MPICH-G2: A Grid-enabled implementation of the Message Passing Interface

Abstract

Proposed running head: MPICH-G2: A Grid-Enabled MPI Application development for distributed computing "Grids" can benefit from tools that variously hide or enable application-level management of critical aspects of the heterogeneous environment. As part of an investigation of these issues, we have developed MPICH-G2, a Grid-enabled implementation of the Message Passing Interface (MPI) that allows a user to run MPI programs across multiple computers, at the same or different sites, using the same commands that would be used on a parallel computer. This library extends the Argonne MPICH implementation of MPI to use services provided by the Globus Toolkit for authentication, authorization, resource allocation, executable staging, and I/O, as well as for process creation, monitoring, and control. Various performancecritical operations, including startup and collective operations, are configured to exploit network topology information. The library also exploits MPI constructs for performance management; for example, the MPI communicator construct is used for application-level discovery of, and adaptation to, both network topology and network quality-of-service mechanisms. We describe the MPICH-G2 design and implementation, present performance results, and review application experiences, including record-setting distributed simulations.

QCG-OMPI: MPI applications on grids

“…MPICH-G2 [16] [26] is based on the MPICH [24] library and uses the Globus Toolkit (GT) [17] to schedule, deploy and coordinate a job across the grid. It does not include any firewall nor NAT bypassing mechanism, although it can be set up to use a specific range of ports that correspond to ports that are left open by the firewall.…”

Load-balancing scatter operations for grid computing

“…All machines run Globus [15] and we use MPICH-G2 [22] as message passing library. Table 1 shows the resources used in the experiment.…”

“…Thus, much work has been devoted to that purpose: for MPI, numerous projects including MagPIe [23], MPI-StarT [20], and MPICH-G2 [22], aim at improving communications performance in presence of heterogeneous networks. Most of the gain is obtained by reworking the design of collective communication primitives.…”

P2P-MPI: A Peer-to-Peer Framework for Robust Execution of Message Passing Parallel Programs on Grids

“…Most MPI implementations are designed for the development of highly ecient programs, preferably on dedicated, homogeneous and stable hardware such as supercomputers. Some projects have developed improved algorithms for communications in grids (MPICH-G2 [17], PACX-MPI [16], MagPIe [18] for instance) but still, assume hardware stability. This This design means no overhead in process management but makes fault handling di cult: one process failure causes the whole application to fail.…”