Patents by Inventor MONYCKY VASCONCELOS FRAZAO

MONYCKY VASCONCELOS FRAZAO 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).

  • System and method for processing convolutions on crossbar-based neural network accelerators for increased inference throughput
    Patent number: 12254395
    Abstract: Systems and methods are provided to improve traditional chip processing. Using crossbar computations, the convolution layer can be flattened into vectors, and the vectors can be grouped into a matrix where each row or column is a flattened filter. Each submatrix of the input corresponding to a position of a convolution window is also flattened into a vector. The convolution is computed as the dot product of each input vector and the filter matrix. Using intra-crossbar computations, the unused space of the crossbars is used to store replicas of the filters matrices and the unused space in XIN is used to store more elements of the input. In inter-crossbar computations, the unused crossbars are used to store replicas of the filters matrices and the unused XINs are used to store more elements of the input. Then, the method performs multiple convolution iterations in a single step.
    Type: Grant
    Filed: September 21, 2020
    Date of Patent: March 18, 2025
    Assignee: Hewlett Packard Enterprise Development LP
    Inventors: Glaucimar Da Silva Aguiar, Francisco Plínio Oliveira Silveira, Eun Sub Lee, Rodrigo Jose Da Rosa Antunes, Joaquim Gomes Da Costa Eulalio De Souza, Martin Foltin, Jefferson Rodrigo Alves Cavalcante, Lucas Leite, Arthur Carvalho Walraven Da Cunha, Monycky Vasconcelos Frazao, Alex Ferreira Ramires Trajano
  • SYSTEM AND METHOD FOR PROCESSING CONVOLUTIONS ON CROSSBAR-BASED NEURAL NETWORK ACCELERATORS FOR INCREASED INFERENCE THROUGHPUT
    Publication number: 20220092393
    Abstract: Systems and methods are provided to improve traditional chip processing. Using crossbar computations, the convolution layer can be flattened into vectors, and the vectors can be grouped into a matrix where each row or column is a flattened filter. Each submatrix of the input corresponding to a position of a convolution window is also flattened into a vector. The convolution is computed as the dot product of each input vector and the filter matrix. Using intra-crossbar computations, the unused space of the crossbars is used to store replicas of the filters matrices and the unused space in XIN is used to store more elements of the input. In inter-crossbar computations, the unused crossbars are used to store replicas of the filters matrices and the unused XINs are used to store more elements of the input. Then, the method performs multiple convolution iterations in a single step.
    Type: Application
    Filed: September 21, 2020
    Publication date: March 24, 2022
    Inventors: GLAUCIMAR DA SIKVA AGUIAR, FRANCISCO PLÍNIO OLIVEIRA SILVEIRA, EUN SUB LEE, RODRIGO JOSE DA ROSA ANTUNES, JOAQUIM GOMES DA COSTA EULALIO DE SOUZA, MARTIN FOLTIN, JEFFERSON RODRIGO ALVES CAVALCANTE, LUCAS LEITE, ARTHUR CARVALHO WALRAVEN DA CUNHA, MONYCKY VASCONCELOS FRAZAO, ALEX FERREIRA RAMIRES TRAJANO