Finding a Tradeoff between Host Interrupt Load and MPI Latency over Ethernet - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Finding a Tradeoff between Host Interrupt Load and MPI Latency over Ethernet

Résumé

Achieving high-performance message passing on top of generic Ethernet hardware suffers from the NIC interrupt-driven model where coalescing is usually involved. We present an in-depth study of the impact of interrupt coalescing on the Open-MX performance. It shows that disabling coalescing may not be relevant for most metrics except small-message latency. Two new coalescing strategies are then presented so as to efficiently support both latency-friendly and coalescing-friendly workloads thanks to the NIC looking at Open-MX messages and streams before deciding when to raise interrupts. The implementation of these strategies in the firmware of Myri-10G NICs shows that Open-MX is now able to achieve a low small-message latency, a high large-message throughput, and a satisfying message rate without having to manually tune the coalescing delay depending on the benchmark. Real application performance evaluation further shows that our modifications even improve the NAS Parallel Benchmark IS execution time by 7-8% thanks to our NIC firmware raising up to 20% of additional interrupts at the correct time.
Fichier principal
Vignette du fichier
article.pdf (132.16 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00397328 , version 1 (20-06-2009)

Identifiants

Citer

Brice Goglin, Nathalie Furmento. Finding a Tradeoff between Host Interrupt Load and MPI Latency over Ethernet. Cluster 2009, Sep 2009, New Orleans, United States. ⟨10.1109/CLUSTR.2009.5289165⟩. ⟨inria-00397328⟩
207 Consultations
250 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More