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

Computing device, computing equipment and method for thread group accumulation

A computing device, computing equipment technology, applied in the computer field, can solve problems such as huge overhead

Pending Publication Date: 2021-05-18
SHANGHAI BIREN TECH CO LTD
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This creates a huge overhead of up to 94%

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
  • Computing device, computing equipment and method for thread group accumulation
  • Computing device, computing equipment and method for thread group accumulation
  • Computing device, computing equipment and method for thread group accumulation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0016] As used herein, the term "comprise" and its variants mean open inclusion, ie "including but not limited to". The term "or" means "and / or" unless otherwise stated. The term "based on" means "based at least in part on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment." The term "another embodiment" means "at least on...

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 embodiment of the invention relates to a computing device, computing equipment and a method for thread group accumulation, and relates to the field of computers. The computing device includes: a storage unit; an accumulation calculation unit which is coupled with the storage unit and is configured to receive a first thread group accumulation instruction, a plurality of first values corresponding to the number of thread group channels and a first storage address from a vector processing unit coupled with the computing device, in response to the first thread group accumulation instruction, generate a current accumulation result based on the plurality of first values, and store the current accumulation result in a first storage address in the storage unit for reading by the vector processing unit. Therefore, accumulation in the thread group can be decoupled to the special hardware for processing, so that the overall accumulation performance is remarkably improved.

Description

technical field [0001] Embodiments of the present disclosure generally relate to the field of computers, and specifically relate to a computing device, a computing device, and a method for thread group accumulation. Background technique [0002] Multiple thread groups (warps) may be included in the vector processing unit. Accumulation often occurs within thread groups. For example, in Recurrent Neural Network (RNN), there are a large number of matrix multiply vector (MMV) and add operations. This operation is able to keep cumulative results on a thread group basis. Finally, the accumulation needs to be done within the thread group to generate the final result. This can be achieved by continuously shuffling the values ​​in the thread group channels (also called threads) and then summing the swapped values, or by using a shared memory location for accumulation. [0003] No matter which of the above methods is used, a large number of instructions will be consumed to complet...

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): G06F9/48
CPCG06F9/4881G06F17/16G06F7/5443G06F7/50G06F7/76
Inventor 不公告发明人
Owner SHANGHAI BIREN TECH CO LTD
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