SpOctA: A 3D Sparse Convolution Accelerator with Octree-Encoding-Based Map Search and Inherent Sparsity-Aware Processing

TL;DR

SpOctA is a specialized accelerator for 3D sparse convolution networks that significantly improves speed and energy efficiency in point cloud processing by leveraging octree encoding and inherent sparsity.

Contribution

It introduces a novel accelerator design that co-optimizes map search and computation, achieving substantial speedups and energy savings over existing solutions.

Findings

Achieves 8.8-21.2x search speedup

Reduces processing latency by 44.4-79.1%

Improves energy efficiency by 1.5-3.1x

Abstract

Point-cloud-based 3D perception has attracted great attention in various applications including robotics, autonomous driving and AR/VR. In particular, the 3D sparse convolution (SpConv) network has emerged as one of the most popular backbones due to its excellent performance. However, it poses severe challenges to real-time perception on general-purpose platforms, such as lengthy map search latency, high computation cost, and enormous memory footprint. In this paper, we propose SpOctA, a SpConv accelerator that enables high-speed and energy-efficient point cloud processing. SpOctA parallelizes the map search by utilizing algorithm-architecture co-optimization based on octree encoding, thereby achieving 8.8-21.2x search speedup. It also attenuates the heavy computational workload by exploiting inherent sparsity of each voxel, which eliminates computation redundancy and saves 44.4-79.1% processing latency. To optimize on-chip memory management, a SpConv-oriented non-uniform caching strategy is introduced to reduce external memory access energy by 57.6% on average. Implemented on a 40nm technology and extensively evaluated on representative benchmarks, SpOctA rivals the state-of-the-art SpConv accelerators by 1.1-6.9x speedup with 1.5-3.1x energy efficiency improvement.