Automated Cluster Provisioning And Workflow Management for Parallel Scientific Applications in the Cloud

@inproceedings{Posey2017AutomatedCP,
  title={Automated Cluster Provisioning And Workflow Management for Parallel Scientific Applications in the Cloud},
  author={Brandon Posey and Christopher Gropp and Alexander Herzog and Amy W. Apon},
  year={2017}
}
Many commercial cloud providers and tools are available that researchers could utilize to advance computational science research. However, adoption by the research community has been slow. In this paper we describe the automated Provisioning And Workflow (PAW) management tool for parallel scientific applications in the cloud. PAW is a comprehensive resource provisioning and workflow tool that automates the steps of dynamically provisioning a large scale cluster environment in the cloud… CONTINUE READING

Figures, Results, and Topics from this paper.

Key Quantitative Results

  • Use of Spot can decrease costs, as the average spot prices for different instances types is up to 90% less than the on-demand price for the same instance type.

Citations

Publications citing this paper.

Addressing the Challenges of Executing a Massive Computational Cluster in the Cloud

  • 2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)
  • 2018
VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-7 OF 7 REFERENCES

Pegasus WMS.

Vahi, Karan
  • Pegasus WMS,
  • 2017
VIEW 1 EXCERPT

The Future of Cloud for Academic Research Computing.

Bottum, Jim
  • DOI: 10.13140/RG.2.2.10071.88489
  • 2017
VIEW 2 EXCERPTS

Probabilistic topic models

  • Commun. ACM
  • 2012
VIEW 1 EXCERPT