Memory Controller Bank Scheduling for Lower-Power Plane-Level Jobs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High-performance and high-capacity semiconductor memory devices consume excessive power, necessitating the optimization of power consumption.
Innovation Solution
A memory controller determines a target bank within a storage device based on plane-level job information to optimize power consumption by minimizing overlap in job performance times, and re-determines the target bank if low overlap is expected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If high-performance and high-capacity memory devices are used, then data management capability is improved, but power consumption increases
Solution Approach 1:
The memory device is divided into multiple banks, and each bank is further divided into multiple planes. This segmentation allows the memory controller to selectively activate only the necessary banks and planes for pending jobs, rather than keeping the entire high-capacity device active, thereby reducing overall power consumption while maintaining data management capability.
Solution Approach 2:
The memory controller dynamically determines target banks based on real-time plane information of pending jobs. By adaptively selecting which banks to activate based on current workload requirements, the system optimizes power consumption while maintaining the necessary data management performance.
2Productivity
If multiple banks are activated simultaneously, then job processing parallelism is improved, but power consumption increases
Solution Approach 1:
The system dynamically adjusts the number and selection of active banks based on the specific pending jobs. Rather than maintaining a fixed high level of parallelism that consumes constant power, the memory controller activates only the minimum necessary banks to handle current job requirements, achieving optimal balance between productivity and power consumption.
Solution Approach 2:
The memory controller changes operational parameters (which banks are active) based on workload characteristics. By varying the activation state of banks according to job requirements, the system achieves efficient parallelism when needed while reducing power consumption during lower-demand periods.
3Use of energy by moving object
If banks are frequently switched to optimize power, then power consumption is reduced, but system complexity increases
Solution Approach 1:
The memory controller autonomously manages bank selection based on plane information of pending jobs without requiring external intervention or complex coordination. The controller self-determines the optimal target bank for each job, simplifying the overall system architecture while achieving power optimization.
Data Source
AI summary
A storage device is included. The storage device includes: a memory device including a plurality of planes, wherein each of the plurality of planes is provided in one of a plurality of banks of the memory device; and a memory controller configured to: receive, from a host, a plurality of jobs to be performed on the memory device, the plurality of jobs including a plane-level job to be performed in a plane from among the plurality of planes; determine, for each of the plurality of planes at a first time, a target bank from among the plurality of banks based on plane information associated with a job from among the plurality of jobs that is pending in the storage device; and transmit the job for the target bank to the memory device.