中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

23 records (took 0.019 seconds)

    Highly performant pipeline parallel deep neural network training
    1.
    发明授权
    Highly performant pipeline parallel deep neural network training 有权

    公开(公告)号：US12056604B2

    公开(公告)日：2024-08-06

    申请号：US16024369

    申请日：2018-06-29

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： Vivek Seshadri ,  Amar Phanishayee ,  Deepak Narayanan ,  Aaron Harlap ,  Nikhil Devanur Rangarajan

    IPC: G06N3/08 ,  G06N3/04

    CPC classification number: G06N3/08 ,  G06N3/04

    Abstract: Layers of a deep neural network (DNN) are partitioned into stages using a profile of the DNN. Each of the stages includes one or more of the layers of the DNN. The partitioning of the layers of the DNN into stages is optimized in various ways including optimizing the partitioning to minimize training time, to minimize data communication between worker computing devices used to train the DNN, or to ensure that the worker computing devices perform an approximately equal amount of the processing for training the DNN. The stages are assigned to the worker computing devices. The worker computing devices process batches of training data using a scheduling policy that causes the workers to alternate between forward processing of the batches of the DNN training data and backward processing of the batches of the DNN training data. The stages can be configured for model parallel processing or data parallel processing.

    Adjusting activation compression for neural network training
    4.
    发明授权
    Adjusting activation compression for neural network training 有权

    公开(公告)号：US12165038B2

    公开(公告)日：2024-12-10

    申请号：US16276395

    申请日：2019-02-14

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Daniel Lo ,  Bita Darvish Rouhani ,  Eric S. Chung ,  Yiren Zhao ,  Amar Phanishayee ,  Ritchie Zhao

    IPC: G06N3/08 ,  G06F9/30 ,  G06F18/21 ,  G06N3/063 ,  G06N3/084

    Abstract: Apparatus and methods for training a neural network accelerator using quantized precision data formats are disclosed, and, in particular, for adjusting floating-point formats used to store activation values during training. In certain examples of the disclosed technology, a computing system includes processors, memory, and a floating-point compressor in communication with the memory. The computing system is configured to produce a neural network comprising activation values expressed in a first floating-point format, select a second floating-point format for the neural network based on a performance metric, convert at least one of the activation values to the second floating-point format, and store the compressed activation values in the memory. Aspects of the second floating-point format that can be adjusted include the number of bits used to express mantissas, exponent format, use of non-uniform mantissas, and/or use of outlier values to express some of the mantissas.

    NEURAL NETWORK ACTIVATION COMPRESSION WITH OUTLIER BLOCK FLOATING-POINT
    6.
    发明申请
    NEURAL NETWORK ACTIVATION COMPRESSION WITH OUTLIER BLOCK FLOATING-POINT 审中-公开

    公开(公告)号：US20200210839A1

    公开(公告)日：2020-07-02

    申请号：US16237202

    申请日：2018-12-31

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Daniel Lo ,  Amar Phanishayee ,  Eric S. Chung ,  Yiren Zhao ,  Ritchie Zhao

    IPC: G06N3/08 ,  G06F7/499 ,  G06F9/50 ,  G06N5/04 ,  G06N20/00 ,  G06F9/30

    Abstract: Apparatus and methods for training a neural network accelerator using quantized precision data formats having outlier values are disclosed, and in particular for storing activation values from a neural network in a compressed format for use during forward and backward propagation training of the neural network. In certain examples of the disclosed technology, a computing system is configured to perform forward propagation for a layer of a neural network to produced first activation values in a first block floating-point format. In some examples, activation values generated by forward propagation are converted by the compressor to a second block floating-point format having a narrower numerical precision than the first block floating-point format. Outlier values, comprising additional bits of mantissa and/or exponent are stored in ancillary storage for subset of the activation values. The compressed activation values are stored in the memory, where they can be retrieved for use during back propagation.

    Neural network activation compression with non-uniform mantissas
    9.
    发明授权
    Neural network activation compression with non-uniform mantissas 有权

    公开(公告)号：US12277502B2

    公开(公告)日：2025-04-15

    申请号：US18415159

    申请日：2024-01-17

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Daniel Lo ,  Amar Phanishayee ,  Eric S. Chung ,  Yiren Zhao

    IPC: G06N3/084 ,  G06F9/30 ,  H03M7/30 ,  H03M7/46

    Abstract: Apparatus and methods for training a neural network accelerator using quantized precision data formats are disclosed, and in particular for storing activation values from a neural network in a compressed format having lossy or non-uniform mantissas for use during forward and backward propagation training of the neural network. In certain examples of the disclosed technology, a computing system includes processors, memory, and a compressor in communication with the memory. The computing system is configured to perform forward propagation for a layer of a neural network to produced first activation values in a first block floating-point format. In some examples, activation values generated by forward propagation are converted by the compressor to a second block floating-point format having a non-uniform and/or lossy mantissa. The compressed activation values are stored in the memory, where they can be retrieved for use during back propagation.

Patent Agency Ranking