Bridging the Gap Between HPC and Cloud Using HyperFlow and PaaSage
A hybrid HPC/Cloud architecture is a potential solution to the ever-increasing demand for high-availability on-demand resources for eScience applications. eScience applications are primarily compute-intensive, and thus require HPC resources. They usually also include pre- and post-processing steps, which can be moved into the Cloud in order to keep costs low. We believe that currently no methodology exists to bridge the gap between HPC and Cloud in a seamless manner. The goal is to lower the gap for non-professionals in order to exploit external facilities through an automated deployment and scaling both vertically (HPC) and horizontally (Cloud). This paper demonstrates how representative eScience applications can easily be transferred from HPC to Cloud using the model-based cross-cloud deployment platform PaaSage.
KeywordsCloud computing HPC eScience Workflow management
We thankfully acknowledge the support of the EU 7th Framework Programme (FP7/2013-2016) under grant agreement number 317715. Access to Omistack Cloud resources was kindly provided by University of Ulm, Germany. HyperFlow and Scalarm are partially supported by the AGH Statutory Fund.
- 2.Balis, B., Figiela, K., Malawski, M., Pawlik, M., Bubak, M.: A lightweight approach for deployment of scientific workflows in cloud infrastructures. In: Wyrzykowski, R., Deelman, E., Dongarra, J., Karczewski, K., Kitowski, J., Wiatr, K. (eds.) PPAM 2015. LNCS, vol. 9573, pp. 281–290. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-32149-3_27 CrossRefGoogle Scholar
- 3.Baur, D., Domaschka, J.: Experiences from building a cross-cloud orchestration tool. In: Proceedings of the 3rd Workshop on CrossCloud Infrastructures and Platforms, pp. 4:1–4:6. ACM (2016). https://doi.org/10.1145/2904111.2904116
- 4.Kim, H., el Khamra, Y., Jha, S., Parashar, M.: Exploring application and infrastructure adaptation on hybrid grid-cloud infrastructure. In: Proceedings 19th ACM International Symposium on High Performance Distributed Computing, HPDC 2010, pp. 402–412. ACM (2010). https://doi.org/10.1145/1851476.1851536
- 6.Marathe, A., Harris, R., Lowenthal, D.K., de Supinski, B.R., Rountree, B., Schulz, M., Yuan, X.: A comparative study of high-performance computing on the cloud. In: Proceedings of the 22nd International Symposium on High-Performance Parallel and distributed Computing, pp. 239–250. ACM (2013). https://doi.org/10.1145/2462902.2462919
- 8.Rossini, A.: Cloud application modelling and execution language (CAMEL) and the PaaSage workflow. In: Advances in Service-Oriented and Cloud Computing—Workshops of ESOCC, vol. 567, pp. 437–439, September 2015. https://doi.org/10.1007/978-3-319-33313-7