High performance checksum computation for fault-tolerant MPI over InfiniBand

Alexandre Denis 1, 2, * François Trahay 3 Yutaka Ishikawa 4
* Corresponding author
1 RUNTIME - Efficient runtime systems for parallel architectures
Inria Bordeaux - Sud-Ouest, UB - Université de Bordeaux, CNRS - Centre National de la Recherche Scientifique : UMR5800
Abstract : With the increase of the number of nodes in clusters, the probability of failures and unusual events increases. In this paper, we present checksum mechanisms to detect data corruption. We study the impact of checksums on network communication performance and we propose a mechanism to amortize their cost on InfiniBand. We have implemented our mechanisms in the NEWMADELEINE communication library. Our evaluation shows that our mechanisms to ensure message integrity do not impact noticeably the application performance, which is an improvement over the state of the art MPI implementations.
Keywords : NewMadeleine MadMPI MPI
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-00716478
Contributor : Alexandre Denis <>
Submitted on : Tuesday, July 10, 2012 - 4:09:23 PM
Last modification on : Thursday, September 12, 2019 - 3:40:03 PM
Long-term archiving on : Thursday, December 15, 2016 - 9:42:12 PM

File

final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00716478, version 1

Citation

Alexandre Denis, François Trahay, Yutaka Ishikawa. High performance checksum computation for fault-tolerant MPI over InfiniBand. the 19th European MPI Users' Group Meeting (EuroMPI 2012), Sep 2012, Vienna, Austria. ⟨hal-00716478⟩

Share

Metrics

Record views

447

Files downloads

572