Back to results
US 12,762,751 B2Granted
Calculating data compression parameters
AssigneeNVIDIA Corporation
InventorsYerlan Idelbayev, Pavlo Molchanov, Hongxu Danny Yin, Maying Shen, Jose Manuel Alvarez Lopez
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques for calculating data compression parameters using codebook entry values. In at least one embodiment, one or more circuits is to calculate one or more data compression parameters based, at least in part, on at least on one or more values of the data to be compressed in relation to at least two codebook entry values.
Claims33
One or more processors, comprising circuitry to:
- calculate a plurality of sets of candidate quantization scale parameters and one or more assignment parameters indicating an assignment of one or more data values to one or more codebook entry values based, at least in part, on minimization of one or more errors of quantizing the one or more data values to the one or more codebook entry values;
- select, from the plurality of sets of candidate quantization scale parameters, a set of quantization scale parameters that minimizes the one or more errors of quantizing the one or more data values;
- and
- generate a quantized version of a neural network using the selected set of quantization scale parameters.
1 more element
A system comprising:
- one or more processors to calculate a plurality of sets of candidate quantization scale parameters and one or more assignment parameters indicating an assignment of one or more data values to one or more codebook entry values based, at least in part, on minimization of one or more errors of quantizing the one or more data values to the one or more codebook entry values;
- select, from the plurality of sets of candidate quantization scale parameters, a set of quantization scale parameters that minimizes the one or more errors of quantizing the one or more data values;
- and
- generate a quantized version of a neural network using the selected set of quantization scale parameters.
1 more element
A method comprising:
- calculating, for one or more layers of a neural network, a plurality of sets of candidate quantization scale parameters and one or more assignment parameters indicating an assignment of one or more data values to one or more codebook entry values based, at least in part, on minimization of one or more errors of quantizing the one or more data values to the one or more codebook entry values;
- selecting, from the plurality of sets of candidate quantization scale parameters, a set of quantization scale parameters that minimizes the one or more errors of quantizing the one or more data values;
- and
- generating a quantized version of a neural network using the selected set of quantization scale parameters.
1 more element
A system comprising:
- one or more processors to calculate a plurality of sets of candidate quantization scale parameters and one or more assignment parameters indicating an assignment of one or more data values to one or more codebook entry values for each layer of a multilayered neural network based, at least in part, on minimization of one or more errors of quantizing the one or more data values to the one or more codebook entry values;
- select, from the plurality of sets of candidate quantization scale parameters, a set of quantization scale parameters that minimizes the one or more errors of quantizing the one or more data values;
- and
- generate a quantized version of a neural network using the selected set of quantization scale parameters.
1 more element
Dependencies are inferred from the claim text.