Author | Gerrett Diamond, Cameron W. Smith, Mark S. Shephard |
---|---|
Title | Dynamic Load Balancing of Massively Parallel Unstructured Meshes |
Year | 2017 |
Journal | ScalA'17: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems |
Pages | 7 |
Collection | The International Conference for High Performance Computing, Networking, Storage and Analysis |
Abstract | Simulating systems with evolving relational structures on massively parallel computers require the computational work to be evenly distributed across the processing resources throughout the simula- tion. Adaptive, unstructured, mesh-based nite element and nite volume tools best exemplify this need. We present EnGPar and its di usive partition improvement method that accounts for multiple application speci ed criteria. EnGPar’s performance is compared against its predecessor, ParMA. Speci cally, partition improvement results are provided on up to 512Ki processes of the Argonne Lead- ership Computing Facility’s Mira BlueGene/Q system. |
PDF File | Download |