Dynamic Memory Die Allocation via PVT-Aware Defect Lookup
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage devices lack the ability to dynamically allocate memory effectively based on process, voltage, and temperature (PVT) changes, leading to inefficient use of memory dies and potential defects under specific conditions.
Innovation Solution
A storage device with a state detector, memory information storage, and memory controller that monitors temperature and voltage, allocates memory dies without defects at the current conditions, and performs error correction for dies that may have defects under different conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If memory allocation is performed without considering PVT conditions, then allocation speed is improved, but memory reliability deteriorates due to defects under specific conditions
Solution Approach 1:
The system performs preliminary testing of memory dies under various PVT conditions during manufacturing, storing defect information in advance. During operation, the memory controller retrieves pre-stored defect information corresponding to current PVT conditions to perform allocation, avoiding real-time testing while ensuring reliability.
Solution Approach 2:
The memory allocation system dynamically adapts to changing PVT conditions by retrieving condition-specific defect information from storage. The memory controller selects memory dies based on current temperature, voltage, and process conditions, making the allocation process adaptive rather than static.
2Measurement precision
If all memory dies are tested under all PVT conditions, then defect detection precision is improved, but testing time and complexity increase
Solution Approach 1:
Instead of uniformly testing all memory dies under all PVT conditions, the system applies targeted testing based on local characteristics. Defect information is stored specifically for each PVT condition combination, and only the relevant condition-specific data is retrieved during allocation, reducing unnecessary testing.
Solution Approach 2:
Comprehensive PVT testing is performed preliminarily during manufacturing before the memory devices are deployed. The results are stored in defect information storage, allowing the system to achieve high defect detection precision during operation without performing repeated comprehensive tests.
3Reliability
If memory allocation considers multiple PVT conditions, then memory reliability is improved, but allocation complexity increases
Solution Approach 1:
A defect information storage component acts as an intermediary between PVT condition monitoring and memory allocation decisions. The storage component pre-organizes defect information according to PVT conditions, allowing the memory controller to make reliable allocation decisions by simple lookup rather than complex real-time analysis.
Solution Approach 2:
The complex task of analyzing PVT conditions and identifying suitable memory dies is performed preliminarily during manufacturing and testing. The results are pre-organized in defect information storage, converting a complex real-time decision problem into a simple retrieval and matching operation.
4Reliability
If defective memory dies are excluded from allocation, then memory reliability is improved, but usable memory quantity decreases
Solution Approach 1:
The system dynamically determines which memory dies are defective based on current PVT conditions. A memory die may be excluded under certain conditions but included under others, maximizing the usable memory quantity while maintaining reliability by excluding dies only when necessary for the current operating conditions.
Data Source
AI summary
Provided herein may be a storage device for supporting dynamic allocation of memory and a method of operating the same. The storage device may include a plurality of memory dies, a state detector configured to detect respective memory states of the plurality of memory dies, a memory information storage configured to store defect information that is information about memory dies in which defects have occurred among the plurality of memory dies, and a memory controller configured to, in response to a memory die allocation request for performing an operation corresponding to an externally provided operation request, determine allocation of a memory die based on a result of comparison between each detected memory state and the defect information.