to pull together stadium-sized light sources that are miles long when it comes to and x-ray free-electron laser, or a computing facility, these are dollar amounts that even the most well-endowed of non-government science organizations would have a hard time doing. And so once again, I think it’s very important and there’s a long history that to a large degree started right after World War II around the importance of having a federal footprint that we could have these facilities that could be open to a broad range of researchers. That’s the core of what we are as a National Lab complex. That’s the basis of who we are. And so this is just an evolution of the next range of us pushing technology in HPC amongst other user facilities for us to invest. And we’re very gratified that we see the nation supporting that at all time high levels.

HPCwire: Having supercomputers, the hardware, is important, but there is no benefit to these powerful machines without the people — people to design and build and program them and also the computational scientists and engineers who utilize them. What role does the DOE have in training and workforce development to ensure a sustainable talent pipeline?

Dabbar: To a reasonable degree, the department takes the lead on hardware, meaning we build a lot of user facilities the others would have a hard time building as I was commenting to. And then we have access to those, both with our own researchers to use them as well as people from outside the lab complex. Part of it is dealing with the actual research itself and moving forward the bounds of knowledge on a particular topic, but we know that we helped develop the whole workforce of the whole chain of everything that we do research on, from the university level and up. To a large degree, we are a very heavy funder of graduate school training, effectively, through our grant processes. So as we go through each and every one of our particular areas of science, last year’s number was $3.1 billion a year of grants; this year’s number will be a little higher.

The grants that go out to a large degree are spread to universities all over the United States. A principal investigator makes a grant proposal whether it’s to use a particular HPC machine or to use a light source or to do some research at their own lab or university. So we spread around a lot of money to help drive research, but we clearly know a secondary aspect of that is that the PI has a whole bunch of grad students and others that are supporting them, undergrads, that are supporting them in the labs. So whenever I go to universities, I hear about people who receive our grants who are working on something very specific and it’s not just the principal investigator who may be a senior researcher or a professor at a university but the money flows down all the way through in terms of all the lab support all the research support. We know a very important secondary aspect of our entire grant program is that we feed the whole system in terms of STEM, in terms of education. It’s an important part of not only the DOE, but the National Science Foundation, National Institutes of Health, the whole federal complex–this is a big part of what we do for the nation.

HPCwire: Here at Supercomputing and within the high-performance computing sphere, there is ongoing outreach to communicate the value of HPC to the broader community. How do you explain to colleagues, stakeholders and everyday people why supercomputing is important and why it’s worth investing in?

Dabbar: I think the world is increasingly becoming knowledgeable about the importance of computing power, of data. Obviously there are broad discussions and use by the broad community of all sorts of information technology that just a decade ago just was not even available. So I think it’s much easier to discuss this for people to have knowledge of the importance of this, than not so many years ago. I think the importance is that many people don’t realize that the National Labs and what we do and research even exist, and that’s actually one of the big challenges that I have. It’s not [around the value of] big data and information technology and artificial intelligence — the average person actually gets a lot of the basics of those now nowadays. But what about the big facilities? What are the big things worked on? Why is it important to have those? I think the knowledge of that is actually not good at all. So one of the things that Secretary Rick Perry and myself and the rest of the leadership team have been trying very hard to do is to increase communication around the National Lab complex capabilities and what we do, such as Sierra, such as Summit, such as high performance computing, and what we do with those capabilities within the broader user facility complex for science. We will try to make a little dent in that while we are in leadership in this position.

Subscribe to HPCwire's Weekly Update!

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

AWS Expands Worldwide Availability to AMD-based Instances

July 22, 2019

Setting aside potential setbacks caused by U.S. trade policies, the steady cadence of AMD’s revival in HPC and the datacenter continued last week with AWS expanding availability of its AMD Epyc-based instances. Recall Read more…

By Staff

Microsoft Investing $1B in OpenAI Artificial General Intelligence R&D

July 22, 2019

Artificial general intelligence (AGI) is AI’s moonshot, the next giant leap for the AI field. Microsoft regards it to be feasible enough to warrant a $1 billion investment in OpenAI, the not-for-profit research organi Read more…

By Doug Black

Researchers Use Supercomputing to Study Links Between Hurricanes and Climate Change

