Invention Grant
- Patent Title: Feature map caching method of convolutional neural network and system thereof
-
Application No.: US16543645Application Date: 2019-08-19
-
Publication No.: US11782839B2Publication Date: 2023-10-10
- Inventor: Ping Chao , Chao-Yang Kao , Youn-Long Lin
- Applicant: NEUCHIPS CORPORATION
- Applicant Address: TW Hsinchu
- Assignee: NEUCHIPS CORPORATION
- Current Assignee: NEUCHIPS CORPORATION
- Current Assignee Address: TW Hsinchu
- Agency: CKC & Partners Co., LLC
- Main IPC: G06F5/06
- IPC: G06F5/06 ; G06N3/04 ; G06F12/0871 ; G06F12/0893 ; G06N3/063

Abstract:
A feature map caching method of a convolutional neural network includes a connection analyzing step and a plurality of layer operation steps. The connection analyzing step is for analyzing a network to establish a convolutional neural network connection list. The convolutional neural network connection list includes a plurality of tensors and a plurality of layer operation coefficients. Each of the layer operation coefficients includes a step index, at least one input operand label and an output operand label. The step index as a processing order for the layer operation step. At least one of the layer operation steps is for flushing at least one of the tensors in a cache according to a distance between the at least one of the layer operation steps and a future layer operation step of the layer operation steps. The distance is calculated according to the convolutional neural network connection list.
Public/Granted literature
- US20200065250A1 FEATURE MAP CACHING METHOD OF CONVOLUTIONAL NEURAL NETWORK AND SYSTEM THEREOF Public/Granted day:2020-02-27
Information query