Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A distributed automated software testing method and platform for AI chip platform

A software testing method and distributed technology, applied in the direction of software testing/debugging, error detection/correction, multi-program installation, etc., to achieve the effect of efficient investigation

Active Publication Date: 2021-09-21
INST OF SOFTWARE - CHINESE ACAD OF SCI
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional automated software testing does not support this scenario

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
  • A distributed automated software testing method and platform for AI chip platform
  • A distributed automated software testing method and platform for AI chip platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described by examples below, but the scope of the present invention is not limited in any way.

[0033] Set up the following test scenarios: one server, one server; eight clients, namely AI_client1, AI_client2, AI_client3, AI_client4, x86_client1, x86_client2, x86_client3, x86_client4; the use case test table has 5 detection items, which are case1, case2, and case3 , case4, case5, the specific contents of the five test items are shown in Table 1:

[0034] Table 1 is the description of the 5 cases

[0035] Case name describe Case1 Testing ResNet based on TensorFlow Case2 Test SSD based on TensorFlow Case3 Testing VGG based on TensorFlow Case4 Testing AlexNet based on TensorFlow Case5 Testing Conv based on TensorFlow

[0036] The implementation steps are as follows:

[0037] 1) Server-side system initialization: load test table case1~case5, client configuration table and other confi...

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 distributed automatic software testing method and platform for an AI chip platform. The platform can automatically distribute AI software testing tasks to different AI chip platform client computers through the server. After the test is completed, the test results are unified to the server for management, and then automatically release the environment update task according to the demand and then send it to the X86 client. Initiate the same test task for the second time, which runs pure software on the X86 client, and collects and manages the test results of the second time in a unified manner. When the two tests are finished, it will automatically compare and analyze the two test results, and output the analysis results; and, trace the changes of the two offline models before and after, locate the nodes of the offline model or input errors, Help software engineers and hardware engineers troubleshoot problems.

Description

technical field [0001] The invention belongs to the technical field of computer software, relates to the scenario of performing AI chip platform software testing on multiple computers or development boards at one time, and proposes a distributed automatic software testing method and platform for AI chip platforms. Background technique [0002] Software testing (or software testing) is a process used to identify the correctness, integrity, security and quality of software. Software testing is a review or comparison process between the actual output and the expected output. The purpose is to operate the program under specified conditions to find program errors, measure software quality, and evaluate whether it can meet the design requirements. process. Software testing arose along with the production of software, which was completed by software developers themselves in the early days, and now it is completed by specialized testers. [0003] With the increasing diversificatio...

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 Patents(China)
IPC IPC(8): G06F11/36G06F9/54
CPCG06F9/546G06F11/3664G06F11/3688G06F11/3692G06F2209/548
Inventor 于佳耕侯朋朋卢欣晔汲如意苏航
Owner INST OF SOFTWARE - CHINESE ACAD OF SCI
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
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