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.