HgPCN:面向端到端嵌入式点云推理的异构架构
HgPCN: A Heterogeneous Architecture for E2E Embedded Point Cloud Inference
AI总结:
针对嵌入式边缘端点云工作负载端到端处理实时性不足的问题,提出HgPCN异构架构,通过八叉树索引采样和基于体素扩展聚合的定制单元分别优化预处理下采样与推理数据结构化瓶颈,实现实时点云推理。
摘要:
点云是一种重要的几何数据结构,在自动驾驶、增强现实等众多嵌入式应用中发挥作用。现有**点云网络(Point Cloud Networks, PCNs)**已被证实在通过推理执行点云分析(包括物体部件分割、形状分类等)方面取得了巨大成功。然而,边缘计算端的点云应用所需的不只是推理步骤,它们需要对点云工作负载进行**端到端(end-to-end, E2E)**处理:原始数据预处理、输入准备以及执行点云分析的推理。当前支持点云工作负载端到端处理的PCN方案无法满足边缘端的实时延迟要求,即AI服务的处理速度跟不上3D传感器生成原始数据的速度。点云工作负载端到端处理的延迟源于两个原因:预处理阶段的内存密集型下采样操作,以及推理阶段中输入准备的数据结构化步骤。本文提出HgPCN,一种面向实时嵌入式点云应用的端到端异构架构。在HgPCN中,我们提出了两种基于空间索引的新颖方法来解决上述两个已识别的瓶颈。在HgPCN的预处理引擎中,采用**八叉树索引采样(Octree-Indexed-Sampling)**方法来优化预处理阶段的内存密集型下采样瓶颈。在推理引擎中,HgPCN对商用**深度学习加速器(Deep Learning Accelerator, DLA)**进行扩展,加入了基于**体素扩展聚合(Voxel-Expanded Gathering)**方法的定制化数据结构化单元,从根本上减少推理阶段数据结构化步骤的工作负载。
英文摘要:
Point cloud is an important type of geometric data structure for many embedded applications such as autonomous driving and augmented reality. Current Point Cloud Networks (PCNs) have proven to achieve great success in using inference to perform point cloud analysis, including object part segmentation, shape classification, and so on. However, point cloud applications on the computing edge require more than just the inference step. They require an end-to-end (E2E) processing of the point cloud workloads: pre-processing of raw data, input preparation, and inference to perform point cloud analysis. Current PCN approaches to support end-to-end processing of point cloud workload cannot meet the real-time latency requirement on the edge, i.e., the ability of the AI service to keep up with the speed of raw data generation by 3D sensors. Latency for end-to-end processing of the point cloud workloads stems from two reasons: memory-intensive down-sampling in the pre-processing phase and the data structuring step for input preparation in the inference phase. In this paper, we present HgPCN, an end-to-end heterogeneous architecture for real-time embedded point cloud applications. In HgPCN, we introduce two novel methodologies based on spatial indexing to address the two identified bottlenecks. In the Pre-processing Engine of HgPCN, an Octree-Indexed-Sampling method is used to optimize the memory-intensive down-sampling bottleneck of the pre-processing phase. In the Inference Engine, HgPCN extends a commercial DLA with a customized Data Structuring Unit which is based on a Voxel-Expanded Gathering method to fundamentally reduce the workload of the data structuring step in the inference phase.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。