Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
JOB DECOMPOSITION PROCESSING METHOD FOR DISTRIBUTED COMPUTING
Document Type and Number:
WIPO Patent Application WO/2023/206635
Kind Code:
A1
Abstract:
Disclosed in the present invention is a job decomposition processing method for distributed computing. The method comprises: analyzing, by means of static program analysis, a source program to be run, and determining a function call graph included in the source program; then, determining, by means of dynamic program analysis or/and an intelligent program decomposition algorithm, feature information of functions included in the source program, wherein the function feature information is used for representing related information during the running of each function; decomposing the source program according to the function feature information, a function relationship, and available resource information of a computing platform, so as to form an execution suggestion for each function on the computing platform, i.e. which hardware resources are used for computing each function; and finally, inserting a modifier into the source program, and starting computing on the computing platform. By means of the method in the present invention, a user can realize distributed execution of a source program without the need for modifying the source program, the repeatability of a distributed execution scheme is ensured, the subjectivity of a manual operation is avoided, and the time is saved on and labor cost is reduced.

Inventors:
BAI WENYUAN (CN)
GAO FENG (CN)
Application Number:
PCT/CN2022/092960
Publication Date:
November 02, 2023
Filing Date:
May 16, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ZHEJIANG LAB (CN)
International Classes:
G06F9/48; G06F8/72
Domestic Patent References:
WO2018045541A12018-03-15
Foreign References:
CN113342489A2021-09-03
CN113535363A2021-10-22
CN102096603A2011-06-15
US20190108067A12019-04-11
Attorney, Agent or Firm:
HANGZHOU QIUSHI PATENT OFFICE CO., LTD. (CN)
Download PDF: