NVIDIA Jetson Platform Characterization

Abstract

This study characterizes the NVIDIA Jetson TK1 and TX1 Platforms, both built on a NVIDIA Tegra System on Chip and combining a quad-core ARM CPU and an NVIDIA GPU. Their heterogeneous nature, as well as their wide operating frequency range, make it hard for application developers to reason about performance and determine which optimizations are worth pursuing. This paper attempts to inform developers’ choices by characterizing the platforms’ performance using Roofline models obtained through an empirical measurement-based approach as well as through a case study of a heterogeneous application (matrix multiplication). Our results highlight a difference of more than an order of magnitude in compute performance between the CPU and GPU on both platforms. Given that the CPU and GPU share the same memory bus, their Roofline models’ balance points are also more than an order of magnitude apart. We also explore the impact of frequency scaling build CPU and GPU Roofline profiles and characterize both platforms’ balance point variation, power consumption, and performance per watt as frequency is scaled.

The characterization we provide can be used in two main ways. First, given an application, it can inform the choice and number of processing elements to use (i.e., CPU/GPU and number of cores) as well as the optimizations likely to lead to high performance gains. Secondly, this characterization indicates that developers can use frequency scaling to tune the Jetson Platform to suit the requirements of their applications. Third, given a required power/performance budget, application developers can identify the appropriate parameters to use to tune the Jetson platforms to their specific workload requirements. We expect that this optimization approach can lead to overall gains in performance and/or power efficiency without requiring application changes.