Memory Controller Multi-Core Job Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Memory systems experience delayed event processing due to completion delays in specific jobs, leading to reduced response speed to hosts.
Innovation Solution
A memory system with a memory controller that utilizes multiple cores to monitor events and perform distributed execution of jobs by selecting appropriate cores to run specific firmwares, dividing jobs into sub-jobs, and storing information in shared memory for efficient execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single core executes a target job, then the job can be completed, but the event processing completion time is delayed
Solution Approach 1:
The patent segments the target job into multiple sub-jobs that can be executed in parallel by different cores. The control core divides the workload and distributes sub-jobs to worker cores, enabling simultaneous execution and reducing overall completion time while improving event processing productivity.
2Productivity
If multiple cores are used for distributed execution, then processing speed improves, but system complexity increases
Solution Approach 1:
The patent introduces a control core as an intermediary that manages the coordination between worker cores. The control core handles job segmentation, sub-job distribution, and result aggregation, simplifying the complexity of multi-core coordination by centralizing control functions while enabling parallel execution.
Solution Approach 2:
The patent implements a universal firmware loading mechanism where the control core can load and manage firmwares for multiple worker cores. This multi-functional approach allows the same control infrastructure to handle diverse job types and core configurations, reducing system complexity through standardized management.
3Speed
If job execution is distributed across multiple cores, then response speed to host improves, but firmware management complexity increases
Solution Approach 1:
The patent implements a self-service firmware management system where worker cores automatically load and execute firmwares based on sub-job assignments from the control core. This automated approach eliminates manual firmware configuration for each core, reducing management complexity while enabling fast parallel response to host requests.
Data Source
AI summary
Embodiments of the present disclosure relate to a memory system and an operating method thereof. According to the embodiments of the present disclosure, the memory system may include a plurality of cores, a control core, and a shared memory. When processing the event, the control core may select a first core executing a target job requiring distributed execution among the plurality of cores, and the first core may run a first firmware among the plurality of firmwares to execute the target job. The control core may select a second core to execute the target job together with the first core, and may control the second core to run the first firmware. The control core may control the first core and the second core to perform distributed execution of the target job.