The portals 3.3 message passing interface document revision 2.1.

This report presents a specification for the portals 3.3 message passing interface. Portals 3.3 are intended to allow scalable, high-performance network communication between nodes of a parallel computing system. Specifically, it is designed to support a parallel computing platform composed of clusters of commodity workstations connected by a commodity system area network fabric. In addition, Portals 3.3 are well suited to massively parallel processing and embedded systems. Portals 3.3 represent an adaption of the data movement layer developed for massively parallel processing platforms, such as the 4500-node Intel TeraFLOPS machine. Version 3.0 of Portals runs on the Cplant cluster at Sandia National Laboratories, and version 3.3 is running on Cray’s Red Storm system.

[1]  R. Brightwell,et al.  Design and implementation of MPI on Puma portals , 1996, Proceedings. Second MPI Developer's Conference.

[2]  Rolf Riesen,et al.  RMPP: the reliable message passing protocol , 2002, 27th Annual IEEE Conference on Local Computer Networks, 2002. Proceedings. LCN 2002..

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

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

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

[6]  Scott Pakin,et al.  Efficient layering for high speed communication: Fast Messages 2.x , 1998, Proceedings. The Seventh International Symposium on High Performance Distributed Computing (Cat. No.98TB100244).