Hierarchical Data Aggregation for Computational Storage Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computational storage devices struggle to perform meaningful operations on modified data portions due to incomplete information, leading to inefficient data retrieval and processing, especially when data is compressed or encrypted.
Innovation Solution
Data is divided into portions before modification, allowing computational storage devices to restore and perform operations locally, such as decryption and decompression, thereby reducing data transfer and enhancing processing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is compressed or encrypted before storage, then data security and storage efficiency are improved, but computational storage devices cannot perform meaningful operations on the modified data portions
Solution Approach 1:
The patent divides data into multiple portions and stores them across different storage devices. By segmenting data, the system enables computational storage devices to perform operations on individual portions without requiring full data decryption or decompression, thus maintaining security while enabling local processing capabilities.
2Productivity
If data is divided into portions and stored across multiple devices, then processing can be distributed, but data retrieval requires coordinating multiple storage devices
Solution Approach 1:
The patent performs preliminary actions by pre-processing data portions at storage devices before retrieval. Computational storage devices execute operations such as compression, encryption, or filtering on data portions while they are stored, so that when data is retrieved, much of the processing has already been completed, reducing the coordination burden during data access.
3Loss of energy
If computational storage devices perform operations locally, then bandwidth consumption is reduced, but devices need to restore modified data portions which requires additional computational resources
Solution Approach 1:
The patent applies partial action by having computational storage devices perform only the necessary operations on data portions rather than restoring and processing complete data sets. Devices execute specific operations such as filtering, aggregation, or transformation on individual data portions, consuming computational resources only where needed while minimizing bandwidth usage.
Data Source
AI summary
A method for computational storage may include storing, at a storage device, two or more portions of data, wherein a first one of the two or more portions of data comprises a first fragment of a record and a second one of the two or more portions of data comprises a second fragment of the record, and performing, by the storage device, an operation on the first and second fragments of the record. The method may further include performing, by the storage node, a second operation on first and second fragments of a second record. The operation may include a data selection operation, and the method may further include sending a result of the data selection operation to a server. The method may further include sending a result of a first data selection operation to a server.