paper-with-me

홈 › Papers

Idle is the New Sleep: Configuration-Aware Alternative to Powering Off FPGA-Based DL Accelerators During Inactivity

2024-06-28 · Chao Qian, Christopher Cichiwskyj, Tianheng Ling, Gregor Schiele

In the rapidly evolving Internet of Things (IoT) domain, we concentrate on enhancing energy efficiency in Deep Learning accelerators on FPGA-based heterogeneous platforms, aligning with the principles of sustainable computing. Instead of focusing on the inference phase, we introduce innovative optimizations to minimize the overhead of the FPGA configuration phase. By fine-tuning configuration parameters correctly, we achieved a 40.13-fold reduction in configuration energy. Moreover, augmented with power-saving methods, our Idle-Waiting strategy outperformed the traditional On-Off strategy in duty-cycle mode for request periods up to 499.06 ms. Specifically, at a 40 ms request period within a 4147 J energy budget, this strategy extends the system lifetime to approximately 12.39x that of the On-Off strategy. Empirically validated through hardware measurements and simulations, these optimizations provide valuable insights and practical methods for achieving energy-efficient and sustainable deployments in IoT.

📄 PDF Abstract BibTeX arXiv:2407.12027

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mixed Neural Network Approach for Temporal Sleep Stage Classification

2016-10-15 · Hao Dong, Akara Supratak, Wei Pan, Chao Wu 외

This paper proposes a practical approach to addressing limitations posed by use of single active electrodes in applications for sleep stage classification. Electroencephalography (EEG)-based characterizations of sleep st…

ClassificationEEGElectroencephalogram (EEG)General Classification

Deep Reinforcement Learning with Spatio-temporal Traffic Forecasting for Data-Driven Base Station Sleep Control

2021-01-21 · Qiong Wu, Xu Chen, Zhi Zhou, Liang Chen 외

To meet the ever increasing mobile traffic demand in 5G era, base stations (BSs) have been densely deployed in radio access networks (RANs) to increase the network coverage and capacity. However, as the high density of B…

Deep Reinforcement Learning

Improving the Efficiency of a Deep Reinforcement Learning-Based Power Management System for HPC Clusters Using Curriculum Learning

2025-02-27 · Thomas Budiarjo, Santana Yuda Pradata, Kadek Gemilang Santiyuda, Muhammad Alfian Amrizal 외

High energy consumption remains a key challenge in high-performance computing (HPC) systems, which often feature hundreds or thousands of nodes drawing substantial power even in idle or standby modes. Although powering d…

Deep Reinforcement LearningManagementReinforcement Learning (RL)

Feature matching as improved transfer learning technique for wearable EEG

2021-12-29 · Elisabeth R. M. Heremans, Huy Phan, Amir H. Ansari, Pascal Borzée 외

Objective: With the rapid rise of wearable sleep monitoring devices with non-conventional electrode configurations, there is a need for automated algorithms that can perform sleep staging on configurations with small amo…

EEGElectroencephalogram (EEG)Sleep StagingTransfer Learning

Vision Transformer Accelerator ASIC for Real-Time, Low-Power Sleep Staging

2025-02-22 · Tristan Robitaille, Xilin Liu

This paper introduces a lightweight vision transformer aimed at automatic sleep staging in a wearable device. The model is trained on the MASS SS3 dataset and achieves an accuracy of 82.9% on a 4-stage classification tas…

Sleep Staging