Shared Memory File Access via Working Buffer Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Shared memory multiprocessor systems face inefficiencies in data transfer and processing due to the lack of a streamlined method for distributing and processing data across multiple processors, leading to suboptimal performance in parallel execution of applications.
Innovation Solution
A method involving the allocation of working buffers between a shared file and multiple address spaces, where data is copied and processed in parallel by processors, with aggregators managing data transfer between the shared file, working buffers, and address spaces, enabling simultaneous data transfer and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is transferred sequentially from shared file to processors, then data transfer can be managed simply, but processing time increases and parallel efficiency decreases
Solution Approach 1:
The patent introduces working buffers as intermediary storage structures between the shared file and processor address spaces. Each working buffer is associated with a specific processor and enables parallel data transfer operations. By segmenting the data transfer process into multiple simultaneous operations across different buffers, the system achieves both improved processing efficiency and reduced transfer time without compromising memory management simplicity.
Solution Approach 2:
The working buffers serve as intermediary structures that mediate between the shared file and processor address spaces. These buffers enable decoupled data transfer and processing operations, allowing data to be transferred in parallel while maintaining simple memory management. The intermediary buffers resolve the contradiction by providing a layer that supports both efficiency and simplicity simultaneously.
2Productivity
If multiple working buffers are allocated for parallel data transfer, then data processing efficiency improves, but device complexity increases
Solution Approach 1:
The working buffers are designed with universal characteristics that allow them to serve multiple functions: data transfer staging, parallel processing coordination, and memory management simplification. Each buffer is associated with a processor but can be managed through a unified mechanism, enabling parallel processing performance improvement without proportionally increasing memory management complexity.
Solution Approach 2:
The patent changes the parameter of data transfer from sequential to parallel by introducing multiple working buffers. This parameter change enables simultaneous data transfer operations across different processors while the buffers themselves are designed with simplified management characteristics. The parameter change in transfer methodology brings productivity improvement without the expected complexity increase.
Data Source
AI summary
A method for processing using a shared file that includes allocating a first working buffer between the shared file and a plurality of address spaces, wherein each of the plurality of address spaces is associated with one of a plurality of processors, copying first data from the shared file to the first working buffer by a first aggregator copying the first data from the first working buffer to the plurality of address spaces by the first aggregator, processing the first data, in parallel, by the plurality of processors to obtain a result, wherein the plurality of processors access data from the plurality of address spaces, and storing the result in the shared memory.