JetsonLEAP: A framework to measure power on a heterogeneous system-on-a-chip device

Abstract

Computer science marches towards energy-aware practices. This trend impacts not only the design of computer architectures, but also the design of programs. However, developers still lack affordable and accurate technology to measure energy consumption in computing systems. The goal of this paper is to mitigate such problem. To this end, we introduce JetsonLEAP, a framework that supports the implementation of energy-aware programs. Jet-sonLEAP consists of an embedded hardware, in our case, the Nvidia Tegra TK1 System-on-a-chip device, a circuit to control the flow of energy, of our own design, plus a library to instrument program parts. We discuss two different circuit setups. The most precise setup lets us reliably measure the energy spent by 225,000 instructions, the least precise, although more affordable setup, gives us a window of 975,000 instructions. To probe the precision of our system, we use it in tandem with a high-precision, high-cost acquisition system, and show that results do not differ in any significant way from those that we get using our simpler apparatus. Our entire infrastructure -board, power meter and both circuits -can be reproduced with about $500.00. To demonstrate the efficacy of our framework, we have used it to measure the energy consumed by programs running on ARM cores, on the GPU, and on a remote server. Furthermore, we have studied the impact of OpenACC directives on the energy efficiency of high-performance applications.

Mapping Computations in Heterogeneous Multicore Systems with Statistical Regression on Inputs

“…The board features 2GB of LPDDR3 RAM. We use the energy measurement framework proposed by Bessa et al [17]. Power is measured by a National Instruments DAQ USB 6009 device, at a rate of 12,000 samples per second.…”

“…We have evaluated JINN-C with two objective functions: runtime and energy consumption. We measure energy for the entire board using physical probes, following Bessa et al's methodology [17].…”

A Compiler-Centric Infra-Structure for Whole-Board Energy Measurement on Heterogeneous Android Systems

“…The technology described in this paper, henceforth called AndroidLeap, is based on the JetsonLeap framework [12], [13], which, in turn, expands the AtomLeap framework [14]. JetsonLeap measures energy consumed by programs written in C, and running on the Nvidia Tegra TK1 board.…”

“…Diagram of the measurement circuit of AndroidLeap. This circuit follows the design in JetsonLeap[13]. Power profile with background interference.…”