The EH Model: Early Design Space Exploration of Intermittent Processor Architectures

Miguel, Joshua San; Ganesan, Karthik; Badr, Mario; Xia, Chunqiu; Li, Rose; Hsiao, Hsuan; Jerger, Natalie Enright

doi:10.1109/micro.2018.00055

Cited by 23 publications

(19 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The energy cost of a checkpoint is the product of the average number of bytes it contains d b and the energy cost of writing and reading a byte of data e b . As prior work [2], [3], we find that backup and restore costs are nearly perfectly linear in the number of bytes that needs to be read or written. Idle: ULP-systems use sleep modes, which are low-energy states where selected components are either power-gated or clock-gated, to save energy while idle.…”

Section: The Pes Modelsupporting

confidence: 64%

“…We now evaluate PES and compare to the EH-model [2], [3]. While EH only models compute, it is straightforward to extend it to model periodic systems that sleep (see Section 2).…”

Section: Resultsmentioning

confidence: 99%

“…Our Periodic Energy-Harvesting Systems (PES) model enables IoT developers to select sustainable near-energy-neutral design points by faithfully modeling the energy consumption of computation and communication. In contrast, the state-of-theart EH-model [2], [3] only models computation and backup; backups have a high energy cost in communicating systems because the connection to the back-end system needs to be reestablished when power returns. Across our IoT applications, PES predicts energy consumption with an average error of 0.5% (maximally 1.4%) relative to our real-hardware baseline and simulator for energy-feasible and intermittent design points, respectively.…”

Section: Resume Thresholdmentioning

confidence: 99%

See 2 more Smart Citations

Modeling Periodic Energy-Harvesting Computing Systems

Ghasemi

Jahre

2021

IEEE Comput. Arch. Lett.

View full text Add to dashboard Cite

The Internet of Things (IoT) requires Ultra-Low Power (ULP) systems that communicate wirelessly and solely rely on harvested energy to scalably interact with the environment. This is challenging for IoT developers because (i) energy and performance are fundamentally intertwined -since capturing sensor samples and communicating more frequently increases energy consumption -and (ii) the performance versus energy trade-off typically needs to evaluated before ULP-platform selection -as the developer needs to be sure that a sufficiently performant system can be built before incurring the (substantial) effort of implementing the application on the ULP-platform. In this paper, we present the Periodic Energy-Harvesting Systems (PES) model which enables such trade-offs by faithfully modeling the energy impact of changing sampling and communication rates. Across our IoT applications, PES has an average energy prediction error of only 0.5%. In contrast, the average error of the state-of-the-art EH-model is 77.0%.

show abstract

Section: The Pes Modelsupporting

confidence: 64%

“…We now evaluate PES and compare to the EH-model [2], [3]. While EH only models compute, it is straightforward to extend it to model periodic systems that sleep (see Section 2).…”

Section: Resultsmentioning

confidence: 99%

Section: Resume Thresholdmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Periodic Energy-Harvesting Computing Systems

Ghasemi

Jahre

2021

IEEE Comput. Arch. Lett.

View full text Add to dashboard Cite

show abstract

“…Also, in EH applications, volatile processors are undesired, as they would be inefficient in application cases where the primary energy supply is uncontrollable. The intermittency of such power supply would necessitate backup/reinitialization schemes for computational accuracy, which could be so recurrent as to impact forward progress and incur significant energy overhead [41]. Approximation-based computing in applications that are amenable to approximation [42], nonvolatile Ferroelectric random-access memory [43], resistive randomaccess memory [44], magnetic random-access memory [45], negative capacitance field-effect transistors [46], and ferroelectric field-effect transistors [47] based processing are alternatives currently being explored for LENs applications.…”

Section: Background and Recent Trends In Energy Efficiency: A Taxonomymentioning

confidence: 99%

Energy Efficient Design Techniques in Next-Generation Wireless Communication Networks: Emerging Trends and Future Directions

Ogbebor

Imoize

Atayero

2020

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The projected rise in wireless communication traffic has necessitated the advancement of energy-efficient (EE) techniques for the design of wireless communication systems, given the high operating costs of conventional wireless cellular networks, and the scarcity of energy resources in low-power applications. The objective of this paper is to examine the paradigm shifts in EE approaches in recent times by reviewing traditional approaches to EE, analyzing recent trends, and identifying future challenges and opportunities. Considering the current energy concerns, nodes in emerging wireless networks range from limited-energy nodes (LENs) to high-energy nodes (HENs) with entirely different constraints in either case. In view of these extremes, this paper examines the principles behind energy-efficient wireless communication network design. We then present a broad taxonomy that tracks the areas of impact of these techniques in the network. We specifically discuss the preponderance of prediction-based energy-efficient techniques and their limits, and then discuss the trends in renewable energy supply systems for future networks. Finally, we recommend more context-specific energy-efficient research efforts and cross-vendor collaborations to push the frontiers of energy efficiency in the design of wireless communication networks.

show abstract

“…Analytical models. Several analytical models have been proposed to evaluate intermittent computing methods [6], [23], [24] and energy-neutral systems [2]. The most comprehensive, EH-model [24], can provide early estimations of completion time for several recent intermittent computing methods using different state retention mechanisms.…”

Section: Background and Related Workmentioning

confidence: 99%

NVIDIA GPGPUs Instructions Energy Consumption

Arafa

ElWazir

Elkanishy

et al. 2020

2020 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)

View full text Add to dashboard Cite

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].

show abstract

The EH Model: Early Design Space Exploration of Intermittent Processor Architectures

Cited by 23 publications

References 39 publications

Modeling Periodic Energy-Harvesting Computing Systems

Modeling Periodic Energy-Harvesting Computing Systems

Energy Efficient Design Techniques in Next-Generation Wireless Communication Networks: Emerging Trends and Future Directions

NVIDIA GPGPUs Instructions Energy Consumption

Contact Info

Product

Resources

About