GPU Acceleration of 3D Agent-Based Biological Simulations

  title={GPU Acceleration of 3D Agent-Based Biological Simulations},
  author={Ahmad Hesam and Lukas Breitwieser and Fons Rademakers and Zaid Al-Ars},
  journal={2021 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)},
Researchers in biology are faced with the tough challenge of developing high-performance computer simulations of their increasingly complex agent-based models. BioDynaMo is an open-source agent-based simulation platform that aims to alleviate researchers from the intricacies that go into the development of high-performance computing. Through a high-level interface, researchers can implement their models on top of BioDynaMo's multi-threaded core execution engine to rapidly develop simulations… Expand


BioDynaMo: a general platform for scalable agent-based simulation
The performance results show that BioDynaMo performs up to three orders of magnitude faster than the state-of-the-art baseline, which makes it feasible to simulate each use case with one billion agents on a single server, showcasing the potential Bio DynaMo has for computational biology research. Expand
An Empirical Roofline Methodology for Quantitatively Assessing Performance Portability
The Roofline model is extended so that it empirically captures a more realistic set of performance bounds for CPUs and GPUs, factors in the true cost of different floating-point instructions when counting FLOPs, incorporates the effects of different memory access patterns, and facilitates the performance portability analysis. Expand
Efficient Acceleration of the Pair-HMMs Forward Algorithm for GATK HaplotypeCaller on Graphics Processing Units
This article proposes to accelerate the pair-HMMs forward algorithm on graphics processing units (GPUs) to improve the performance of GATK HC and identifies the GPU-based implementations with the highest performance for the various analyzed data sets. Expand
PhysiCell: An open source physics-based cell simulator for 3-D multicellular systems
PhysiCell is demonstrated by simulating the impact of necrotic core biomechanics, 3-D geometry, and stochasticity on the dynamics of hanging drop tumor spheroids and ductal carcinoma in situ (DCIS) of the breast. Expand
Agent-Based Modeling and Simulation
This brief tutorial introducesAgent-based modeling by describing the foundations of ABMS, discussing some illustrative applications, and addressing toolkits and methods for developing agent-based models. Expand
BrainFrame: A node-level heterogeneous accelerator platform for neuron simulations
BrainFrame is proposed and built, a heterogeneous acceleration platform that incorporates three distinct acceleration technologies, an Intel Xeon-Phi CPU, a NVidia GP-GPU and a Maxeler Dataflow Engine, and the PyNN software framework is also integrated into the platform. Expand
Simulating tissue mechanics with agent-based models: concepts, perspectives and some novel results
An overview of agent-based models that are used to simulate mechanical and physiological phenomena in cells and tissues is presented, and the underlying concepts, limitations, and future perspectives of these models are discussed. Expand
Biocellion: accelerating computer simulation of multicellular biological system models
Biocellion, a high-performance software framework, to solve the computing challenge using parallel computers by allowing modelers without parallel computing expertise to efficiently exploit parallel computers with less effort than writing sequential programs from scratch. Expand
Electronics based on two-dimensional materials.
A review of electronic devices based on two-dimensional materials, outlining their potential as a technological option beyond scaled complementary metal-oxide-semiconductor switches and the performance limits and advantages, when exploited for both digital and analog applications. Expand
Large-Scale Parallel Simulations of 3D Cell Colony Dynamics
This article presents a novel, high-performance computational approach allowing simulations of 3D cell colony dynamics at a previously unavailable tissue scale and achieves simulation of cell colonies composed of 109 cells, which allows for describing tumor growth in its early clinical stage. Expand