OpenCL application to accelerate the lossless image compression algorithm based on cascading fragmentation and the pixels sequence ordering

Abstract

The previous papers of authors describes approach to building the ordered sequence of image pixels at lossless compression, which comprises methods of cascading fragmentation, and code book. For fragment sized 6*6 the code book contained 22144 various bypasses, every must be estimated for the cost of coding. The search of optimal bypass is an exhaustive search. Present paper describes increasing the image lossless compression speed by using parallel computing based on OpenCL. Algorithm functions with great runtime were changed, in order to transfer calculations to OpenCL using GPU/CPU. Gained in experiments acceleration degree for different algorithm functions ranging in 3..32.