NVIDIA GPGPUs Instructions Energy Consumption

Abstract

Energy-driven computing is an emerging paradigm that aims to fuel the proliferation of tiny and low-cost IoT sensing and monitoring devices. Energy-driven computers are generally powered by energy harvesting sources, and adapt their operation at runtime according to energy availability; thus, they must be designed and tested according to the expected dynamics of their power source. However, today's processor simulators and debuggers typically assume that power is always available, so they are unable to correctly model the interactions between power supply, power consumption and energy-driven execution. To address this shortcoming, we propose Fused, an open source full-system simulator for energy-driven computers. Fused models execution, power consumption, and power supply in a closed loop, thus correctly models the interaction between them. It targets energydriven embedded systems, and employs SystemC for digital and mixed-signal simulation to model a microcontroller and mixedsignal circuitry, enabling hardware-software codesign and design space exploration. Fused includes a high-level power modelling methodology, whereby events recorded during simulation are correlated to power measurements of real hardware to extract features for power modelling. Results show that Fused can model the execution time and power consumption of a commercially available microcontroller with a geometric mean error of 0.2% and 3.4% respectively, across a wide range of workloads. Through a case-study, we demonstrate that Fused can accurately model a state-of-the art intermittent computing system, where execution is heavily dependent on energy availability: although up to 70 power cycles were needed to complete the tested workload on the constrained energy supply, Fused modelled the completion time with less than 7% error. Index Terms-Virtual prototyping, SystemC, Embedded systems I. INTRODUCTION With the advent of IoT, tiny, low-cost computing devices are becoming ubiquitous. The Ericsson mobility report predicts that by 2024, there will be 22 billion devices connected to the internet, excluding PCs, laptops, tablets and mobile phones [1]. This drives a need for ever smaller and more low-cost devices. Traditionally, this need has been met by battery-powered devices, but the batteries limit deployment lifetime and lead to increased cost, volume and mass. An attractive option is to augment, or even replace, battery power with energy harvested from ambient solar, mechanical (wind, vibration, motion), RF, or thermal energy sources. But harvested energy is often scarce, dynamic, and unpredictable [2].

Efficient DEVS Simulations Design on Heterogeneous Platforms

“…In this work we use the NVIDIA Management Library (NVML). To the best of our knowledge this is the only software tool validated to be accurate [Arafa20a;Arafa20b]. It allows to obtain a complete report of the GPUs energy use when executing a program.…”