Related papers: SGDRC: Software-Defined Dynamic Resource Control f…

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.…

Deep Neural Networks (DNNs) are useful in many applications, including transportation, healthcare, and speech recognition. Despite various efforts to improve accuracy, few works have studied DNN in the context of real-time requirements.…

GPUs are used for training, inference, and tuning the machine learning models. However, Deep Neural Network (DNN) vary widely in their ability to exploit the full power of high-performance GPUs. Spatial sharing of GPU enables multiplexing…

Hardware accelerators such as GPUs are required for real-time, low-latency inference with Deep Neural Networks (DNN). However, due to the inherent limits to the parallelism they can exploit, DNNs often under-utilize the capacity of today's…

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes…

In cloud environments, GPU-based deep neural network (DNN) inference servers are required to meet the Service Level Objective (SLO) latency for each workload under a specified request rate, while also minimizing GPU resource consumption.…

With recent advancing of Internet of Things (IoTs), it becomes very attractive to implement the deep convolutional neural networks (DCNNs) onto embedded/portable systems. Presently, executing the software-based DCNNs requires…

Spiking Neural Networks (SNNs) are bio-plausible models that hold great potential for realizing energy-efficient implementations of sequential tasks on resource-constrained edge devices. However, commercial edge platforms based on standard…

Deep Neural Networks (DNNs) are widely used by engineers to solve difficult problems that require predictive modeling from data. However, these models are often massive, with millions or billions of parameters, and require substantial…

Stochastic gradient descent (SGD) is a widely adopted iterative method for optimizing differentiable objective functions. In this paper, we propose and discuss a novel approach to scale up SGD in applications involving non-convex functions…

Training Deep Neural Networks (DNNs) is a widely popular workload in both enterprises and cloud data centers. Existing schedulers for DNN training consider GPU as the dominant resource, and allocate other resources such as CPU and memory…

Deep neural network (DNN) inference is increasingly being executed on mobile and embedded platforms due to several key advantages in latency, privacy and always-on availability. However, due to limited computing resources, efficient DNN…

The growth of large language models (LLMs) increases challenges of accelerating distributed training across multiple GPUs in different data centers. Moreover, concerns about data privacy and data exhaustion have heightened interest in…

Edge computing and IoT applications are severely constrained by limited hardware resource. This makes memory consuming DNN frameworks not applicable to edge computing. Simple algorithms such as direct convolution are finding their way in…

With the sharp growth of cloud services and their possible combinations, the scale of data center network traffic has an inevitable explosive increasing in recent years. Software defined network (SDN) provides a scalable and flexible…

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…

The rapid development of deep neural networks (DNNs) is inherently accompanied by the problem of high computational costs. To tackle this challenge, dynamic voltage frequency scaling (DVFS) is emerging as a promising technology for…

Deep learning recommendation models (DLRMs) have been widely applied in Internet companies. The embedding tables of DLRMs are too large to fit on GPU memory entirely. We propose a GPU-based software cache approaches to dynamically manage…

Physical reservoir computing (PRC) is a promising brain-inspired computing architecture for overcoming the von Neumann bottleneck by utilizing the intrinsic dynamics of physical systems. However, a major obstacle to its real-world…

Software-defined networking (SDN) is the concept of decoupling the control and data planes to create a flexible and agile network, assisted by a central controller. However, the performance of SDN highly depends on the limitations in the…