Processing Unit Resource Allocation for Real-Time Memory Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In high-performance computing platforms, especially in vehicle applications like autonomous driving, the competition for shared resources such as memory can lead to significant lengthening of execution times due to access conflicts among processes, which is critical for real-time requirements and quality of service (QoS).
Innovation Solution
A method where individual processes are assigned a setpoint processing time and a permissible extension, allowing dynamic adaptation of resource distribution based on actual processing times to prevent deviations beyond the setpoint, ensuring timely execution and minimizing conflicts by prioritizing critical processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple processes share a common resource (memory) on a multi-core platform, then resource utilization is improved, but execution time is significantly lengthened due to access conflicts
Solution Approach 1:
The patent implements dynamic resource distribution where the resource allocation to each process is continuously adjusted based on actual execution progress. The control unit monitors actual processing times and dynamically modifies the resource distribution in subsequent time intervals, transforming the static sharing mechanism into a dynamic one that adapts to real-time conditions, thereby reducing execution time while maintaining high resource utilization.
Solution Approach 2:
The system employs a feedback mechanism where the control unit continuously monitors the actual processing time of each process and uses this information to adjust resource distribution. The actual processing time serves as feedback that triggers adaptive changes in resource allocation, creating a closed-loop control system that optimizes both resource utilization and execution time by responding to real-time performance data.
2Productivity
If processes are executed together on a shared platform to improve productivity, then throughput is increased, but quality of service deteriorates due to access conflicts and timing deviations
Solution Approach 1:
The patent applies dynamic resource distribution that adapts to the actual execution progress of each process. By continuously monitoring and adjusting resource allocation in subsequent time intervals, the system maintains high throughput while ensuring that timing requirements are met, thus preserving quality of service even when multiple processes execute concurrently on the shared platform.
Solution Approach 2:
The system changes the distribution parameters of the shared resource based on actual processing times. By modifying resource allocation parameters dynamically rather than using fixed distribution, the system achieves high productivity while maintaining reliability, as the parameters are adjusted to prevent timing deviations and meet quality of service requirements.
3Ease of operation
If static resource distribution is used to simplify system operation, then ease of operation is improved, but adaptability to varying process requirements deteriorates
Solution Approach 1:
The system implements self-service through automatic monitoring and adjustment of resource distribution. The control unit autonomously monitors actual processing times and adjusts resource allocation without requiring manual intervention, thereby maintaining ease of operation while achieving high adaptability to varying process requirements through automated response to changing conditions.
Solution Approach 2:
The patent transforms the static resource distribution into a dynamic one that automatically adapts to process requirements. The system maintains operational simplicity by using automated monitoring and adjustment mechanisms, eliminating the need for complex manual configuration while achieving high adaptability through real-time response to actual processing times.
4Reliability
If resource distribution is dynamically adapted to meet real-time requirements, then quality of service is improved, but device complexity increases due to monitoring and control mechanisms
Solution Approach 1:
The control unit is designed with multi-functionality, serving both as a resource distributor and a performance monitor. By combining these functions in a single unit, the system achieves high quality of service through dynamic resource adaptation while minimizing the increase in device complexity, as the same hardware component performs multiple roles rather than requiring separate dedicated units.
Solution Approach 2:
The system uses self-service monitoring where the control unit automatically tracks actual processing times and adjusts resource distribution without external intervention. This approach improves quality of service through continuous optimization while keeping the control mechanism relatively simple, as the system monitors and adjusts itself using existing control unit capabilities rather than requiring additional complex monitoring infrastructure.
Data Source
AI summary
A method for operating a processing unit, in which a multiplicity of processes are carried out, which together access a resource according to a predefined resource distribution. The method includes a determination of an instantaneous actual processing time of at least one of the multiplicity of processes during an execution of the at least one of the multiplicity of processes, within which the at least one of the multiplicity of processes is processed; a comparison of the actual processing time with a setpoint processing time assigned to the at least one of the multiplicity of processes and/or with a sum of the assigned setpoint processing time and a processing time extension assigned to the at least one of the multiplicity of processes; and an adaptation of the predefined resource distribution as a function of a result of this comparison.