公开(公告)号：US20250156678A1

公开(公告)日：2025-05-15

申请号：US19024363

申请日：2025-01-16

Applicant: Imagination Technologies Limited

Inventor： Daniel Barnard ,  Clifford Gibson ,  Colin McQuillan

IPC: G06N3/04 ,  G06F12/02 ,  G06F12/06 ,  G06N3/045 ,  G06N3/063

Abstract: Input data for a convolutional neural network (CNN) is stored in a buffer comprising a plurality of banks, by receiving input data comprising input data values to be processed in the CNN, determining addresses in the buffer in which the received input data values are to be stored, keeping a cursor for one or more salient positions to reduce arithmetic performed to determine the addresses in the buffer in which the received input data values are to be stored, and storing the received input data values at the determined addresses in the buffer.

公开(公告)号：US12277488B2

公开(公告)日：2025-04-15

申请号：US17868675

申请日：2022-07-19

Applicant: Imagination Technologies Limited

Inventor： Daniel Barnard ,  Clifford Gibson ,  Colin McQuillan

IPC: G06N3/04 ,  G06F12/02 ,  G06F12/06 ,  G06N3/045 ,  G06N3/063

Abstract: A method for providing input data for a layer of a convolutional neural network (CNN). Input data is received comprising 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.

公开(公告)号：US20220383067A1

公开(公告)日：2022-12-01

申请号：US17868675

申请日：2022-07-19

Applicant: Imagination Technologies Limited

Inventor： Daniel Barnard ,  Clifford Gibson ,  Colin McQuillan

IPC: G06N3/04 ,  G06F12/02 ,  G06N3/063 ,  G06F12/06

Abstract: A method for providing input data for a layer of a convolutional neural network “CNN”, the method comprising: receiving input data comprising input data values to be processed in a layer of the CNN; determining addresses in banked memory of a buffer 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; and storing the received input data values at the determined addresses in the buffer for retrieval for processing in the layer.

公开(公告)号：US20180101763A1

公开(公告)日：2018-04-12

申请号：US15726633

申请日：2017-10-06

Applicant: Imagination Technologies Limited

Inventor： Daniel Barnard ,  Clifford Gibson ,  Colin McQuillan

IPC: G06N3/04 ,  G06F12/06

CPC classification number: G06N3/04 ,  G06F12/0207 ,  G06F12/0607 ,  G06F12/0653 ,  G06F2212/1016 ,  G06F2212/251 ,  G06N3/0454 ,  G06N3/063

Abstract: A method for providing input data for a layer of a convolutional neural network “CNN”, the method comprising: receiving input data comprising input data values to be processed in a layer of the CNN; determining addresses in banked memory of a buffer 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; and storing the received input data values at the determined addresses in the buffer for retrieval for processing in the layer.

公开(公告)号：US11423285B2

公开(公告)日：2022-08-23

申请号：US17401219

申请日：2021-08-12

Applicant: Imagination Technologies Limited

Inventor： Daniel Barnard ,  Clifford Gibson ,  Colin McQuillan

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.

公开(公告)号：US20210390368A1

公开(公告)日：2021-12-16

申请号：US17401219

申请日：2021-08-12

Applicant: Imagination Technologies Limited

Inventor： Daniel Barnard ,  Clifford Gibson ,  Colin McQuillan

IPC: G06N3/04 ,  G06F12/02 ,  G06N3/063 ,  G06F12/06

Abstract: A method for providing input data for a layer of a convolutional neural network “CNN”, the method comprising: receiving input data comprising input data values to be processed in a layer of the CNN; determining addresses in banked memory of a buffer 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; and storing the received input data values at the determined addresses in the buffer for retrieval for processing in the layer.

公开(公告)号：US11100386B2

公开(公告)日：2021-08-24

申请号：US15726633

申请日：2017-10-06

Applicant: Imagination Technologies Limited

Inventor： Daniel Barnard ,  Clifford Gibson ,  Colin McQuillan

IPC: G06N3/04 ,  G06F12/02 ,  G06N3/063 ,  G06F12/06

Abstract: Data for layers of a convolutional neural network (CNN) is provided by receiving input data values to be processed in a layer of the CNN and determining addresses in banked memory of a buffer 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 then stored at the determined addresses in the buffer for retrieval for processing in the layer.