In general, one of the complexities of large simulations is related to the usage of the heterogeneous computational resources that are needed to execute them. The definition of workflows, usually linked to concrete orchestrations solutions, has reduced most of that complexity. These solutions are oriented to High Performance Computing (HPC) or just deals with services managed remotely. This paper presents a novel solution we propose for running simulations in a hybrid HPC and Cloud infrastructure, exploiting the performance and power of HPC systems and benefiting from the fast and flexible provision of Cloud resources.
We provide our vision about the typical simulation workflows and the kind of computational resources that fits best in each phase. In line with such vision, we describe the research done in order to enable the definition of the workflows extending the TOSCA standard (originally focused on Cloud solutions), used by our orchestrator and other solutions. We propose several extensions (types, relationships, compute properties and job properties), compatible with the standard definition, so Cloud and HPC tasks can be processed as expected. The paper also shows a use case implemented with the proposed approach, highlighting some of the benefits found so far.