CISE launches new funding opportunity: Principles and Practice of Scalable Systems (PPoSS)
January 17, 2020
CISE launches new funding opportunity: Principles and Practice of Scalable Systems (PPoSS); webinar scheduled for Jan. 27 at 1pm EST
Earlier this month, the National Science Foundation’s (NSF) Directorate for Computer and Information Science and Engineering (CISE) launched the Principles and Practice of Scale Systems (PPoSS) program, a directorate-wide effort aimed at developing the next generation of scalable systems and applications. The PPoSS program, with a planned investment of nearly $90 million over the next decade, builds on the successes of the Scalable Parallelism in the eXtreme (SPX) and eXploiting Parallelism and Scalability (XPS) programs, as well as multiple community visioning workshops and white papers. A webinar for prospective PPoSS principal investigators is scheduled for Monday, Jan. 27, 2020, at 1pm EST.
In Summer 2019, NSF/CISE funded a workshop that brought together researchers from academia, government, and industry to discuss future directions in parallel and distributed computing. With an underlying emphasis on sustaining scalable system performance in modern computing environments, the workshop surfaced a variety of challenges in systems design and implementation that have been exacerbated by the rapid evolution and proliferation of machine learning (ML) and artificial intelligence (AI) techniques. Achieving this will require coordinated progress across a number of computing disciplines.
“Given these community inputs, and on the heels of the successes of SPX and XPS, we are delighted to launch PPoSS this month,” said Erwin Gianchandani, NSF Acting Assistant Director for CISE. “This program will intentionally support a community of researchers that spans the entire hardware/software stack and will lay the groundwork for sustainable approaches for engineering highly performant, scalable, and robust computing applications for decades to come.”The principles developed through the resultant cross-disciplinary collaborations will lead to rigorous and reproducible artifacts for the design and implementation of large-scale systems and applications across the full hardware/software stack. At the same time, these principles and methodologies will provide guarantees on correctness and accuracy, robustness, and security and privacy.
The program anticipates funding approximately 15 Planning Grants and 4 Large awards pending the availability of funds and quality of proposals received. Planning Grants will provide up to $250,000 over one year, and Large awards will provide up to $5 million over five years.
Research topics that could be addressed in either Planning Grants or Large awards include but are not limited to:
§ Computer Architecture: addressing the challenges that arise when deploying accelerators for individual computations in extreme scale systems where multiple accelerators co-exist.
§ High-Performance Computing: developing principles of design and implementation to bestow applications with high performance and extreme scalability, while simultaneously optimizing their power footprints and permitting a broad range of resource usage behaviors that may diﬀer across components of the applications and phases of their workﬂows
§ Programming Languages and Compilers: understanding interoperability across applications and across devices in the context of heterogeneity, its semantics in the presence of extreme variations in abstractions, and how the semantics can be engineered within programming languages and compilers to obtain scalability across the full hardware/software stack.
§ Security and Privacy: developing extreme-scale algorithms that can address the security and privacy issues involved in emerging domains such as edge computing, conﬁdential cloud computing, and secure distributed computation.
§ Systems: reducing principles of large-scale system design that enable use of components that come from multiple, possibly untrusted third parties, yet also enable performance, portability, correctness, accuracy, and other desirable properties.
§ Theory and Algorithms: adapting and/or extending the extant theories of distributed, parallel, streaming, and sublinear algorithms to address challenges in developing computational models, providing fault tolerance, and the multi-user and constantly changing environment of modern large-scale systems.
Both the use of AI and ML methods and the interplay between program synthesis and AI and ML will drive the need for more performance and more parallelism in all the research thrusts.
The first submission deadline for Planning Grants is March 30, 2020. A subsequent submission deadline for both Planning Grants and Large grants is January 25, 2021. Please see the program solicitation for more details.
If you are interested in joining the webinar, please click here to register.
The U.S. National Science Foundation propels the nation forward by advancing fundamental research in all fields of science and engineering. NSF supports research and people by providing facilities, instruments and funding to support their ingenuity and sustain the U.S. as a global leader in research and innovation. With a fiscal year 2021 budget of $8.5 billion, NSF funds reach all 50 states through grants to nearly 2,000 colleges, universities and institutions. Each year, NSF receives more than 40,000 competitive proposals and makes about 11,000 new awards. Those awards include support for cooperative research with industry, Arctic and Antarctic research and operations, and U.S. participation in international scientific efforts.