Project Grant 2313023

Award Date 7/1/23
Completion Date 6/30/26
Dollars Obligated $533K
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Cambridge, MA 02139, USA
Similar Awards
This $266,667 Project Grant award from the National Science Foundation's Division of Computing and Communication Foundations supports research on improving the development process for hardware accelerators and their associated software. The project, titled "Collaborative Research: SHF: Medium: High-Performance, Verified Accelerator Programming", aims to extend the concept of end-to-end formal verification to cover hardware accelerators, specifically tensor processing units (TPUs),...
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $550,000 over 3 years to The Trustees of Princeton University to develop advanced techniques for formal verification of computer architectures. The key objectives are to: 1) Create architecture-driven abstractions, component interfaces, and invariants to enable modular functional verification of complex processors; 2) Leverage...
This $400,000 Project Grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research to improve the scalability and usability of formal hardware verification techniques for computer architectures. The key objectives are: Developing architecture-driven abstractions, component interfaces, and invariants to enable modular-refinement-based functional verification of complex processors. Leveraging...
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports the development of novel fuzzing techniques to improve the scalability and effectiveness of hardware security verification. The $196,120 award to Texas A&M Engineering Experiment Station (Tees) aims to orchestrate formal verification, symbolic execution, and static analysis methods to provide better guidance for hardware fuzzing and...
This $900,000 project grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop the VERITAS framework for formally verifying performance properties of network control algorithms. Led by the Massachusetts Institute of Technology, researchers will create a means to encode algorithms in first-order logic, specify hypotheses about performance, and test hypotheses through simulation in a customizable network model. Additionally, given...
This $387,341 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports the development of theory, algorithms, and prototype tools for extending auto-active verification techniques to cover security and privacy requirements expressed as hyperproperties. The research aims to transform computing practice by enabling mathematically precise specifications and machine-checked proofs of software system...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program award, with a total funding of $175,000, supports the development of novel verification methodologies to enhance software quality, safety, and security for safety-critical and security-critical applications such as self-driving cars and digital medical services. The project aims to develop verification techniques based on first-order assertions and auxiliary logical variables,...
The National Science Foundation (NSF) awarded a $865,209 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the Massachusetts Institute of Technology (MIT) on January 15, 2025. The grant supports the development of novel tools and techniques for proving the functional correctness of programmable networking hardware, with a focus on optimizations that improve performance through increased concurrency. The project aims to derive optimized,...
This three-year, $500,000 project grant from the National Science Foundation's Division of Computing and Communication Foundations, under the Computer and Information Science and Engineering program (CFDA 47.070), will support research to advance neural network verification techniques. The grantee, Stanford University, will partner with the Hebrew University of Jerusalem to pursue three goals: developing more scalable verification methods using abstraction and compositional reasoning;...
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...

This $533,000 Project Grant, awarded by the National Science Foundation (NSF) Office of Advanced Cyberinfrastructure under the Computer and Information Science and Engineering (CFDA 47.070) program, supports collaborative research by the Massachusetts Institute of Technology (MIT) to develop end-to-end formal verification techniques for hardware accelerators, specifically tensor processing units (TPUs).

The key objectives are to dramatically reduce the costs of developing and iterating on hardware accelerators while providing strong mathematical correctness guarantees. This will be achieved through formal verification across three main levels: a high-level source language with programmer-guided optimization, a lower-level C-like language with support for accelerator interfaces, and verified hardware models for processors and accelerators. The research aims to enable applications, such as machine learning systems, to provide rigorous privacy and correctness guarantees despite using complex performance optimizations.

Generated 4/2/24, 3:32 AM