PCIe Error Reporting with Hybrid Hardware-Software Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing error reporting systems in devices, which rely solely on hardware, lack flexibility and scalability, requiring costly and time-consuming hardware re-spin for feature upgrades, bug fixes, and changes in device functionality.
Innovation Solution
A hybrid approach combining device hardware and software for error reporting, where the device hardware generates interrupts and the software determines error attributes and owners, allowing flexible and scalable error management without modifying hardware.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If error reporting is implemented using hardware only, then reliability of error detection is improved, but adaptability and ease of modification deteriorate as any changes require hardware re-spin
Solution Approach 1:
The error reporting system is segmented into hardware components (error detection logic, interrupt generation) and software components (error attribute determination, owner identification). The hardware handles reliable error detection and interrupt generation, while the software handles flexible error management and reporting, allowing modifications without hardware changes.
Solution Approach 2:
The processor acts as an intermediary between the hardware error detection mechanism and the software error management system. The hardware generates interrupts that are received and processed by the processor, which then coordinates with software to determine error attributes and generate reports, enabling flexible error management while maintaining reliable detection.
2Measurement precision
If error reporting is implemented using hardware only, then measurement precision of error attributes is improved, but device complexity and manufacturing cost increase due to hardware re-spin requirements
Solution Approach 1:
The complex error management functions (determining error attributes, identifying error owners, generating detailed reports) are extracted from the hardware and transferred to the software domain. The hardware is simplified to only perform error detection and interrupt generation, while the processor and software handle the complex error analysis and reporting, reducing hardware complexity and manufacturing costs.
Solution Approach 2:
The patent replaces the mechanical/hardware-based error management system with a software-based system. Instead of using hardware circuits to determine error attributes and generate reports, the system uses software routines executed on the processor, allowing flexible error management without complex hardware modifications.
3Manufacturing precision
If hardware re-spin is performed for feature upgrades, then manufacturing precision is maintained, but loss of time and increase in manufacturing cost occur
Solution Approach 1:
The error reporting system is made dynamic and configurable through software. Error management parameters, thresholds, and reporting formats can be changed dynamically by updating software without requiring hardware re-spin. This allows rapid adaptation to new requirements while maintaining the stability of the hardware fabrication.
Data Source
AI summary
A hybrid approach using hardware and software is used for report management in peripheral component interconnect (PCI) express devices. The device hardware detects an error associated with a transaction with a host computer. The device software identifies a function associated with the error and determines various attributes of the error. The device software then exposes the attributes of the error in the PCI express and the advanced error reporting (AER) capabilities. The error can be reported in a message transaction to the host computer.