Related papers: Zygarde: Time-Sensitive On-Device Deep Inference a…
Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains hindered by substantial parameter counts, computational demands, and the probability of…
Larger Spiking Neural Network (SNN) models are typically favorable as they can offer higher accuracy. However, employing such models on the resource- and energy-constrained embedded platforms is inefficient. Towards this, we present a…
Giant Deep Neural Networks (DNNs), have become indispensable for accurate and robust support of large-scale cloud based AI services. However, serving giant DNNs is prohibitively expensive from an energy consumption viewpoint easily…
Recurrent neural networks (RNNs) have shown state of the art results for speech recognition, natural language processing, image captioning and video summarizing applications. Many of these applications run on low-power platforms, so their…
Robots deployed in dynamic environments must contend with environment-driven changes that reshape computation at runtime: new tasks may appear, precedence relations can shift, and overall workload structure evolves, all of which degrade…
The growing demand for multi-DNN workloads with unpredictable task arrival times has highlighted the need for interruptible scheduling on edge accelerators. However, existing preemptive frameworks typically assume known task arrival times…
In this paper, we address the power-aware scheduling of sporadic constrained-deadline hard real-time tasks using dynamic voltage scaling upon multiprocessor platforms. We propose two distinct algorithms. Our first algorithm is an off-line…
Deep neural networks (DNNs) have substantial computational requirements, which greatly limit their performance in resource-constrained environments. Recently, there are increasing efforts on optical neural networks and optical computing…
The growing renewable energy sources have posed significant challenges to traditional power scheduling. It is difficult for operators to obtain accurate day-ahead forecasts of renewable generation, thereby requiring the future scheduling…
A novel energy reduction strategy to maximally exploit the dynamic workload variation is proposed for the offline voltage scheduling of preemptive systems. The idea is to construct a fully-preemptive schedule that leads to minimum energy…
Processing visual data on mobile devices has many applications, e.g., emergency response and tracking. State-of-the-art computer vision techniques rely on large Deep Neural Networks (DNNs) that are usually too power-hungry to be deployed on…
The computation and storage requirements for Deep Neural Networks (DNNs) are usually high. This issue limits their deployability on ubiquitous computing devices such as smart phones, wearables and autonomous drones. In this paper, we…
Modern computing paradigms, such as cloud computing, are increasingly adopting GPUs to boost their computing capabilities primarily due to the heterogeneous nature of AI/ML/deep learning workloads. However, the energy consumption of GPUs is…
Energy consumption is a critical design issue in real-time systems, especially in battery- operated systems. Maintaining high performance, while extending the battery life between charges is an interesting challenge for system designers.…
With the fast development of deep neural networks (DNNs), many real-world applications are adopting multiple models to conduct compound tasks, such as co-running classification, detection, and segmentation models on autonomous vehicles.…
We evolve PyDTNN, a framework for distributed parallel training of Deep Neural Networks (DNNs), into an efficient inference tool for convolutional neural networks. Our optimization process on multicore ARM processors involves several…
Energy-efficient real-time task scheduling has been actively explored in the past decade. Different from the past work, this paper considers schedulability conditions for stochastic real-time tasks. A schedulability condition is first…
Edge intelligence enables resource-demanding Deep Neural Network (DNN) inference without transferring original data, addressing concerns about data privacy in consumer Internet of Things (IoT) devices. For privacy-sensitive applications,…
Deep neural networks have significantly improved performance on a range of tasks with the increasing demand for computational resources, leaving deployment on low-resource devices (with limited memory and battery power) infeasible. Binary…
Deploying deep neural networks (DNNs) on power-sensitive edge devices presents a formidable challenge. While Dynamic Voltage and Frequency Scaling (DVFS) is widely employed for energy optimization, traditional model-level scaling is often…