to support portable messaging-passing programming in a grid. Different from traditional MPI implementations, it supports transparent migration of MPI processes during execution. This feature facilitates more flexible task scheduling and more effective resource sharing. The migration mechanism is implemented

Abstract—Emerging large-scale systems have many nodes with several processors per node and multiple cores per processor. These systems require effective task distribution between cores, processors and nodes to achieve high levels of performance and utilization. Current scheduling strategies

that maintains a consistent view of active nodes in the presence of faults. Our protocol shows response times in the order of hundreds of microseconds and singledigit milliseconds for reconfiguration using MPI over BlueGene/L and TCP over Gigabit, respectively. The protocol can be adapted to match the network

HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

million MPI processes, which is 20x faster than the system RAM disk and 1000x faster than the parallel file system.

Recently, the Cluster of Computers (COC) has been used to run large parallel programs increasingly. Task migration is a desirable and useful facility to implement Load-Balance and High-Availibility in COCs. This paper presents a quick migration protocol for MPI tasks, which allows nonmigrating

Writing parallel applications for computational grids is a challenging task. To achieve good performance, algorithms designed for local area networks must be adapted to the differences in link speeds. An important class of algorithms are collective operations, such as broadcast and reduce. We have

Many institutions already have networks of workstations, which could potentially be harnessed as a powerful parallel processing resource. A new, automatic task allocation system has been built on top of MPI, an environment that permits parallel programming by using the message--passing paradigm

against the hardware limits and also the relative performance of the different modes of operation of BlueGene/L. We show that dedicating one of the processors of a node to communication functions greatly improves the bandwidth achieved by MPI operation, whereas running two MPI tasks per compute node can

of applications for which a mixture of task and data parallelism is most appropriate. Such applications can be structured as collections of data-parallel tasks that communicate by using explicit message passing. Because the Message Passing Interface (MPI) defines standardized, familiar mechanisms