公开(公告)号：US20200019854A1

公开(公告)日：2020-01-16

申请号：US16480545

申请日：2018-02-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Arun ABRAHAM ,  Suhas Parlathaya KUDRAL ,  Balaji Srinivas HOLUR ,  Sarbojit GANGULY ,  Venkappa MALA ,  Suneel Kumar SURIMANI ,  Sharan Kumar ALLUR

IPC: G06N3/08 ,  G06F9/48 ,  G06F9/445

Abstract: The present invention describes a method of accelerating execution of one or more application tasks in a computing device using machine learning (ML) based model. According to one embodiment, a neural accelerating engine present in the computing device receives a ML input task for execution on the computing device from a user. The neural accelerating engine further retrieves a trained ML model and a corresponding optimal configuration file based on the received ML input task. Also, the current performance status of the computing device for executing the ML input task is obtained. Then, the neural accelerating engine dynamically schedules and dispatches parts of the ML input task to one or more processing units in the computing device for execution based on the retrieved optimal configuration file and the obtained current performance status of the computing device.

公开(公告)号：US20220076102A1

公开(公告)日：2022-03-10

申请号：US17417189

申请日：2020-06-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Arun ABRAHAM ,  Akshay PARASHAR ,  Suhas P K ,  Vikram Nelvoy RAJ END IRAN

IPC: G06N3/04

Abstract: A method of managing deep neural network (DNN) models on a device is provided. The method includes extracting information associated with each of a plurality of DNN models, identifying, from the information, common information which is common across the plurality of DNN models, separating and storing the common information into a designated location in the device, and controlling at least one DNN model among the plurality of DNN models to access the common information.

公开(公告)号：US20220366217A1

公开(公告)日：2022-11-17

申请号：US17864596

申请日：2022-07-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Briraj SINGH ,  Amogha UDUPA SHANKARANARAYANA GOPAL ,  Aniket DWIVEDI ,  Bharat MUDRAGADA ,  Alladi Ashok Kumar SENAPATI ,  Suhas Parlathaya KUDRAL ,  Arun ABRAHAM ,  Praveen Doreswamy NAIDU

IPC: G06N3/04

Abstract: Embodiments herein provide a method and system for network and hardware aware computing layout selection for efficient Deep Neural Network (DNN) Inference. The method comprises: receiving, by the electronic device, a DNN model to be executed, wherein the DNN model is associated with a task; dividing the DNN model into a plurality of sub-graphs, wherein each sub-graph is to be processed individually; identifying a computing unit from a plurality of computing units for execution of each sub-graph based on a complexity score; and determining a computing layout from a plurality of computing layouts for each identified computing unit, wherein the sub-graph is executed on the identified computing unit through the determined computing layout.

公开(公告)号：US20230068381A1

公开(公告)日：2023-03-02

申请号：US17961453

申请日：2022-10-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Tejpratap Venkata Subbu Lakshmi GOLLANAPALLI ,  Arun ABRAHAM ,  Raja KUMAR ,  Pradeep NELAHONNE SHIVAMURTHAPPA ,  Vikram Nelvoy RAJENDIRAN ,  Prasen Kumar SHARMA

IPC: G06N3/08 ,  G06V10/82

Abstract: Various embodiments of the disclosure disclose a method for quantizing a Deep Neural Network (DNN) model in an electronic device. The method includes: estimating, by the electronic device, an activation range of each layer of the DNN model using self-generated data (e.g. retro image, audio, video, etc.) and/or a sensitive index of each layer of the DNN model; quantizing, by the electronic device, the DNN model based on the activation range and/or the sensitive index; and allocating, by the electronic device, a dynamic bit precision for each channel of each layer of the DNN model to quantize the DNN model.

公开(公告)号：US20210232921A1

公开(公告)日：2021-07-29

申请号：US17159598

申请日：2021-01-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Akshay PARASHAR ,  Arun ABRAHAM ,  Payal ANAND ,  Deepthy RAVI ,  Venkappa MALA ,  Vikram Nelvoy RAJENDIRAN

IPC: G06N3/08 ,  G06N3/063 ,  G06F9/30 ,  G06F9/38 ,  G06F9/48

Abstract: A method, an apparatus, and a system for configuring a neural network across heterogeneous processors are provided. The method includes creating a unified neural network profile for the plurality of processors; receiving at least one request to perform at least one task using the neural network; determining a type of the requested at least one task as one of an asynchronous task and a synchronous task; and parallelizing processing of the neural network across the plurality of processors to perform the requested at least one task, based on the type of the requested at least one task and the created unified neural network profile.