公开(公告)号：US11803747B2

公开(公告)日：2023-10-31

申请号：US16878720

申请日：2020-05-20

Applicant: Google LLC

Inventor： Samuel Bengio ,  Mohammad Norouzi ,  Benoit Steiner ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le ,  Naveen Kumar ,  Yuefeng Zhou ,  Rasmus Munk Larsen

IPC: G06N3/08 ,  G06N5/04 ,  G06N3/10 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06N3/044 ,  G06N3/045 ,  G06N3/105 ,  G06N5/04

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described. The method includes receiving data specifying a machine learning model to be placed for distributed processing on multiple hardware devices; generating, from the data, a sequence of operation embeddings, each operation embedding in the sequence characterizing respective operations necessary to perform the processing of the machine learning model; processing the sequence of operation embeddings using a placement recurrent neural network in accordance with first values of a plurality network parameters of the placement recurrent neural network to generate a network output that defines a placement of the operations characterized by the operation embeddings in the sequence across the plurality of devices; and scheduling the machine learning model for processing by the multiple hardware devices by placing the operations on the multiple devices according to the placement defined by the network output.

公开(公告)号：US10438113B2

公开(公告)日：2019-10-08

申请号：US16040186

申请日：2018-07-19

Applicant: Google LLC

Inventor： Benoit Steiner ,  Anna Darling Goldie ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le

IPC: G06N3/04 ,  G06N20/00 ,  G06F16/901 ,  G06N3/063 ,  G06N3/08 ,  G06N5/04 ,  G06F9/50

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices includes receiving data specifying machine learning operations, and determining a placement that assigns each of the operations specified by the data to a respective device from the multiple hardware devices. Determining the placement includes: generating, from the data, a respective operation embedding for each of the operations; grouping the operations into multiple operation groups, comprising processing each of the respective operation embeddings using a grouper neural network having multiple grouper parameters, in which the grouper neural network is configured to, for each of the operations, process the operation embedding for the operation in accordance with first values of the grouper parameters to generate a grouper output that assigns the operation to an operation group from the multiple operation groups; and assigning each of the operation groups to a respective device from the multiple hardware devices.

公开(公告)号：US20240062062A1

公开(公告)日：2024-02-22

申请号：US18376362

申请日：2023-10-03

Applicant: Google LLC

Inventor： Samuel Bengio ,  Mohammad Norouzi ,  Benoit Steiner ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le ,  Naveen Kumar ,  Yuefeng Zhou ,  Rasmus Munk Larsen

IPC: G06N3/08 ,  G06N5/04 ,  G06N3/10 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06N5/04 ,  G06N3/105 ,  G06N3/044 ,  G06N3/045

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described. The method includes receiving data specifying a machine learning model to be placed for distributed processing on multiple hardware devices; generating, from the data, a sequence of operation embeddings, each operation embedding in the sequence characterizing respective operations necessary to perform the processing of the machine learning model; processing the sequence of operation embeddings using a placement recurrent neural network in accordance with first values of a plurality network parameters of the placement recurrent neural network to generate a network output that defines a placement of the operations characterized by the operation embeddings in the sequence across the plurality of devices; and scheduling the machine learning model for processing by the multiple hardware devices by placing the operations on the multiple devices according to the placement defined by the network output.

公开(公告)号：US11455514B2

公开(公告)日：2022-09-27

申请号：US16554217

申请日：2019-08-28

Applicant: Google LLC

Inventor： Benoit Steiner ,  Anna Darling Goldie ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le

IPC: G06N3/04 ,  G06F9/50 ,  G06N20/00 ,  G06F16/901 ,  G06N3/063 ,  G06N3/08 ,  G06N5/04

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices includes receiving data specifying machine learning operations, and determining a placement that assigns each of the operations specified by the data to a respective device from the multiple hardware devices. Determining the placement includes: generating, from the data, a respective operation embedding for each of the operations; grouping the operations into multiple operation groups, comprising processing each of the respective operation embeddings using a grouper neural network having multiple grouper parameters, in which the grouper neural network is configured to, for each of the operations, process the operation embedding for the operation in accordance with first values of the grouper parameters to generate a grouper output that assigns the operation to an operation group from the multiple operation groups; and assigning each of the operation groups to a respective device from the multiple hardware devices.

公开(公告)号：US10692003B2

公开(公告)日：2020-06-23

申请号：US16445330

申请日：2019-06-19

Applicant: Google LLC

Inventor： Samuel Bengio ,  Mohammad Norouzi ,  Benoit Steiner ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le ,  Naveen Kumar ,  Yuefeng Zhou ,  Rasmus Munk Larsen

IPC: G06N3/08 ,  G06N5/04 ,  G06N3/04 ,  G06N3/10

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described. The method includes receiving data specifying a machine learning model to be placed for distributed processing on multiple hardware devices; generating, from the data, a sequence of operation embeddings, each operation embedding in the sequence characterizing respective operations necessary to perform the processing of the machine learning model; processing the sequence of operation embeddings using a placement recurrent neural network in accordance with first values of a plurality network parameters of the placement recurrent neural network to generate a network output that defines a placement of the operations characterized by the operation embeddings in the sequence across the plurality of devices; and scheduling the machine learning model for processing by the multiple hardware devices by placing the operations on the multiple devices according to the placement defined by the network output.

