3D-Stacked NVM Compression via OR Logic and Identifier Rotation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data compression methods for NVM face challenges in reducing writing power consumption and latency due to complex algorithms and trade-offs between compression efficiency and system performance, while also dealing with the limitations of NVM such as high writing power consumption, latency, and short service life.
Innovation Solution
A hardware-supported 3D-stacked NVM data compression method that divides written-back data into sub-blocks, uses OR or exclusive OR operations to determine compression strategies, and employs identifier rotation for efficient data placement, reducing hardware costs and improving wear-leveling, thereby enhancing writing speed and extending NVM service life.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If complex compression algorithms are used to improve compression efficiency, then data volume is reduced, but memory latency and system performance deteriorate
Solution Approach 1:
The patent segments data into fixed-size units (e.g., 64 bytes) and processes each unit independently through simple compression operations. This segmentation allows parallel processing and avoids the complexity of analyzing entire data streams, thereby reducing latency while maintaining compression efficiency.
Solution Approach 2:
The patent employs lightweight, disposable compression structures such as fixed-length prefix codes and simple run-length encoding schemes that can be quickly computed and discarded after use. These inexpensive compression mechanisms do not require complex state management or long processing sequences, thus minimizing latency overhead.
2Productivity
If compression algorithms with low compression rate are used, then system performance is maintained, but compression effectiveness is insufficient to improve NVM defects
Solution Approach 1:
The patent dynamically adjusts compression parameters such as block size, encoding precision, and compression threshold based on data characteristics and system state. By changing these parameters adaptively, the system achieves high compression rates for suitable data patterns while maintaining fast processing for other cases, thus balancing compression effectiveness with system performance.
3Quantity of substance
If multiple memory chips are organized in 3D-stacked structure to increase capacity, then memory capacity and bandwidth are improved, but writing power consumption and latency remain high
Solution Approach 1:
The patent extracts and compresses redundant information from data before writing to NVM, removing unnecessary data elements that would otherwise consume write operations and power. By taking out only the essential information and representing it more compactly, the system reduces the number of write operations required, thereby lowering writing power consumption in 3D-stacked NVM systems.
4Use of energy by moving object
If data compression is applied to reduce data volume, then writing power consumption is reduced, but hardware complexity increases
Solution Approach 1:
The patent replaces complex mechanical or software-based compression systems with simplified hardware logic circuits that perform basic compression operations. By substituting intricate control mechanisms with dedicated hardware structures such as lookup tables, comparators, and simple encoders, the system achieves data compression with minimal hardware overhead and without requiring complex control logic.
Data Source
AI summary
The present disclosure involves a hardware-supported 3D-stacked NVM data compression method and system, involving setting a first identifier to mark a compression state of written-back data, the method at least comprising steps of: dividing the written-back data into a plurality of sub-blocks and acquiring a plurality of first output results through OR operations among the sub-blocks, respectively, or acquiring a plurality of second output results through exclusive OR operations among the sub-blocks, and determining a compression strategy for the written-back data based on the first output results or the second output results; and setting a second identifier to mark a storing means of the written-back data so that the second identifier is in pair with the first identifier, and configuring a storage strategy for the written-back data that includes at least rotating the second identifier.