Semiconductor Memory ECC Engine for Multi-Bit Syndrome Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing bit errors and decreasing yield in DRAM devices due to reduced fabrication design rules affect the performance and reliability of semiconductor memory devices.
Innovation Solution
An error correction code (ECC) engine is integrated into semiconductor memory devices, utilizing a primitive polynomial-based ECC encoder and decoder to generate and correct syndromes for single, adjacent, and non-adjacent bit errors in memory cells, enhancing error correction efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If fabrication design rules are reduced to increase memory density, then memory capacity is improved, but bit error rate increases and yield decreases
Solution Approach 1:
The patent applies preliminary action by generating syndromes in advance during the write operation, before data is read back. The ECC encoder computes syndromes based on the data being written and stores them alongside the main data. When reading, these pre-computed syndromes are immediately available for error detection and correction, eliminating the need to recompute them and reducing read latency.
Solution Approach 2:
The patent uses syndromes as an intermediary element between the stored data and the error correction process. The syndrome acts as a mediator that contains encoded information about potential errors in the data, allowing the ECC decoder to identify and correct errors without directly analyzing the entire data pattern. This intermediary approach enables efficient error detection and correction.
2Reliability
If traditional ECC methods are used, then single bit errors are corrected, but adjacent and non-adjacent bit errors cannot be effectively corrected
Solution Approach 1:
The patent implements universality by designing a single syndrome generation and application mechanism that handles multiple error patterns (single bit errors, adjacent bit errors, and non-adjacent bit errors). The same ECC encoder and decoder infrastructure is used for all error types, with the syndrome automatically adapting to the specific error pattern detected. This multi-functional approach eliminates the need for separate correction circuits for different error types.
Solution Approach 2:
The patent applies parameter changes by modifying the syndrome generation process to account for different error patterns. The ECC encoder generates syndromes that encode information about multiple possible error types. During decoding, the syndrome values are analyzed to determine which error pattern is present, and the correction process adjusts its parameters accordingly to handle the specific error type detected.
3Reliability
If comprehensive error correction for all error patterns is implemented, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent applies discarding and recovering by selectively applying syndromes based on the detected error pattern. The ECC decoder analyzes the syndrome to determine which type of error occurred (single bit, adjacent bits, or non-adjacent bits) and only applies the corresponding correction. This selective approach discards unnecessary correction operations for error patterns that don't match, reducing computational complexity while maintaining comprehensive error correction capability.
Data Source
AI summary
An ECC engine of a semiconductor memory device includes an ECC encoder and an ECC decoder. The ECC encoder generates parity data based on main data based on a primitive polynomial and stores a codeword including the main data and the parity data in a target page. The ECC decoder reads the codeword from the target page based on an address to generate a syndrome and corrects at least one error bit in the read codeword based on the syndrome by respectively applying different syndromes to a single bit error in the read codeword, adjacent bit errors and non-adjacent bit errors occurring in non-adjacent two memory cells in the target page. The ECC decoder generates the different syndromes based on a parity check matrix generated as a function of the primitive polynomial. The primitive polynomial has an alpha matrix as a solution belonging to a Galois field.