Vectorization and Parallelization of 2-D Wavelet Lifting

Discrete wavelet transforms, Image processing

The article presents several novel SIMD-vectorized algorithms of 2-D discrete wavelet transform. For all of the platforms used in the tests, these algorithms are significantly faster than other known methods. The final publication is available at Springer via http://dx.doi.org/10.1007/s11554-015-0486-6.

With the start of the widespread use of discrete wavelet transform in image processing, the need for its efficient implementation is becoming increasingly more important. This work presents several novel SIMD-vectorized algorithms of 2-D discrete wavelet transform, using a lifting scheme. At the beginning, a stand-alone core of an already known single-loop approach is extracted. This core is further simplified by an appropriate reorganization of operations. Furthermore, the influence of the CPU cache on a 2-D processing order is examined. Finally, SIMD-vectorizations and parallelizations of the proposed approaches are evaluated. The best of the proposed algorithms scale almost linearly with the number of threads. For all of the platforms used in the tests, these algorithms are significantly faster than other known methods, as shown in the experimental sections of the paper.