Boosting the Performance of Object Tracking with a Half-Precision Particle Filter on GPU

Boosting the Performance of Object Tracking with a Half-Precision Particle Filter on GPU

High-performance GPU-accelerated particle filter methods are critical for object detection applications, ranging from autonomous driving, robot localization, to time-series prediction. In this work, we investigate the design, development and optimization of particle-filter using half-precision on CU...

Full description

Saved in:
Bibliographic Details
Main Authors: Schieffer, Gabin, Pornthisan, Nattawat, de Medeiros, Daniel Araújo, Markidis, Stefano, Wahlgren, Jacob, Peng, Ivy
Format: Journal Article
Language:English
Published: 01-08-2023
Subjects:
Computer Science - Distributed, Parallel, and Cluster Computing
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:High-performance GPU-accelerated particle filter methods are critical for object detection applications, ranging from autonomous driving, robot localization, to time-series prediction. In this work, we investigate the design, development and optimization of particle-filter using half-precision on CUDA cores and compare their performance and accuracy with single- and double-precision baselines on Nvidia V100, A100, A40 and T4 GPUs. To mitigate numerical instability and precision losses, we introduce algorithmic changes in the particle filters. Using half-precision leads to a performance improvement of 1.5-2x and 2.5-4.6x with respect to single- and double-precision baselines respectively, at the cost of a relatively small loss of accuracy.
DOI:10.48550/arxiv.2308.00763