“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