A Class-Structured Approach to Couple Application and Hybrid Core Parallelism

This paper presents an application that performs multi-objective geospatial optimizations for tactical mission planning in an urban environment. Utilizing a XML-driven C++ framework developed for hybrid platforms, the application distributes computational tasks to a collection of heterogeneous OpenCL devices and achieves efficient task parallel scaling. The framework abstracts the details of the mission scenario setup, compute device architecture details, and task scheduling to enable robust extensibility in software. Performance scalability and multi-objective parameter visualization for a prototypical mission scenario are documented in this study.