Search papers, labs, and topics across Lattice.
This paper introduces a scalable multi-GPU framework for simulating 3D multicellular growth that leverages GPU acceleration, spatial binning, and an innovative RNN-based workload balancing controller. The controller dynamically adjusts workload partitions based on observed execution times and partition states, significantly improving computational efficiency over static and reactive load-balancing methods. Experimental results demonstrate that the framework achieves up to three orders of magnitude acceleration in interaction computation and reduces mean global imbalance from 11.3% to 3.5%, leading to a 9.0% decrease in end-to-end runtime.
RNN-guided load balancing slashes global workload imbalance to 3.5%, boosting simulation efficiency in multicellular growth models.
Detailed multicellular growth simulations based on subcellular element models (SEMs) can capture complex tissue development, but their element-level interactions impose substantial computational cost. This work presents a scalable multi-GPU framework for 3D multicellular growth simulation that combines GPU acceleration, spatial binning, domain decomposition, and workload-aware partitioning. Cell movement, growth, and division continuously reshape the spatial workload distribution, causing initially balanced partitions to become inefficient over time. To address this, we introduce an RNN-based load-balancing controller that observes recent per-rank execution times and partition states and learns residual corrections to a reactive boundary-adjustment rule. The controller is trained offline in a differentiable surrogate of the load-balancing loop with randomized workload dynamics, requiring no measured execution traces for training. We evaluate the framework in terms of single-GPU acceleration, multi-GPU computation scaling, controller-level load-balancing behavior, and end-to-end simulation performance, with comparisons against static partitioning, reactive load balancing, and conventional time-series prediction baselines. A representative embryonic epidermal development use case further demonstrates the type of spatially and temporally evolving workload targeted by the framework. In our evaluation, GPU acceleration with spatial binning accelerates the interaction computation by roughly three orders of magnitude over a serial CPU baseline. RNN-guided load balancing reduces the mean global imbalance from 11.3% under static partitioning to 3.5%, lowers end-to-end runtime by 9.0% relative to static partitioning, and reduces slice migration by 7.7x compared with the reactive baseline, showing that history-aware control can improve workload balance while avoiding unnecessary repartitioning.
