公开(公告)号：US20250131286A1

公开(公告)日：2025-04-24

申请号：US19000562

申请日：2024-12-23

Applicant: Apple Inc.

Inventor： Gaurav KAPOOR ,  Cecile M. FORET ,  Francesco ROSSI ,  Kit-Man WAN ,  Umesh S. VAISHAMPAYAN ,  Etienne BELANGER ,  Albert ANTONY ,  Alexey MARINICHEV ,  Marco ZULIANI ,  Xiaojin SHI

IPC: G06N3/10 ,  G06F8/41 ,  G06F9/50 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08

Abstract: The subject technology provides receiving a neural network (NN) model to be executed on a target platform, the NN model including multiple layers that include operations and some of the operations being executable on multiple processors of the target platform. The subject technology further sorts the operations from the multiple layers in a particular order based at least in part on grouping the operations that are executable by a particular processor of the multiple processors. The subject technology determines, based at least in part on a cost of transferring the operations between the multiple processors, an assignment of one of the multiple processors for each of the sorted operations of each of the layers in a manner that minimizes a total cost of executing the operations. Further, for each layer of the NN model, the subject technology includes an annotation to indicate the processor assigned for each of the operations.

公开(公告)号：US20230177350A1

公开(公告)日：2023-06-08

申请号：US17903991

申请日：2022-09-06

Applicant: Apple Inc.

Inventor： Gaurav KAPOOR ,  Cecile M. FORET ,  Francesco ROSSI ,  Kit-Man WAN ,  Umesh S. VAISHAMPAYAN ,  Etienne BELANGER ,  Albert ANTONY ,  Alexey MARINICHEV ,  Marco ZULIANI ,  Xiaojin SHI

IPC: G06N3/10 ,  G06N3/08 ,  G06N3/04 ,  G06F8/41 ,  G06N3/063

CPC classification number: G06N3/10 ,  G06N3/08 ,  G06N3/04 ,  G06F8/443 ,  G06F8/41 ,  G06F8/4441 ,  G06N3/063 ,  G06F9/50

Abstract: The subject technology provides receiving a neural network (NN) model to be executed on a target platform, the NN model including multiple layers that include operations and some of the operations being executable on multiple processors of the target platform. The subject technology further sorts the operations from the multiple layers in a particular order based at least in part on grouping the operations that are executable by a particular processor of the multiple processors. The subject technology determines, based at least in part on a cost of transferring the operations between the multiple processors, an assignment of one of the multiple processors for each of the sorted operations of each of the layers in a manner that minimizes a total cost of executing the operations. Further, for each layer of the NN model, the subject technology includes an annotation to indicate the processor assigned for each of the operations.

公开(公告)号：US20230376293A1

公开(公告)日：2023-11-23

申请号：US18199344

申请日：2023-05-18

Applicant: Apple Inc.

Inventor： Ashok AYYAMANI ,  Mohammad J. ABDELHADI ,  Ryan J. ALLEN ,  James D. BATSON ,  Christopher Y. BROWN ,  Etienne BELANGER ,  Karl C. HSU ,  Jeffrey D. KOFTINOFF ,  Eric S. LEE ,  Nur O. MONSON ,  George E. WILLIAMS

IPC: G06F8/41 ,  G06F8/30 ,  G06F21/52

CPC classification number: G06F8/443 ,  G06F8/30 ,  G06F21/52

Abstract: The present disclosure generally relates deploying an application. Some techniques described herein occur during compile time while executable code is being generated from source code. In one example, the executable code causes different operations in an application to be assigned to different compute systems such that particular operations are required to be executed on particular compute systems. The executable code may further include bridges that assist data being transmitted between different compute systems, the bridges generated during compile time. In another example, the executable code causes data to be sent to a recording service during execution of an application. The recording service, though not included in the source code before compile time, is configured to receive copies of data transmitted on a compute system including the recording service. The recording service may also be configured to receive metadata corresponding to operations executed on the compute system.

公开(公告)号：US20200082274A1

公开(公告)日：2020-03-12

申请号：US16262809

申请日：2019-01-30

Applicant: Apple Inc.

Inventor： Francesco ROSSI ,  Cecile M. FORET ,  Gaurav KAPOOR ,  Kit-Man WAN ,  Umesh S. VAISHAMPAYAN ,  Etienne BELANGER ,  Albert ANTONY ,  Alexey MARINICHEV ,  Marco ZULIANI ,  Xiaojin SHI

IPC: G06N3/10 ,  G06N3/04 ,  G06N3/08

Abstract: The subject technology provides receiving a neural network (NN) model to be executed on a target platform, the NN model including multiple layers that include operations and some of the operations being executable on multiple processors of the target platform. The subject technology further sorts the operations from the multiple layers in a particular order based at least in part on grouping the operations that are executable by a particular processor of the multiple processors. The subject technology determines, based at least in part on a cost of transferring the operations between the multiple processors, an assignment of one of the multiple processors for each of the sorted operations of each of the layers in a manner that minimizes a total cost of executing the operations. Further, for each layer of the NN model, the subject technology includes an annotation to indicate the processor assigned for each of the operations.

公开(公告)号：US20200082273A1

公开(公告)日：2020-03-12

申请号：US16262807

申请日：2019-01-30

Applicant: Apple Inc.

Inventor： Francesco ROSSI ,  Cecile M. FORET ,  Gaurav KAPOOR ,  Kit-Man WAN ,  Umesh S. VAISHAMPAYAN ,  Etienne BELANGER

IPC: G06N3/10 ,  G06F9/48

Abstract: The subject technology runs a compiled neural network (NN) model on a particular processor with multiple priority queues for executing different processes, the compiled NN model being assigned to a particular priority queue, and the compiled NN model includes context switch instructions that were previously inserted into a neural network (NN) model from which the compiled NN model was compiled. The subject technology determines that a particular context switch instruction has been executed by the particular processor. The subject technology determines that a different process is waiting to be executed, the different process being assigned to a different priority queue and the different process being a higher priority process than the running compiled NN model. In response to executing the particular context switch instruction, the subject technology performs a context switch to the different process assigned to the different priority queue when the different process is waiting to be executed.