July 19, 2019

As climate change looms, researchers are scrambling to answer the question of how a warming planet will affect the frequency and severity of already-deadly hurricanes. Now, a team of researchers from the University of Il Read more…

By Oliver Peckham

HPE Extreme Performance Solutions

Bring the Combined Power of HPC and AI to Your Business Transformation

A growing number of commercial businesses are implementing HPC solutions to derive actionable business insights, to run higher performance applications and to gain a competitive advantage. Read more…

IBM Accelerated Insights

With HPC the Future is Looking Grid

Gone are the days when problems such as unraveling genetic sequences or searching for extra-terrestrial life were solved using only a single high-performance computing (HPC) resource located at one facility. Read more…

San Diego Supercomputer Center to Welcome ‘Expanse’ Supercomputer in 2020

July 18, 2019

With a $10 million dollar award from the National Science Foundation, San Diego Supercomputer Center (SDSC) at the University of California San Diego is procuring a new supercomputer, called Expanse, to be deployed next Read more…

By Staff report

Microsoft Investing $1B in OpenAI Artificial General Intelligence R&D

July 22, 2019

Artificial general intelligence (AGI) is AI’s moonshot, the next giant leap for the AI field. Microsoft regards it to be feasible enough to warrant a $1 billi Read more…

By Doug Black

Informing Designs of Safer, More Efficient Aircraft with Exascale Computing

July 18, 2019

During the process of designing an aircraft, aeronautical engineers must perform predictive simulations to understand how airflow around the plane impacts fligh Read more…

By Rob Johnson

Intel Debuts Pohoiki Beach, Its 8M Neuron Neuromorphic Development System

July 17, 2019

Neuromorphic computing has received less fanfare of late than quantum computing whose mystery has captured public attention and which seems to have generated mo Read more…

By John Russell

Goonhilly Unveils New Immersion-Cooled Platform, Doubles Down on Sustainability Mission

July 16, 2019

Goonhilly Earth Station has opened its new datacenter – an enhancement to its existing tier 3 facility – in Cornwall, England, touting an ambitious commitme Read more…

By Oliver Peckham

ISC19 Cluster Competition: Application Results, Finally!

July 15, 2019

Our exhaustive coverage of the ISC19 Student Cluster Competition continues as we discuss the application scores below. While the scores were typically high, som Read more…

By Dan Olds

Nvidia Expands DGX-Ready AI Program to 19 Countries

July 11, 2019

Nvidia’s DGX-Ready Data Center Program, announced in January and designed to provide colo and public cloud-like options to access the company’s GPU-powered Read more…

By Doug Black

Argonne Team Makes Record Globus File Transfer

July 10, 2019

A team of scientists at Argonne National Laboratory has broken a data transfer record by moving a staggering 2.9 petabytes of data for a research project.  The data – from three large cosmological simulations – was generated and stored on the Summit supercomputer at the Oak Ridge Leadership Computing Facility (OLCF)... Read more…

By Oliver Peckham

Nvidia, Google Tie in Second MLPerf Training ‘At-Scale’ Round

July 10, 2019

Results for the second round of the AI benchmarking suite known as MLPerf were published today with Google Cloud and Nvidia each picking up three wins in the at Read more…

By Tiffany Trader

High Performance (Potato) Chips

May 5, 2006

In this article, we focus on how Procter & Gamble is using high performance computing to create some common, everyday supermarket products. Tom Lange, a 27-year veteran of the company, tells us how P&G models products, processes and production systems for the betterment of consumer package goods. Read more…

By Michael Feldman

Cray, AMD to Extend DOE’s Exascale Frontier

May 7, 2019

Cray and AMD are coming back to Oak Ridge National Laboratory to partner on the world’s largest and most expensive supercomputer. The Department of Energy’s Read more…

By Tiffany Trader

Graphene Surprises Again, This Time for Quantum Computing

May 8, 2019

Graphene is fascinating stuff with promise for use in a seeming endless number of applications. This month researchers from the University of Vienna and Institu Read more…

By John Russell

AMD Verifies Its Largest 7nm Chip Design in Ten Hours

June 5, 2019

AMD announced last week that its engineers had successfully executed the first physical verification of its largest 7nm chip design – in just ten hours. The AMD Radeon Instinct Vega20 – which boasts 13.2 billion transistors – was tested using a TSMC-certified Calibre nmDRC software platform from Mentor. Read more…

By Oliver Peckham

TSMC and Samsung Moving to 5nm; Whither Moore’s Law?

