Configurable Reporting for Integrated Circuit Error Conditions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing computing systems face performance impacts when handling error conditions due to the generation of interrupt signals, as they often require the host processor to halt operations, making it difficult to identify the instruction causing the error and leading to inefficiencies in error handling and system performance.

Innovation Solution

The implementation of a configurable reporting mechanism in offload engines that allows for customizable notification messages, halt signals, and interrupt signals based on error types, enabling minimal performance impact and providing additional information about error conditions without requiring extensive I/O operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If interrupt signals are generated to notify error conditions, then error detection capability is improved, but system performance deteriorates due to host processor halting

Engineering Contradiction:
Improveerror detection capabilityVSAvoidsystem performance
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The error reporting function is segmented into two parts: (1) the offload engine generates notification messages for error conditions, and (2) the host processor handles these messages asynchronously without halting. This segmentation allows error detection to proceed independently from the main processing flow, resolving the contradiction between reliable error detection and sustained system performance.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

A notification message queue acts as an intermediary between the offload engine and the host processor. The offload engine deposits error notifications into this queue, and the host processor retrieves and processes them at its own pace. This intermediary mechanism decouples the error reporting from the processing pipeline, maintaining system performance while ensuring error detection.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If host processor halts to handle errors, then error handling completeness is improved, but processing continuity deteriorates

Engineering Contradiction:
Improveerror handling completenessVSAvoidprocessing continuity
Core Design Contradiction:
ReliabilityVSDuration of action of moving object

Solution Approach 1:

The offload engine performs preliminary error detection and packaging of error information into notification messages before the host processor needs to handle them. This preliminary action ensures that when the host processor does intervene, it receives complete error information without needing to halt processing to gather details, thus maintaining processing continuity while ensuring error handling completeness.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements a feedback mechanism where the offload engine continuously monitors for error conditions and feeds back notification messages to the host processor through the queue. This continuous feedback loop ensures that errors are detected and reported without interrupting the main processing flow, as the feedback is delivered asynchronously alongside normal operation.

Inventive Principle:
Principle #23Feedback

3Loss of information

If extensive I/O operations are performed for error reporting, then error information completeness is improved, but processing efficiency deteriorates

Engineering Contradiction:
Improveerror information completenessVSAvoidprocessing efficiency
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The notification message queue provides exactly the right amount of error information needed for effective error handling without excessive data transfer. Each notification message contains essential error details (error type, status, and relevant information) sufficient for the host processor to take appropriate action, avoiding the need for extensive I/O operations while maintaining error information completeness.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS10956248B1Configurable reporting for device conditions
Publication Date: 2021.03.23 AMAZON TECH INC
  • US10956248B1 patent drawing
  • US10956248B1 patent drawing
  • US10956248B1 patent drawing

AI summary

An integrated circuit configured to execute program instructions can generate, based on a configuration, any combination of a notification message, a halt signal, or an interrupt signal for a condition detected in the integrated circuit. The detected condition can be an error condition or a non-error condition. The notification message for the condition may be written to memory accessible by a host processor. The non-error condition may be used by the host processor to monitor internal states of the integrated circuit. The halt signal may be used to stop the integrated circuit from executing the instructions.