Compiling method and device and electronic equipment

CN119621073AActive Publication Date: 2025-03-14龙芯中科(合肥)技术有限公司
View PDF 8 Cites -1 Cited by

Patent Information

Application Number
CN202510162234.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-13
Publication Date
2025-03-14
Estimated Expiration
2045-02-13

Smart Images

  • Figure CN119621073A_ABST
    Figure CN119621073A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a compiling method and device and electronic equipment, and is applied to a universal graphics processor, the method comprises the following steps: calling a deep learning compiler, and converting a to-be-compiled deep learning model into an intermediate expression file of the deep learning compiler; obtaining a target compiler matched with the architecture of the general graphic processor; the target compiler is used for translating the deep learning model into a target model in an equivalent machine language format; compiling the intermediate expression file by using the target compiler, and constructing a running environment corresponding to the deep learning model to obtain a compiled target model; and importing to-be-processed target image data into the target model for processing to obtain a target processing result. According to the embodiment of the invention, the model compiling process is simplified, the compiling complexity is reduced, and the model compiling efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Neural network model compiling method and system, equipment and storage medium

    CN113918163A

  • Hardware adaptation device and method based on deep learning

    CN114186678A

  • Advanced RISC Machines (ARM) processor-oriented deep learning model deployment method and equipment

    CN115660104A

  • Plug-in generation method and device, electronic equipment and storage medium

    CN116974646A

  • Deep learning model compiling method and compiler supporting multiple kinds of hardware

    CN119045823A

Cited By

  • Compiling method and device, electronic equipment, storage medium and product

    CN120491976A

  • Application dynamic compatibility method and system, electronic equipment and storage medium

    CN120872402A

  • A dynamic compatibility method and system, an electronic device, and a storage medium are provided

    CN120872402B