Related papers: TenonOS: A Self-Generating LibOS-on-LibOS Framewor…

We present LionsOS, an operating system for security- and safety-critical embedded systems. LionsOS is based on the formally verified seL4 microkernel and designed with verification in mind. It uses a static architecture and features a…

The surging demand for GPUs in datacenters for machine learning (ML) has made efficient GPU utilization crucial. However, meeting the diverse needs of ML models while optimizing resource usage is challenging. To enable transparent,…

At design time, modern operating systems are locked in a specific safety and isolation strategy that mixes one or more hardware/software protection mechanisms (e.g. user/kernel separation); revisiting these choices after deployment requires…

Efficient tensor computation is a cornerstone of modern deep learning (DL) workloads, yet existing approaches struggle to achieve flexible and performant design and implementation of tensor layouts -- mappings between logical tensors and…

Nowadays, the use of embedded operating systems in different embedded projects is subject to a tremendous growth. Embedded Linux is becoming one of those most popular EOSs due to its modularity, efficiency, reliability, and cost. One way to…

Many applications have service requirements that are not easily met by existing operating systems. Real-time and security-critical tasks, for example, often require custom OSes to meet their needs. However, development of special purpose…

We present LibrettOS, an OS design that fuses two paradigms to simultaneously address issues of isolation, performance, compatibility, failure recoverability, and run-time upgrades. LibrettOS acts as a microkernel OS that runs servers in an…

Deep learning inference on embedded devices is a burgeoning field with myriad applications because tiny embedded devices are omnipresent. But we must overcome major challenges before we can benefit from this opportunity. Embedded processors…

Compared to overlay-based tensor architectures like VTA or Gemmini, compilers that directly translate machine learning models into a dataflow architecture as HLS code, such as HLS4ML and FINN, generally can achieve lower latency by…

Asynchronous frameworks for distributed embedded systems, like ROS and MQTT, are increasingly used in safety-critical applications such as autonomous driving, where the cost of unintended behavior is high. The coordination mechanism between…

Modern tensor applications, especially foundation models and generative AI applications require multiple input modalities (both vision and language), which increases the demand for flexible accelerator architecture. Existing frameworks…

The embedded systems engineering industry faces increasing demands for more functionality, rapidly evolving components, and shrinking schedules. Abilities to quickly adapt to changes, develop products with safe design, minimize project…

Embedded Linux processors are increasingly used for real-time computing tasks such as robotics and Internet of Things (IoT). These applications require robust and reproducible behavior from the host OS, commonly achieved through immutable…

Scaling data volume and diversity is critical for generalizing embodied intelligence. While synthetic data generation offers a scalable alternative to expensive physical data acquisition, existing pipelines remain fragmented and…

Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference deployment without significantly compromising model…

Generative models have demonstrated remarkable potential in time series analysis tasks, like synthesis, forecasting, imputation, etc. However, offering limited coverage for generative models, existing time series libraries are mainly…

Training graph neural networks (GNNs) on large-scale graph data holds immense promise for numerous real-world applications but remains a great challenge. Several disk-based GNN systems have been built to train large-scale graphs in a single…

We present LoopStack, a domain specific compiler stack for tensor operations, composed of a frontend, LoopTool, and an efficient optimizing code generator, LoopNest. This stack enables us to compile entire neural networks and generate code…

We introduce MENO (''Matrix Exponential-based Neural Operator''), a hybrid surrogate modeling framework for efficiently solving stiff systems of ordinary differential equations (ODEs) that exhibit a sparse nonlinear structure. In such…

Modern deep learning workloads often consist of many small tensor operations, especially in inference, attention, and micro-batched training. In these settings, kernel launch overhead can become a major bottleneck, sometimes exceeding the…