Patents by Inventor Aoxiang Fan

Aoxiang Fan 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).

  • Memory Allocation Method and Apparatus for Neural Network
    Publication number: 20250004839
    Abstract: A memory allocation method for a neural network includes determining information about N memory blocks, sorting the N memory blocks in descending order based on sizes of the N memory blocks, allocating a first memory block to the neural network, to perform an operation for a first node set in the neural network, determining whether a memory block in an allocated set is reusable for an nth memory block, where the allocated set includes a memory block that has been allocated to the neural network, if the memory block in the allocated set is reusable for the nth memory block, allocating, to the neural network, the memory block to perform an operation for an nth node set in the neural network, then updating the allocated set, and sequentially performing the foregoing determining from n=2 to n=N based on the sort sequence.
    Type: Application
    Filed: July 3, 2024
    Publication date: January 2, 2025
    Inventors: Lihua Huang, Hao Ding, Aoxiang Fan
  • Memory allocation method and apparatus for neural network
    Patent number: 12039371
    Abstract: A memory allocation method for a neural network includes determining information about N memory blocks, sorting the N memory blocks in descending order based on sizes of the N memory blocks, allocating a first memory block to the neural network, to perform an operation for a first node set in the neural network, determining whether a memory block in an allocated set is reusable for an nth memory block, where the allocated set includes a memory block that has been allocated to the neural network, if the memory block in the allocated set is reusable for the nth memory block, allocating, to the neural network, the memory block to perform an operation for an nth node set in the neural network, then updating the allocated set, and sequentially performing the foregoing determining from n=2 to n=N based on the sort sequence.
    Type: Grant
    Filed: December 4, 2020
    Date of Patent: July 16, 2024
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Lihua Huang, Hao Ding, Aoxiang Fan
  • Memory Allocation Method and Apparatus for Neural Network
    Publication number: 20210089355
    Abstract: A memory allocation method for a neural network includes determining information about N memory blocks, sorting the N memory blocks in descending order based on sizes of the N memory blocks, allocating a first memory block to the neural network, to perform an operation for a first node set in the neural network, determining whether a memory block in an allocated set is reusable for an nth memory block, where the allocated set includes a memory block that has been allocated to the neural network, if the memory block in the allocated set is reusable for the nth memory block, allocating, to the neural network, the memory block to perform an operation for an nth node set in the neural network, then updating the allocated set, and sequentially performing the foregoing determining from n=2 to n=N based on the sort sequence.
    Type: Application
    Filed: December 4, 2020
    Publication date: March 25, 2021
    Inventors: Lihua Huang, Hao Ding, Aoxiang Fan