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 2008.06967cs.CVcs.AR
收藏

Mesorasi:通过延迟聚合实现点云分析的架构支持

Mesorasi: Architecture Support for Point Cloud Analytics via Delayed-Aggregation

University of Rochester(罗切斯特大学);Arm Research(Arm研究院)

Yu Feng, Boyuan Tian, Tiancheng Xu, Paul Whatmough, Yuhao Zhu

摘要:

点云分析有望成为电池供电的嵌入式和移动平台上的关键工作负载,广泛应用于自动驾驶、机器人和增强现实等新兴应用领域,这些领域的效率至关重要。本文提出了Mesorasi,这是一种算法架构协同设计的系统,可以同时提高点云分析的性能和能源效率,同时保持其准确性。我们对最先进的点云算法的广泛表征表明,虽然在结构上让人联想到卷积神经网络(CNN),但由于点云数据的独特特性,点云算法表现出固有的计算和内存效率低下。我们提出了延迟聚合,一个新的算法原语建立高效的点云算法。延迟聚集算法利用点云算法中关键操作的近似分布特性,隐藏了点云算法的性能瓶颈,减少了计算和存储冗余。延迟聚合让点云算法在移动GPU上实现了1.6倍的加速和51.1%的能耗降低,同时保持了准确性(-0.9%损失到1.2%增益)。为了最大限度地提高算法的优势,我们提出了对当代CNN加速器的微小扩展,这些加速器可以集成到移动片上系统(SoC)中,而无需修改其他SoC组件。通过额外的硬件支持,Mesorasi实现了高达3.6倍的加速。

英文摘要:

Point cloud analytics is poised to become a key workload on battery-powered embedded and mobile platforms in a wide range of emerging application domains, such as autonomous driving, robotics, and augmented reality, where efficiency is paramount. This paper proposes Mesorasi, an algorithm-architecture co-designed system that simultaneously improves the performance and energy efficiency of point cloud analytics while retaining its accuracy. Our extensive characterizations of state-of-the-art point cloud algorithms show that, while structurally reminiscent of convolutional neural networks (CNNs), point cloud algorithms exhibit inherent compute and memory inefficiencies due to the unique characteristics of point cloud data. We propose delayed-aggregation, a new algorithmic primitive for building efficient point cloud algorithms. Delayed-aggregation hides the performance bottlenecks and reduces the compute and memory redundancies by exploiting the approximately distributive property of key operations in point cloud algorithms. Delayed-aggregation let point cloud algorithms achieve 1.6x speedup and 51.1% energy reduction on a mobile GPU while retaining the accuracy (-0.9% loss to 1.2% gains). To maximize the algorithmic benefits, we propose minor extensions to contemporary CNN accelerators, which can be integrated into a mobile Systems-on-a-Chip (SoC) without modifying other SoC components. With additional hardware support, Mesorasi achieves up to 3.6x speedup.

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。

↑