公开(公告)号：US20240143986A1

公开(公告)日：2024-05-02

申请号：US18216008

申请日：2023-06-29

Applicant: Imagination Technologies Limited

Inventor： Aria Ahmadi ,  Cagatay Dikici ,  Clement Charnay ,  Jason Rogers

IPC: G06N3/063 ,  G06N3/0464

CPC classification number: G06N3/063 ,  G06N3/0464

Abstract: Methods of dividing a neural network into chunks of operations executable in a hardware pass of hardware to execute a neural network. The layers of the neural network are divisible into layer groups that comprise a sequence of layers executable in the same hardware pass of the hardware. Each layer group is divisible into chunks of operations executable in a hardware pass of the hardware. The chunks for a layer group are defined by split parameters. A layer group loss function is obtained that represents a performance metric associated with executing a layer group on the hardware as a function of the split parameters and neural network architecture parameters for the layer group. A neural network loss function is generated based on the layer group loss function that represents the performance metric associated with executing the neural network on the hardware; and the split parameters for the one or more layer groups are selected that minimize the neural network loss function under constraints imposed by the hardware.

公开(公告)号：US20220253506A1

公开(公告)日：2022-08-11

申请号：US17583411

申请日：2022-01-25

Applicant: Imagination Technologies Limited

Inventor： Aria Ahmadi ,  Cagatay Dikici ,  Clement Charnay

IPC: G06F17/15 ,  G06F9/54 ,  G06K9/62

Abstract: A method and data processing system implement dilated convolution operations in hardware. Embodiments provide various ways to implement a dilated convolution based on a number of constituent convolutions, by either splitting the kernel to construct a set of constituent convolutions with smaller kernels, or dividing the input data into multiple parts and applying a convolution to each part separately. The constituent convolutions are evaluated in hardware and their results are combined to produce the result of the dilated convolution.