Probabilistic Algorithm with Dynamic Load Balancing for GPU-Accelerated Tumor Growth Simulations

Abstract

Efficient simulation of tumor growth using cellular automata (CA) requires high computational power, especially when scaling to large biological systems. In this paper, we present a GPU-accelerated dynamic load balancing strategy for tumor growth simulation, using CUDA to optimize execution and scalability. We compare our approach with traditional CPU implementations and static load balancing methods, and demonstrate significant performance gains. Our results show that the proposed strategy reduces execution time by up to 54% for a 1024×1024 grid of CUDA thread blocks while maintaining accuracy, making it a promising approach for large-scale biomedical simulations.