New National HPC Strategy Is Bold, Important and More Daunting than US Moonshot

By William Gropp and Thomas Sterling

August 6, 2015

“In order to maximize the benefits of HPC for economic competitiveness and scientific discovery, the United States Government must create a coordinated Federal strategy in HPC research, development, and deployment.” With these words, the President of the United States established the National Strategic Computing Initiative (NSCI) through Executive Order to implement this whole-of-government strategy in collaboration with industry and academia. Not since the signing of legislation in 1991 for the HPCC initiative has the nation articulated a bold and specific goal for the advancement of HPC and the benefits to be derived. While not over constraining the details of how exascale computing is to be achieved and exploited, this executive order establishes a national framework, objectives, and federal agency responsibilities across the government to regain international leadership and address the daunting technical challenges in the employment of exascale technologies.

Among the strategic goals of this singular national endeavor is the unification of data-intensive and compute-intensive approaches to architecture, system software, and programming methodologies and tools to maximize the benefits of HPC for the US. Today, systems in these arenas are perceived as distinct in role and structure. But it is recognized by expert practitioners in these sub-domains that each must rely, sometimes heavily, on the capabilities of the other. Computing in the science disciplines is often heavily engaged in the manipulation of data both from external sources and of their own creation requiring management of the entire storage hierarchy including mass storage while depending on I/O and system bandwidth for rapid data transport. Conversely, big data applications including graph analytics require massive concurrency of operation consistent with design properties of HPC systems. And of course, they both are derived from the same enabling technologies. It is indicative of this complementarity that such leadership vendors as Cray Inc. and IBM Corp. are equally focused on both aspects of the high end computing. Therefore, a national realization and goal of bringing the two domains into a single composite mutually supportive computing fabric will accelerate the ability to achieve sophisticated computational products integrating both modalities and also facilitate both through the research and development projected through this national enterprise.

The scale of computing mandated by this Presidential order for which cooperative research across the country is to be energized is “exascale” which is neither limited to a single parameter like FLOPS, nor a single operating point like 1 exaflops. Exascale is as much about data storage capacity and transport as it is related to arithmetic capability. And while 1 exaflops sustained performance on some select workload will serve as a demonstrable milestone, it will only be one of many across a broad performance regime that may span orders of magnitude in capability.

Further, the charter for the NSCI is not about creating a stunt machine for national stature – quite the opposite. It is about the deployment and application of systems delivering 1 exaflops and more sustained performance on real-world computational challenges of importance to the country and its society. This is to be accomplished through a cohesive multi-agency collaboration as well as public-private sector partnerships, over a sustained period of effort of probably well over a decade. Not simply targeting a next and arbitrary milestone, the NSCI directs the creation of a strategic vision and realistic Federal investment strategy for the US “to sustain and enhance its scientific, technological, and economic leadership position in HPC research, development, and deployment” and to transition HPC research into development of operational systems. This is about real world impact and opportunity of a future generation of supercomputing to be derived through the innovation and skills of the nations diverse and best skill force in a unified effort.

Not merely motivating the necessary achievement of exascale computing, this initiative intends to accelerate delivery of computing by two orders of magnitude with respect to contemporary system performance even as it merges the two dominant classes of STEM and Big Data computing that today appear as separate forms. Of significance is the explicit recognition and acknowledgement of the end of Moore’s Law and the need to establish a viable path forward for improved capabilities beyond these asymptotic limitations of anticipated semiconductor technology. Towards the effective utility of such sustained computing capability and capacity, it is stated as an objective to ensure and deploy a national HPC ecosystem capable of providing easy access to US resources for economic competitiveness, scientific discovery, and national security. A key strategy to this end is to encourage collaboration among the public and private sectors for the sharing of results of research and development.

The plan of action is to leverage the expertise, missions, and historical capabilities of many federal agencies working in concert to bring the full strengths of the nation in alignment. The lead agencies designated are the Department of Energy, the Department of Defense, and the National Science Foundation, each with its specific roles and responsibilities. IARPA and NIST will provide important foundational research and development capabilities for future computing paradigms and advanced measurement methods. And a number of agencies will deploy such future systems for their mission-driven objectives including NASA, FBI, NIH, DHS, and NOAA. This overall process will be guided by and receive oversight by an Executive Council comprising OSTP and OMB.

The NSCI framework leaves many facets of its implementation to the planning process to be lead by the Executive Council and involve the contributing bodies of the participating Federal agencies. This provides flexibility in determining the details of carrying out this mandate even as it sets the goals and charter for the contributing entities. Heavy reliance on US computer industry and academic research is emphasized even as the direction is derived by the mission agencies. The budget and its profile over the many years is unspecified but the requirements that such a budget needs to enable is clearly represented. An overarching philosophy that permeates the NSCI is one of cooperation and collaboration demanding a culture of community mutual involvement and sharing. This is a new challenge as well and one that may prove as significant as the purely technical ones. Historical tensions at many levels will have to be overcome but success at the national level may only be realized through a renaissance of mutually supportive engagement. Without this, US preeminence in exascale computing may prove unrealizable.

