Related papers: Decoupled Access-Execute enabled DVFS for tinyML d…

Deep Neural Network (DNN) inference is emerging as the fundamental bedrock for a multitude of utilities and services. CPUs continue to scale up their raw compute capabilities for DNN inference along with mature high performance libraries to…

Neural Network designs are quite diverse, from VGG-style to ResNet-style, and from Convolutional Neural Networks to Transformers. Towards the design of efficient accelerators, many works have adopted a dataflow-based, inter-layer pipelined…

We present the first end-to-end deployment of the Gemma3 family of large language and vision models on a tiled edge dataflow architecture (AMD Ryzen AI NPU). Our work introduces a set of hardware-aware techniques. For prefill, we introduce…

Efficient on-device neural network (NN) inference offers predictable latency, improved privacy and reliability, and lower operating costs for vendors than cloud-based inference. This has sparked recent development of microcontroller-scale…

Modern deep learning applications urge to push the model inference taking place at the edge devices for multiple reasons such as achieving shorter latency, relieving the burden of the network connecting to the cloud, and protecting user…

Tiny machine learning (TinyML) aims to run ML models on small devices and is increasingly favored for its enhanced privacy, reduced latency, and low cost. Recently, the advent of tiny AI accelerators has revolutionized the TinyML field by…

Most investigations into near-memory hardware accelerators for deep neural networks have primarily focused on inference, while the potential of accelerating training has received relatively little attention so far. Based on an in-depth…

Today, most embedded systems use Dynamic Voltage and Frequency Scaling (DVFS) to minimize energy consumption and maximize performance. The DVFS technique works by regulating the important parameters that govern the amount of energy consumed…

Convolutional Neural Networks (CNNs) have shown outstanding accuracy for many vision tasks during recent years. When deploying CNNs on portable devices and embedded systems, however, the large number of parameters and computations result in…

Intracortical brain-machine interfaces demand low-latency, energy-efficient solutions for neural decoding. Spiking Neural Networks (SNNs) deployed on neuromorphic hardware have demonstrated remarkable efficiency in neural decoding by…

Network function virtualization (NFV) and software defined networking (SDN) are two promising technologies to enable 5G and 6G services and achieve cost reduction, network scalability, and deployment flexibility. However, migration to full…

Scaling deep learning recommendation models is an effective way to improve model expressiveness. Existing approaches often incur substantial computational overhead, making them difficult to deploy in large-scale industrial systems under…

In many modern AI chips and multicore systems-on-chip, embedded applications exhibit predictable inter-core traffic behavior that can be characterized at design time. For such applications, a variety of design-time traffic management and…

This paper proposes a hardware-aware intrusion detection system (IDS) for Internet of Things (IoT) and Industrial IoT (IIoT) networks; it targets scenarios where classification is essential for fast, privacy-preserving, and…

Wearable devices are revolutionizing personal technology, but their usability is often hindered by frequent charging due to high power consumption. This paper introduces Distributed Neural Networks (DistNN), a framework that distributes…

Deploying neural networks on constrained hardware platforms such as 32-bit microcontrollers is a challenging task because of the large memory, computing and energy requirements of their inference process. To tackle these issues, several…

Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs in a wide range of situations, especially mobile…

Edge devices demand low energy consumption, cost and small form factor. To efficiently deploy convolutional neural network (CNN) models on edge device, energy-aware model compression becomes extremely important. However, existing work did…

The emergence of Machine Learning (ML) as a powerful technique has been helping nearly all fields of business to increase operational efficiency or to develop new value propositions. Besides the challenges of deploying and maintaining ML…

While there exist many ways to deploy machine learning models on microcontrollers, it is non-trivial to choose the optimal combination of frameworks and targets for a given application. Thus, automating the end-to-end benchmarking flow is…