中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.017 seconds)

    VERIFICATION OF COMPUTER-EXECUTABLE CODE GENERATED FROM A MODEL
    1.
    发明申请
    VERIFICATION OF COMPUTER-EXECUTABLE CODE GENERATED FROM A MODEL 有权
    从模型生成的计算机可执行代码的验证

    公开(公告)号：US20140380269A1

    公开(公告)日：2014-12-25

    申请号：US14475302

    申请日：2014-09-02

    Applicant: THE MATHWORKS, INC.

    Inventor： Mirko Conrad ,  Xiaocang Lin ,  Jun Yan ,  Peter S. Szpak ,  Appa rao Nirakh ,  Jayaprabha Shankar

    IPC: G06F9/44

    CPC classification number: G06F8/35 ,  G06F11/3604

    Abstract: In an embodiment, a model is sliced into a plurality of slices. A slice in the plurality of slices is selected. A portion of code, that corresponds to the selected slice, is identified from code generated from the model. The identified code is verified to be equivalent to the selected slice. Equivalence may include equivalent functionality, equivalent data types, equivalent performance, and/or other forms of equivalence between the selected slice and the identified generated code.

    Abstract translation: 在一个实施例中，将模型切成多个切片。 选择多个切片中的切片。 根据从模型生成的代码来识别对应于所选切片的一部分代码。 所识别的代码被验证为等同于所选择的切片。 等效性可以包括等效的功能，等效的数据类型，等效的性能，和/或所选切片和所识别的生成的代码之间的等价的其他形式。

    Systems and methods for generating code for parallel processing units
    2.
    发明授权
    Systems and methods for generating code for parallel processing units 有权

    公开(公告)号：US10949182B2

    公开(公告)日：2021-03-16

    申请号：US15816377

    申请日：2017-11-17

    Applicant: The MathWorks, Inc.

    Inventor： Girish Venkataramani ,  Rama P. Kokku ,  Jayaprabha Shankar ,  James L. Brock ,  Chun-Yu Shei ,  Vijaya Raghavan

    IPC: G06F8/41

    Abstract: Systems and methods generate code from a source program where the generated code may be compiled and executed on a Graphics Processing Unit (GPU). A parallel loop analysis check may be performed on regions of the source program identified for parallelization. One or more optimizations also may be applied to the source program that convert mathematical operations into a parallel form. The source program may be partitioned into segments for execution on a host and a device. Kernels may be created for the segments to be executed on the device. The size of the kernels may be determined, and memory transfers between the host and device may be optimized.

    SYSTEMS AND METHODS FOR QUANTIZING A NEURAL NETWORK
    5.
    发明申请
    SYSTEMS AND METHODS FOR QUANTIZING A NEURAL NETWORK 有权

    公开(公告)号：US20210174214A1

    公开(公告)日：2021-06-10

    申请号：US17108643

    申请日：2020-12-01

    Applicant: The MathWorks, Inc.

    Inventor： Vaidehi Venkatesan ,  Jayaprabha Shankar ,  Shixin Zhuang ,  Girish Venkataramani ,  FNU Hanumantharayappa

    IPC: G06N3/10 ,  G06N3/04 ,  G06N3/08

    Abstract: Systems and methods quantize an application having a trained Deep Neural Network (DNN) for deployment on target hardware. The application may be instrumented to observe data values generated during execution of the application. Statistics may be generated for the observed data values and presented in a visualization tool. The application may be quantized through a rules based approach. The quantization may be based on the statistics and on constraints imposed by resources available at the target hardware. The systems and methods may present the proposed data types resulting from the quantization and may create a quantized version of the application incorporating the proposed data types. The systems and methods may generate performance data to validate the quantized version of the application. Changes to the rules may be made and the quantization process repeated if the performance is not satisfactory.

Patent Agency Ranking