As heterogeneous many-core systems gain prominence in embedded domains, efficient scheduling mechanisms become increasingly vital. Existing solutions often suffer from trade-offs between real-time responsiveness, parallelism, and programmability. We propose a hybrid hardware-software scheduling framework for heterogeneous many-core systems, which ensures the software algorithm’s scheduling results while dynamically adjusting task execution at runtime based on hardware status. Task dependencies are analyzed offline using a domain-specific language (DSL) to generate optimized schedules. At runtime, a hardware scheduler performs fast dependency checks and task dispatching. Experimental results show efficient parallel scheduling with minimal overhead, positioning the framework as a practical solution for latency-sensitive applications such as wireless baseband processing.

Hardware Trojans in high level synthesis (HLS) generated intellectual property (IP) designs pose significant security threats. The HLS frameworks, while enabling efficient hardware design from high-level descriptions to its respective register transfer level (RTL) counterpart, may introduce security vulnerabilities. These vulnerabilities allow malicious Trojan to be stealthily injected during phases like scheduling, allocation, and mux-interconnect design stage. Compromised HLS frameworks exacerbate this risk, potentially embedding backdoors or degrading IP operation in multiple ways. This paper proposes a novel HLS Trojan detection technique by employing a decision tree classifier-based machine learning model. Key hardware IP RTL features are extracted and analyzed, achieving high detection accuracy with zero false positives for specific trojans considered here, ensuring robust IP security.

In mixed-criticality (MC) systems, each task has multiple WCETs for different operation modes. Determining WCETs for low-criticality modes (LO modes) is challenging. A lower WCET improves processor utilization, but a longer one reduces mode switches, maintaining smooth task execution even with low utilization. Most research focuses on WCETs for the highest-criticality mode, with fewer solutions for LO modes in graph-based applications. This letter proposes GNN-MiCS, a machine learning and graph neural networks (GNNs) scheme to determine WCETs for directed acyclic graph applications in LO modes. GNN-MiCS generates test sets and computes proper WCETs based on the application graph to enhance system timing behavior. Experiments show our approach improves MC system utilization by up to 45.85% and 22.45% on average while maintaining a reasonable number of mode switches in the worst-case scenario.

Distributed systems often require dynamic capabilities to ensure adaptability, efficiency, and fault-tolerance. In applications where determinism and timing are crucial, a clear and well-defined approach to deterministic dynamism is much needed, but inherently difficult to define. This letter gives dynamism deterministic semantics, thus enabling precise and repeatable behavior. To this end, we select the Lingua Franca (LF) coordination language that is based on the reactor model, and introduce dynamism to the distributed LF programs, referred to as federations. This letter outlines the challenges associated with incorporating transient federates, which are capable of joining and leaving the federation at arbitrary times, and proposes solutions to the identified problems. A realistic example of an online auction system is used to illustrate the approach. Furthermore, the potential applications of this mechanism are discussed, along with the challenges that need to be addressed.

Real-time monitoring of one-dimensional (1D) biopotentials, such as electrocardiograms (ECG), necessitates effective feature extraction and classification, a strength of Deep Learning (DL) algorithms. Designing 1D Convolutional Neural Network (1D CNN) accelerators for biopotential classification via open-source codesign workflows, particularly High-Level Synthesis for Machine Learning (HLS4ML), offers advantages over GPU-based or Cloud-based solutions, including high performance, low latency, low power consumption, swift time-to-market, and cost-effectiveness. We present an implementation of a quantized-pruned (QP) 1D CNN model on the PYNQ Z2 SoC using HLS4ML by seamlessly deploying its soft IP core generated via Vivado Accelerator backend, showcasing the efficacy of Quantization Aware Training (QAT) in reducing power consumption to 1.655W from 1.823W. Our approach demonstrates improved area consumption, resource utilization, and inferences per second compared to the baseline (B) 1D CNN model, with a controlled 4% or less reduction in weighted Accuracy, Precision, Recall, and F1-score, revealing the nuanced trade-offs between performance metrics and system efficiency for real-time 3-Channel ECG Arrhythmia classification.

