A study of mobile device utilization

By Cao Gao, Anthony Gutierrez, M. Rajan, Ronald Dreslinski Jr., T. Mudge, Carole-Jean Wu. 2015

66 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering, Hardware and Architecture, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Electrical and Electronic Engineering

In Hardware and Architecture

In Human-Computer Interaction

Carole-Jean Wu

Citations in the corpus

Sustainable AI: Environmental Implications, Challenges and Opportunities (2021, background): “However, amortizing the embodied carbon footprint is particularly challenging due to significant under-utilization (Gao et al., 2015), motivating new environmentally-sustainable system design.”
DORA: Optimizing Smartphone Energy Efficiency and Web Browser Performance under Interference (2018, background): “5A recent characterization study has shown that the average thread-level parallelism for mobile Apps hovers around 2 [45].”
ACT: designing sustainable computer systems with an architectural carbon modeling tool (2022, background): “GPU requires an average 35% utilization, well beyond the typical usage behavior of mobile platforms [32].”
AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning (2021, background): “The overhead from training computation can be further alleviated by leveraging idle cores in mobile SoCs — the average thread level parallelism for mobile applications is around 2 [31, 60]”
AutoScale: Energy Efficiency Optimization for Stochastic Edge Inference Using Reinforcement Learning (2020, background): “As mobile systems become powerful [31], [41], [50], [107], there has been increasing push to execute DNN inference at the edge [10], [25], [42], [53], [55], [65], [106], [107], [111], [121].”
Machine Learning at Facebook: Understanding Inference at the Edge (2019, result): “A similar observation was made in 2015 [6].”
AutoScale: Optimizing Energy Efficiency of End-to-End Edge Inference under Stochastic Variance (2020, background): “As mobile systems become higherperforming [27,35,41,90], there have been increasing pushes Figure 14: The reward is usually converged in 40-50 runs.”
Improving smartphone user experience by balancing performance and energy with probabilistic QoS guarantee (2016, result): “This agrees with the observation made in a recent mobile device utilization study [17]—the processor utilization of web browsing has peaks and valleys between one to three cores of a four-core application processor with an average utilization to be below two cores.”