20240046065. SYSTEM, DEVICES AND/OR PROCESSES FOR DEFINING A SEARCH SPACE FOR NEURAL NETWORK PROCESSING DEVICE ARCHITECTURES simplified abstract (Arm Limited)

From WikiPatents
Jump to navigation Jump to search

SYSTEM, DEVICES AND/OR PROCESSES FOR DEFINING A SEARCH SPACE FOR NEURAL NETWORK PROCESSING DEVICE ARCHITECTURES

Organization Name

Arm Limited

Inventor(s)

Hokchhay Tann of Burlington MA (US)

Ramon Matas Navarro of Newburyport MA (US)

Igor Fedorov of Ashland MA (US)

Chuteng Zhou of Somerville MA (US)

Paul Nicholas Whatmough of Cambridge MA (US)

Matthew Mattina of Boylston MA (US)

SYSTEM, DEVICES AND/OR PROCESSES FOR DEFINING A SEARCH SPACE FOR NEURAL NETWORK PROCESSING DEVICE ARCHITECTURES - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240046065 titled 'SYSTEM, DEVICES AND/OR PROCESSES FOR DEFINING A SEARCH SPACE FOR NEURAL NETWORK PROCESSING DEVICE ARCHITECTURES

Simplified Explanation

The patent application describes methods, apparatuses, and/or articles of manufacture that use computing devices to determine options for decisions related to the design features of a computing device. In one implementation, the application focuses on identifying design options for two or more decisions in the context of a neural network processing device. These design options are determined based on a combination of available computing resources and predefined performance constraints.

  • The patent application focuses on using computing devices to assist in making design decisions for a computing device.
  • Specifically, it addresses the design options for a neural network processing device.
  • The design options are identified by considering available computing resources and predefined performance constraints.

Potential Applications:

  • This technology can be applied in the field of computer hardware design to optimize the design features of computing devices.
  • It can be used in the development of neural network processing devices to enhance their performance and efficiency.

Problems Solved:

  • The technology solves the problem of manually determining design options for computing devices, which can be time-consuming and error-prone.
  • It addresses the challenge of optimizing the design features of neural network processing devices to meet performance constraints and utilize available computing resources effectively.

Benefits:

  • The use of computing devices to determine design options streamlines the decision-making process and reduces human effort.
  • By considering available computing resources and performance constraints, the technology helps in creating more efficient and effective computing devices.
  • The optimization of design features leads to improved performance and functionality of neural network processing devices.


Original Abstract Submitted

example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to determine options for decisions in connection with design features of a computing device. in a particular implementation, design options for two or more design decisions of neural network processing device may be identified based, at least in part, on combination of a definition of available computing resources and one or more predefined performance constraints.