Although the critical role of advanced computing in science and engineering is well understood and a number of reports have been prepared to address foundation-wide or disciplinary requirements, not all research areas or programs have defined their requirements for advanced computing or established processes for regularly updating and refining them, such as by constructing roadmaps that describe science and engineering goals and advanced computing resources needed. One example is the report of the Snowmass 2013 Computing Frontier Working Group on Lattice Field Theory.1 Such analyses may provide additional useful information for understanding aggregate capability and capacity needs and expected trends in these needs, for understanding overall National Science Foundation (NSF) resource requirements, for prioritizing investments, and for aligning research program and supporting advanced computing investments. Such community-led efforts seem a natural fit for NSF.
_____________________
1 T. Blum, R.S. Van de Water, D. Holmgren, R. Brower, S. Catterall, N. Christ, A. Kronfeld, et al., Lattice field theory for the energy and intensity frontiers: Scientific goals and computing needs, Report of the Snowmass 2013 Computing Frontier working group on Lattice Field Theory, arXiv:1310.6087v1, submitted October 23, 2013.
7. For its final report, the committee will explore and seeks comment on whether wider collection and more frequent updating of requirements for advanced computing could be used to inform strategic planning, priority setting, and resource allocation; how these requirements might be used; and how they might best be developed, collected, and aggregated.
In 2009, the NSF-wide Advisory Committee for Cyberinfrastructure (ACCI) established six task forces to investigate long-term cyberinfrastructure issues with a focus on its major elements, including high-performance computing, campus bridging, grand challenges, data, and software. Their final reports in 20112 provide detailed descriptions of the state of the major elements of NSF’s advanced cyberinfrastructure ecosystem and recommendations for advancing them in support of research. New initiatives aligned with these recommendations have resulted in advances in the state of key elements of cyberinfrastructure, including software, data, hardware, and networking. At first glance, it is once again tempting to seek a structural approach similar to the one used in the ACCI task forces whereby one considers prioritizing investments for the major elements of the ecosystem, such as hardware, software, storage, etc. Such a structural approach could potentially lead to optimal solutions for each element by resolving the complex trade-offs that arise when these elements contend for resources.
However, none of these elements can be directly utilized by the science and engineering user community. In fact, scientists can effectively utilize infrastructure only when it is presented to them as an integrated whole encompassing appropriate hardware, software, data, networking, technical services, etc. Additionally, customizations to meet the requirements of workflows along broad thematic areas can further enhance utility to catalyze the next generation of scientific outcomes. In this approach, requirements can be used to understand the needed functional capabilities. The latter, in turn, could be used to inform how strategic investments should be made.
_____________________
2 See National Science Foundation, “ACCI—Task Forces,” http://www.nsf.gov/cise/aci/taskforces (accessed September 25, 2014).
ENHANCED ORGANIZATIONAL STABILITY AND FLEXIBILITY OF NSF-FUNDED ADVANCED COMPUTING CENTERS
Any funding and organizational structure must balance organizational stability and sustainability against responsiveness to technological change and customer needs. NSF has long supported leading-edge cyberinfrastructure via a series of solicitations and open competitions. Although this has stimulated intellectual competition and increased NSF’s financial leverage, it has also made deep and sustainable collaboration difficult among frequent competitors. Individual awardees, quite rationally, often focus more on maximizing their long-term probability of continued funding, rather than adapting and responding to community needs.
Frequent competitions can also make it more difficult for NSF-funded service providers to recruit and retain talented staff when the horizon for funding is only 2-5 years. This is especially true when the competition for information technology and computational science expertise with industry is so great. In contrast, longer horizons could also let NSF and its service providers evolve services and staffing in response to changing community needs and business partnerships. In turn, Major Research Equipment and Facilities Construction (MREFC) projects could coordinate and plan computing support and data analysis needs with NSF’s cyberinfrastructure providers. Longer-term funding horizons could also allow service providers to work more collaboratively with NSF on responses to community needs, encourage inter-organizational collaboration, and facilitate longer-term budget planning and staged equipment acquisitions across multiple sites.
8. The committee seeks comments on the tension between the benefits of competition and the need for continuity as well as alternative models that might more clearly delineate the distinction between performance review and accountability and organizational continuity and service capabilities.
ENHANCED STRATEGIC PLANNING AND INTERNAL COORDINATION
Despite its vital role in science and engineering, the committee observes that advanced computing receives relatively little attention in the current NSF strategic plan, and decision making about advanced computing is distributed across the Division for Advanced Cyberinfrastructure, other divisions and division programs, the Major Research Instrumentation Program, and individual research institutions. Both coordination and strategic decision making seem especially important in an era of growing demand and cost, and place a premium on shared solutions where possible.
Top-down mandates often prove ineffective, even when the coordination is very much needed, and reaching consensus through “grass-roots” efforts may be too slow. Both top-down and bottom-up processes require mechanisms for identifying detailed needs of directorates and their programs and for ensuring adequate community input; the committee will be exploring and seeks comment on ways this might be done.
9. The committee seeks comments on how NSF might best coordinate and set overall strategy for advanced computing-related activities and investments as well as the relative merits of both formal, top-down coordination and enhanced, bottom-up process.