Fog devices in fog computing frameworks are responsible for fetching and executing the tasks submitted by the deployed resource-constraint embedded edge devices. Based on the availability of resources, tasks are offloaded to the virtual machines hosted by the fog devices. These tasks may then get scheduled to guarantee a number of efficiency-related metrics. While throughput has a decisive impact on the timely execution of tasks, the appropriate utilization of this metric has not been considered in the existing mechanisms. In this letter, we first discuss the proper use of this objective in the fitness function of meta-heuristic algorithms. Then, we explain that adopting throughput by the fitness functions in the form of two conventionally used weighted-sum, and fractional techniques may ignore solutions with a better guarantee ratio. Consequently, we propose a novel approach called DATA to be replaced with these two old approaches. DATA is a throughput, and deadline-aware task scheduling mechanism for time-sensitive fog frameworks, which its fitness function utilizes genetic optimization by encoding the solutions into chromosomes. It uses single gene mutation and two-point crossover. In this approach, two populations are considered to search the problem space. The main population is evaluated based on the guarantee ratio, while the helper population is evaluated based on the throughput. Furthermore, the helper population uses weighted-sum. The initial population is generated randomly by the uniform distribution, to provide a load-balancing. Based on our extensive evaluations, the selected solution by DATA provides the highest guarantee ratio, while having the lowest possible makespan.

Intelligent connected vehicles (ICVs) are the result of technological advancements in the new era, greatly enhancing the driving experience. However, due to the complex nature of the system, the intelligence of devices, and the connectivity of data, a complex physical fusion system has been created. The in-vehicle Telematics Box (T-Box), serving as the central communication and data hub, faces challenges, such as network vulnerabilities, data privacy, and malicious attacks through untrusted software updates. Therefore, an in-vehicle T-Box with high reliability, security, and performance is an urgent product in the era of the Internet of Vehicles. This article investigates the endogenous security of the T-Box in ICV, with a focus on the integration of dynamic heterogeneous redundancy (DHR) architecture. The underlying idea is to transform the original system into multiple heterogeneous systems, where some of them handle the same business functions. By applying a consensus mechanism to detect malicious nodes and dynamically scheduling healthy nodes into the working mode, a self-purifying defense system with intrinsic security is formed. This design approach endows the T-Box with inherent defense capabilities against unknown vulnerabilities. Meanwhile, the in-vehicle T-Box is redesigned in the software and hardware implementation scheme. Experimental results demonstrate that the new design notably enhances and ensures the robust stability and elevated reliability of the in-vehicle T-Box. Evidently, the upgraded T-Box ensures the safe processing of in-vehicle CAN bus data.

This work focuses on advancing security research in the hardware design space by formally defining the realistic problem of Hardware Trojan (HT) detection. The goal is to model HT detection more closely to the real world, i.e., describing the problem as The Seeker's Dilemma where a detecting agent is unaware of whether circuits are infected by HTs or not. Using this theoretical problem formulation, we create a benchmark that consists of a mixture of HT-free and HT-infected restructured circuits while preserving their original functionalities. The restructured circuits are randomly infected by HTs, causing a situation where the defender is uncertain if a circuit is infected or not. We believe that our innovative benchmark and methodology of creating benchmarks will help the community judge the detection quality of different methods by comparing their success rates in circuit classification. We use our developed benchmark to evaluate three state-of-the-art HT detection tools to show baseline results for this approach. We use Principal Component Analysis to assess the strength of our benchmark, where we observe that some restructured HT-infected circuits are mapped closely to HT-free circuits, leading to significant label misclassification by detectors.

Machine learning methods have been used to solve real-time scheduling problems but none has yet made an architecture that utilizes influences between real-time tasks as input features. This paper proposes a novel approach to partitioned scheduling in real-time systems using graph machine learning. We present a graph representation of real-time task sets that enable graph machine-learning schemes to capture the influence between real-time tasks. By using a graph attention network (GAT) with this method, our model successfully partitioned-schedule task sets that were previously deemed unschedulable by state-of-the-art partitioned scheduling algorithms. The GAT is used to establish relationships between nodes in the graph, which represent real-time tasks, and to learn how these relationships affect the schedulability of the system.