June 12, 2019

With reports that Taiwan Semiconductor Manufacturing Co. (TMSC) and Samsung are moving quickly to 5nm manufacturing, it’s a good time to again ponder whither goes the venerable Moore’s law. Shrinking feature size has of course been the primary hallmark of achieving Moore’s law... Read more…

By John Russell

Deep Learning Competitors Stalk Nvidia

May 14, 2019

There is no shortage of processing architectures emerging to accelerate deep learning workloads, with two more options emerging this week to challenge GPU leader Nvidia. First, Intel researchers claimed a new deep learning record for image classification on the ResNet-50 convolutional neural network. Separately, Israeli AI chip startup Hailo.ai... Read more…

By George Leopold

Nvidia Embraces Arm, Declares Intent to Accelerate All CPU Architectures

June 17, 2019

As the Top500 list was being announced at ISC in Frankfurt today with an upgraded petascale Arm supercomputer in the top third of the list, Nvidia announced its Read more…

By Tiffany Trader

Top500 Purely Petaflops; US Maintains Performance Lead

June 17, 2019

With the kick-off of the International Supercomputing Conference (ISC) in Frankfurt this morning, the 53rd Top500 list made its debut, and this one's for petafl Read more…

By Tiffany Trader

Leading Solution Providers

ISC 2019 Virtual Booth Video Tour

CRAY
CRAY
DDN
DDN
DELL EMC
DELL EMC
GOOGLE
GOOGLE
ONE STOP SYSTEMS
ONE STOP SYSTEMS
PANASAS
PANASAS
VERNE GLOBAL
VERNE GLOBAL

Intel Launches Cascade Lake Xeons with Up to 56 Cores

April 2, 2019

At Intel's Data-Centric Innovation Day in San Francisco (April 2), the company unveiled its second-generation Xeon Scalable (Cascade Lake) family and debuted it Read more…

By Tiffany Trader

Cray – and the Cray Brand – to Be Positioned at Tip of HPE’s HPC Spear

May 22, 2019

More so than with most acquisitions of this kind, HPE’s purchase of Cray for $1.3 billion, announced last week, seems to have elements of that overused, often Read more…

By Doug Black and Tiffany Trader

A Behind-the-Scenes Look at the Hardware That Powered the Black Hole Image

June 24, 2019

Two months ago, the first-ever image of a black hole took the internet by storm. A team of scientists took years to produce and verify the striking image – an Read more…

By Oliver Peckham

Announcing four new HPC capabilities in Google Cloud Platform

April 15, 2019

When you’re running compute-bound or memory-bound applications for high performance computing or large, data-dependent machine learning training workloads on Read more…

By Wyatt Gorman, HPC Specialist, Google Cloud; Brad Calder, VP of Engineering, Google Cloud; Bart Sano, VP of Platforms, Google Cloud

Chinese Company Sugon Placed on US ‘Entity List’ After Strong Showing at International Supercomputing Conference

June 26, 2019

After more than a decade of advancing its supercomputing prowess, operating the world’s most powerful supercomputer from June 2013 to June 2018, China is keep Read more…

By Tiffany Trader

In Wake of Nvidia-Mellanox: Xilinx to Acquire Solarflare

April 25, 2019

With echoes of Nvidia’s recent acquisition of Mellanox, FPGA maker Xilinx has announced a definitive agreement to acquire Solarflare Communications, provider Read more…

By Doug Black

Qualcomm Invests in RISC-V Startup SiFive

June 7, 2019

Investors are zeroing in on the open standard RISC-V instruction set architecture and the processor intellectual property being developed by a batch of high-flying chip startups. Last fall, Esperanto Technologies announced a $58 million funding round. Read more…

By George Leopold

Nvidia Claims 6000x Speed-Up for Stock Trading Backtest Benchmark

May 13, 2019

A stock trading backtesting algorithm used by hedge funds to simulate trading variants has received a massive, GPU-based performance boost, according to Nvidia, Read more…

By Doug Black

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This