Patents by Inventor Gregory M. Stitt

Gregory M. Stitt has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Architecture-independent approximation discovery
    Patent number: 11521076
    Abstract: Systems and methods for discovering approximations for compilers to apply through genetic programming and deterministic symbolic regression heuristics are provided. A method for discovering approximations for compilers and runtime optimization can include profiling a program to identify performance critical functions, determining appropriate candidates for approximation and developing application and architecture specific approximations through machine learning techniques, genetic programming, and deterministic heuristics. Such approximations can target any optimization goal, with a primary emphasis on parallelism, or can provide a set of Pareto-optimal tradeoffs.
    Type: Grant
    Filed: June 29, 2018
    Date of Patent: December 6, 2022
    Assignee: UNIVERSITY OF FLORIDA RESEARCH FOUNDATION, INCORPORATED
    Inventors: Gregory M. Stitt, David M. Campbell, Raz Aloni, Thomas Vaseliou, Jayson Salkey
  • Overlay architecture for programming FPGAs
    Patent number: 10516396
    Abstract: An overlay architecture and an associated method that uses datapath merging to provide minimal-overhead support for multiple source netlists, and optionally provides an adjustable amount of flexibility through a secondary interconnect network is disclosed.
    Type: Grant
    Filed: April 28, 2017
    Date of Patent: December 24, 2019
    Assignee: University of Florida Research Foundation, Incorporated
    Inventors: James R. Coole, Gregory M. Stitt
  • ARCHITECTURE-INDEPENDENT APPROXIMATION DISCOVERY
    Publication number: 20190005390
    Abstract: Systems and methods for discovering approximations for compilers to apply through genetic programming and deterministic symbolic regression heuristics are provided. A method for discovering approximations for compilers and runtime optimization can include profiling a program to identify performance critical functions, determining appropriate candidates for approximation and developing application and architecture specific approximations through machine learning techniques, genetic programming, and deterministic heuristics. Such approximations can target any optimization goal, with a primary emphasis on parallelism, or can provide a set of Pareto-optimal tradeoffs.
    Type: Application
    Filed: June 29, 2018
    Publication date: January 3, 2019
    Inventors: Gregory M. Stitt, David M. Campbell, Raz Aloni, Thomas Vaseliou, Jayson Salkey
  • OVERLAY ARCHITECTURE FOR PROGRAMMING FPGAS
    Publication number: 20170317678
    Abstract: An overlay architecture and an associated method that uses datapath merging to provide minimal-overhead support for multiple source netlists, and optionally provides an adjustable amount of flexibility through a secondary interconnect network is disclosed.
    Type: Application
    Filed: April 28, 2017
    Publication date: November 2, 2017
    Applicant: University of Florida Research Foundation, Inc.
    Inventors: James R. Coole, Gregory M. Stitt