×

Dynamic configuration of processing modules in a network communications processor architecture

  • US 9,444,757 B2
  • Filed: 07/27/2011
  • Issued: 09/13/2016
  • Est. Priority Date: 04/27/2009
  • Status: Expired due to Fees
First Claim
Patent Images

1. A method of updating configuration data of a network computer processor implemented in an integrated circuit chip, the network computer processor having a control processor, one or more hardware accelerators, and at least one shared memory shared between the control processor and one or more hardware accelerators, the method comprising:

  • writing, by the control processor of the network computer processor, updated configuration data to the at least one shared memory;

    sending, by the control processor, a configuration update request to one or more of the hardware accelerators, wherein the configuration update request corresponds to updated configuration data stored in the at least one share memory;

    determining whether the configuration update request corresponds to settings of a given one of the hardware accelerators;

    when the configuration update request corresponds to settings of a given one of the hardware accelerators;

    updating, by a destination accelerator, one or more register values corresponding to configuration settings of the accelerator with the corresponding updated configuration data of the configuration operations;

    otherwise, when the configuration update request corresponds to configuration data stored in the at least one shared memory;

    performing, by a combination of multiple parallel processing operations in the at least one shared memory, a coherent memory update operation corresponding to the configuration data stored in the at least one shared memory; and

    updating one or more task templates of the network computer processor stored in the at least one shared memory, each task template corresponding to a virtual pipeline of the network computer processor, the virtual pipeline defining a processing order of a task through one or more of the hardware accelerators.

View all claims
  • 5 Assignments
Timeline View
Assignment View
    ×
    ×