NAND Flash Peak Current Budgeting for Concurrent Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing power consumption in NAND flash memory systems becomes challenging when multiple memory devices operate concurrently, as peak current demands can exceed specifications, leading to potential quality of service issues and voltage droops due to varying RC characteristics of bonding wires.
Innovation Solution
Implementing predictive peak current monitoring and using multiple current demand budgets to manage power distribution among dies, where each die assesses its expected peak current magnitude and adjusts operations based on a main and secondary budget to avoid exceeding power limits, allowing for informed decision-making on pausing or transitioning to low-peak-current operating modes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple memory devices operate concurrently, then system productivity increases, but peak current demand exceeds specifications causing voltage droops
Solution Approach 1:
The system performs preliminary assessment of expected peak current magnitude before initiating access operations. Each die determines its expected peak current demand in advance and communicates this information to other dies, allowing the system to proactively manage power distribution and prevent voltage droops before they occur.
Solution Approach 2:
The system dynamically adjusts operating modes based on real-time power availability. Dies can transition between normal operating mode and low-peak-current operating mode depending on the current power distribution state, allowing flexible adaptation to varying power conditions while maintaining overall system productivity.
2Productivity
If multiple memory devices operate concurrently, then system throughput increases, but voltage droops occur due to varying RC characteristics
Solution Approach 1:
The system implements a feedback mechanism where each die monitors the power distribution state and communicates power availability information to other dies. This feedback loop allows the system to adjust operations in real-time, ensuring voltage stability is maintained even when multiple devices operate concurrently with varying RC characteristics.
Solution Approach 2:
The system changes operational parameters (operating mode) based on power availability. When power is sufficient, dies operate in normal mode for maximum performance; when power is constrained, dies transition to low-peak-current mode to maintain voltage stability, thus adapting to varying RC characteristics dynamically.
3Speed
If normal operating mode is used, then access speed is maximized, but power consumption exceeds available power distribution
Solution Approach 1:
The system dynamically selects operating mode based on real-time power availability assessment. Dies can switch between normal operating mode (higher speed, higher power) and low-peak-current operating mode (lower speed, lower power), allowing the system to optimize the trade-off between access speed and power consumption according to current power distribution conditions.
Solution Approach 2:
The system changes the operating parameter (mode) to match power availability. When power is abundant, normal mode provides maximum access speed; when power is constrained, transitioning to low-peak-current mode reduces power consumption to match available power distribution, preventing power violations.
4Use of energy by moving object
If power management control is implemented, then power consumption is managed, but device complexity increases
Solution Approach 1:
The power management system is segmented and distributed across individual dies rather than centralized. Each die independently determines its own expected peak current demand and makes autonomous decisions about operating mode selection, reducing the complexity burden on any single component while achieving system-wide power management.
Solution Approach 2:
Each die performs self-assessment of its power requirements and makes autonomous decisions about its operating mode. The system uses self-service mechanisms where dies communicate their power needs and adjust their own operations based on collective power availability information, reducing the need for complex external control logic.
Data Source
AI summary
A memory device might include a controller configured to cause the memory device to generate a first sum of expected peak current magnitudes for a plurality of memory devices, and generate a second sum of expected peak current magnitudes for a subset of the plurality of memory devices, if the memory device were to initiate a next phase of an access operation in a selected operating mode; to compare the first sum to a first current demand budget for the plurality of the memory devices; to compare the second sum to a second current demand budget for the subset of memory devices; and to initiate the next phase of the access operation in the selected operating mode in response to the first sum being less than or equal to the first current demand budget and the second sum being less than or equal to the second current demand budget.