Project Grant 2411386

Award Date 10/1/24
Completion Date 9/30/27
Dollars Obligated $300K
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Chicago, IL 60637, USA
Similar Awards
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $300,000 to the Rochester Institute of Technology (RIT) to develop innovative checkpointing technologies for scientific applications. The VLCC-STATES project aims to streamline the use of checkpointing patterns, which are critical capabilities enabling resilience, reproducibility, and performance optimization for a wide range of scientific...
This Project Grant award of $224,984 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research at the College of William & Mary in Williamsburg, Virginia focused on developing automated checkpoint and restart capabilities for deep learning applications running on high-performance computing (HPC) clusters. The key objectives of this 3-year project are to: 1) exploit properties of deep neural network models to...
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will fund research at the University of Georgia Research Foundation, Inc. (UGA Research Foundation) to develop improved checkpoint and restart capabilities for deep learning applications running on high-performance computing (HPC) clusters. The overarching goal of the $150,000 award is to enable more efficient, resilient, and flexible execution of...
This $225,000 Project Grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program supports the CROPDL research project at Florida State University (FSU). The key objectives of CROPDL are to develop efficient application-level checkpoint and restart capabilities to enable more resilient, faster, and higher resource-utilized deep learning training on shared high-performance computing (HPC) clusters. The project aims to...
This $500,000 Project Grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program will support the development of scalable software to realize "data polymorphism," a novel paradigm that enables fast and adaptable scientific data retrieval with tailored error control. The key product deliverables include: A generic framework to abstract the generation of progressive representations for scientific data,...
This $300,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop strategies for efficiently leveraging idle resources in high-performance computing (HPC) systems to accelerate large-scale artificial intelligence (AI) workloads. The key objectives are to: 1) analyze patterns of idle resources in HPC environments, 2) develop methods to safely and rapidly harvest these idle resources, and...
The University of Chicago received a $1.3 million project grant award from the National Science Foundation Office of Advanced Cyberinfrastructure to develop a high-performance storage infrastructure for activity and log workloads under the Computer and Information Science and Engineering program (CFDA 47.070). The four-year award running from June 2021 through May 2025 will support the collaborative research project "Frameworks: Collaborative Research: Chronolog: A High-Performance...
This $360,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to improve the reliability and performance of parallelizing compilers by automatically verifying that translated parallel code has the same functionality as the original sequential code. The project will involve precise modeling of sequential and parallel program behavior, developing a verification tool, and mathematically proving the...
This $400,000 project grant awarded by the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) is developing tools to help scientific software developers easily find and fix defects in their code. The project is taking a novel modular approach to program specification and verification, using symbolic execution and model checking techniques to verify that scientific software packages adhere to their specifications. The University of...
This Project Grant from the National Science Foundation's $300,000 Computer and Information Science and Engineering program (CFDA 47.070) supports collaborative research on learning fault tolerance at scale from January 1, 2022 to December 31, 2024. Vanderbilt University is the primary awardee and will receive $300,000 to advance the development of state-of-the-art fault tolerance algorithms and deepen theoretical understanding of the problem. The University of Kansas Center for Research Inc....

This $300,000 Project Grant awarded by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports the "Versioned Lineage-Driven Checkpointing of Composable States (VLCC-States)" research project.

The project aims to streamline the development and use of checkpointing patterns for scientific applications, which simplify and improve reusability of integration efforts across different communities, reduce development costs, and enable flexible customization for optimal performance and scalability. The key technical innovations include composable providers of intermediate states, multi-level co-optimized caching and prefetching techniques, and specialized checkpointing tools for large AI models. The University of Chicago, the award recipient, will engage industry and national research lab partners to co-design, tune capabilities, and evaluate the VLCC-States implementation. The project will also undertake educational and broadening participation activities to improve community awareness of scientific data management challenges.

Generated 1/28/25, 9:39 AM