Invention Grant
- Patent Title: Buffer addressing for a convolutional neural network
-
Application No.: US17401219Application Date: 2021-08-12
-
Publication No.: US11423285B2Publication Date: 2022-08-23
- Inventor: Daniel Barnard , Clifford Gibson , Colin McQuillan
- Applicant: Imagination Technologies Limited
- Applicant Address: GB Kings Langley
- Assignee: Imagination Technologies Limited
- Current Assignee: Imagination Technologies Limited
- Current Assignee Address: GB Kings Langley
- Agency: Potomac Law Group, PLLC
- Agent Vincent M DeLuca
- Priority: GB1616953 20161006
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06F12/02 ; G06N3/063 ; G06F12/06

Abstract:
Input data for a layer of a convolutional neural network (CNN) is provided by receiving input data values to be processed in a layer of the CNN. Addresses in banked memory of a buffer are determined in which the received data values are to be stored based upon format data indicating a format parameter of the input data in the layer and indicating a format parameter of a filter which is to be used to process the input data in the layer. The received input data values are stored at the determined addresses in the buffer for retrieval for processing in the layer.
Public/Granted literature
- US20210390368A1 Buffer Addressing for a Convolutional Neural Network Public/Granted day:2021-12-16
Information query