Sparse-aware convolution and techniques for acceleration thereof
AssigneeQUALCOMM Incorporated
InventorsJamie Menjay Lin, Shizhong Steve Han, Fatih Murat Porikli
Life of this patent
Estimating the term…
Abstract
Certain aspects of the present disclosure provide techniques for performing tabular convolution, including performing a tabularization operation on input data to generate a tabularized representation of the input data and performing a convolution operation using the tabularized representation of the input data to generate a convolution output.
Claims27
A method, comprising:
- performing a tabularization operation on input data to generate a tabularized representation of the input data, wherein performing the tabularization operation comprises populating the tabularized representation of the input data according to an indexing rule, wherein the indexing rule defines a plurality of index values based on a relationship between an active element of the input data and a plurality of elements of the input data adjacent to the active element;
- performing, using a convolutional layer of a neural network, a convolution operation using the tabularized representation of the input data to generate a convolution output;
- and
- generating, using the neural network, an inference, based on the convolution output.
A processing system, comprising:
- a memory comprising computer-executable instructions;
- and
- one or more processors configured to execute the computer-executable instructions and cause the processing system to:
- perform a tabularization operation on input data to generate a tabularized representation of the input data, wherein performance of the tabularization operation comprises population of the tabularized representation of the input data according to an indexing rule, wherein the indexing rule defines a plurality of index values based on a relationship between an active element of the input data and a plurality of elements of the input data adjacent to the active element;
- perform, using a convolutional layer of a neural network, a convolution operation using the tabularized representation of the input data to generate a convolution output;
- and
- generate, using the neural network, an inference, based on the convolution output.
A non-transitory computer-readable medium comprising computer-executable instructions that, when executed by one or more processors of a processing system, cause the processing system to perform a method, the method comprising:
- performing a tabularization operation on input data to generate a tabularized representation of the input data, wherein performing the tabularization operation comprises populating the tabularized representation of the input data according to an indexing rule, wherein the indexing rule defines a plurality of index values based on a relationship between an active element of the input data and a plurality of elements of the input data adjacent to the active element;
- performing, using a convolutional layer of a neural network, a convolution operation using the tabularized representation of the input data to generate a convolution output;
- and
- generating, using the neural network, an inference, based on the convolution output.
Dependencies are inferred from the claim text.