Task Scheduling on Heterogeneous Multi-Core Reconfigurable Platform
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In heterogeneous multi-core reconfigurable computing platforms, existing task scheduling methods fail to effectively reduce reconfiguration overheads and improve resource utilization, particularly when handling hardware tasks that require dynamic reconfiguration during execution.
Innovation Solution
A task scheduling method that determines the priority of hardware tasks based on the length of the task queue and the number of available IP cores, and reconfigures idle reconfigurable resources into the most appropriate IP core to minimize reconfiguration overheads and enhance resource utilization, by using a priority formula and dynamic reconfiguration techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If reconfiguration is performed frequently to handle hardware tasks, then system adaptability is improved, but reconfiguration overheads increase
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing reconfiguration schedules and resource allocation plans before hardware tasks are executed. The scheduling system prepares reconfiguration sequences in advance based on predicted task arrivals and resource availability, so that when reconfiguration is needed, it can be performed with minimal overhead. This resolves the contradiction by reducing the actual reconfiguration time while maintaining system adaptability to handle various hardware tasks.
2Productivity
If reconfigurable resources are allocated to multiple hardware tasks, then resource utilization is improved, but reconfiguration complexity increases
Solution Approach 1:
The patent applies segmentation by dividing reconfigurable resources into multiple independent resource packages, each capable of being configured separately for different hardware tasks. The scheduling system manages each resource package independently, allocating them to different tasks in a modular fashion. This segmentation reduces the complexity of managing large-scale reconfiguration while improving overall resource utilization, as each package can be configured and managed separately rather than as a monolithic system.
3Productivity
If hardware tasks are executed concurrently, then system throughput is improved, but scheduling difficulty increases
Solution Approach 1:
The patent applies dynamics by implementing a dynamic scheduling system that continuously adapts resource allocation and task execution sequences based on real-time system state. The scheduler monitors hardware task arrivals, resource availability, and execution progress, dynamically adjusting the reconfiguration schedule and task assignment to maximize concurrent execution. This dynamic approach enables high system throughput while managing scheduling complexity through adaptive decision-making rather than static pre-planning.
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
Embodiments of the present invention provide a task scheduling method and apparatus on a heterogeneous multi-core reconfigurable computing platform. The method includes: when determining that a state of a to-be-executed hardware task is a ready state, adding the to-be-executed hardware task into a target hardware task queue corresponding to a function of the to-be-executed hardware task; reconfiguring, according to a priority of the to-be-executed hardware task and a usage status of the multiple reconfigurable resource packages, at least one reconfigurable resource package in the multiple reconfigurable resource packages into a target intellectual property IP core that can execute the to-be-executed hardware task, where the priority denotes execution order of the hardware task; and executing the hardware task in the target hardware task queue by using the target IP core. According to the embodiments of the present invention, a more proper resource reconfiguration occasion can be determined, and a more appropriate reconfigurable resource package can be used for resource reconfiguration, thereby reducing reconfiguration overheads and improving utilization of reconfigurable resources in a task scheduling process.