CUDA lossless data compression algorithms: A comparative study

Abstract

As data is being produced in an unprecedented rate, lossless data compression has become an important step in data storage and transmission processing as it helps to reduce the resource usage in these fields. However, the current bottlenecks of existing lossless data compression tools causes the compression and decompression process to be very time consuming for large-scale data processing. General purpose computing on graphic processing units (GPUs) introduces new opportunities where parallelism is available and this could be the solution to address the bottlenecks of the data compression. Several parallel lossless data compression algorithms on GPU have been proposed but there isn't much comparative study conducted on the performance among them. This paper examines the existing CUDA lossless data compression algorithms and compares their performance. These CUDA data compression algorithms are evaluated and tested on different datasets of different sizes. The article is concluded by a comparison of these CUDA lossless data compression algorithms from different aspects.