Parallel Processing Job Scheduling via Node Coordinate Lists
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In parallel processing systems, determining the execution start time of a job to be advanced when one job ends before its scheduled end time becomes increasingly time-consuming as the number of nodes increases, leading to potential resource unavailability due to prolonged search times.
Innovation Solution
A method involving the creation of aligned job lists that store information on the order and node usage of jobs across coordinate axes, allowing for the identification of unused nodes and determining which jobs' start times can be advanced by referencing these lists before the end of a job's execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the number of nodes in the parallel processing system increases, then the processing capacity and resource availability improve, but the time required to determine which jobs' start times can be advanced increases significantly
Solution Approach 1:
The patent divides the job list into multiple segments sorted by different criteria (execution end time, node usage patterns, coordinate axis positions). Instead of searching through all jobs simultaneously, the system segments the search space and processes each segment independently, reducing the overall search time while maintaining comprehensive coverage of potential candidates for advancement.
Solution Approach 2:
The patent performs preliminary sorting and organization of jobs into structured lists before the actual search for advancement opportunities. By pre-organizing job information according to multiple criteria (execution timing, node allocation, spatial distribution), the system eliminates the need for exhaustive searches when determining which jobs can be advanced, significantly reducing search time in large-scale systems.
2Productivity
If the system performs a comprehensive search to identify jobs that can be advanced, then resource allocation efficiency improves, but the CPU processing time increases
Solution Approach 1:
The system pre-sorts jobs into structured lists based on execution end times, node usage patterns, and coordinate axis positions before the scheduling decision needs to be made. This preliminary organization allows the system to quickly identify candidate jobs for advancement without performing comprehensive searches at the moment of scheduling, thus maintaining high resource allocation efficiency while minimizing CPU processing time.
Solution Approach 2:
The patent applies different sorting and filtering criteria to different segments of the job list based on local characteristics. Jobs are organized according to their specific properties (execution timing, spatial distribution, resource requirements), allowing the system to efficiently search within relevant subsets rather than processing the entire job set uniformly, thereby reducing overall CPU processing time while maintaining comprehensive resource allocation efficiency.
Data Source
AI summary
A parallel processing system creates a list when determining a start and an end times of processings for nodes and one or more of the nodes used by the processings, the list indicating an order of executing the processings and a number and positions of nodes used by the processings on coordinate axes, nodes included in the nodes and adjacent to each other in coordinate axis directions on the coordinate axes being coupled to each other, identifies a number of unused nodes on the coordinate axes at a time when the execution of a processing ends before an end time of the processing, and determines, based on the number and the list, a processing, a start time of which is to be advanced, from the processings at a time when the execution of the one of the processings ends before the end time of the one of the processings.