Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Flexible accelerator for sparse tensor in convolutional neural network

A convolution and accumulator technology, applied in the field of non-transitory computer readable media, which can solve the problems of limited configuration and processing of input data.

Pending Publication Date: 2022-07-08
WESTERN DIGITAL TECH INC
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, currently used mechanisms are limited in how they can be configured in machine learning applications and how they process input data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Flexible accelerator for sparse tensor in convolutional neural network
  • Flexible accelerator for sparse tensor in convolutional neural network
  • Flexible accelerator for sparse tensor in convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In the following detailed description, reference is made to the accompanying drawings which form a part hereof. In the drawings, similar symbols typically identify similar components, unless context dictates otherwise. The exemplary embodiments described in the detailed description, drawings, and claims are not intended to be limiting. Other embodiments may be utilized, and other changes may be made, without departing from the spirit or scope of the subject matter presented here. It will be readily appreciated that the various aspects of the present disclosure as generally described herein and illustrated in the drawings may be arranged, substituted, combined and designed in a wide variety of different configurations, all of which are expressly contemplated and become part of this disclosure.

[0029] Neural networks continue to evolve towards larger and deeper architectures as they engage in more complex processing tasks in a wider range of scenarios. Large neural n...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a system with a multiplication circuit. The multiplication circuit is provided with a plurality of multipliers. Each multiplier of the plurality of multipliers is configured to receive the data value and the weight value to generate a product value in a convolution operation of the machine learning application. The system also includes an accumulator configured to receive the product value from each multiplier of the plurality of multipliers, and a register bank configured to store an output of the convolution operation. The accumulator is further configured to receive a portion of the values stored in the register bank and combine the received portion of the values with the product values to generate a combined value. The register bank is further configured to replace the portion of values with the combined values.

Description

Background technique [0001] The applicant provides the following instructions to aid the reader's understanding. Neither the information presented nor the references cited are admitted to be prior art. [0002] Machine learning algorithms are widely used in fields such as medical imaging, computer vision, advertising, gaming, and more. Machine learning algorithms process large amounts of input data. As the amount of input data increases, so does the computational time and computing resources required to process the large amount of input data. However, the mechanisms currently used are limited in how they can be configured in machine learning applications and how input data can be processed. SUMMARY OF THE INVENTION [0003] According to some aspects of the present disclosure, a system is disclosed. The system includes a multiplying circuit having multiple multipliers. Each of the plurality of multipliers is configured to receive a data value and a weight value to genera...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/063G06V10/764
CPCG06F17/16G06V10/955G06V10/82G06N3/063G06N3/084G06V10/764G06V10/7715G06N3/045G06F17/153G06N3/08G06N20/00G06F18/2137G06N3/044
Inventor K·古纳姆A·库尔卡尼Z·班迪克
Owner WESTERN DIGITAL TECH INC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com