Network Offload Engine for Multi-Core Avionics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Avionics processing systems face challenges in sharing network resources across multiple cores due to determinism issues and cost inefficiencies, particularly in safety-critical environments where applications with varying criticality levels require access to limited bandwidth network connections with latency guarantees, necessitating a solution that minimizes complexity and maintains determinism.
Innovation Solution
A multicore processor system with a shared system memory, where one partition acts as a network offload engine with a dedicated operating system and network stack, controlling access through a flow control component, and utilizing a cross-platform inter-partition communication component to manage network operations requests across partitions, thereby isolating asynchronous network traffic and reducing the need for multiple certified network components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a complete network solution is provided for each individual core or partition, then network access capability is improved, but device complexity and cost increase due to requiring unique network interfaces and separate certification for each core
Solution Approach 1:
The patent merges network functionality into a shared partition that serves multiple cores, eliminating the need for separate network interfaces per core. The shared partition contains a single network interface controller and network stack that all cores can access through controlled communication channels.
Solution Approach 2:
The shared partition is designed to provide universal network access capabilities to multiple cores simultaneously. A single network interface controller and network stack serve multiple applications across different cores, reducing overall system complexity while maintaining full network functionality.
2Device complexity
If network resources are shared across multiple cores, then device complexity is reduced, but determinism deteriorates due to bandwidth limitations and access conflicts between applications with different criticality levels
Solution Approach 1:
The patent segments network access into priority-based channels within the shared partition. High-criticality applications receive guaranteed bandwidth and priority access through dedicated communication queues, while lower-criticality applications share remaining resources, ensuring deterministic behavior for time-sensitive operations.
Solution Approach 2:
The shared partition acts as an intermediary between multiple cores and the network interface controller. It implements flow control mechanisms and access arbitration that guarantee deterministic access for high-priority applications while managing shared resource allocation, preventing access conflicts and ensuring timing requirements are met.
3Reliability
If network access is restricted to a single core or partition, then determinism is improved, but productivity decreases due to limited network resource utilization
Solution Approach 1:
The patent implements dynamic network resource allocation within the shared partition based on application criticality and current system state. The flow control component adjusts bandwidth allocation and access priorities in real-time, granting deterministic guarantees to high-criticality applications while allowing flexible access for lower-priority applications, thereby maximizing overall network utilization.
Solution Approach 2:
The system changes operational parameters such as bandwidth allocation, access priority, and queue scheduling based on application requirements. High-criticality applications receive fixed parameter allocations for deterministic behavior, while other applications share dynamically adjusted parameters, optimizing both determinism and resource utilization simultaneously.
Data Source
AI summary
A multicore processor system and a method of operating the system defines a processor partition (which may include one or more processor cores) as a network offload engine for a network connected to the processor system. Network operations requests from other cores or partitions of the processor system are forwarded to the network offload engine by a cross-platform inter-partition communications component including a relay task in the network offload engine for receiving network operations requests from network proxies in the other partitions. The network offload engine then controls access to network resources by the other cores or partitions and applications running thereon. A second or additional core or partition of the processor system may be similarly defined as a network offload engine for a second or additional network, receiving network operations requests from the other partitions through a similar system of relay task and network proxies.