NanoCheckpoints: A Task-Based Asynchronous Dataflow Framework for Efficient and Scalable Checkpoint/Restart

In this paper, we present NanoCheckpoints which is a lightweight software-based checkpoint/restart scheme for task-parallel HPC applications. We leverage OmpSs, a task-based OpenMP derivative programming model (PM) and its Nanos asynchronous dataflow runtime. NanoCheckpoints achieves minimal overhea...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Proceedings - Euromicro Workshop on Parallel and Distributed Processing S. 99 - 102
Hauptverfasser:	Subasi, Omer, Arias, Javier, Unsal, Osman, Labarta, Jesus, Cristal, Adrian
Format:	Tagungsbericht Journal Article
Sprache:	Englisch
Veröffentlicht:	IEEE 01.03.2015
Schlagworte:	Arrays Benchmark testing Benchmarks Checkpoint/restart Checkpointing Conferences Dataflow Derivatives Error recovery Instruction sets Nanostructure Networks Reliability Runtime Scalability Task parallelism Tasks Weight reduction
ISSN:	1066-6192
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!