35 search results - page 3 / 7 » Collective operations in NEC's high-performance MPI librarie... |
IJHPCA
2010
13 years 6 months ago
2010
We describe and evaluate a new, pipelined algorithm for large, irregular all-gather problems. In the irregular all-gather problem each process in a set of processes contributes in...
PDCN
2004
13 years 8 months ago
2004
In this paper we investigate a tunable MPI collective communications library on a cluster of SMPs. Most tunable collective communications libraries select optimal algorithms for i...
CCGRID
2008
IEEE
14 years 1 months ago
2008
IEEE
Collective operations and non-blocking point-to-point operations are two important parts of MPI that each provide important performance and programmability benefits. Although non...
CCGRID
2006
IEEE
14 years 1 months ago
2006
IEEE
With the increasing number of processors in modern HPC(High Performance Computing) systems, there are two emergent problems to solve. One is scalability, the other is fault tolera...
PPOPP
1999
ACM
13 years 11 months ago
1999
ACM
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 differ...