Processor Selection for Job Scheduling Using Measured Power
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large-scale computational systems, such as supercomputers and multiprocessor computers, consume excessive power, leading to high operational costs despite existing efficiency improvements like using only efficient components, reducing chip frequency and voltage, and disabling unused chips, as further efficiency gains are needed to significantly reduce power consumption.
Innovation Solution
A method of allocating computational system parts to jobs based on power consumption by determining the necessary parts to meet job requirements and adding parts that minimize power usage, ranking parts by power consumption, and using a parts information storage to allocate the most efficient components for each job.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If parts are selected based on lowest power consumption, then power consumption is reduced, but job execution requirements may not be met
Solution Approach 1:
The patent segments the parts selection process into two distinct phases: first identifying all parts that meet the job's functional requirements, then selecting from those qualified parts the ones with lowest power consumption. This segmentation resolves the contradiction by ensuring functional capability is established before optimizing for energy efficiency.
Solution Approach 2:
The patent performs preliminary filtering of parts based on job requirements before the actual selection for power consumption optimization. By pre-establishing the set of qualified parts that can execute the job, the system ensures functional requirements are met before applying the power consumption minimization criterion.
2Loss of energy
If incremental efficiency improvements of 10% are achieved, then cost savings increase, but system complexity increases
Solution Approach 1:
The patent implements a feedback mechanism where power consumption measurements from actual job execution are used to update and refine future parts selection decisions. The system learns from past performance data to continuously improve its efficiency while maintaining a systematic approach that manages complexity through structured feedback loops.
Solution Approach 2:
The system automatically performs parts selection and power consumption optimization without requiring manual intervention. The parts assembler autonomously queries the parts information storage, evaluates power consumption data, and makes allocation decisions, reducing operational complexity while achieving efficiency improvements.
Data Source
AI summary
In a design structure for allocating a plurality of parts of a computational system to a computational job, a set of requirements necessary to execute the job is determined. A set of parts of the plurality of parts is assembled so that the set of parts is capable of meeting the set of requirements and so that a part is added to the set of parts based on a determination that the addition of the part will minimize power consumption by the set of parts. The set of parts are caused to execute the job.