Related papers: Virtualization of Tiny Embedded Systems with a rob…
The increasing demand for large language model (LLM) serving has necessitated significant advancements in the optimization and profiling of LLM inference systems. As these models become integral to a wide range of applications, the need for…
Embedded and IoT devices, largely powered by microcontroller units (MCUs), could be made more intelligent by leveraging on-device deep learning. One of the main challenges of neural network inference on an MCU is the extremely limited…
Reasoning about fine-grained spatial relationships in warehouse-scale environments poses a significant challenge for existing vision-language models (VLMs), which often struggle to comprehend 3D layouts, object arrangements, and multimodal…
Serving Large Language Models (LLMs) in production faces significant challenges from highly variable request patterns and severe resource fragmentation in serverless clusters. Current systems rely on static pipeline configurations that…
Virtual machines (VMs) are highly beneficial for microcontroller development. In particular, interactive programming environments greatly facilitate iterative development processes, and higher execution speeds expand the range of…
This paper introduces a novel approach in neuromorphic computing, integrating heterogeneous hardware nodes into a unified, massively parallel architecture. Our system transcends traditional single-node constraints, harnessing the neural…
Virtualization is the abstraction of details. Algorithms and programming languages provide abstraction, too. Virtualization of hardware and embedded systems is becoming more and more important in heterogeneous environments and networks,…
Compared to the first generation of deep neural networks, dominated by regular, compute-intensive kernels such as matrix multiplications (MatMuls) and convolutions, modern decoder-based transformers interleave attention, normalization, and…
The ever-increasing complexity of HW/SW systems presents a persistent challenge, particularly in safety-critical domains like automotive, where extensive testing is imperative. However, the availability of hardware often lags behind,…
Virtualization is generally adopted in server and desktop environments to provide for fault tolerance, resource management, and energy efficiency. Virtualization enables parallel execution of multiple operating systems (OSs) while sharing…
In recent decades, Machine Learning (ML) has become extremely important for many computing applications. The pervasiveness of ultra-low-power embedded devices such as ESP32 or ESP32 Cam with tiny Machine Learning (tinyML) applications will…
The byte-addressable Non-Volatile Memory (NVM) is a promising technology since it simultaneously provides DRAM-like performance, disk-like capacity, and persistency. The current NVM deployment is symmetric, where NVM devices are directly…
Examples of embedded intelligence include a wide variety of tiny neural networks used on-board wireless sensors and actuators, which are expected to continuously perform inference on time-series of the data they sense. In order to fit…
As Moore's Law has slowed and Dennard Scaling has ended, architects are increasingly turning to heterogeneous parallelism and domain-specific hardware-software co-designs. These trends present new challenges for simulation-based performance…
Specialized Deep Learning (DL) acceleration stacks, designed for a specific set of frameworks, model architectures, operators, and data types, offer the allure of high performance while sacrificing flexibility. Changes in algorithms,…
Large-scale distributed computing infrastructures such as the Worldwide LHC Computing Grid (WLCG) require comprehensive simulation tools for evaluating performance, testing new algorithms, and optimizing resource allocation strategies.…
Virtualization has rapidly become a go-to technology for increasing efficiency in the data center. With virtualization technologies providing tremendous flexibility, even disparate architectures may be deployed on a single machine without…
With the surge of inexpensive computational and memory resources, neural networks (NNs) have experienced an unprecedented growth in architectural and computational complexity. Introducing NNs to resource-constrained devices enables…
Tiny Machine Learning (TinyML) systems, which enable machine learning inference on highly resource-constrained devices, are transforming edge computing but encounter unique security challenges. These devices, restricted by RAM and CPU…
Support vector machines (SVMs) are an important tool in modern data analysis. Traditionally, support vector machines have been fitted via quadratic programming, either using purpose-built or off-the-shelf algorithms. We present an…