ICE-based heterogeneous platform efficient intelligent computing application architecture and construction method thereof

A heterogeneous platform and construction method technology, applied in the field of artificial intelligence, can solve problems such as poor flexibility, long cycle, high development and operation costs, and achieve the effect of reducing the degree of coupling

Pending Publication Date: 2021-11-26
BEIJING INST OF COMP TECH & APPL
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is how to provide an ICE-based heterogeneous platform high-efficiency intelligent computing application architecture and its construction method to solve the problems of high development and maintenance costs, long cycles, and poor flexibility caused by differences in different learning frameworks

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
  • ICE-based heterogeneous platform efficient intelligent computing application architecture and construction method thereof
  • ICE-based heterogeneous platform efficient intelligent computing application architecture and construction method thereof
  • ICE-based heterogeneous platform efficient intelligent computing application architecture and construction method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the purpose, content and advantages of the present invention clearer, the specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0036] The purpose of the present invention is to propose an ICE-based heterogeneous platform efficient intelligent computing application framework, which is realized based on the ZeroC ICE micro-service platform, ICE can effectively shield the differences of different learning frameworks, and combine different operating frameworks through network connections to enable It forms a unified computing resource pool, ensures the correct execution of different intelligent computing services and maximizes computing efficiency, and realizes the transparency and optimization of service scheduling. In addition, microservice platforms such as Spring Cloud and dubbo only support Java or other Different specific languages, ZeroC ICE ...

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 relates to an ICE-based heterogeneous platform efficient intelligent computing application architecture and a construction method thereof, and belongs to the field of artificial intelligence. The architecture is constructed based on ICE micro-service platform, a communication module is separated from an intelligent application, the coupling degree between services is reduced, the hierarchy is clear and convenient to maintain, and ICE realizes remote communication by using a remote procedure call protocol; a neutral language Slice unified service interface definition of ICE is used, and a compiling tool of ICE is used to translate the Slice language into a language supported by each learning framework, so that cross-language support of an intelligent application system is realized. Automatic management of intelligent application services is realized based on an IceGrid plug-in, wherein the functions of registration, positioning, deployment and the like of large-scale services are realized. The intelligent application system constructed based on the architecture model can shield the difference of the bottom-layer framework, and when the bottom-layer framework is updated and upgraded, the client application is not influenced, so that an upper-layer user gets rid of dependence on a single framework manufacturer.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and in particular relates to an ICE-based heterogeneous platform efficient intelligent computing application framework and a construction method thereof. Background technique [0002] In recent years, with the continuous improvement of hardware performance and software algorithms, the wide application of Internet big data and the continuous breakthrough of large-scale computing capabilities based on cloud platforms, artificial intelligence with deep learning as the core has developed rapidly and is applicable to different computing scenarios. Deep learning frameworks emerge in endlessly, among which Caffe, TensorFlow, PyTorch, etc. are representative. These deep learning frameworks can provide the underlying architecture and interfaces of basic artificial intelligence algorithms, and are important software foundations to promote the development of the artificial intelligence industry. Howev...

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
IPC IPC(8): G06F8/41G06F8/65
CPCG06F8/41G06F8/65
Inventor 瞿秋薏寇金桥吴敏王浩枫
Owner BEIJING INST OF COMP TECH & APPL
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