公开(公告)号：US20240320779A1

公开(公告)日：2024-09-26

申请号：US18591993

申请日：2024-02-29

Applicant: Imagination Technologies Limited

Inventor： Gunduz Vehbi Demirci ,  Cagatay Dikici ,  Grant Michael Stevens ,  Le Yang

IPC: G06T1/20 ,  G06V10/82 ,  G06V10/94

CPC classification number: G06T1/20 ,  G06V10/82 ,  G06V10/94

Abstract: Methods of implementing a sparse submanifold deconvolution on a graphics processing unit, the sparse submanifold deconvolution being representable as a direct convolution between an input tensor to the sparse submanifold deconvolution and each of a plurality of a sub-filters, each sub-filter of the plurality of sub-filters comprising a subset of weights of a filter of the sparse submanifold deconvolution. The methods include: receiving, at the graphics processing unit, the input tensor in a dense format; receiving, at the graphics processing unit, information identifying target positions of an output tensor of the sparse submanifold deconvolution; performing, at the graphics processing unit, an indexed unfold operation on the input tensor based on the identified target positions of the output tensor to generate an input matrix comprising elements of the input tensor in each sub-window of the input tensor relevant to at least one of the identified target positions of the output tensor; and performing, at the graphics processing unit, a matrix multiplication between a weight matrix and the input matrix to generate an output matrix that comprises elements of the output tensor at the identified target positions.

公开(公告)号：US20240320299A1

公开(公告)日：2024-09-26

申请号：US18591869

申请日：2024-02-29

Applicant: Imagination Technologies Limited

Inventor： Gunduz Vehbi Demirci ,  Cagatay Dikici ,  Grant Michael Stevens ,  Le Yang

IPC: G06F17/16

CPC classification number: G06F17/16

Abstract: Methods of implementing a standard deconvolution on a graphics processing unit, the standard deconvolution being representable as a direct convolution between an input tensor to the standard deconvolution and each of a plurality of a sub-filters, each sub-filter of the plurality of sub-filters comprising a subset of weights of a filter of the standard deconvolution. The methods comprising: receiving, at the graphics processing unit, the input tensor in a dense format; identifying, at the graphics processing unit, active positions of the received input tensor; performing, at the graphics processing unit, an indexed unfold operation on the input tensor based on the identified active positions to generate an input matrix comprising elements of the input tensor in each non-zero sub-window of the input tensor; and performing, at the graphics processing unit, a matrix multiplication between a weight matrix and the input matrix to generate an output matrix that comprises elements of an output tensor of the standard deconvolution that are based on the non-zero sub-windows of the input tensor.

公开(公告)号：US20240169025A1

公开(公告)日：2024-05-23

申请号：US18385690

申请日：2023-10-31

Applicant: Imagination Technologies Limited

Inventor： Le Yang ,  Aria Ahmadi ,  Cagatay Dikici

IPC: G06F17/16

CPC classification number: G06F17/16

Abstract: A method of implementing a scatter operation in fixed-function hardware of a neural network accelerator involves converting two or more vectors of indices to sparse index tensors in a one-hot sparse format. An update tensor is generated, by applying the update values to one of the sparse index tensors (or a tensor derived from it). In some examples, an input data tensor is updated based on the update tensor. In other examples, the update tensor itself is output.

公开(公告)号：US20240169024A1

公开(公告)日：2024-05-23

申请号：US18385487

申请日：2023-10-31

Applicant: Imagination Technologies Limited

Inventor： Le Yang ,  Aria Ahmadi ,  Cagatay Dikici

IPC: G06F17/16 ,  G06F7/50 ,  G06F7/523

CPC classification number: G06F17/16 ,  G06F7/50 ,  G06F7/523

Abstract: A method of implementing a scatter operation in fixed-function hardware of a neural network accelerator involves converting two or more vectors of indices to sparse index tensors in a one-hot sparse format. An update tensor is generated, by applying the update values to one of the sparse index tensors (or a tensor derived from it). In some examples, an input data tensor is updated based on the update tensor. In other examples, the update tensor itself is output.

公开(公告)号：US20240160692A1

公开(公告)日：2024-05-16

申请号：US18385556

申请日：2023-10-31

Applicant: Imagination Technologies Limited

Inventor： Le Yang ,  Aria Ahmadi ,  Cagatay Dikici

IPC: G06F17/16 ,  G06F7/50 ,  G06F7/523

CPC classification number: G06F17/16 ,  G06F7/50 ,  G06F7/523

Abstract: A method of implementing a scatter operation in fixed-function hardware of a neural network accelerator involves converting two or more vectors of indices to sparse index tensors in a one-hot sparse format. An update tensor is generated, by applying the update values to one of the sparse index tensors (or a tensor derived from it). In some examples, an input data tensor is updated based on the update tensor. In other examples, the update tensor itself is output.

公开(公告)号：US20240320298A1

公开(公告)日：2024-09-26

申请号：US18591401

申请日：2024-02-29

Applicant: Imagination Technologies Limited

Inventor： Gunduz Vehbi Demirci ,  Cagatay Dikici ,  Grant Michael Stevens ,  Le Yang

IPC: G06F17/16

CPC classification number: G06F17/16

Abstract: Methods of implementing a sparse submanifold convolution using a neural network accelerator. The methods include: receiving, at the neural network accelerator, an input tensor in a sparse format; performing, at the neural network accelerator, for each position of a kernel of the sparse submanifold convolution, a 1×1 convolution between the received input tensor and weights of filters of the sparse submanifold convolution at that kernel position to generate a plurality of partial outputs; and combining appropriate partial outputs of the plurality of partial outputs to generate an output tensor of the sparse submanifold convolution in sparse format.

公开(公告)号：US20240320778A1

公开(公告)日：2024-09-26

申请号：US18591092

申请日：2024-02-29

Applicant: Imagination Technologies Limited

Inventor： Gunduz Vehbi Demirci ,  Cagatay Dikici ,  Grant Michael Stevens ,  Le Yang

IPC: G06T1/20 ,  G06F17/16

CPC classification number: G06T1/20 ,  G06F17/16

Abstract: Methods of implementing a sparse submanifold convolution on a graphics processing unit. The methods include: receiving, at the graphics processing unit, an input tensor in a dense format; identifying, at the graphics processing unit, active positions of the input tensor; performing, at the graphics processing unit, an indexed unfold operation on the input tensor based on the identified active positions to generate an input matrix comprising elements of the input tensor in each active window of the input tensor; and performing, at the graphics processing unit, a matrix multiplication between a weight matrix and the input matrix to generate an output matrix that comprises elements of an output tensor of the sparse submanifold convolution based on the active windows. The methods may further comprise performing, at the graphics processing unit, an indexed fold operation on the output matrix based on the active windows to generate an output tensor in a dense format.

公开(公告)号：US20240320297A1

公开(公告)日：2024-09-26

申请号：US18591211

申请日：2024-02-29

Applicant: Imagination Technologies Limited

Inventor： Gunduz Vehbi Demirci ,  Cagatay Dikici ,  Grant Michael Stevens ,  Le Yang

IPC: G06F17/16

CPC classification number: G06F17/16

Abstract: Methods of implementing a standard convolution on a graphics processing unit. The methods include: receiving, at the graphics processing unit, an input tensor in a dense format; identifying, at the graphics processing unit, active positions of the input tensor; performing, at the graphics processing unit, an indexed unfold operation on the input tensor based on the identified active positions of the input tensor to generate an input matrix comprising elements of the input tensor in each non-zero window of the input tensor; and performing, at the graphics processing unit, a matrix multiplication between a weight matrix and the input matrix to generate an output matrix that comprises elements of an output tensor of the standard convolution based on the non-zero windows of the input tensor.