Error-Tolerant Processing Circuitry for Adaptive Voltage and Clock Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data processing systems face inefficiencies in error management, particularly in detecting and repairing errors that occur during operation, which can lead to excessive time and circuit overhead, and limit the operating parameters of the system.
Innovation Solution
The system incorporates an error-resistant and error-prone portion of processing circuitry, where errors in the error-prone portion are tolerated and used to indicate the limits of operating parameters, allowing the system to continue operation without correcting these errors, thus maintaining a non-zero error rate and optimizing performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If error detection and repair mechanisms are implemented in data processing systems, then system reliability is improved, but time overhead and circuit complexity increase
Solution Approach 1:
The processing circuitry is divided into error-resistant portion and error-prone portion, segmenting the data processing function to handle different bits with different error tolerance levels
Solution Approach 2:
Different portions of the processing circuitry are assigned different error resistance characteristics - the error-resistant portion has higher error resistance while the error-prone portion has lower error resistance, matching the different error tolerance requirements of different bit positions
2Reliability
If error detection and repair mechanisms are implemented in data processing systems, then system reliability is improved, but circuit complexity increases
Solution Approach 1:
The processing circuitry is divided into error-resistant portion and error-prone portion, segmenting the data processing function to handle different bits with different error tolerance levels
Solution Approach 2:
Different portions of the processing circuitry are assigned different error resistance characteristics - the error-resistant portion has higher error resistance while the error-prone portion has lower error resistance, matching the different error tolerance requirements of different bit positions
3Productivity
If operating parameters are pushed to higher clock frequencies and lower voltages, then productivity is improved, but error rate increases
Solution Approach 1:
The processing circuitry is divided into error-resistant portion and error-prone portion, segmenting the data processing function to handle different bits with different error tolerance levels
Solution Approach 2:
Different portions of the processing circuitry are assigned different error resistance characteristics - the error-resistant portion has higher error resistance while the error-prone portion has lower error resistance, matching the different error tolerance requirements of different bit positions
Data Source
AI summary
A data processing system 2 is used to perform processing operations to generate a result value. The processing circuitry which generates the result value has an error resistant portion 32 and an error prone portion 30. The probability of an error in operation of the error prone portion for a given set of operating parameters (clk, V) is greater than the probability of an error for that same set of operating parameters within the error resistant portion. Error detection circuitry 38 detects any errors arising in the error prone portion. Parameter control circuitry 40 responds to detected errors to adjust the set of operating parameters to maintain a non-zero error rate in the errors detected by the error detection circuitry. Errors within the one or more bits generated by the error prone portion are not corrected as the apparatus is tolerant to errors occurring within such bit values of the result value.


