The Performance of the MPI Collective Communication Routines for Large Messages on the Cray T3E-600, the Cray Origin 2000, and the IBM SP
Glenn R. Luecke, Bruno Raffin, Bruno Ran, James J. Coyle · 1999
We have implemented eight of the MPI collective routines using MPI point-to-point communication routines with algorithms designed to be ecient for large messages. The performance of our implementations of these collective routines is compared with the vendor implementations on the Cray T3E-600, the Cray Origin 2000 and on the IBM SP. Many of our implementations signicantly outperformed vendor implementations on the T3E and the Origin 2000. On the SP, only our implementation of the broadcast signicantly outperformed IBM's implementation. Keywords: MPI; Collective Communication Routines for Large Messages; Cray T3E; Origin 2000; IBM SP. 1 Introduction Today, MPI [15] is probably the most used message passing library for programming distributed memory parallel computers. Implementations of MPI are available for all commercially available parallel platforms. The MPI collective communication routines provide important functionality for scientic computing and the algorithms chos...