Enabling simulation of high‐dimensional micro‐macro biophysical models through hybrid CPU and multi‐GPU parallelism

Micro-macro models provide a powerful tool to study the relationship between microscale mechanisms and emergent macroscopic behavior. However, detailed microscopic modeling requires tracking evolving potentially high-dimensional configuration space at high computational cost. In this work, we present novel parallel algorithm for simulating micro-macro model of gliding motility assay. We utilize holistic approach aligning data residency simulation scales with hybrid CPU multi-GPU hardware. Our achieves speedup factor 9.25× over previous GPU-accelerated methods on same Furthermore, by decoupling dependencies in microstructure update, are able efficiently distribute multiple GPUs minimal overhead. test up four observe excellent scaling, suggesting that significant further speedups achievable additional GPUs. enables simulations higher complexity resolution than would otherwise be feasible.