Français Anglais
Accueil Annuaire Plan du site
Accueil > Evenements > Séminaires
Séminaire d'équipe(s) Parall
Adaptive Lightweight Scheduling for Improving Bulk-Synchronous MPI Application Scalability on Multi-core Clusters
Vivek Kale

02 February 2012, 10h30 - 02 February 2012, 11h30
Salle/Bat : 455/PCRI-N
Contact :

Activités de recherche :

Résumé :
Several prior studies have shown
that operating system (OS) services, which induce system noise,
can be a fundamental and significant
problem in scaling bulk-synchronous MPI applications
to a very large number of nodes of a multi-core cluster.
One solution for mitigating noise impact on
bulk-synchronous MPI applications is to turn off certain OS
services on the machine. However, this is typically infeasible
because these system services may be essential, or even
required, for some applications. Furthermore, the end user
typically has no direct control over these system services.
Thus, we need an application-level solution.
Building upon previous work that demonstrated the utility
of lightweight scheduling, we discuss the advanced
techniques of adaptive lightweight scheduling, and provide insights
of our advanced scheduler through experimentation on two different
high-performance clusters with very different noise signatures.
By doing this, we show larger performance gains with our adaptive
lightweight scheduler, as compared to our original lightweight
scheduler.

Pour en savoir plus :
Séminaires
Recent advances in high-performance computing
Calcul à haute performance
Friday 29 September 2017 - 09h30
Salle : 465 - PCRI-N
Jose Roman, Lokmane Abbas Turki, Camille Coti .............................................

Modélisation énergétique qualitative de l'organism
Biologie des systèmes
Thursday 21 September 2017 - 14h30
Salle : 465 - PCRI-N
Marc Irigoin-Guichandut .............................................

Involution Delay Model: Faithful Delay Prediction
Tuesday 25 July 2017 - 14h00
Salle : 465 - PCRI-N
Jürgen Maier .............................................

Building Distributed Computing Abstractions in the
Algorithmique distribuée
Tuesday 11 July 2017 - 10h30
Salle : 465 - PCRI-N
Antonella Del Pozzo .............................................

Slow Molecule Revolution
Algorithmique distribuée
Wednesday 05 July 2017 - 10h30
Salle : 465 - PCRI-N
David Doty .............................................