Christopher J Leary

US Patent:

20220391472, Dec 8, 2022

Filed:

Jun 16, 2022

Appl. No.:

17/842420

Inventors:

- Mountain View CA, US
Rahul Nagarajan - Sunnyvale CA, US
Dong Hyuk Woo - San Jose CA, US
Christopher Daniel Leary - Sunnyvale CA, US

International Classification:

G06F 17/16
G06F 17/14

Abstract:

Methods, systems, and apparatus, including a system for transforming sparse elements to a dense matrix. The system is configured to receive a request for an output matrix based on sparse elements including sparse elements associated with a first dense matrix and sparse elements associated with a second dense matrix; obtain the sparse elements associated with the first dense matrix fetched by a first group of sparse element access units; obtain the sparse elements associated with the second dense matrix fetched by a second group of sparse element access units; and transform the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix to generate the output dense matrix that includes the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix.

US Patent:

20210034697, Feb 4, 2021

Filed:

Jul 14, 2020

Appl. No.:

16/928242

Inventors:

- Mountain View CA, US
Rahul Nagarajan - Sunnyvale CA, US
Dong Hyuk Woo - San Jose CA, US
Christopher Daniel Leary - Sunnyvale CA, US

International Classification:

G06F 17/16
G06F 17/14

Abstract:

Methods, systems, and apparatus, including a system for transforming sparse elements to a dense matrix. The system is configured to receive a request for an output matrix based on sparse elements including sparse elements associated with a first dense matrix and sparse elements associated with a second dense matrix; obtain the sparse elements associated with the first dense matrix fetched by a first group of sparse element access units; obtain the sparse elements associated with the second dense matrix fetched by a second group of sparse element access units; and transform the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix to generate the output dense matrix that includes the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix.

US Patent:

20200012705, Jan 9, 2020

Filed:

Sep 16, 2019

Appl. No.:

16/571749

Inventors:

- Mountain View CA, US
Rahul Nagarajan - Sunnyvale CA, US
Dong Hyuk Woo - San Jose CA, US
Christopher Daniel Leary - Sunnyvale CA, US

International Classification:

G06F 17/16
G06F 17/14

Abstract:

Methods, systems, and apparatus, including a system for transforming sparse elements to a dense matrix. The system is configured to receive a request for an output matrix based on sparse elements including sparse elements associated with a first dense matrix and sparse elements associated with a second dense matrix; obtain the sparse elements associated with the first dense matrix fetched by a first group of sparse element access units; obtain the sparse elements associated with the second dense matrix fetched by a second group of sparse element access units; and transform the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix to generate the output dense matrix that includes the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix.

US Patent:

20190287210, Sep 19, 2019

Filed:

Jun 6, 2019

Appl. No.:

16/433819

Inventors:

- Mountain View CA, US
Christopher Daniel Leary - Sunnyvale CA, US

Assignee:

Google LLC - Mountain View CA

International Classification:

G06T 1/20
G06F 16/901
G06N 3/10
G06F 9/50
G06N 3/063

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a data entity that causes a processing unit to process a computational graph. In one aspect, a method includes the actions of receiving data identifying a computational graph, the computational graph including a plurality of nodes representing operations; obtaining compilation artifacts for processing the computational graph on a processing unit; and generating a data entity from the compilation artifacts, wherein the data entity, when invoked, causes the processing unit to process the computational graph by executing the operations represented by the plurality of nodes.

US Patent:

20180197267, Jul 12, 2018

Filed:

Jan 6, 2017

Appl. No.:

15/400937

Inventors:

- Mountain View CA, US
Christopher Daniel Leary - Sunnyvale CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G06T 1/20
G06N 3/08

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a data entity that causes a processing unit to process a computational graph. In one aspect, method includes the actions of receiving data identifying a computational graph, the computational graph including a plurality of nodes representing operations; obtaining compilation artifacts for processing the computational graph on a processing unit; and generating a data entity from the compilation artifacts, wherein the data entity, when invoked, causes the processing unit to process the computational graph by executing the operations represented by the plurality of nodes.

US Patent:

20180060276, Mar 1, 2018

Filed:

Sep 5, 2017

Appl. No.:

15/695144

Inventors:

- Mountain View CA, US
Rahul Nagarajan - Sunnyvale CA, US
Dong Hyuk Woo - San Jose CA, US
Christopher Daniel Leary - Mountain View CA, US

International Classification:

G06F 17/16
G06F 17/14

Abstract:

Methods, systems, and apparatus, including a system for transforming sparse elements to a dense matrix. The system is configured to receive a request for an output matrix based on sparse elements including sparse elements associated with a first dense matrix and sparse elements associated with a second dense matrix; obtain the sparse elements associated with the first dense matrix fetched by a first group of sparse element access units; obtain the sparse elements associated with the second dense matrix fetched by a second group of sparse element access units; and transform the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix to generate the output dense matrix that includes the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix.

US Patent:

20170228341, Aug 10, 2017

Filed:

Feb 5, 2016

Appl. No.:

15/016420

Inventors:

- Mountain View CA, US
Rahul Nagarajan - Sunnyvale CA, US
Dong Hyuk Woo - San Jose CA, US
Christopher Daniel Leary - Mountain View CA, US

International Classification:

G06F 17/16
G06F 17/14

Abstract:

Methods, systems, and apparatus, including a system for transforming sparse elements to a dense matrix. The system is configured to receive a request for an output matrix based on sparse elements including sparse elements associated with a first dense matrix and sparse elements associated with a second dense matrix; obtain the sparse elements associated with the first dense matrix fetched by a first group of sparse element access units; obtain the sparse elements associated with the second dense matrix fetched by a second group of sparse element access units; and transform the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix to generate the output dense matrix that includes the sparse elements associated with the first dense matrix and the sparse elements associated with the second dense matrix.

US Patent:

20170228342, Aug 10, 2017

Filed:

Feb 5, 2016

Appl. No.:

15/016486

Inventors:

- Mountain View CA, US
Rahul Nagarajan - Sunnyvale CA, US
Dong Hyuk Woo - San Jose CA, US
Christopher Daniel Leary - Mountain View CA, US

International Classification:

G06F 17/16
H03M 7/30
G06F 17/14

Abstract:

Methods, systems, and apparatus, including a system for transforming sparse elements into a dense matrix. The system includes a data fetch unit that includes a plurality of processors, the data fetch unit configured to determine, based on identifications of the subset of the particular sparse elements, a processor designation for fetching the subset of the particular sparse elements. The system includes a concatenation unit configured to generate an output dense matrix based on a transformation that is applied to the sparse elements fetched by the data fetch unit.