Optimizing MPI Communication within large Multicore nodes with Kernel assistance

Abstract : As the number of cores per node increases in modern clusters, intra-node communication efficiency becomes critical to application performance. We present a study of the traditional double-copy model in MPICH2 and a kernel-assisted single-copy strategy with KNEM on different shared-memory hosts with up to 96 cores. We show that KNEM suffers less from process placement on these complex architectures. It improves throughput up to a factor of 2 for large messages for both point-to-point and collective operations, and significantly improves NPB execution time. We detail when to switch from one strategy to the other depending on the communication pattern and we show that \ioat copy offload only appears to be an interesting solution for older architectures.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/inria-00451471
Contributor : Brice Goglin <>
Submitted on : Tuesday, February 2, 2010 - 4:09:32 PM
Last modification on : Wednesday, May 15, 2019 - 5:24:09 PM
Long-term archiving on : Wednesday, November 30, 2016 - 1:02:51 PM

File

CAC10.pdf
Files produced by the author(s)

Identifiers

Citation

Stéphanie Moreaud, Brice Goglin, David Goodell, Raymond Namyst. Optimizing MPI Communication within large Multicore nodes with Kernel assistance. Workshop on Communication Architecture for Clusters, held in conjunction with IPDPS 2010, Apr 2010, Atlanta, United States. 7 p., ⟨10.1109/IPDPSW.2010.5470849⟩. ⟨inria-00451471⟩

Share

Metrics

Record views

724

Files downloads

495