K.-L. Park, H.-J. Lee, O.-Y. Kwon, S.-Y. Park, H.-W. Park, and S.-D. Kim
MPI, grid, collective operations, network-aware, improving performance
The authors design and implement a dynamic and effective communication MPI (Message-Passing Interface) library for the grid environment, especially to design collective operations such as broadcast and reduce. The purpose of the grid environment is to aggregate a large number of resources. So, it is inevitable that networks will be heterogeneous, and thus application performance will be affected. However, these issues have not until now been considered in designing communication primitives. Thus, these characteristics from the grid networks are speciļ¬ed and adapted into the communication algorithm design in this research. For an effective solution, we characterize the grid network on the basis of actual measurement, and design an effective communication algorithm called HLOT (Hierarchical Latency Optimal Tree) that can reduce the communication delay by utilizing the network status aggressively. Also, by using the proposed algorithm, we implement various collective communication routines of MPI library and demonstrate their effectiveness. The experimental results show that performance gain of more than 200% can be achieved in performing collective operations and around 130% in performing an applications benchmark, compared to MPICH-G2, that is, conventional grid-enabled MPI library.
Important Links:
Go Back
