Parallel and distributed computing enable the execution of large and complex simulations. Yet, the usual separation of (headless) simulation execution and (subsequent, offline) output analysis often renders the simulation endeavor long and inefficient. Recently, Visual Interactive Simulation (VIS) tools and methods that address this end-to-end efficiency are gaining relevance, offering in-situ visualization, real-time debugging, and computational steering. Here, the typically distributed computing nature of the simulation execution poses synchronization challenges between the headless simulation engine and the user-facing frontend required for Visual Interactive Simulation. To the best of our knowledge, state-of-the-art synchronization approaches fall short due to their rigidity and inability to adapt to real-time user-centric changes. This paper introduces a novel adaptive algorithm to dynamically adjust the simulation’s pacing through a buffer-based framework, informed by predictive workload analysis. Our extensive experimental evaluation across diverse synthetic scenarios illustrates our method’s effectiveness in enhancing runtime efficiency and synchronicity, significantly reducing end-to-end time while minimizing user interaction delays, thereby addressing key limitations of existing synchronization strategies.     «

Parallel and distributed computing enable the execution of large and complex simulations. Yet, the usual separation of (headless) simulation execution and (subsequent, offline) output analysis often renders the simulation endeavor long and inefficient. Recently, Visual Interactive Simulation (VIS) tools and methods that address this end-to-end efficiency are gaining relevance, offering in-situ visualization, real-time debugging, and computational steering. Here, the typically distributed computi...     »