Project Grant 2621699
- The National Science Foundation Division of Information and Intelligent Systems awarded the Trustees of Boston University $394,792 on January 1, 2027, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop a cross-layer co-design framework for stable mixed-precision acceleration in computing hardware and software. The project addresses numerical precision tradeoffs in high-performance computing workloads including physical artificial intelligence applications...
- The National Science Foundation Division of Computer and Network Systems awarded Trustees of Dartmouth College $498,819 on August 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop theoretically grounded, computationally efficient methods for safe multi-task learning and control on resource-constrained autonomous systems. The project integrates meta-learning, adaptive control, model predictive control (MPC), and embedded optimization to enable...
- The National Science Foundation Division of Electrical, Communications and Cyber Systems awarded Trustees of Dartmouth College $485,757 on October 15, 2026, under the Engineering program (CFDA 47.041) to develop a high-throughput semiconductor device platform accelerating material-process-device co-design through automated experimentation, machine learning, and electrostatic modeling. The project combines automated experiments with physics-informed machine learning to efficiently explore large...
- The Trustees of Dartmouth College received a $440,000 project grant award from the National Science Foundation Division of Electrical, Communications and Cyber Systems to develop a new type of artificial intelligence that requires no more power to operate than what is available from a self-powered sensor. The goal of the research is to design, implement, and evaluate an analog long short-term memory that is 16 times more power efficient than the state-of-the-art. This will be achieved through...
- The National Science Foundation (NSF) awarded a $327,311 Project Grant under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) to Trustees of Dartmouth College to conduct collaborative research on connections between optimization methods and property testing for processing large data sets and developing accurate predictive models. The three-year project, which began on April 1, 2024, aims to discover mathematical relationships between sublinear...
- The Trustees of Dartmouth College were awarded a $461,611 Project Grant from the National Science Foundation Office of Advanced Cyberinfrastructure to support research activities under the Computer and Information Science and Engineering federal grant program. This four-year award provides funding from September 2021 through September 2025 for the COLLABORATIVE RESEARCH project titled "FRAMEWORKS: CONVERGENCE OF BAYESIAN INVERSE METHODS AND SCIENTIFIC MACHINE LEARNING IN EARTH SYSTEM MODELS...
- The National Science Foundation (NSF) has awarded a $299,999 Project Grant to the College of William & Mary under the Computer and Information Science and Engineering (CFDA 47.070) program. The grant, titled "COLLABORATIVE RESEARCH: CNS CORE: SMALL: A COMPILATION SYSTEM FOR MAPPING DEEP LEARNING MODELS TO TENSORIZED INSTRUCTIONS (DELITE)," will fund research to develop a compilation system that can optimize deep neural network (DNN) workloads for emerging tensorized instruction...
- This Project Grant award of $450,000 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop novel approaches to electronic design automation (EDA) for creating high-performance and efficient computer hardware. The research introduces a strategy that combines formal techniques with learning-based optimization to enable differentiable hardware synthesis, particularly suited for heterogeneous computing. This new...
- The National Science Foundation Division of Information and Intelligent Systems awarded Regents of the University of Michigan $800,000 on September 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop a neuro-symbolic framework for hardware-software co-design of specialized computing accelerators. The project combines artificial intelligence pattern-finding methods with mathematical proof techniques to explore large design spaces for accelerator...
- The National Science Foundation Division of Computing and Communication Foundations awarded Northeastern University $599,921 on January 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop hardware-algorithm co-design approaches that enhance the reliability, efficiency, and sustainability of deep neural networks deployed in safety-critical and life-critical applications. The project addresses failures and design bugs observed during AI system...
The National Science Foundation Division of Information and Intelligent Systems awarded Trustees of Dartmouth College $405,886 on January 1, 2027, for collaborative research on scalable cross-layer co-design for stable mixed-precision acceleration under the Computer and Information Science and Engineering program (CFDA 47.070). The project, performed in Hanover, New Hampshire through December 31, 2029, develops a unified high-level synthesis framework that combines numerical precision analysis and control theory to design stable mixed-precision custom accelerator hardware and optimized code. The framework addresses numerical stability challenges in reduced-precision computing across energy-intensive workloads including real-time robot control, large-scale neural network training, power grid management, and quantum physics simulation. Specific deliverables include precision-aware high-level synthesis for hardware design with resource allocation, architecture-aware vectorized code generation for CPUs and GPUs, and extension of the framework to nondeterministic iterative algorithms that dominate physical artificial intelligence applications. The research systematically interfaces numerical analysis and control theory with hardware-software co-design to provide provable stability guarantees while improving performance and energy efficiency.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $405.9k | 7/30/26 |