Parallel Hierarchical Block Wavelet Compression for an Optimal Compression of 3-D BEM Problems

摘要

Today's low-cost hardware developments allow for a parallelization over several selectable CPU cores by using Intel's OpenMP library. But if one applies this feature to a numerical simulation based on a boundary element method (BEM), there is still a huge bottle neck—the shared memory of such a system. So, if a low-cost hardware should be effectively used for large BEM problems, a memory compression algorithm that is easy to be scheduled in parallel is of first choice. Within our development of the Hierarchical Block Wavelet Compression, this bottle neck will be tackled in pure mathematical manners. Furthermore, its parallelization will be discussed and an optimal compression by varying the compression rate over different areas of the BEM problem will be presented.