Executive Summary
1. The focal point of this work is the statement made in [wp]: “The largest single factor preventing more aggressive use of [high performance computing] is the lack of computational scientists.”
2. Computational science is defined in the PITAC report. We use the term computational science in an inclusive sense, including such terms as “high performance computing,” “supercomputing”, “computational physics” and similar terms.
3. The research will consider
a. Tools and techniques to support multidisciplinary teams as suggested in [pitac].
b. Educational materials to educate the next generation of computational scientists.
Details Support
1. Computational Science is the center of high performance computing and people are the center of computational science. [wp, pitac]
a. The multidisciplinary teams required to address computational science challenges represent what will be the most common mode of 21st century science and engineering R&D. [pitac]
b. Extracting scientific meaning from these data requires coupling numerical, statistical, and logical modeling techniques in ways that are unique to each discipline. [FoSC]
c. But “Graduate enrollment in 2003 grew in all major S&E fields and in all subfields except computer sciences (table 2). Computer sciences enrollment dropped 3 percent from the previous year, the first decrease in that field since 1995.” [NSF]
d. Supercomputing is not computational science, merely a subset.
i. The primary challenge introduced by supercomputing is that many conventional algorithms for these problems must be modified so as to scale effectively to much larger data sets or numbers of processors and to run efficiently on machines with deep memory hierarchies. [FoSC]
ii. Supercomputer system software must provide continuing support for the basic operations used in the applications by keeping the legacy software running until it can be replaced, by providing tools for performance tuning and debugging on new Platforms. and bv Providing effective methods for Porting and evolution. [FoSC]
iii. SOFTWARE RESEARCH. The development of scalable scientific codes today is a laborious process. Mathematical algorithms are translated by a programmer into detailed programs and tuned to a specific architecture using programming notations that reflect the underlying architecture a manual, error-intensive process.[FoSC]
iv. Much of supercomputing today is done on commodity grids. This is a completely different development paradigm that the specialized supercomputer, requiring different skill sets.
2. What is computational science?
a. “As a basis for responding to the charge from the Office of Science and Technology Policy, the PITAC developed a definition of computational science. This definition recognizes the diverse components, ranging from algorithms, software, architecture, applications, and infrastructure that collectively represent computational science. Computational science is a rapidly growing multidisciplinary field that uses advanced computing capabilities to understand and solve complex problems. Computational science fuses three distinct elements:
§ Algorithms (numerical and non-numerical) and modeling and simulation software developed to solve science (e.g., biological, physical, and social), engineering, and humanities problems
§ Computer and information science that develops and optimizes the advanced system hardware, software, networking, and data management components needed to solve computationally demanding problems
§ The computing infrastructure that supports both the science and engineering problem solving and the developmental computer and information science”
b. “Computational science provides a unique window through which researchers can investigate problems that are otherwise impractical or impossible to address, ranging from scientific investigations of the biochemical processes of the human brain and the fundamental forces of physics shaping the universe, to analysis of the spread of infectious disease or airborne toxic agents in a terrorist attack, to supporting advanced industrial methods with significant economic benefits, such as rapidly designing more efficient airplane wings computationally rather than through expensive and time-consuming wind tunnel experiments. [pitac]”
c. “However, only a small fraction of the potential of computational science is being realized, thereby compromising U.S. preeminence in science and engineering. Among the obstacles to progress are rigid disciplinary silos in academia that are mirrored in Federal research and development agency organizational structures. These silos stifle the development of multidisciplinary research and educational approaches essential to computational science. [pitac]”
d. “Our report recommends that both universities and Federal R&D agencies must fundamentally change these organizational structures to promote and reward collaborative research. [pitac transmittal letter to pres]”
e. “While it is itself a discipline, computational science serves to advance all of science. The most scientifically important and economically promising research frontiers in the 21st century will be conquered by those most skilled with advanced computing technologies and computational science applications.[pitac]”
f. “The universality of computational science is its intellectual strength. It is also its political weakness. Because all research domains benefit from computational science but none is solely defined by it, the discipline has historically lacked the cohesive, well-organized community of advocates found in other disciplines.”
3. PITAC Principal finding and recommendation
a. PRINCIPAL FINDING. “Computational science is now indispensable to the solution of complex problems in every sector, from traditional science and engineering domains to such key areas as national security, public health, and economic innovation. Advances in computing and connectivity make it possible to develop computational models and capture and analyze unprecedented amounts of experimental and observational data to address problems previously deemed intractable or beyond imagination. Yet, despite the great opportunities and needs, universities and the Federal government have not effectively recognized the strategic significance of computational science in either their organizational structures or their research and educational planning. These inadequacies compromise U.S. scientific leadership, economic competitiveness, and national security. [pitac]”
b. PRINCIPAL RECOMMENDATION.
i. “Universities and the Federal government’s R&D agencies must make coordinated, fundamental, structural changes that affirm the integral role of computational science in addressing the 21st century’s most important problems, which are predominantly multidisciplinary, multi-agency, multisector, and collaborative. To initiate the required transformation, the Federal government, in partnership with academia and industry, must also create and execute a multi-decade roadmap directing coordinated advances in computational science and its applications in science and engineering disciplines.[pitac]”
ii. “To confront these issues, universities must significantly change their organizational structures to promote and reward collaborative research that invigorates and advances multidisciplinary science. They must also implement new multidisciplinary structures and organizations that provide rigorous, multifaceted educational preparation for the growing ranks of computational scientists the Nation will need to remain at the forefront of scientific discovery. [pitac]”
4. “High-performance computing [qua supercomputing] is not only a key tool to increasing competitiveness, it is also a tool that is essential to business survival. Nearly 100% of the respondents indicated that HPC tools are indispensable. [wp]”
5. Two-thirds of the respondents indicated that they have important problems that they simply can’t solve today. Examples of current unsolved problems include modeling block engine assembly in full detail, simulating vehicle rollover, real-time processing of data from remote sensors, protein folding, and coordinating databases across tens of thousands of servers. [wp]
6. Business and Technical Barriers Are Inhibiting the Use of Supercomputing
a. “The largest single [barrier inhibiting use of SC] is the lack of computational scientists, human experts (internal or external) who can apply HPC tools to the problems in question and the budget to hire them.”[wp]
b. most industrial sites require software compatibility in their HPC servers and the cost to change or rewrite software is frequently seen as prohibitive.[wp]
7. The need for more powerful and ease of use
a. When asked what could be accomplished if the "ease-of-use" barrier were addressed with systems that are 10 times easier to program, respondents overwhelmingly indicated that they could develop more powerful applications and fundamentally rewrite their current codes.
b. Not surprisingly, they also indicated that they could shorten design cycles and time to market, a natural by-product of better applications.
c. In addition, more easily programmable systems would enable a wider universe of researchers, scientists, inventors, designers, manufacturers, and mathematicians to use high-performance computing to solve their problems, extending the benefits of these systems more broadly across the private sector for increased industrial and national competitiveness.
d. "It would make these tools available to a much wider array of scientists who have good ideas but may not have programming skills." [wp]
References
[FoSC] Computer Science and Telecommunications Board (CSTB). “The Future of Supercomputing: An Interim Report (2003)”
[wp] Earl Joseph and Christopher G. Willard. White Paper: Council of Competitiveness Study of U.S. Industrial HPC Users. DARPA. July, 2004.
[PITAC] President’s Information Technology Advisory Council, Report to the President,June 2005. “Computational Science: Ensuring America’s Competitiveness”
[NSF] Julia Oliver. Graduate Enrollment in Science and Engineering Programs Up in 2003, but Declines for First-Time Foreign Students NSF 05-317 | August 2005