---
title: "基于RNN负载均衡的可扩展多GPU三维多细胞生长模拟"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.25890v1"
permalink: "https://feed.astralor.com/items/itm_6bca7a7c1fedc4093925925a"
published: "2026-08-26T15:06:10.000Z"
score: 70
channel: "ai"
tags: ["GPU加速","RNN","亚细胞元素模型","多细胞模拟","负载均衡"]
---

# 基于RNN负载均衡的可扩展多GPU三维多细胞生长模拟

## AI 点评

> 这篇论文有趣的地方在于把RNN当作负载均衡的控制器，而不是单纯预测负载，这给动态调度问题提供了新视角。对于做HPC和科学计算仿真的人，尤其涉及GPU集群调度的工程师，值得一读。不过论文的验证场景偏生物模拟，通用性还需要更多跨领域验证。

## 速览

基于亚细胞元素模型的三维多细胞生长模拟具有较高计算开销，本文提出一种可扩展多GPU框架，融合GPU加速、空间分箱、区域分解和负载感知分区。针对细胞动态变化导致初始分区失衡的问题，引入基于RNN的负载均衡控制器，它观测历史执行时间和分区状态，学习对反应式边界调整规则的残差修正。控制器在可微分替代环境中离线训练，无需实测轨迹。实验表明，基于空间分箱的GPU加速相比串行CPU基线提升了约三个数量级；RNN引导的负载均衡将全局平均不均衡度从静态分区的11.3%降至3.5%，端到端运行时间降低9.0%，切片迁移量比反应式基线减少7.7倍。

## 关键点

- 提出一种面向3D多细胞生长模拟的可扩展多GPU框架，整合GPU加速、空间分箱、区域分解与负载感知分区。
- 创新性地引入RNN负载均衡控制器，离线训练学习反应式规则之外的历史感知残差修正。
- GPU加速结合空间分箱使交互计算速度比串行CPU基线提升约三个数量级。
- RNN负载均衡将全局不均衡度从11.3%降至3.5%，端到端运行时间降低9.0%，迁移量减少7.7倍。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_6bca7a7c1fedc4093925925a