Memory System Dynamic Parameter Adjustment for Workload Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face a trade-off between uniformity of time required for processing commands and data throughput, necessitating a solution to optimize performance by adjusting parameter values based on workload classes.
Innovation Solution
A memory system that stores parameter values in a nonvolatile storage space according to workload classes, detects command ratios, selects the appropriate workload class, processes commands under determined execution conditions, and updates parameter values based on performance results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the memory system uses fixed parameter values for command processing, then the uniformity of time required for processing commands is improved, but the data throughput per hour deteriorates
Solution Approach 1:
The patent implements dynamic parameter adjustment by detecting workload class based on command ratios and selecting different parameter groups accordingly. The system transitions from fixed parameters to dynamically adjustable parameters that adapt to varying workload conditions, resolving the trade-off between uniformity and throughput by optimizing for each workload type separately
Solution Approach 2:
The patent changes operational parameters based on detected workload class. Multiple groups of parameters are stored in the memory device, and the controller selects the appropriate group based on the detected workload characteristics, allowing the system to optimize both uniformity and throughput by using different parameter sets for different workload scenarios
2Productivity
If the memory system optimizes for high data throughput, then the productivity is improved, but the uniformity of time required for processing commands deteriorates
Solution Approach 1:
The system stores multiple parameter groups optimized for different workload characteristics and selects the appropriate group based on detected command ratios. This allows the system to achieve high throughput for specific workload types while maintaining uniformity by using parameters specifically optimized for that workload class
3Device complexity
If the memory system uses a single set of parameter values, then the device complexity is reduced, but the adaptability to different workload classes deteriorates
Solution Approach 1:
The patent implements a universal parameter storage structure where a single memory device contains multiple parameter groups that can serve different workload classes. The controller detects workload characteristics and selects the appropriate parameter group, making the system adaptable to various workloads without requiring separate hardware configurations for each workload type
Solution Approach 2:
The system pre-stores multiple groups of parameters in the memory device during manufacturing or initialization. These pre-prepared parameter sets are ready for immediate selection based on detected workload class, eliminating the need for real-time parameter calculation or complex adaptive algorithms
Data Source
AI summary
A memory system comprising: a memory device having a nonvolatile specific storage space configured to store workload information including groups of parameter values, grouped respectively corresponding to a plurality of workload classes in a table form, and a controller configured to detect a ratio of a set command inputted from an outside in a set operation mode, select one of the workload classes as a detected class, load, from the specific storage space, one of the groups corresponding to the detected class, process the set command under an execution condition determined by applying the loaded group, and update the group corresponding to the detected class with parameter values inputted from the outside.