The NSCI charter is a balanced agenda of research and development of future technologies and methodologies as well as responsible deployment of systems and infrastructures to carry through the mission-critical obligations of the diverse participating agencies. The benefits sought are for the economy, society, and security of the nation and its citizens. It is a call to engagement. More than the next moonshot, it demands the talents, creativity, resources, and commitments of the nation’s forces be brought to bear on the needs of the country in the next generations in computing even as the ways of synthesizing practical experience and future innovation have yet to be prescribed.

This is a very exciting time but one that will demand responsible consideration and conviction as the new map of the field of exascale computing is being charted. This is not just the next American moonshot. It is more than a moonshot. As daunting as landing on the Moon was more than a generation ago, we understood the physics of the problem, where the Moon would be and when, and what success looked like. NSCI does not have such certainty. Perhaps most importantly it must create a future technological context with long lasting consequences and unending application. When Eugene Cernan stepped back on the ladder of Apollo 17 in 1972, he left the last footprints to impress the surface of the Moon in more than 50 years. We’ve never gone back. NSCI must build the bridge to the future of computing across which the US only goes forward. It will create the new physics, the new math (e.g., parallel algorithms), the new concepts of programming, architecture, and supportive software and infrastructures that will launch the US to the furthest frontiers of computing opportunity. But NSCI is only the first step. It is now the responsibility of this nation’s creators and users to come together in mutual supporting roles to advance this mandate in the service of the country and its people.

William Gropp and Thomas Sterling are co-editors of HPCwire’s Exascale Edition

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!

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 13), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue’s max capacity and doubling 2016 attendee numbers), the one Read more…

By Tiffany Trader

Machine Learning at HPC User Forum: Drilling into Specific Use Cases

September 22, 2017

The 66th HPC User Forum held September 5-7, in Milwaukee, Wisconsin, at the elegant and historic Pfister Hotel, highlighting the 1893 Victorian décor and art of “The Grand Hotel Of The West,” contrasted nicely with Read more…

By Arno Kolster

Google Cloud Makes Good on Promise to Add Nvidia P100 GPUs

September 21, 2017

Google has taken down the notice on its cloud platform website that says Nvidia Tesla P100s are “coming soon.” That's because the search giant has announced the beta launch of the high-end P100 Nvidia Tesla GPUs on t Read more…

By George Leopold

HPE Extreme Performance Solutions

HPE Prepares Customers for Success with the HPC Software Portfolio

High performance computing (HPC) software is key to harnessing the full power of HPC environments. Development and management tools enable IT departments to streamline installation and maintenance of their systems as well as create, optimize, and run their HPC applications. Read more…

Cray Wins $48M Supercomputer Contract from KISTI

September 21, 2017

It was a good day for Cray which won a $48 million contract from the Korea Institute of Science and Technology Information (KISTI) for a 128-rack CS500 cluster supercomputer. The new system, equipped with Intel Xeon Scal Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 13), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Machine Learning at HPC User Forum: Drilling into Specific Use Cases

September 22, 2017

The 66th HPC User Forum held September 5-7, in Milwaukee, Wisconsin, at the elegant and historic Pfister Hotel, highlighting the 1893 Victorian décor and art o Read more…

By Arno Kolster

Stanford University and UberCloud Achieve Breakthrough in Living Heart Simulations

September 21, 2017

Cardiac arrhythmia can be an undesirable and potentially lethal side effect of drugs. During this condition, the electrical activity of the heart turns chaotic, Read more…

By Wolfgang Gentzsch, UberCloud, and Francisco Sahli, Stanford University

PNNL’s Center for Advanced Tech Evaluation Seeks Wider HPC Community Ties

September 21, 2017

Two years ago the Department of Energy established the Center for Advanced Technology Evaluation (CENATE) at Pacific Northwest National Laboratory (PNNL). CENAT Read more…

By John Russell

Exascale Computing Project Names Doug Kothe as Director

September 20, 2017

The Department of Energy’s Exascale Computing Project (ECP) has named Doug Kothe as its new director effective October 1. He replaces Paul Messina, who is stepping down after two years to return to Argonne National Laboratory. Kothe is a 32-year veteran of DOE’s National Laboratory System. Read more…

