Seine: a dynamic geometry-based shared-space interaction framework for parallel scientific applications

Abstract

SUMMARYWhile large-scale parallel/distributed simulations are rapidly becoming critical research modalities in academia and industry, their efficient and scalable implementations continue to present many challenges. A key challenge is that the dynamic and complex communication/coordination required by these applications (dependent on the state of the phenomenon being modeled) are determined by the specific numerical formulation, the domain decomposition and/or sub-domain refinement algorithms used, etc. and are known only at runtime. This paper presents Seine, a dynamic geometry-based shared-space interaction framework for scientific applications. The framework provides the flexibility of shared-space-based models and supports extremely dynamic communication/coordination patterns, while still enabling scalable implementations. The design and prototype implementation of Seine are presented. Seine complements and can be used in conjunction with existing parallel programming systems such as MPI and OpenMP. An experimental evaluation using an adaptive multi-block oil-reservoir simulation is used to demonstrate the performance and scalability of applications using Seine.

Distributed computing practice for large‐scale science and engineering applications

“…These examples also serve to illustrate an opportunity, as these tools, and the abstractions they provided were reused across these applications. Finally, the coupled fusion application had unique requirements for asynchronous coordination and data communication within traditional HPC environments that led to the development of the Seine and DART frameworks .…”

Dynamic Data-Driven Systems Approach for Simulation Based Optimizations

“…Implementing these communication and coordination patterns using commonly used parallel programming frameworks is non-trivial. Seine/MACE [22,23], developed as part of this effort, provides a virtual shared space abstraction to support interactions in parallel multi-block simulations. Seine builds on two key observations: (a) formulations of the targeted simulations are based on geometric multi-dimensional domains (e.g., a grid or a mesh) and (b) interactions in these applications are typically between entities that are geometrically close in this domain (e.g., neighboring cells, nodes or elements).…”

“…Furthermore, multiple shared spaces can exist simultaneously in the application domain. An experimental evaluation demonstrates its scalability and low operational overheads, as well as its ability to effectively support distributed multiblock simulations [23].…”

Towards Dynamic Data-Driven Management of the Ruby Gulch Waste Repository

“…-The Seine/MACE Computational Engine [18] that implements a dynamic geometry-based shared space interaction model to support the dynamic and complex communication and coordination patterns required by the multiblock parallel multi-block simulations. -The Accord Programming System [19] that enables the definition of autonomic components and the dynamic composition, management and optimization of these components using externally defined rules and constraints.…”