The implementation of the BSP parallel computing model on the InteGrade Grid middleware
MGC '05 Proceedings of the 3rd international workshop on Middleware for grid computing
| Hi-index | 0.00 |
Inside a dedicated parallel computer the communicationtimes were generally modeled in the same way, independentlyof which processors communicate. In a network where the links among the computers are heterogeneous, or in hierarchical clusters, this might not be true anymore.Computers that have faster links, or are closer to each other should be able to exchange messages faster. These differences on communication times should be considered, notonly for attributing tasks to the processors but also in globalsynchronization/communication. The goal of this paper isto study irregular all-to-all communications in a network ofdedicated clusters.