OAC: OAC Core Research (OAC Core)

Office of Advanced Cyberinfrastructure Core Research Program (OAC Core)

PROGRAM DESCRIPTION

The Office of Advanced Cyberinfrastructure (OAC) supports translational research and education activities in all aspects of advanced cyberinfrastructure (CI) that lead to deployable, scalable, and sustainable systems capable of transforming science and engineering research and education. Advanced CI includes the spectrum of computational, data, software, networking, and security resources, tools, and services, along with the computational and data skills and expertise, that individually and collectively enable the conduct of science and engineering research and education. As part of its portfolio of investments, OAC supports research on advanced CI to address new CI frontiers for discovery leading to major innovations, and also supports development and deployment processes as well as expert services necessary for realizing the research CI that is critical to the advancement of science and engineering research and education.

This program aims to address the CI research challenges that significantly impact the future capabilities of advanced research CI by engaging a diverse community of computer and computational science and engineering researchers, scientists, faculty, and students. The context is emerging translational research challenges as highlighted by various recent reports. For example, the National Strategic Computing Initiative (NSCI) states, “High-performance computing (HPC) is essential to the Nation’s global economic competitiveness, scientific discovery, and security.” Likewise, the Federal Big Data Research and Development Strategic Plan states,  “A national Big Data innovation ecosystem is essential to enabling knowledge discovery from and confident action informed by the vast resource of new and diverse datasets that are rapidly becoming available in nearly every aspect of life.” The 2017 National Academies’ report on Future Directions for NSF Advanced Computing Infrastructure to Support U.S. Science and Engineering in 2017-2020 recognizes that “large-scale simulation and the accumulation and analysis of massive amounts of data are revolutionizing many areas  of science and engineering research.” And the 2019 NSF document entitled Transforming Science Through Cyberinfrastructure: NSF’s Blueprint for a National Cyberinfrastructure Ecosystem for Science and Engineering in the 21st Century aims to “recognize and support the translational research continuum, from (i) catalyzing core cyberinfrastructure innovations essential to address disruptive changes in applications and technologies, through (ii) fostering the development of community tools and frameworks, to (iii) enabling the deployment and operation of sustainable production-quality cyberinfrastructure services.”

The OAC Core Research program seeks innovative proposals for translational research on the design, development, deployment, experimentation, and application of advanced research CI. OAC Core Research investments are further characterized by one or more of the following key attributes:

• Multi-disciplinary: leveraging techniques from multiple disciplines and may require collaboration among investigators from relevant disciplines/sub-disciplines (e.g., computer science and physics; operating systems and computer architecture, etc.);

• Extreme-scale: exploring pathways to leading-edge, leadership-scale research CI, from architecture to algorithms to models;

• Driven by science and engineering research: exploring scalable models, algorithms, techniques, and tools needed for fundamentally new science and engineering advances;

• An end-to-end solution: pursuing novel integrated systems that support complete research workflows; and

• Deployable as robust research CI: exploring seamless pathways for integration into robust CI systems or operational scientific and engineering research applications.

This research program seeks to broaden participation by a wide range of science and engineering disciplines and institutions, and by harnessing the capabilities of larger segments of diverse underrepresented groups. Proposals from, and in partnership with, the aforementioned communities are especially encouraged. For a multi-disciplinary project requiring CI as well as discipline-specific research expertise, the proposal must include at least one funded or unfunded collaborator with expertise relevant to the targeted research discipline.

The OAC Core Research program supports and sustains advancements in multiple disciplinary areas spanning computer as well as computational and data-driven science and engineering with advanced CI thrusts. OAC projects must address new CI frontiers for discovery and lead to major innovations. The OAC Core Research areas include architectures and middleware for extreme-scale systems, scalable algorithms and applications, and the advanced CI ecosystem more broadly. Examples of research topics supported by OAC include, but are not limited to, the following:

• Research in architecture for extreme-scale systems may include design, benchmarking, and analysis of extreme-scale systems for performance, programmability, and usability; storage, networks, and input/output (I/O); data centers and extreme-scale networked systems; and next-generation architectures;

• Research in middleware may include resource management, monitoring, fault tolerance, and cybersecurity;

• Research in scalable algorithms and applications shall be driven by science and engineering applications and may include numerical and high-performance scientific computing methods; data, software, and visualization approaches; and modeling and simulation capabilities; and

• Research in the advanced CI ecosystem may include research in programming languages, libraries, and related environments; performance tuning and interoperability tools; shared CI, e.g., platforms and gateways; and sociotechnical aspects relevant to the advanced CI ecosystem, e.g., best practices, standards, policies, and virtual organizations.

Such translational CI research should be aimed towards realizing next-generation, extreme-scale research CI. Research in next-generation hardware and software systems should aim to increase coherence between the technology base used for modeling and simulation and that used for data analytics, as articulated in the NSCI, allowing dynamic interaction between analysis and simulation. OAC Core Research should also aim to enable an enduring national advanced CI ecosystem allowing dynamic interaction of computation with other elements of CI, such as scientific instruments, large data repositories, and mobile devices; integrating security and privacy as foundational elements; and significantly enhancing productivity in the development and use of parallel HPC applications.