Performance Analysis and Optimization Opportunities for NVIDIA Automotive GPUs

• Published in: Journal of parallel and distributed computing 2021-06, Vol.152, p.21-32
• Main Authors: Tabani, Hamid, Mazzocchetti, Fabio, Benedicte, Pedro, Abella, Jaume, Cazorla, Francisco J.
• Format: Article
• Language: English
• Subjects: Automotive GPUs; Design space exploration; Optimization; Performance analysis
• ISSN: 0743-7315; 1096-0848
• DOI: 10.1016/j.jpdc.2021.02.008

Advanced Driver Assistance Systems (ADAS) and Autonomous Driving (AD) bring unprecedented performance requirements for automotive systems. Graphic Processing Unit (GPU) based platforms have been deployed with the aim of meeting these requirements, being NVIDIA Jetson TX2 and its high-performance successor, NVIDIA AGX Xavier, relevant representatives. However, to what extent high-performance GPU configurations are appropriate for ADAS and AD workloads remains as an open question. This paper analyzes this concern and provides valuable insights on this question by modeling two recent automotive NVIDIA GPU-based platforms, namely TX2 and AGX Xavier. In particular, our work assesses their microarchitectural parameters against relevant benchmarks, identifying GPU setups delivering increased performance within a similar cost envelope, or decreasing hardware costs while preserving original performance levels. Overall, our analysis identifies opportunities for the optimization of automotive GPUs to further increase system efficiency. •Performance analysis of automotive GPUs.•Analysis of latest NVIDIA automotive SoCs (NVIDIA TX2 and NVIDIA AGX Xavier).•Use of fully-system CPU–GPU cycle-level simulator.•Proposing improved configurations to provide similar performance at lower costs.