Patents by Inventor Dan Luu
Dan Luu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20230206070Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of layers, the circuit comprising: activation circuitry configured to receive a vector of accumulated values and configured to apply a function to each accumulated value to generate a vector of activation values; and normalization circuitry coupled to the activation circuitry and configured to generate a respective normalized value from each activation value.Type: ApplicationFiled: March 1, 2023Publication date: June 29, 2023Inventors: Gregory Michael Thorson, Christopher Aaron Clark, Dan Luu
-
Patent number: 11620508Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of layers, the circuit comprising: activation circuitry configured to receive a vector of accumulated values and configured to apply a function to each accumulated value to generate a vector of activation values; and normalization circuitry coupled to the activation circuitry and configured to generate a respective normalized value from each activation value.Type: GrantFiled: January 11, 2019Date of Patent: April 4, 2023Assignee: Google LLCInventors: Gregory Michael Thorson, Christopher Aaron Clark, Dan Luu
-
Patent number: 11586920Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: GrantFiled: June 29, 2020Date of Patent: February 21, 2023Assignee: Google LLCInventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Publication number: 20220366255Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: ApplicationFiled: July 27, 2022Publication date: November 17, 2022Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Patent number: 11049016Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: GrantFiled: March 19, 2020Date of Patent: June 29, 2021Assignee: Google LLCInventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Publication number: 20210019618Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: ApplicationFiled: June 29, 2020Publication date: January 21, 2021Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Publication number: 20200218981Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: ApplicationFiled: March 19, 2020Publication date: July 9, 2020Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Patent number: 10699188Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: GrantFiled: August 25, 2017Date of Patent: June 30, 2020Assignee: Google LLCInventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Publication number: 20200057942Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: ApplicationFiled: October 25, 2019Publication date: February 20, 2020Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Publication number: 20190354862Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: ApplicationFiled: August 1, 2019Publication date: November 21, 2019Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Publication number: 20190228301Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of layers, the circuit comprising: activation circuitry configured to receive a vector of accumulated values and configured to apply a function to each accumulated value to generate a vector of activation values; and normalization circuitry coupled to the activation circuitry and configured to generate a respective normalized value from each activation value.Type: ApplicationFiled: January 11, 2019Publication date: July 25, 2019Inventors: Gregory Michael Thorson, Christopher Aaron Clark, Dan Luu
-
Patent number: 10192162Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of layers, the circuit comprising: activation circuitry configured to receive a vector of accumulated values and configured to apply a function to each accumulated value to generate a vector of activation values; and normalization circuitry coupled to the activation circuitry and configured to generate a respective normalized value from each activation value.Type: GrantFiled: September 3, 2015Date of Patent: January 29, 2019Assignee: Google LLCInventors: Gregory Michael Thorson, Christopher Aaron Clark, Dan Luu
-
Patent number: 10074051Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of layers, the circuit comprising: activation circuitry configured to receive a vector of accumulated values and configured to apply a function to each accumulated value to generate a vector of activation values; and normalization circuitry coupled to the activation circuitry and configured to generate a respective normalized value from each activation value.Type: GrantFiled: December 22, 2016Date of Patent: September 11, 2018Assignee: Google LLCInventors: Gregory Michael Thorson, Christopher Aaron Clark, Dan Luu
-
Publication number: 20180046907Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: ApplicationFiled: August 25, 2017Publication date: February 15, 2018Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Patent number: 9747546Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: GrantFiled: September 3, 2015Date of Patent: August 29, 2017Assignee: Google Inc.Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Patent number: 9710748Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: GrantFiled: December 22, 2016Date of Patent: July 18, 2017Assignee: Google Inc.Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Publication number: 20170103315Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of layers, the circuit comprising: activation circuitry configured to receive a vector of accumulated values and configured to apply a function to each accumulated value to generate a vector of activation values; and normalization circuitry coupled to the activation circuitry and configured to generate a respective normalized value from each activation value.Type: ApplicationFiled: December 22, 2016Publication date: April 13, 2017Inventors: Gregory Michael Thorson, Christopher Aaron Clark, Dan Luu
-
Publication number: 20170103313Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: ApplicationFiled: December 22, 2016Publication date: April 13, 2017Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu
-
Publication number: 20160342889Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of layers, the circuit comprising: activation circuitry configured to receive a vector of accumulated values and configured to apply a function to each accumulated value to generate a vector of activation values; and normalization circuitry coupled to the activation circuitry and configured to generate a respective normalized value from each activation value.Type: ApplicationFiled: September 3, 2015Publication date: November 24, 2016Applicant: Google Inc.Inventors: Gregory Michael Thorson, Christopher Aaron Clark, Dan Luu
-
Publication number: 20160342891Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.Type: ApplicationFiled: September 3, 2015Publication date: November 24, 2016Applicant: Google Inc.Inventors: Jonathan Ross, Norman Paul Jouppi, Andrew Everett Phelps, Reginald Clifford Young, Thomas Norrie, Gregory Michael Thorson, Dan Luu