Project Grant DESC0021515

The National Science Foundation (NSF) awarded a $175,000 Computer and Information Science and Engineering (CISE) Program grant to The Trustees of the Stevens Institute of Technology to develop a compressor-assisted collective communication framework for large-scale deep learning on GPU-based systems. The two-year project aims to address challenges with the communication overhead of training massive deep learning models by investigating efficient lossy compression techniques for gradient data and...

This $200,000 federal Project Grant award from the National Science Foundation's (NSF) Mathematical and Physical Sciences program (CFDA 47.049) supports research to develop advanced analog circuits and systems for dense, in-situ spectrum monitoring. The key products and services to be delivered include: (1) Ultra-efficient, single-shot analog cross-correlators capable of rapidly computing cross-correlations between input signals and template waveforms. This enables low-latency spectrum sensing...

Distributed Spectrum Inc. was awarded a $251,904 Project Grant from the National Science Foundation on January 1, 2022 to develop ultra-low-cost distributed spectrum monitoring technologies. The award is part of the NSF's Technology, Innovation, and Partnerships program (CFDA 47.084), which seeks to advance science and engineering research leading to breakthrough technologies and solutions to national challenges. Under this Phase I Small Business Innovation Research award expiring December 31,...

This National Science Foundation (NSF) award under the Computer and Information Science and Engineering (CFDA 47.070) program provides $554,699 to Georgia Tech Research Corporation (Georgia Tech) to develop a distributed FPGA (field-programmable gate array) system for real-time fraud detection on large-scale dynamic financial activity graphs. The project aims to achieve microsecond-level latency in detecting fraudulent transactions using graph neural networks (GNNs), which is a significant...

This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering program (CFDA 47.070) supports a collaborative research effort to accelerate the execution of large-scale graph problems on distributed computing systems. The $2,656,268 award, active from August 1, 2023 to July 31, 2028, aims to develop new algorithms, software frameworks, and hardware accelerators to efficiently process large graph datasets in domains like computational...

This Project Grant award from the National Science Foundation (NSF) under the Technology, Innovation, and Partnerships (TIP) program (CFDA 47.084) provides $275,000 to Axpro Semi, a small business located in Sunnyvale, CA. The funding supports the development of a RISC-V and FPGA pipeline-coupled heterogeneous compute microprocessor architecture and emulation software tools. The goal is to dramatically improve CPU performance and enable more affordable, energy-efficient, and scalable computing...

This $300,000 Project Grant from the National Science Foundation's Technology, Innovation, and Partnerships program will fund the Massachusetts Institute of Technology's development of an open-source ecosystem for OpenCilk, a task-parallel programming platform for multicore computers. The goal is to establish an academic user and contributor base for OpenCilk by focusing outbound networking, inbound engagement, and peer collaboration strategies on academic researchers, educators, and students....

This Project Grant award from the National Science Foundation's Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will fund research to develop new compiler techniques for managing scale in fully homomorphic encryption (FHE) programs. The $218,301 award, effective October 1, 2024 through September 30, 2027, supports three research tasks: 1) a new scale management solution to minimize FHE program latency, 2) an automatic bootstrapping management technique to optimize...

This Project Grant award from the National Science Foundation (NSF) Engineering program (CFDA 47.041) provides $400,000 over 3 years to the University of California, Berkeley to develop novel intelligent large-scale multi-antenna array architectures operating at 140 GHz. The key products and services to be delivered include: Analytical and behavioral modeling of non-idealities in large scalable antenna arrays Design of reconfigurable D-band (140 GHz) front-ends with performance tuning...

This National Science Foundation (NSF) CAREER award (CFDA 47.041 - Engineering) provides $550,000 over 5 years to Florida A&M University (FAMU) to develop a reconfigurable real-time radio frequency (RF) analog co-processor in a compact, low-cost form factor. The project aims to: Design an RF analog co-processor that can perform configurable mathematical operations directly on electromagnetic waveforms, reducing computational load in digital signal processing. Develop a film with tunable...