Conflict Mitigation for Multi-Master Embedded Platforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multi-master embedded platforms, conflicts arising from competing access to shared resources lead to unpredictable operation, making it difficult to guarantee worst-case execution times and reliability, especially in critical applications like avionics, where traditional methods face challenges in identifying and controlling interference channels and conflicts.
Innovation Solution
A method involving the construction of sensitive or template applications to identify and measure conflicts by executing them in parallel with operational applications, using aggressiveness parameters to determine conflict patterns and measuring interference on shared resources, allowing for conflict mitigation without analyzing extensive combinations of applications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple applications are executed in parallel on multi-core processors, then productivity increases, but conflicts on shared resources increase leading to unpredictable execution times
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing conflict information for application pairs before actual execution. The system computes conflict graphs and execution time impacts in advance, allowing the runtime scheduler to make deterministic decisions without analyzing conflicts during execution, thus maintaining predictability while enabling parallel execution.
Solution Approach 2:
The patent uses copying by creating a conflict graph model that replicates the essential conflict relationships between applications. Instead of directly managing complex real-time conflicts, the system copies conflict patterns into a data structure that can be pre-analyzed and used for deterministic scheduling decisions, separating the complexity of actual execution from the predictability requirement.
2Measurement precision
If traditional methods analyze all potential interference channels between applications, then measurement precision improves, but device complexity increases significantly
Solution Approach 1:
The patent extracts only the essential conflict information from the complex web of potential interference channels. Instead of analyzing all possible channels, the system identifies and extracts only the critical conflict paths that actually matter for execution time predictability, filtering out redundant or non-critical channels through the conflict graph abstraction.
Solution Approach 2:
The patent segments the complex conflict analysis problem into manageable components by organizing applications into pairs and analyzing conflicts between specific pairs rather than all applications simultaneously. The conflict graph is divided into discrete edges representing pairwise conflicts, making the overall analysis tractable while maintaining precision.
3Measurement precision
If worst-case execution time is calculated by considering all possible application combinations, then measurement precision improves, but the time required for calculation increases exponentially
Solution Approach 1:
The patent applies preliminary action by pre-computing conflict information and execution time impacts for all application pairs during a preparation phase. This allows the actual WCET calculation during system operation to use pre-stored data rather than performing exhaustive analyses in real-time, significantly reducing calculation time while maintaining accuracy.
Solution Approach 2:
The patent uses partial action by calculating and storing only the necessary conflict information for pairwise applications rather than exhaustively analyzing all possible combinations during runtime. The system performs excessive analysis during preparation (computing all pairwise conflicts) but uses this pre-computed data efficiently during actual execution, balancing thoroughness with speed.
Data Source
AI summary
The present invention relates to a method of mitigating conflicts for an operational application implemented by an embedded platform. This method comprising the following steps:constructing at least one first sensitive application configured to be conflicted by the operational application or at least one template application configured to impose conflicts on the operational application;the embedded platform executing the operational application in parallel with the first sensitive application or the template application;determining conflicts generated on the first sensitive application by the operational application or, respectively, on the operational application by the template application;measuring the determined conflicts.