Faster than the Speed of Life: Accelerating Developmental Biology Simulations with GPUs and FPGAs

Abstract

Life scientists are faced with the tough challenge of developing high-performance computer simulations of their increasingly complex models. BioDynaMo is an open-source biological simulation platform that aims to alleviate them from the intricacies that go into development. Life scientists are able to base their models on top of BioDynaMo’s highly optimized core execution engine. At the core of all biological simulations is the mechanical interactions between possibly millions of objects. In this work we investigate the currently implemented method of handling mechanical interactions, and ways to improve the performance in order to enable large-scale and complex simulations. We propose to replace the existing kd-tree implementation for neighborhood operations with a uniform grid method that allows us to take advantage of architectures of hardware accelerators, such as GPUs and FPGAs. As a result, the multi-threaded uniform grid implementation accounts for a 14× speedup with respect to the serial baseline version. Accelerating the mechanical interactions through hardware acceleration proved to perform best on a GPU, with a resulting speedup of 134×.