Design, Implementation, and Performance of MPI on Portals 3.0

This paper describes an implementation of the Message Passing Interface (MPI) on the Portals 3.0 data movement layer. Portals 3.0 provides low-level building blocks that are flexible enough to support higher-level message passing layers, such as MPI, very efficiently. Portals 3.0 is also designed to allow for programmable network interface cards to offload message processing from the host processor, allowing for the ability to overlap computation and MPI communication. We describe the basic building blocks in Portals 3.0, show how they can be put together to implement MPI, and describe the protocols of our MPI implementation. We look at several key operations within the implementation and describe the effects that a Portals 3.0 implementation has on scalability and performance. We also present preliminary performance results from our implementation for Myrinet.

[1]  Rolf Riesen,et al.  SUNMOS for the Intel Paragon - a brief user`s guide , 1994 .

[2]  Hiroshi Tezuka.  PM : A High-Performance Communication Library for Multi-user Parallel Environments , 1996 .

[3]  William Gropp,et al.  MPICH2: A New Start for MPI Implementations , 2002, PVM/MPI.

[4]  Rolf Riesen,et al.  Portals 3.0: protocol building blocks for low overhead communication , 2002, Proceedings 16th International Parallel and Distributed Processing Symposium.

[5]  Wu-chun Feng,et al.  The Quadrics Network: High-Performance Clustering Technology , 2002, IEEE Micro.

[6]  Seth Copen Goldstein,et al.  Active messages: a mechanism for integrating communication and computation , 1998, ISCA '98.

[7]  Ron Brightwell,et al.  The Portals 3.0 Message Passing Interface Revision 1.0 , 1999 .

[8]  Thorsten von Eicken,et al.  U-Net: a user-level network interface for parallel and distributed computing , 1995, SOSP.

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

[10]  Andrew A. ChienJanuary.  Fast Messages ( FM ) : E cient , Portable Communication for Workstation Clusters and Massively-Parallel Processors , 1997 .

[11]  Mario Lauria,et al.  MPI-FM: High Performance MPI on Workstation Clusters , 1997, J. Parallel Distributed Comput..

[12]  R. Brightwell,et al.  Scalable Parallel Application Launch on Cplant ™ , 2001, ACM/IEEE SC 2001 Conference (SC'01).

[13]  W. Vogels,et al.  A User-Level Network Interface for Parallel and Distributed Computing , 1995 .

[14]  Hiroshi Tezuka,et al.  The design and implementation of zero copy MPI using commodity hardware with a high performance network , 1998, ICS '98.

[15]  Ron Brightwell,et al.  Portals and Networking for the Lustre File System , 2002 .

[16]  Message Passing Interface Forum.  MPI: A message - passing interface standard , 1994 .

[17]  David S. Greenberg,et al.  Massively parallel computing using commodity components , 2000, Parallel Comput..

[18]  Jack Dongarra,et al.  Recent Advances in Parallel Virtual Machine and Message Passing Interface, 15th European PVM/MPI Users' Group Meeting, Dublin, Ireland, September 7-10, 2008. Proceedings , 2008, PVM/MPI.

[19]  Christopher Wilson,et al.  COMB: a portable benchmark suite for assessing MPI overlap , 2002, Proceedings. IEEE International Conference on Cluster Computing.

[20]  Charles L. Seitz,et al.  Myrinet: A Gigabit-per-Second Local Area Network , 1995, IEEE Micro.

[21]  Bernard Tourancheau,et al.  BIP: A New Protocol Designed for High Performance Networking on Myrinet , 1998, IPPS/SPDP Workshops.

[22]  Seth Copen Goldstein,et al.  Active Messages: A Mechanism for Integrated Communication and Computation , 1992, [1992] Proceedings the 19th Annual International Symposium on Computer Architecture.

[23]  Message P Forum,et al.  MPI: A Message-Passing Interface Standard , 1994 .

[24]  Bernard Tourancheau,et al.  The Design for a High-Performance MPI Implementation on the Myrinet Network , 1999, PVM/MPI.

[25]  Ron Brightwell,et al.  Scalable parallel application launch on Cplant , 2001, SC.