Dictionary Compression Parallel Search With Updated Match Results
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In dictionary compression, parallel searches of the history buffer for partial data strings can lead to inefficiencies due to hardware resource shortages, resulting in incomplete compression of data.
Innovation Solution
A dictionary compressor that includes a buffer, a search unit, and an update unit, where the search unit performs parallel searches to acquire match data strings and updates search results using a first search result to improve the efficiency of dictionary compression.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If parallel searches of the history buffer are performed for multiple partial data strings, then the throughput of dictionary compression is improved, but hardware resource shortage occurs causing past data strings to not be read at appropriate timing
Solution Approach 1:
The patent applies preliminary action by calculating hash values for all partial data strings before performing the actual search in the history buffer. This allows the system to prepare search keys in advance, enabling more efficient parallel search operations without overwhelming hardware resources during the critical search and read timing phase.
Solution Approach 2:
The patent introduces a hash table as an intermediary structure between the partial data strings and the history buffer. Instead of directly searching the history buffer for each partial data string, the system uses hash values to quickly locate candidate positions in the history buffer, reducing the computational burden and improving timing reliability.
2Speed
If parallel searches are performed for multiple partial data strings, then compression speed is increased, but data compression efficiency decreases due to failed conversions to match distance and length
Solution Approach 1:
The system performs preliminary hash value calculations and uses them to guide the search process, ensuring that even in parallel operation, all partial data strings that can be compressed are properly identified and converted to match distance and length pairs before the compression stage.
Solution Approach 2:
The patent implements a feedback mechanism where the results of parallel searches are collected and processed to ensure completeness. The system tracks which partial data strings were successfully compressed and which were not, allowing it to adjust and ensure that compression efficiency is maintained while benefiting from parallel processing speedups.
Data Source
AI summary
According to one embodiment, a dictionary compressor for compressing input first data includes a buffer and a search unit. The buffer stores data input to the dictionary compressor prior to the first data. The search unit acquires, from the first data, partial data strings each having a first data length and having head positions in the first data, respectively, that are sequentially shifted by a second data length shorter than the first data length. The search unit performs search processes in parallel and acquires search results respectively corresponding to the search processes, the search processes searching the buffer to acquire respective match data strings that at least partially match the partial data strings, respectively.