Implementation of Compression Technique JPEG2000 on CUDA

Abstract

The strong need for increased computational performance in science and engineering has led to the use of heterogeneous computing, with GPUs, acting as coprocessors to the CPUs for arithmetic intensive data-parallel workloads. CUDA - Compute Uni ed Device Architecture is a new industry standard for task-parallel and data-parallel heterogeneous computing on NVIDIA GPUs. Basic goal of CUDA is to help programmers focus on the task of parallelization of the algorithms rather than spending time on their implementation. Key to performance on this platform is using massive multithreading to utilize the large number of cores and hide global memory latency. To achieve this, developers need to maintain the right balance between each thread's resource usage and the number of simultaneously active threads.The resources to manage include the number of registers and the amount of on-chip memory used per thread, number of threads per multiprocessor, and global memory bandwidth. The parallel versions of JPEG2000 are implemented on GeForce GT 130 on Mac OS using CUDA technology. The results are presented along with methodology used for parallelization of code for NVIDIA GPU. We also obtain increased performance by reordering accesses to o -chip global memory to combine requests to the same or contiguous memory locations and apply classical optimizations to reduce the number of executed operations.