ECC Memory Write Masking Without Pre-Read Overhead
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory devices experience increased response time and power consumption due to the need for pre-reading data before executing a write command, especially when implementing a data masking DM function with an error correction circuit (ECC) on chip, which is inefficient for high-speed data processing.
Innovation Solution
A memory device and system that includes a write command determination unit, a data modulation unit, and an ECC engine, which allows for the identification of whether a write command is a normal write or a Read Modify Write (RMW) command, enabling the generation of modulation data by combining read and write data without pre-reading, thus reducing unnecessary delays and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If pre-reading data is performed before write command execution to support data masking function, then data masking capability is achieved, but response time increases
Solution Approach 1:
The patent applies preliminary action by determining the write command type (normal write or RMW) before actual write execution. The write command determination unit identifies whether masking is needed in advance, allowing the system to prepare appropriately without unnecessarily pre-reading data for all write commands. This selective preliminary determination resolves the contradiction by enabling data masking capability only when required, thus avoiding the time penalty of universal pre-reading.
Solution Approach 2:
The patent implements dynamics by making the write operation mode flexible and adaptive based on command type. The system dynamically switches between two modes: (1) direct write mode for normal write commands without masking, and (2) read-modify-write mode for commands requiring masking. This dynamic adaptation allows the system to achieve data masking capability only when needed, preventing the response time increase that would occur with static pre-reading for all writes.
2Adaptability or versatility
If pre-reading data is performed before write command execution, then data masking function is supported, but power consumption increases
Solution Approach 1:
The write command determination unit performs preliminary identification of the command type before executing the write operation. By determining in advance whether masking is required, the system avoids unnecessary pre-reading operations for normal write commands, thereby reducing power consumption while maintaining data masking functionality when needed.
Solution Approach 2:
The system dynamically adjusts its operation mode based on the write command type, switching between energy-efficient direct write mode and data masking mode. This dynamic behavior ensures that the power-consuming pre-reading operation is performed only when absolutely necessary, resolving the contradiction between supporting data masking function and minimizing power consumption.
3Device complexity
If conventional write operation is used without command type identification, then processing is simpler, but response time increases due to unnecessary pre-reading
Solution Approach 1:
The patent segments the write operation into distinct types (normal write and RMW) based on command identification. By dividing write operations into categories, the system can apply different processing paths: simple direct write for normal commands and read-modify-write for masking commands. This segmentation maintains relative simplicity while eliminating the response time penalty of unnecessary pre-reading for all writes.
Solution Approach 2:
The system dynamically selects the appropriate write operation mode based on command type identification. Rather than using a static, overly cautious approach that pre-reads all writes, the system adapts its behavior to match the actual requirements of each command, achieving faster response times while maintaining manageable complexity through automated command-type-based decision making.
Data Source
AI summary
A memory device, a memory system, and a method of operating the same. The memory device includes a memory cell array including a plurality of memory cells and a write command determination unit (WCDU) that determines whether a write command input to the memory device is (to be) accompanied a masking signal. The WCDU produces a first control signal if the input write command is (to be) accompanied by a masking signal. A data masking unit combines a portion of read data read from the memory cell array with a corresponding portion of input write data corresponding to the write command and generates modulation data in response to the first control signal. An error correction code (ECC) engine generates parity of the modulation data.