Patents by Inventor Temitayo Fadelu

Temitayo Fadelu 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).

  • PREEMPTION IN A MACHINE LEARNING HARDWARE ACCELERATOR
    Publication number: 20230418677
    Abstract: The present disclosure describes a system and method for preempting a long-running process with a higher priority process in a machine learning system, such as a hardware accelerator. The machine learning hardware accelerator can be a multi-chip system including semiconductor chips that can be application-specific integrated circuits (ASIC) designed to perform machine learning operations. An ASIC is an integrated circuit (IC) that is customized for a particular use.
    Type: Application
    Filed: December 21, 2020
    Publication date: December 28, 2023
    Inventors: Temitayo Fadelu, Ravi Narayanaswami, JiHong Min, Dongdong Li, Suyog Gupta, Jason Jong Kyu Park
  • VIRTUALIZING EXTERNAL MEMORY AS LOCAL TO A MACHINE LEARNING ACCELERATOR
    Publication number: 20220044153
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for virtualizing external memory as local to a machine learning accelerator. One ambient computing system comprises: an ambient machine learning engine; a low-power CPU; and an SRAM that is shared among at least the ambient machine learning engine and the low-power CPU; wherein the ambient machine learning engine comprises virtual address logic to translate from virtual addresses generated by the ambient machine learning engine to physical addresses within the SRAM.
    Type: Application
    Filed: October 21, 2021
    Publication date: February 10, 2022
    Inventors: Lawrence J. Madar, III, Temitayo Fadelu, Harshit Khaitan, Ravi Narayanaswami
  • Virtualizing external memory as local to a machine learning accelerator
    Patent number: 11176493
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for virtualizing external memory as local to a machine learning accelerator. One ambient computing system comprises: an ambient machine learning engine; a low-power CPU; and an SRAM that is shared among at least the ambient machine learning engine and the low-power CPU; wherein the ambient machine learning engine comprises virtual address logic to translate from virtual addresses generated by the ambient machine learning engine to physical addresses within the SRAM.
    Type: Grant
    Filed: April 29, 2019
    Date of Patent: November 16, 2021
    Assignee: Google LLC
    Inventors: Lawrence J. Madar, III, Temitayo Fadelu, Harshit Khaitan, Ravi Narayanaswami
  • VIRTUALIZING EXTERNAL MEMORY AS LOCAL TO A MACHINE LEARNING ACCELERATOR
    Publication number: 20200342350
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for virtualizing external memory as local to a machine learning accelerator. One ambient computing system comprises: an ambient machine learning engine; a low-power CPU; and an SRAM that is shared among at least the ambient machine learning engine and the low-power CPU; wherein the ambient machine learning engine comprises virtual address logic to translate from virtual addresses generated by the ambient machine learning engine to physical addresses within the SRAM.
    Type: Application
    Filed: April 29, 2019
    Publication date: October 29, 2020
    Inventors: Lawrence J. Madar, III, Temitayo Fadelu, Harshit Khaitan, Ravi Narayanaswami