Sciweavers

Share
IPPS
2009
IEEE

Designing multi-leader-based Allgather algorithms for multi-core clusters

8 years 12 months ago
Designing multi-leader-based Allgather algorithms for multi-core clusters
The increasing demand for computational cycles is being met by the use of multi-core processors. Having large number of cores per node necessitates multi-core aware designs to extract the best performance. The Message Passing Interface (MPI) is the dominant parallel programming model on modern high performance computing clusters. The MPI collective operations take a significant portion of the communication time for an application. The existing optimizations for collectives exploit shared memory for intranode communication to improve performance. However, it still would not scale well as the number of cores per node increase. In this work, we propose a novel and scalable multileader-based hierarchical Allgather design. This design allows better cache sharing for Non-Uniform Memory Access (NUMA) machines and makes better use of the network speed available with high performance interconnects such as InfiniBand. The new multi-leader-based scheme achieves a performance improvement of up ...
Krishna Chaitanya Kandalla, Hari Subramoni, Gopala
Added 24 May 2010
Updated 24 May 2010
Type Conference
Year 2009
Where IPPS
Authors Krishna Chaitanya Kandalla, Hari Subramoni, Gopalakrishnan Santhanaraman, Matthew J. Koop, Dhabaleswar K. Panda
Comments (0)
books