Multi-core System Dynamic Memory Partitioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional single-core systems face limitations in performance improvements when transitioning to multi-core systems due to structural differences, requiring new approaches for data processing and software adaptation.
Innovation Solution
A method for processing data in parallel in a multi-core system involves acquiring local memory information, partitioning data into subdata, and dynamically managing memory allocation through multi-buffering and repartitioning based on available memory capacity to optimize data distribution across multiple cores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is partitioned and allocated to multiple cores based on local memory information, then parallel processing performance is improved, but system complexity increases due to dynamic memory management requirements
Solution Approach 1:
The patent divides the data into multiple partitions and assigns them to different cores based on local memory information. This segmentation enables parallel processing by distributing workloads across multiple cores while managing memory resources efficiently, directly resolving the contradiction between improving productivity and managing system complexity.
Solution Approach 2:
The patent implements dynamic memory allocation and repartitioning based on runtime changes in local memory capacity. When a core's local memory capacity changes, the system dynamically adjusts data allocation through repartitioning operations, allowing the system to adapt to varying conditions while maintaining optimal parallel processing performance.
2Productivity
If multi-buffering is performed when local memory capacity increases, then data processing efficiency is improved, but memory allocation complexity increases
Solution Approach 1:
The patent monitors local memory capacity at runtime and uses this feedback to trigger multi-buffering operations when capacity increases. This feedback mechanism allows the system to automatically adjust memory allocation strategies based on actual hardware conditions, improving processing efficiency while managing complexity through automated responses to capacity changes.
Solution Approach 2:
The patent changes memory allocation parameters dynamically based on local memory capacity. When capacity increases, the system modifies allocation parameters to enable multi-buffering, allowing more efficient data processing. This parameter adjustment approach resolves the contradiction by adapting the system behavior to hardware conditions without manual intervention.
3Productivity
If repartitioning is performed when local memory capacity is reduced, then data distribution optimization is improved, but processing time increases due to frequent repartitioning operations
Solution Approach 1:
The system performs self-adjustment through automated repartitioning when local memory capacity changes. This self-service mechanism ensures optimal data distribution without external intervention, improving productivity by continuously adapting to hardware conditions while minimizing the impact of repartitioning operations on overall processing time through efficient algorithms.
Data Source
AI summary
A multi-core system and a method for processing data in parallel in the multi-core system are provided. In the multi-core system, partitioning and allocating of data may be dynamically controlled based on local memory information. Thus, it is possible to increase an availability of a Central Processing Unit (CPU) and a local memory, and is possible to improve a performance of data parallel processing.