Image Data Compression Mapping LSBs for 10-Bit GPU Support
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data compression technologies struggle to efficiently compress and decompress image data, particularly for 10-bit data values, without significantly increasing silicon area in GPUs and other processing units.
Innovation Solution
A computer-implemented method and units for compressing and decompressing image data by mapping the two least significant bits of each data value onto an m-bit encoding, selected from 2m possible encodings, to minimize error and maintain high image quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If compression and decompression units are configured in hardware to compress and decompress 10-bit data values in addition to 8-bit data values, then support for 10-bit data is achieved, but silicon area increases significantly
Solution Approach 1:
The compression unit is designed with a universal architecture that can handle both 8-bit and 10-bit data values using the same hardware components. The unit selects appropriate encoding schemes based on input data width, allowing a single multi-functional unit to replace what would otherwise require separate dedicated units for each data type.
Solution Approach 2:
The invention changes the parameter of data width handling by using variable-length encodings (5-bit for 8-bit data, 10-bit for 10-bit data) and adjustable replication factors. This allows the same hardware structure to adapt to different input data widths without requiring separate dedicated circuits for each data type.
2Loss of energy
If data is compressed before transfer to memory, then memory bandwidth is reduced and power consumption decreases, but compression complexity increases
Solution Approach 1:
The compression process is segmented into distinct stages: analyzing the input data pattern (uniform vs. non-uniform), selecting the appropriate encoding scheme, and executing the corresponding compression algorithm. This segmentation allows the system to use simple encoding paths for common cases while maintaining the option for more complex encoding when needed.
Solution Approach 2:
The invention applies partial compression actions by using different encoding depths based on data characteristics. For uniform data, a simple encoding with minimal replication is used. For non-uniform data, more aggressive compression with higher replication factors is applied, optimizing the balance between compression ratio and computational effort.
Data Source
AI summary
A computer-implemented method for compressing, an input group of m data values compresses the two least significant bits of each of the data values by mapping the two least significant bits of each of the data values in the input group of m data values collectively onto an m-bit encoding and storing the m-bit encoding, the m-bit encoding being selected from 2m m-bit encodings, the 2m m-bit encodings comprising a first group of encodings comprising (2m−4) m-bit encodings and a second group of encodings comprising four m-bit encodings, wherein if the selected encoding is an encoding from the first group of encodings then the selected encoding represents the two least significant bits for a representative group of m data values in which the second least significant bit of each of the data values is the same as a respective bit of the m-bit encoding, and wherein if the selected encoding is an encoding from the second group of encodings then the selected encoding represents the two least significant bits for a representative group of m data values in which the two least significant bits for each of the data values in the representative group are equal to the two least significant bits of the other data values in the representative group.