Task Scheduling in Heterogeneous Multi-Processor Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional task scheduling in heterogeneous multi-processor systems allocates tasks based solely on load values, leading to inefficient resource utilization and increased power consumption, as all tasks are often routed to high-performance processors, even if user interaction is minimal, causing performance perception issues and excessive energy use.
Innovation Solution
An electronic device with a controller that identifies tasks based on user interaction and allocates them to either high-performance or low-performance processors according to a schedule policy, allowing for differential task allocation and migration based on importance and interaction levels, thereby optimizing processor usage and reducing power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If all tasks are allocated to high-performance processors based on load values, then task processing speed is improved, but power consumption increases
Solution Approach 1:
The patent applies local quality by differentiating task allocation policies based on task characteristics. High-priority tasks with user interaction are allocated to high-performance processors for fast processing, while low-priority tasks are allocated to low-performance processors to conserve energy. This selective allocation strategy ensures that only necessary tasks consume high power, resolving the contradiction between overall processing speed and power consumption.
2Device complexity
If tasks are allocated based solely on load values, then scheduling simplicity is maintained, but task processing efficiency deteriorates
Solution Approach 1:
The patent changes the scheduling parameter from单一的 load value to a composite parameter that includes both load value and task priority. This parameter change enables the scheduler to distinguish between high-priority and low-priority tasks, allocating them to appropriate processors. The approach maintains scheduling simplicity by using clear priority levels while significantly improving processing efficiency through intelligent task routing.
3Speed
If all tasks are processed by high-performance processors, then user interaction responsiveness is improved, but resource utilization efficiency deteriorates
Solution Approach 1:
The patent segments tasks into different priority levels, specifically identifying high-priority tasks that require user interaction. Only these segmented high-priority tasks are allocated to high-performance processors to ensure responsiveness. Low-priority tasks are separated and handled by low-performance processors, preventing energy waste on non-critical operations while maintaining fast response for user-interaction tasks.
Data Source
AI summary
Various embodiments provide an electronic device and a method, the electronic device comprising: a memory; a first processor; a second processor which has attributes different from those of the first processor; and a control unit, wherein the control unit is configured to identify a task loaded into the memory, select which of the first processor and the second processor is to execute the task, on the basis of attribute information corresponding to a user interaction associated with the task, and allocate the task to the selected processor. Other embodiments are also possible.