公开(公告)号：US20210304378A1

公开(公告)日：2021-09-30

申请号：US16836440

申请日：2020-03-31

Applicant: Arm Limited

Inventor： Jens OLSON ,  Suraj SUDHIR

IPC: G06T5/30 ,  G06N3/063

Abstract: A computer-implemented method of providing a filter (F) in a neural processing unit comprises: receiving input corresponding to target dimensions (XT, YT) of the filter; receiving input corresponding to sub-filter dimensions (X1 . . . n′, Y1 . . . n′) of each of a plurality of sub-filters (SF1 . . . n) implementable in the neural processing unit; and defining the filter (F) as a combination of the plurality of sub-filters (SF1 . . . n), the combination having dimensions that equate to the target dimensions (XT, YT), and wherein the sub-filter dimensions (X1 . . . n′, Y1 . . . n′) of at least two of the sub-filters in the combination are unequal.

公开(公告)号：US20210224629A1

公开(公告)日：2021-07-22

申请号：US16748375

申请日：2020-01-21

Applicant: Arm Limited

Inventor： Suraj SUDHIR ,  Jayavarapu Srinivasa RAO ,  Rune HOLM

IPC: G06N3/04 ,  G06N3/10

Abstract: A computer-implemented method, performed in a neural processing system comprising control processor circuitry and arithmetic logic circuitry, of performing a convolution between an input feature map (IFM) and convolutional filter data, resulting in an output feature map (OFM). The method includes, obtaining in the control processor circuitry, dimensional characteristic parameters relating to dimensions of input work batch data arrays and positional characteristic parameters relating to positions of feature map content within the input work batches. The method also includes, in the arithmetic logic circuitry, performing convolutions between the input work batches, generated from the IFM based on the dimensional characteristic parameters and the positional characteristic parameters, and work batch filter data arrays corresponding to the filter to produce a plurality of output work batch data arrays. The plurality of output work batches are combined to generate an OFM.

公开(公告)号：US20210224630A1

公开(公告)日：2021-07-22

申请号：US16797210

申请日：2020-02-21

Applicant: Arm Limited

Inventor： Suraj SUDHIR ,  Jayavarapu Srinivasa RAO ,  Rune HOLM

IPC: G06N3/04 ,  G06F7/57

Abstract: A computer-implemented method, performed in a neural processing system comprising control processor circuitry and arithmetic logic circuitry, of performing a convolution between an input feature map (IFM) and convolutional filter data, resulting in an output feature map (OFM). The method includes, obtaining in the control processor circuitry, dimensional characteristic parameters relating to dimensions of input work batch data arrays and positional characteristic parameters relating to positions of feature map content within the input work batches. The method also includes, in the arithmetic logic circuitry, performing convolutions between the input work batches, generated from the IFM based on the dimensional characteristic parameters and the positional characteristic parameters, and work batch filter data arrays corresponding to the filter to produce a plurality of output work batch data arrays. The plurality of output work batches are combined to generate an OFM.