Project Grant 2217016

Award Date 10/1/22
Completion Date 9/30/27
Dollars Obligated $550K
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Pittsburgh, PA 15213, USA
Similar Awards
This National Science Foundation project grant of $549,790 will fund the development of a full-system computing stack to support sparse computations through September 2027. Under the Computer and Information Science and Engineering program (CFDA 47.070), researchers at Washington University in University City, Missouri will create domain-specific languages, an integrated compiler and scheduler, specialized hardware architectures and high-performance computing systems. Their work aims to...
This Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will fund research by the University of Central Florida to design a transformative computing framework for a wide range of irregular and sparse applications. The key objectives are to: (1) abstract sparse computations using novel graph representations, and (2) utilize graph theory to construct regular and predictive data and computation patterns...
This Project Grant from the National Science Foundation's $125,000 Computer and Information Science and Engineering program will fund the development of optimized sparse tensor network algorithms and specialized accelerator architectures for heterogeneous computing systems. Awarded to North Carolina State University on October 1, 2022 for a one-year period ending September 30, 2023, the grant supports preliminary research to address challenges in sparse tensor network computations through four...
This $125,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program (CFDA #47.070) supports research at the University of California, Merced on developing optimized sparse tensor network algorithms and specialized accelerator architectures. The one-year award beginning October 1, 2022 aims to address challenges in high-dimensional data computation and analytics using tensor representations by exploring memory heterogeneity-aware data...
Cornell University received a three-year Project Grant award of $598,449 from the National Science Foundation Division of Computing and Communication Foundations under the Computer and Information Science and Engineering federal grant program (CFDA 47.070). The award will support research and development of specialized computer chips and software programs to accelerate artificial intelligence workloads using fine-grained unstructured sparsity and mixed precision techniques. Cornell University...
The National Science Foundation (NSF) awarded a $406,004 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to Carnegie Mellon University (CMU). The goal of this 4-year project is to develop new resource allocation policies that enable efficient and timely training of machine learning models by leveraging parallelizable computing resources. The research will focus on modeling the unique characteristics of machine learning training workloads, such as...
This $1,139,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop innovative dataflow processors that can enhance the energy efficiency and security of edge computing systems. The key technical innovations include a parallel dataflow representation of programs and a simplified, scalable spatial architecture for dataflow processors. The research will be conducted by a diverse team at...
This Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $564,958 to Carnegie Mellon University from December 1, 2024 to November 30, 2027. The project aims to advance fundamental knowledge and innovate resource allocation algorithms to address the challenges posed by high variability and uncertainty in both demand and service in modern computing systems, especially those supporting machine learning...
This Project Grant award of $600,000 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research at the University of Central Florida (UCF) to develop software-hardware solutions that enable efficient inference of large AI foundation models on resource-limited computer systems. The key research thrusts include: 1) designing a sparsity-aware scheduling system to address data transfer bottlenecks between GPUs and...
The National Science Foundation awarded The Ohio State University a $110,335 Project Grant under the Computer and Information Science and Engineering program (CFDA 47.070) to conduct research on deep sparse models from August 1, 2022 to June 30, 2023. Specifically, the university will advance the theoretical understanding of deep convolutional neural networks through analyzing and developing algorithms for multi-layered convolutional sparse models. Researchers will derive provable and...

This five-year, $550,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop a full-stack computing architecture for sparse computations. The awardee, Carnegie Mellon University, will receive funding from October 2022 through September 2027.

Sparse computations process unstructured, irregular data and are common in domains like deep learning, data analytics, and scientific computing. However, current computing systems are inefficient for sparse workloads due to challenges across software and hardware stacks. Through this award, Carnegie Mellon University will develop domain-specific languages, a tightly integrated compiler and scheduler, and specialized processor architectures. These innovations will be unified through a novel sparse intermediate representation to optimize sparse algorithms, data structures, and parallel execution. The full-stack approach is intended to achieve significant performance, scalability, and efficiency gains beyond single-layer solutions. Outcomes will be evaluated using diverse sparse applications at large scales up to hundreds of GPUs or tens of specialized processors.

Generated 1/6/24, 10:13 PM