Benutzer: Gast  Login
Titel:

Node Sharing for Increased Throughput and Shorter Runtimes – an Industrial Co-Scheduling Case Study

Dokumenttyp:
Konferenzbeitrag
Autor(en):
de Blanche, Andreas; Lundqvist, Thomas
Abstract:
The allocation of jobs to nodes and cores in industrial clusters is often based on queue-system standard settings, guesses or perceived fairness between different users and projects. Unfortunately, hard empirical data is often lacking and jobs are scheduled and co-scheduled for no apparent reason. In this case-study, we evaluate the performance impact of co-scheduling jobs using three types of applications and an existing 450+ node cluster at a company doing large-scale parallel industrial simul...     »
Stichworte:
Co-scheduling; Cluster; Engineering Simulations; MPI; FEM; Simulation; Scheduling; Multicore; Slowdown; Industrial HPC
Dewey-Dezimalklassifikation:
000 Informatik, Wissen, Systeme
Herausgeber:
Trinitis, Carsten; Weidendorfer, Josef
Kongress- / Buchtitel:
Proceedings of the 3rd Workshop on Co-Scheduling of HPC Applications (COSH 2018)
Datum der Konferenz:
January 23, 2018
Jahr:
2018
Monat:
Jan
Seiten:
15-20
Volltext / DOI:
doi:10.14459/2018md1428537
 BibTeX