On-Chip Debugging Module with Selective Signal Sampling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current on-chip debugging methods are resource-intensive, inflexible, and struggle to effectively analyze errors in real-time, particularly for dedicated chips, as they often require external debuggers and lack the ability to selectively sample data before errors occur, leading to inefficient data collection and high performance demands.

Innovation Solution

An on-chip debugging device with an external interface module, debugging mode control module, debugging monitor module, and information processing module that allows for selective sampling, burst data storage, and trigger conditions to pause or modify chip operations, enabling efficient data collection and analysis without disrupting normal chip operation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If external debuggers and continuous monitoring are used to debug dedicated chips, then debugging capability is provided, but resource consumption increases and normal chip operation is disrupted

Engineering Contradiction:
Improvedebugging capabilityVSAvoidresource consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies preliminary action by pre-configuring trigger conditions and sampling parameters before debugging operations. The debugging monitor module is set up with predetermined trigger conditions that automatically initiate data sampling when specific events occur, eliminating the need for continuous monitoring and reducing resource consumption during normal chip operation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements periodic action through triggered sampling rather than continuous monitoring. The debugging monitor module samples data periodically based on trigger conditions (such as error events or specific state transitions), which significantly reduces resource consumption compared to continuous monitoring while maintaining effective debugging capability.

Inventive Principle:
Principle #19Periodic action

2Loss of information

If all chip internal signals are monitored continuously to capture error data, then complete debugging information is obtained, but hardware design complexity and resource usage increase

Engineering Contradiction:
Improvedebugging information completenessVSAvoidhardware design complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent applies local quality by selectively monitoring specific chip internal signals based on trigger conditions rather than continuously monitoring all signals. The debugging monitor module is configured to sample only relevant signals when predetermined conditions are met, reducing hardware complexity while capturing essential debugging information.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent extracts only the necessary debugging information by using trigger conditions to identify and sample specific signals of interest. Instead of monitoring all chip internal signals, the system extracts and records only those signals that meet the predetermined trigger conditions, simplifying the hardware design while maintaining debugging effectiveness.

Inventive Principle:
Principle #2Taking out (Extraction)

3Loss of information

If trigger conditions are set to start tracking after errors occur, then post-error data is captured, but data before errors (which is needed for root cause analysis) is lost

Engineering Contradiction:
Improveerror cause dataVSAvoidresponse time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-configuring trigger conditions that can detect error states and automatically initiate backward sampling. When a trigger condition is met (such as detecting an error), the debugging monitor module not only captures current data but also retrieves previously sampled data, ensuring that root cause information is preserved without requiring continuous monitoring of all signals.

Inventive Principle:
Principle #10Preliminary action

4Loss of information

If unconditional tracking is performed after trigger conditions are met, then all subsequent data is captured, but data volume becomes excessive and output interface performance requirements increase

Engineering Contradiction:
Improvedebugging data completenessVSAvoidoutput interface performance
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The patent applies partial action by selectively sampling and recording only relevant debugging data based on trigger conditions. Instead of unconditionally tracking all signals after a trigger, the system samples only specific signals that are relevant to the detected condition, reducing data volume while maintaining debugging effectiveness.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12085612B2On-chip debugging device and method
Publication Date: 2024.09.10 SUZHOU CENTEC COMM CO LTD
  • US12085612B2 patent drawing
  • US12085612B2 patent drawing
  • US12085612B2 patent drawing

AI summary

An on-chip debugging device and method is provided. The on-chip debugging device includes: an external interface module configured for outputting chip debugging state information to an external debugger and receiving a control instruction of the external debugger; a debugging mode control module configured for setting a to-be-sampled type of a specified chip internal signal and setting a debugging trigger condition according to the debugging configuration of the external debugger or the internal CPU; a debugging monitor module configured for sampling and recording the internal signal of the chip of the specified type so as to identify the running state of the chip; and a debugging information processing module configured for storing the running state of the chip in an internal debugging memory and sending it to the external debugger by the external interface module or sending it to the internal CPU via an internal bus. The on-chip debugging functions which are relatively simple, occupy less resources and have more powerful functions can be realized by the device and the method.