Takeaways from the Milwaukee HPC User Forum

September 19, 2017

Milwaukee’s elegant Pfister Hotel hosted approximately 100 attendees for the 66th HPC User Forum (September 5-7, 2017). In the original home city of Pabst Blu Read more…

By Merle Giles

Kathy Yelick Charts the Promise and Progress of Exascale Science

September 15, 2017

On Friday, Sept. 8, Kathy Yelick of Lawrence Berkeley National Laboratory and the University of California, Berkeley, delivered the keynote address on “Breakthrough Science at the Exascale” at the ACM Europe Conference in Barcelona. In conjunction with her presentation, Yelick agreed to a short Q&A discussion with HPCwire. Read more…

By Tiffany Trader

DARPA Pledges Another $300 Million for Post-Moore’s Readiness

September 14, 2017

The Defense Advanced Research Projects Agency (DARPA) launched a giant funding effort to ensure the United States can sustain the pace of electronic innovation vital to both a flourishing economy and a secure military. Under the banner of the Electronics Resurgence Initiative (ERI), some $500-$800 million will be invested in post-Moore’s Law technologies. Read more…

By Tiffany Trader

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

NERSC Scales Scientific Deep Learning to 15 Petaflops

August 28, 2017

A collaborative effort between Intel, NERSC and Stanford has delivered the first 15-petaflops deep learning software running on HPC platforms and is, according Read more…

By Rob Farber

Oracle Layoffs Reportedly Hit SPARC and Solaris Hard

September 7, 2017

Oracle’s latest layoffs have many wondering if this is the end of the line for the SPARC processor and Solaris OS development. As reported by multiple sources Read more…

By John Russell

Six Exascale PathForward Vendors Selected; DoE Providing $258M

June 15, 2017

The much-anticipated PathForward awards for hardware R&D in support of the Exascale Computing Project were announced today with six vendors selected – AMD Read more…

By John Russell

Top500 Results: Latest List Trends and What’s in Store

June 19, 2017

Greetings from Frankfurt and the 2017 International Supercomputing Conference where the latest Top500 list has just been revealed. Although there were no major Read more…

By Tiffany Trader

IBM Clears Path to 5nm with Silicon Nanosheets

June 5, 2017

Two years since announcing the industry’s first 7nm node test chip, IBM and its research alliance partners GlobalFoundries and Samsung have developed a proces Read more…

By Tiffany Trader

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

Leading Solution Providers

Graphcore Readies Launch of 16nm Colossus-IPU Chip

July 20, 2017

A second $30 million funding round for U.K. AI chip developer Graphcore sets up the company to go to market with its “intelligent processing unit” (IPU) in Read more…

By Tiffany Trader

Google Releases Deeplearn.js to Further Democratize Machine Learning

August 17, 2017

Spreading the use of machine learning tools is one of the goals of Google’s PAIR (People + AI Research) initiative, which was introduced in early July. Last w Read more…

By John Russell

Russian Researchers Claim First Quantum-Safe Blockchain

May 25, 2017

The Russian Quantum Center today announced it has overcome the threat of quantum cryptography by creating the first quantum-safe blockchain, securing cryptocurrencies like Bitcoin, along with classified government communications and other sensitive digital transfers. Read more…

By Doug Black

EU Funds 20 Million Euro ARM+FPGA Exascale Project

September 7, 2017

At the Barcelona Supercomputer Centre on Wednesday (Sept. 6), 16 partners gathered to launch the EuroEXA project, which invests €20 million over three-and-a-half years into exascale-focused research and development. Led by the Horizon 2020 program, EuroEXA picks up the banner of a triad of partner projects — ExaNeSt, EcoScale and ExaNoDe — building on their work... Read more…

By Tiffany Trader

Google Debuts TPU v2 and will Add to Google Cloud

May 25, 2017

Not long after stirring attention in the deep learning/AI community by revealing the details of its Tensor Processing Unit (TPU), Google last week announced the Read more…

By John Russell

Amazon Debuts New AMD-based GPU Instances for Graphics Acceleration

September 12, 2017

Last week Amazon Web Services (AWS) streaming service, AppStream 2.0, introduced a new GPU instance called Graphics Design intended to accelerate graphics. The Read more…

By John Russell

Cray Moves to Acquire the Seagate ClusterStor Line

July 28, 2017

This week Cray announced that it is picking up Seagate's ClusterStor HPC storage array business for an undisclosed sum. "In short we're effectively transitioning the bulk of the ClusterStor product line to Cray," said CEO Peter Ungaro. Read more…

By Tiffany Trader

GlobalFoundries: 7nm Chips Coming in 2018, EUV in 2019

June 13, 2017

GlobalFoundries has formally announced that its 7nm technology is ready for customer engagement with product tape outs expected for the first half of 2018. The Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Share This