arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.21167cs.AR
收藏

PC2IM: 一种高效的内存计算加速器用于3D点云

PC2IM: An Efficient In-Memory Computing Accelerator for 3D Point Cloud

Dengfeng Wang, Shunqin Cai, Yanan Sun

AI总结:

本文提出PC2IM加速器,通过改进的内存计算技术减少3D点云网络中的内存访问瓶颈,提升计算效率与能效。

摘要:

3D点云神经网络显著提升了资源受限移动智能系统感知能力。然而,点云算法在数据预处理过程中存在大量内存访问,导致特征计算负担大,能耗和延迟高。本文提出一种基于SRAM的计算在内存(SRAM-CIM)加速器(PC2IM),以缓解点云网络中的内存访问瓶颈。提出了一种由定制CIM引擎驱动的数据预处理模块,并将其纳入内存高效的流水线中。具体而言,引入了近似距离SRAM-CIM(APD-CIM)以消除对点云进行中位数空间分区时的重复芯片内存访问,减少临时距离数据的体积。基于APD-CIM,提出了一种两级Ping-Pong-MAX内容可寻址内存(Ping-Pong-MAX CAM)以自适应更新临时距离并执行现场最大值搜索,进一步减少内存访问。此外,还提出了一种高效的基于CIM的特征计算引擎,称为分割-连接SRAM-CIM,以在高精度输入的多层感知机中最小化计算延迟,同时保持高面积和能效。实验结果表明,所提出的PC2IM相比最先进的点云加速器实现了1.5倍的速度提升和2.7倍的能效提升。此外,PC2IM相比GPU实现的速度提升为3.5倍,能效提升为1518.9倍。

英文摘要:

3D point cloud neural networks have significantly enhanced the perceptual capabilities of resource-limited mobile intelligent systems. However, despite the transformative impact, the point cloud algorithm suffers from substantial memory access during data preprocessing and imposes a burdensome workload on feature computing, resulting in high energy consumption and latency. In this paper, an efficient SRAM-based computing-in-memory (SRAM-CIM) accelerator (PC2IM), is proposed to alleviate memory access bottlenecks in point-based 3D point cloud networks. A data preprocessing module driven by the customized CIM engines is proposed and incorporated into a memory-efficient data flow. Specifically, an approximate distance SRAM-CIM (APD-CIM) is introduced to eliminate the repetitive on-chip memory access for point clouds that are spatially partitioned by the median and reduce the volume of temporary distance data. Building on the APD-CIM, a two-level Ping-Pong-MAX Content Addressable Memory (Ping-Pong-MAX CAM) is introduced to adaptively update temporary distances and perform in-situ search for the maximum, further reducing memory access. Additionally, an efficient CIM-based feature computing engine, named split-concatenate SRAM-CIM, is presented to minimize computation latency in multi-layer perceptron with high-precision input, while maintaining high area and energy efficiency. Experiment results show that the proposed PC2IM demonstrates 1.5x speedup and 2.7x enhanced energy efficiency compared to state-of-the-art point cloud accelerator. Moreover, PC2IM achieves 3.5x speedup and 1518.9x enhanced energy efficiency compared to GPU implementations.

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。

↑