Compressed Data Binding With ECC to Reduce Memory Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data processing technologies require excessive memory access when storing data and error control codes together, which negates the bandwidth reduction achieved by lossless compression, leading to increased transfer bandwidth and inefficient memory access.
Innovation Solution
A data processing device with a binding section that combines compressed data with error control codes and transfers them in units of a predetermined data length, reducing the number of memory accesses by utilizing the gap created during compression to include the error control code, thereby minimizing the increase in memory access.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data and error control code are stored separately in memory, then error detection and correction capability is maintained, but memory access amount increases
Solution Approach 1:
The patent combines compressed data and error control codes into a single data structure stored together in memory. The binding section binds the compressed data with its corresponding error control code, allowing them to be transferred and stored as one unit, thereby reducing memory access operations while maintaining error detection and correction capability.
Solution Approach 2:
The error control code is nested within the compressed data structure. The code binding section integrates the error control code with the compressed data, creating a nested structure where the error control code is embedded alongside the data it protects, enabling simultaneous storage and reduced memory access.
2Loss of energy
If lossless compression is applied to data, then transfer bandwidth is reduced, but adding error control code increases memory access amount
Solution Approach 1:
The patent merges the compressed data with its error control code into a single bound data unit. This binding occurs after compression, allowing the system to maintain the bandwidth reduction benefits of compression while minimizing the additional memory access overhead by transferring both compressed data and error control code together in one operation.
3Reliability
If error control code is added to compressed data, then error detection capability is maintained, but data length increases
Solution Approach 1:
The patent applies error control codes selectively to compressed data blocks, where each error control code is bound to a specific compressed data segment. This local binding approach ensures error detection capability for each data block while minimizing the overall data length increase by only adding error control codes where necessary.
Data Source
AI summary
Provided is a data processing device that reduces the amount of memory access in a case where data and an error control code are to be stored in a memory. The processing device includes a data compression section, a code generation section, a binding section, and a transfer section. The data compression section generates second data by performing a predetermined compression process on first data that is to be stored in a memory and of a predetermined data length. The code generation section generates an error control code for the first data or the second data. The binding section generates third data by binding the second data generated by the data compression section to the error control code generated by the code generation section. The transfer section transfers the third data generated by the binding section to the memory in units of the predetermined data length.