MPICH-CM: A Communication Library Design for a P2P MPI Implementation

The paper presents MPICH-CM - a new architecture of communications in message-passing systems, developed for MPICH-V - a MPI implementation for P2P systems. MPICH-CM implies communications between nodes through special Channel Memories introducing fully decoupled communication media. Some new properties of communications based on MPICH-CM are described in comparison with other communication architectures, with emphasis on grid-like and volunteer computing systems. The first implementation of MPICH-CM is performed as a special MPICH device connected with Channel Memory servers. To estimate the overhead of MPICH-CM, the performance of MPICH-CM is presented for basic point-to-point and collective operations in comparison with MPICH p4 implementation.

[1]  Gilles Fedak,et al.  XtremWeb: a generic global computing system , 2001, Proceedings First IEEE/ACM International Symposium on Cluster Computing and the Grid.

[2]  Anthony Skjellum,et al.  A High-Performance, Portable Implementation of the MPI Message Passing Interface Standard , 1996, Parallel Comput..

[3]  Andy Oram,et al.  Peer-to-Peer: Harnessing the Power of Disruptive Technologies , 2001 .

[4]  Richard D. Schlichting,et al.  Supporting Fault-Tolerant Parallel Programming in Linda , 1995, IEEE Trans. Parallel Distributed Syst..

[5]  Gilles Fedak,et al.  Global Computing Systems , 2001, LSSC.

[6]  Samir Al-Khayatt,et al.  A study of encrypted, tunneling models in virtual private networks , 2002, Proceedings. International Conference on Information Technology: Coding and Computing.

[7]  Roy Friedman,et al.  Starfish: Fault-Tolerant Dynamic MPI Programs on Clusters of Workstations , 2004, Cluster Computing.

[8]  Miron Livny,et al.  Managing Checkpoints for Parallel Programs , 1996, JSSPP.

[9]  Jack J. Dongarra,et al.  HARNESS and fault tolerant MPI , 2001, Parallel Comput..