RAIM Memory ECC Decoding for Channel Failure Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current redundant memory systems face challenges in efficiently detecting and correcting errors, particularly due to the phenomenon of 'error mirroring' where external errors are replicated in failing channels, increasing the apparent number of errors and complicating error correction processes.
Innovation Solution
The implementation of a new error control coding system that computes channel-adjusted syndromes and employs efficient encoding and decoding algorithms to address error mirroring, allowing for the detection and correction of failing channels without external aid, while maintaining the strength of Reed-Solomon codes and ensuring regular error correction and detection coverage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional ECC techniques are used in redundant memory systems, then error detection and correction capabilities are provided, but error mirroring occurs where external errors are replicated in failing channels, increasing the apparent number of errors and complicating correction processes
Solution Approach 1:
The patent segments the error correction process by computing separate syndromes for each memory channel independently. Instead of treating all channels uniformly, the decoder computes channel-specific syndromes that isolate errors to their respective channels, preventing error mirroring from propagating across channels and simplifying the overall correction process.
Solution Approach 2:
The patent introduces channel syndromes as intermediary values that mediate between the raw error patterns and the final correction decisions. These syndromes act as intermediaries that capture channel-specific error information without being contaminated by errors from other channels, thereby preventing error mirroring and reducing correction complexity.
2Reliability
If multiple memory device failures are corrected, then system availability is improved, but the complexity of detecting and locating failing channels increases
Solution Approach 1:
The patent divides the memory system into independent channel segments, each with its own syndrome computation. This segmentation allows the system to identify and correct failures in one channel without being confounded by errors in other channels, making it easier to locate and correct multiple simultaneous failures across different channels.
Solution Approach 2:
The patent uses distinct syndrome values for each channel that act as unique identifiers or 'colors' for different channels. When an error occurs, the syndrome's channel-specific signature immediately identifies which channel is affected, making it trivial to locate failing channels even when multiple failures occur simultaneously.
3Measurement precision
If channel-adjusted syndromes are computed and decoded, then error correction accuracy is improved by preventing error mirroring, but the computational complexity increases
Solution Approach 1:
The patent segments the syndrome computation into channel-specific operations rather than computing a single global syndrome. This segmentation improves accuracy by preventing error mirroring, as each channel's syndrome only reflects errors in that channel. The computational complexity is managed by processing each channel independently and efficiently.
Solution Approach 2:
The patent changes the parameter being measured from global syndromes to channel-adjusted syndromes. This parameter change improves error detection accuracy by isolating channel-specific errors, while the computational burden is reduced by using efficient XOR-based syndrome computation that leverages the structure of the memory system.
Data Source
AI summary
Error correction and detection in a redundant memory system including a a computer implemented method that includes receiving data including error correction code (ECC) bits, the receiving from a plurality of channels, each channel comprising a plurality of memory devices at memory device locations. The method also includes computing syndromes of the data; receiving a channel identifier of one of the channels; and removing a contribution of data received on the channel from the computed syndromes, the removing resulting in channel adjusted syndromes. The channel adjusted syndromes are decoded resulting in channel adjusted memory device locations of failing memory devices, the channel adjusted memory device locations corresponding to memory device locations.