公开(公告)号：US10073817B1

公开(公告)日：2018-09-11

申请号：US15792077

申请日：2017-10-24

Applicant: Google LLC

Inventor： Nishant Patil ,  Matthew Sarett ,  Rama Krishna Govindaraju ,  Benoit Steiner ,  Vincent O. Vanhoucke

IPC: G06F7/52 ,  G06F17/16

CPC classification number: G06F17/16

Abstract: The present disclosure relates to optimized matrix multiplication using vector multiplication of interleaved matrix values. Two matrices to be multiplied are organized into specially ordered vectors, which are multiplied together to produce a portion of a product matrix.

公开(公告)号：US20200279163A1

公开(公告)日：2020-09-03

申请号：US16878720

申请日：2020-05-20

Applicant: Google LLC

Inventor： Samuel Bengio ,  Mohammad Norouzi ,  Benoit Steiner ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le ,  Naveen Kumar ,  Yuefeng Zhou ,  Rasmus Munk Larsen

IPC: G06N3/08 ,  G06N5/04 ,  G06N3/04 ,  G06N3/10

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described. The method includes receiving data specifying a machine learning model to be placed for distributed processing on multiple hardware devices; generating, from the data, a sequence of operation embeddings, each operation embedding in the sequence characterizing respective operations necessary to perform the processing of the machine learning model; processing the sequence of operation embeddings using a placement recurrent neural network in accordance with first values of a plurality network parameters of the placement recurrent neural network to generate a network output that defines a placement of the operations characterized by the operation embeddings in the sequence across the plurality of devices; and scheduling the machine learning model for processing by the multiple hardware devices by placing the operations on the multiple devices according to the placement defined by the network output.

公开(公告)号：US20190392294A1

公开(公告)日：2019-12-26

申请号：US16554217

申请日：2019-08-28

Applicant: Google LLC

Inventor： Benoit Steiner ,  Anna Darling Goldie ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le

IPC: G06N3/04 ,  G06N20/00 ,  G06F16/901 ,  G06N3/063 ,  G06N3/08 ,  G06N5/04

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices includes receiving data specifying machine learning operations, and determining a placement that assigns each of the operations specified by the data to a respective device from the multiple hardware devices. Determining the placement includes: generating, from the data, a respective operation embedding for each of the operations; grouping the operations into multiple operation groups, comprising processing each of the respective operation embeddings using a grouper neural network having multiple grouper parameters, in which the grouper neural network is configured to, for each of the operations, process the operation embedding for the operation in accordance with first values of the grouper parameters to generate a grouper output that assigns the operation to an operation group from the multiple operation groups; and assigning each of the operation groups to a respective device from the multiple hardware devices.

公开(公告)号：US20190303761A1

公开(公告)日：2019-10-03

申请号：US16445330

申请日：2019-06-19

Applicant: Google LLC

Inventor： Samy Bengio ,  Mohammad Edward Norouzi ,  Benoit Steiner ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le ,  Naveen Kumar ,  Yuefeng Zhou ,  Rasmus Munk Larsen

IPC: G06N3/08 ,  G06N5/04

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described. The method includes receiving data specifying a machine learning model to be placed for distributed processing on multiple hardware devices; generating, from the data, a sequence of operation embeddings, each operation embedding in the sequence characterizing respective operations necessary to perform the processing of the machine learning model; processing the sequence of operation embeddings using a placement recurrent neural network in accordance with first values of a plurality network parameters of the placement recurrent neural network to generate a network output that defines a placement of the operations characterized by the operation embeddings in the sequence across the plurality of devices; and scheduling the machine learning model for processing by the multiple hardware devices by placing the operations on the multiple devices according to the placement defined by the network output.

公开(公告)号：US20190026624A1

公开(公告)日：2019-01-24

申请号：US16040186

申请日：2018-07-19

Applicant: Google LLC

Inventor： Benoit Steiner ,  Anna Darling Goldie ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le

IPC: G06N3/04 ,  G06N3/08 ,  G06N5/04 ,  G06N99/00 ,  G06F17/30 ,  G06N3/063

CPC classification number: G06N3/0454 ,  G06F9/5066 ,  G06F16/9024 ,  G06N3/0445 ,  G06N3/063 ,  G06N3/084 ,  G06N5/045 ,  G06N20/00

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices includes receiving data specifying machine learning operations, and determining a placement that assigns each of the operations specified by the data to a respective device from the multiple hardware devices. Determining the placement includes: generating, from the data, a respective operation embedding for each of the operations; grouping the operations into multiple operation groups, comprising processing each of the respective operation embeddings using a grouper neural network having multiple grouper parameters, in which the grouper neural network is configured to, for each of the operations, process the operation embedding for the operation in accordance with first values of the grouper parameters to generate a grouper output that assigns the operation to an operation group from the multiple operation groups; and assigning each of the operation groups to a respective device from the multiple hardware devices.