Patents by Inventor Kyrylo PERELYGIN

Kyrylo PERELYGIN 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).

  • Publication number: 20220413945
    Abstract: Apparatuses, systems, and techniques to implement a barrier operation. In at least one embodiment, a memory barrier operation causes accesses to memory by a plurality of groups of threads to occur in an order indicated by the memory barrier operation.
    Type: Application
    Filed: July 2, 2021
    Publication date: December 29, 2022
    Inventors: Piotr Ciolkosz, Kyrylo Perelygin, Harold Carter Edwards, Wesley Maxey
  • Publication number: 20220365750
    Abstract: Apparatuses, systems, and techniques to generate numbers. In at least one embodiment, one or more circuits are to cause one or more thirty-two bit floating point numbers to be truncated to generate one or more rounded numbers based, at least in part, on one or more rounding attributes.
    Type: Application
    Filed: May 16, 2022
    Publication date: November 17, 2022
    Inventors: Girish Bhaskarrao Bharambe, Kyrylo Perelygin, Advait Soman, Andrew Robert Kerr, Farhana Schuchman, Jaydeep Marathe, Stephen Anthony Bernard Jones, Ronny Meir Krashinsky, Jaewook Shin
  • Patent number: 11080111
    Abstract: Apparatuses, systems, and techniques to execute programs in a single hardware context on a graphics processing unit (GPU). In at least one embodiment, resource management patches expressed in library or executable code are applied to one or more kernels to ensure execution in a shared context on a GPU.
    Type: Grant
    Filed: February 24, 2020
    Date of Patent: August 3, 2021
    Assignee: NVIDIA Corporation
    Inventors: Kyrylo Perelygin, Cory Perry, Ze Long
  • Patent number: 9886736
    Abstract: A method for handling parallel processing clients associated with a server in a GPU, the method comprising: receiving a failure indication for at least client running a thread in the GPU; determining threads in the GPU associated with the failing client; exiting threads in the GPU associated with the failing client; and continuing to execute remaining threads in the GPU for other clients running threads in the GPU.
    Type: Grant
    Filed: September 9, 2014
    Date of Patent: February 6, 2018
    Assignee: NVIDIA CORPORATION
    Inventors: Kyrylo Perelygin, Vivek Kini, Vyas Venkataraman
  • Publication number: 20150206272
    Abstract: A method for handling parallel processing clients associated with a server in a GPU, the method comprising: receiving a failure indication for at least client running a thread in the GPU; determining threads in the GPU associated with the failing client; exiting threads in the GPU associated with the failing client; and continuing to execute remaining threads in the GPU for other clients running threads in the GPU.
    Type: Application
    Filed: September 9, 2014
    Publication date: July 23, 2015
    Inventors: Kyrylo PERELYGIN, Vivek KINI, Vyas VENKATARAMAN