Related papers: Sentinel: Runtime Data Management on Heterogeneous…

Non-volatile memory (NVM) provides a scalable and power-efficient solution to replace DRAM as main memory. However, because of relatively high latency and low bandwidth of NVM, NVM is often paired with DRAM to build a heterogeneous memory…

Many high end and next generation computing systems to incorporated alternative memory technologies to meet performance goals. Since these technologies present distinct advantages and tradeoffs compared to conventional DDR* SDRAM, such as…

Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity. In this paper, we present approaches for online resource management in…

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…

Datacenters are increasingly becoming heterogeneous, and are starting to include specialized hardware for networking, video processing, and especially deep learning. To leverage the heterogeneous compute capability of modern datacenters, we…

Optimal deployment of deep neural networks (DNNs) on state-of-the-art Systems-on-Chips (SoCs) is crucial for tiny machine learning (TinyML) at the edge. The complexity of these SoCs makes deployment non-trivial, as they typically contain…

Federated learning (FL) offers a privacy-preserving paradigm for machine learning, but its application in intrusion detection systems (IDS) within IoT networks is challenged by severe class imbalance, non-IID data, and high communication…

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic random-access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it non-trivial to deploy…

Efficient execution of deep learning workloads on dataflow architectures is crucial for overcoming memory bottlenecks and maximizing performance. While streaming intermediate results between computation kernels can significantly improve…

Modern edge data centers simultaneously handle multiple Deep Neural Networks (DNNs), leading to significant challenges in workload management. Thus, current management systems must leverage the architectural heterogeneity of new embedded…

The Data Movement Manager (DMM) is a prototype interface that connects CERN's data management software, Rucio, with the Sofware-Defined Networking (SDN) service SENSE by ESNet. It enables SDN-enabled high-energy physics data flows using the…

Deep neural network (DNN) inference is increasingly being executed on mobile and embedded platforms due to low latency and better privacy. However, efficient deployment on these platforms is challenging due to the intensive computation and…

Two distinguishing features of state-of-the-art mobile and autonomous systems are 1) there are often multiple workloads, mainly deep neural network (DNN) inference, running concurrently and continuously; and 2) they operate on shared memory…

The field of cybersecurity is confronted with two interrelated challenges: a worldwide deficit of qualified practitioners and ongoing human-factor weaknesses that account for the bulk of security incidents. To tackle these issues, we…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Deep neural networks (DNNs) form the cornerstone of modern AI services, supporting a wide range of applications, including autonomous driving, chatbots, and recommendation systems. As models increase in size and complexity, DNN workloads…

As artificial intelligence (AI) and machine learning (ML) technologies disrupt a wide range of industries, cloud datacenters face ever-increasing demand in inference workloads. However, conventional CPU-based servers cannot handle excessive…

Edge computing faces unprecedented resource orchestration challenges from multi-dimensional heterogeneity across device architectures, diverse task requirements in CPU-intensive, GPU-intensive, I/O-intensive, and dynamic network conditions.…

A large language model (LLM) is one of the most important emerging machine learning applications nowadays. However, due to its huge model size and runtime increase of the memory footprint, LLM inferences suffer from the lack of memory…

Deep Neural Networks (DNNs) are increasingly deployed across diverse industries, driving demand for mobile device support. However, existing mobile inference frameworks often rely on a single processor per model, limiting hardware…