公开(公告)号：US12223300B2

公开(公告)日：2025-02-11

申请号：US18309341

申请日：2023-04-28

Applicant: MEDIATEK INC.

Inventor： Meng-Hsuan Yang ,  Po-hua Huang ,  Hsing-Chang Chou ,  Ting Chen Tsan ,  Yu-Lung Lu

IPC: G06F8/41 ,  G06N3/10

Abstract: A method of compiling a deep learning model includes reading metadata from a compiled result, the metadata indicating a structure of the deep learning model corresponding to a low-level IR, receiving shape information of an input tensor of the deep learning model, determining a shape of an output tensor of a first computation operation of the computation operations based on the shape information of the input tensor of the deep learning model and the structure of the deep learning model, tiling the output tensor of the first computation operation into one or more tiles according to the shape of the output tensor of the first computation operation and hardware limitations of a processor executing the deep learning model, and patching one or more copies of a templated hardware command into executable hardware commands.