中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.013 seconds)

    Network processor with command-template packet modification engine
    4.
    发明授权
    Network processor with command-template packet modification engine 有权

    公开(公告)号：US12113881B2

    公开(公告)日：2024-10-08

    申请号：US17485069

    申请日：2021-09-24

    Applicant: Intel Corporation

    Inventor： Weiqiang Ma ,  Atul Kwatra ,  Stephen T. Palermo

    IPC: H04L69/18 ,  H04L69/08

    CPC classification number: H04L69/18 ,  H04L69/08

    Abstract: Various approaches for the packet processing, and the use of templates for generating modification commands for packet processing, are discussed herein. In an example, operations performed by network packet processing circuitry include: obtaining a stream of packets; obtaining a packet modification template that provides at least one command to insert content within the packets and change the packets according to an output format of a network protocol; receiving parameters to modify the packet modification template; and applying the packet modification template to modify the packets. In further examples, application of the packet modification template is performed using multiple processing components arranged in parallel groups of serial pipelines, each of the serial pipelines applying a portion of the packet modification template within at least a first stage and a second stage in each of the serial pipelines.

    Hierarchical reinforcement learning algorithm for NFV server power management
    5.
    发明授权
    Hierarchical reinforcement learning algorithm for NFV server power management 有权

    公开(公告)号：US12001932B2

    公开(公告)日：2024-06-04

    申请号：US16939237

    申请日：2020-07-27

    Applicant: Intel Corporation

    Inventor： Zhu Zhou ,  Xiaotian Gao ,  Chris MacNamara ,  Stephen Doyle ,  Atul Kwatra

    IPC: G06N3/006 ,  G06F1/3287 ,  G06N5/04 ,  G06N20/00

    CPC classification number: G06N3/006 ,  G06F1/3287 ,  G06N5/04 ,  G06N20/00

    Abstract: Methods and apparatus for hierarchical reinforcement learning (RL) algorithm for network function virtualization (NFV) server power management. A first RL model at a first layer is trained by adjusting a frequency of the core of processor while performing a workload to obtain a first trained RL model. The trained RL model is operated in an inference mode while training a second RL model at a second level in the RL hierarchy by adjusting a frequency of the core and a frequency of processor circuitry external to the core to obtain a second trained RL model. Training may be performed online or offline. The first and second RL models are operated in inference modes during online operations to adjust the frequency of the core and the frequency of the circuitry external to the core while executing software on the plurality of cores of to perform a workload, such as an NFV workload.

Patent Agency Ranking