Next: Conclusions Up: Parallel Mesh Generation Previous: Parallel Computing Scheme

Example

The same example, junction of two pipes (Fig. 16), has been selected to demonstrate the parallel performance of the algorithm on IBM SP2 using up to 8 processors. Two meshes has been considered for parallel generation. The smaller one consisting of 92707 nodes was chosen so that it could have been generated on a single processor. The speedup achieved for 1 to 6 processors is depicted in Figure 17. The larger mesh comprises 518929 nodes and the speedup achieved for 4 to 8 processors is displayed also in Figure 17. Note that the speedup for larger mesh has been calculated from the assumption that the speedup is ideally linear up to 4 processors, which is in good agreement with speedup determined from extrapolation of performance of this mesh generator running in sequential mode. The execution time, speedup and efficiency for both meshes are summarized in Tables 1 and 2.



Next: Conclusions Up: Parallel Mesh Generation Previous: Parallel Computing Scheme

Daniel Rypl
2005-12-03