Porting HPC applications to the cloud: A multi-frontal solver case study
详细信息 查看全文
- 作者：Bartosz Balis ; balis@agh.edu.plAuthor Vitae ; Kamil FigielaAuthor Vitae ; Konrad JopekAuthor Vitae ; Maciej MalawskiAuthor Vitae ; Maciej PawlikAuthor Vitae
- 关键词：HPC in the cloud ; Multi-frontal direct solver ; Scientific workflows ; Mesh-based solver
- 刊名：Journal of Computational Science
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：18
- 期：Complete
- 页码：106-116
- 全文大小：2525 K
- 卷排序：18
文摘
A methodology for efficient porting of HPC applications to clouds is proposed. Communication costs are reduced using task agglomeration and mapping heuristics. Scientific workflow model and system are used to implement the methodology. The methodology is evaluated for FEM problems solved with multi-frontal solver. Experimental tests on up to 64 VMs on Amazon EC2 show the speedup of over 39 times.