System for improving computing efficiency of GPU (Graphics Processing Unit) graphics card in large data volume and high concurrency scene

A large amount of data, computing efficiency technology, applied in the field of GPU graphics computing efficiency, can solve the problems of increasing system hardware costs, resource waste, unfriendly and realistic solutions, etc., to improve data processing efficiency, not easy to overflow and timeout Effect

Pending Publication Date: 2022-03-25
时趣互动(北京)科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But this will obviously increase the hardware cost of the system, which is not a friendly and realistic solution for the majority of start-ups or R&D teams with relatively limited funds
Moreover, if the computing power of a single GPU graphics card cannot be fully utilized, horizontally expanding the number of GPU graphics cards will also cause greater waste of resources.

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
  • System for improving computing efficiency of GPU (Graphics Processing Unit) graphics card in large data volume and high concurrency scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0018] see figure 1 , the present invention provides a technical solution:

[0019] A system to improve the computing efficiency of GPU graphics cards in large data volume and high concurrency scenarios, including: client, CPU server, 3 servers for RPC services and GPU graphics cards, the client is used to send concurrent data requests, and the CPU server is used to receive Data processing requests and forwarding polling of requests to subsequent processing ends, ...

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 for improving the computing efficiency of a GPU (Graphics Processing Unit) graphics card under a large data volume and high concurrency scene, the system comprises a client, a CPU (Central Processing Unit) server, three servers for RPC (Remote Procedure Call) service and the GPU graphics card, the client is used for sending a concurrent data request, the CPU server is used for receiving a data processing request and polling and forwarding the request to a subsequent processing end, and the GPU graphics card has a model computing service. According to the method and the device, additional high-performance hardware resources are not added, the relatively cheap CPU server is utilized, and the client only needs to send a relatively small amount of request data each time, so that the GPU display card can reach a full-load operation state, the data processing efficiency is improved, and risks such as overflow and timeout are not easy to occur.

Description

technical field [0001] The invention relates to the technical field of computing efficiency of GPU graphics cards, in particular to a system for improving the computing efficiency of GPU graphics cards in large data volume and high concurrency scenarios. Background technique [0002] After the training of the deep learning model is completed, it is generally necessary to deploy an inference service on the GPU graphics card to provide calculation results based on the deep learning model for the data requests sent by the client. For example, after training the text public opinion classification model, it is necessary to deploy an inference service on the GPU graphics card to quickly provide calculation results for the text public opinion classification request sent by the client. [0003] In order to improve the utilization rate of the GPU graphics card in the scenario of large data volume and high concurrent requests, so as to improve the data processing speed of the inferenc...

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): G06F9/54G06F16/35
CPCG06F9/547G06F16/35G06F2209/541
Inventor 唐亮曹特磊赵伟
Owner 时趣互动(北京)科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap