Granular Reset Management Circuit for Processor Subsystems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multiprocessor systems, component failures can lead to processor downtime and system-wide downtime, as existing mechanisms lack the ability to perform granular resets without rebooting the entire system, which is inefficient and disrupts high availability requirements.
Innovation Solution
A reset management circuit that allows for granular resets of processor subsystems without system-wide reboots by identifying capable subsystems, stopping related traffic, performing resets, and reinitializing them independently, enabling continuous operation of unaffected components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a system-wide reboot is performed to address component failure, then the failed component can be reset, but the entire system experiences downtime and productivity is reduced
Solution Approach 1:
The system is divided into independent reset domains allowing selective resetting of specific subsystems or components without affecting the entire system. Each domain can be independently controlled, enabling granular reset management that maintains productivity while ensuring reliability through targeted component resets.
2Reliability
If the entire system is reset to address a single component failure, then the failed component is restored, but system complexity increases due to full system shutdown and restart procedures
Solution Approach 1:
The reset management system is segmented into domain-specific control units that can independently manage resets within their respective domains. This reduces the complexity of system-wide reset procedures by localizing reset control to specific subsystems, making the overall reset management more manageable and less complex.
Solution Approach 2:
The system performs preliminary identification of failed components and isolates them to specific reset domains before executing resets. This preliminary action prevents unnecessary system-wide shutdowns and simplifies the reset process by pre-determining the scope of required resets based on component failure locations.
3Productivity
If granular reset capability is implemented, then system uptime is maintained during component failures, but the device complexity increases due to additional reset management circuitry
Solution Approach 1:
The processor is divided into multiple independent reset domains, each with its own reset control capabilities. This segmentation enables granular reset management that maintains high system availability while controlling complexity through modular domain structures that can be independently managed and scaled.
Solution Approach 2:
The reset management circuitry is designed with universal control mechanisms that can manage multiple reset domains through a unified interface. This multi-functionality reduces the overall device complexity by using a single versatile reset management structure rather than separate dedicated circuits for each domain.
Data Source
AI summary
A system for granular reset management without reboot is disclosed. The system may include a subsystem, a processor including a reset management circuit coupled to the subsystem. The reset management circuit may include circuitry to receive a command to reset the subsystem, determine whether the subsystem can be reset without performing a system wide reboot, and based on a determination that the subsystem can be reset without performing a system wide reboot, block the use of the subsystem, drain the subsystem, and reset the subsystem. Circuity and method are also disclosed.