|
Published Articles >> Table of Contents >> Abstract
Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID'06)
pp. 43-48
Design of High Performance MVAPICH2: MPI2 over InfiniBand
W. Huang, The Ohio State University, USA
G. Santhanaraman, The Ohio State Univesity, USA
H. -W. Jin, Konkuk University, Korea
Q. Gao, The Ohio State University, USA
D. K. x D. K. Panda, The Ohio State University, USA
Full Article Text:
 
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CCGRID.2006.32
Send link to a friend
| Abstract |
|
MPICH2 provides a layered architecture for implementing MPI-2. In this paper, we provide a new design for implementing MPI-2 over InfiniBand by extending the MPICH2 ADI3 layer. Our new design aims to achieve high performance by providing a multi-communication method framework that can utilize appropriate communication channels/devices to attain optimal performance without compromising on scalability and portability. We also present the performance comparison of the new design with our previous design based on the MPICH2 RDMA channel. We show significant performance improvements in micro-benchmarks and NAS Parallel Benchmarks.
|
 Additional Information
|
Citation:
W. Huang, G. Santhanaraman, H. -W. Jin, Q. Gao, D. K. x D. K. Panda,
"Design of High Performance MVAPICH2: MPI2 over InfiniBand,"
ccgrid,
pp. 43-48,
Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID'06),
2006
|
|
