To utilize the performance benefits of heterogeneous multicore platforms in real-time systems, we need task models that expose parallelism and heterogeneity workload, such as typed DAG tasks, well scheduling algorithms effectively exploit this information. In paper, introduce <i>type-aware federated scheduling</i> for sporadic tasks with implicit deadlines running on a platform two different types cores. type-aware scheduling, can be executed one three strategies: <i>Exclusive...

Since the advent of software defined networks ({SDN}), there have been many attempts to outsource complex and costly local network functionality, i.e. middlebox, cloud in same way as outsourcing computation storage. The privacy issues, however, may thwart enterprises' willingness adopt this innovation since underlying configurations these middleboxes leak crucial confidential information which can be utilized by attackers. To address new problem, we use firewall an sample functionality...

In many modern safety-critical cyber-physical sys-tems, such as in the automotive or robotic domain, appli-cation complexity requires use of multi-core platforms to execute all workloads under strict hard real-time constraints. The sporadic DAG task model is a parallel adept at representing tasks comprised subtasks, which possess internal data flow and precedence constraints induced by synchronization. A significant challenge system's performance its verification stems from...

Over the years, many multiprocessor locking protocols have been designed and analyzed. However, performance of these highly depends on how tasks are partitioned prioritized, resources shared locally globally. This paper answers a few fundamental questions when real-time share in systems. We explore difficulty synchronization problem show that very simplified version this is NP-hard strong sense regardless number processors underlying scheduling paradigm. Therefore, allowance preemption or...

This paper studies the problem of scheduling a set hard real-time sporadic tasks that may access CPU cores and shared resource. Motivated by observation resource is often abundant compared to resources in multi-core many-core systems, we propose resolve this from counter-intuitive shared-resource-centric perspective, focusing on judiciously prioritizing tasks' requests limited preemptive manner while viewing worst-case latency task experience as suspension delays. We develop rather...

When considering recurrent real-time tasks in multiprocessor systems, access to shared resources, via so-called critical sections, can jeopardize the schedulability of system. The reason is that resource mutual exclusive and a task must finish its execution section before another same resource. Therefore, problem synchronization has been extensively studied since 1990s, large number sharing protocols have developed analyzed. Most assume work-conserving scheduling algorithms which make it...

Anonymous content sharing over the Internet protects user privacy and confidentiality. Most overlay anonymous communication protocols employ some relay nodes as proxies to forward require relays perform cryptography or coding operations on messages. They have two major limitations. First, extra computation overhead may discourage from serving relays. Second, long forwarding latency at makes an path easier fail under network churn. In this paper, we present a lightweight decentralized system...

Abstract The linear traveltime interpolation has been a routine method to compute first arrivals of seismic waves and trace rays in complex media. assumes that traveltimes follow distribution on each boundary cells. linearity assumption facilitates the numerical implementation but its violation may result large computational errors. In this paper, we propose new way mitigate potential shortcoming hidden interpolation. We use vertex calculated cell introduce an equivalent homogeneous medium...

The performance of multiprocessor synchronization and locking protocols is a key factor to utilize the computation power systems under real-time constraints.While multiple have been developed in past decades, their highly depends on task partition prioritization.The recently proposed Dependency Graph Approach showed its advantages attracted lot interest.It is, however, restricted sets where each has at most one critical section.In this article, we remove restriction demonstrate how...

Abstract The predictive performance of a machine learning model highly depends on the corresponding hyper-parameter setting. Hence, tuning is often indispensable. Normally such requires dedicated to be trained and evaluated centralized data obtain estimate. However, in distributed scenario, it not always possible collect all from nodes due privacy concerns or storage limitations. Moreover, if has transferred through low bandwidth connections reduces time available for tuning. Model-Based...

Safety-critical systems are often subjected to transient faults. Since these faults may lead soft errors that cause catastrophic consequences, error-handling must be addressed by design. Full-protection against is too costly in terms of resource usage. A common approach relax the demands and limit impact consider (m, k)-constraints, which requires at least m jobs out any k consecutive error-free. To assure k)-compliance, static patterns widely used select job execution modes, i.e., either an...

Due to the growing popularity of Internet Things, edge computing concept has been widely studied relieve load on original cloud and networks while improving service quality for end-users. To simulate such a complex environment involving computing, EdgeCloudSim adopted. However, it suffers from certain efficiency scalability issues due ignorance deficiency in originally adopted data structures maintenance strategies. Specifically, generates all events at beginning simulation stores...

Effectively handling precedence constraints and resource synchronization is a challenging problem in the era of multiprocessor systems even with massively parallel computation power. One common approach to apply list scheduling given task graph constraints. However, some application scenarios, such as OpenMP model partitioned for using binary semaphores, several operations can be forced tied same processor, which invalidates scheduling. This paper studies special case this problem, where...

Model-based Optimization (MBO) is a method to optimize expensive black-box functions that uses surrogate guide the search. We propose two practical approaches allow MBO where relation between input and output changes over time, which are known as dynamic optimization problems (DOPs). The window approach trains only on most recent observations, time-as-covariate includes time an additional variable in surrogate, giving it ability learn effect of outcomes. focus change happens systematically...

Ensuring timing guarantees for every individual tasks is critical in real-time systems. Even periodic tasks, providing with segmented self-suspending behavior challenging due to anomalies, i.e., the reduction of execution/suspension time some jobs increases response another job. The release jitter can add further complexity situation, affecting predictability and existing worst-case analyses sporadic are only over-approximations lead overly pessimistic results. In this work, we address...

Ensuring timing guarantees for every individual tasks is critical in real-time systems. Even periodic tasks, providing with segmented self-suspending behavior challenging due to anomalies, i.e., the reduction of execution or suspension time some jobs increases response another job. The release jitter can add further complexity situation, affecting predictability and existing worst-case analyses sporadic are only over-approximations lead overly pessimistic results. In this work, we address...

Over the years, many multiprocessor locking protocols have been designed and analyzed. However, performance of these highly depends on how tasks are partitioned prioritized resources shared locally globally. This paper answers a few fundamental questions when real-time share in systems. We explore difficulty synchronization problem show that very simplified version this is ${\mathcal NP}$-hard strong sense regardless number processors underlying scheduling paradigm. Therefore, allowance...

Timing guarantee is an important aspect and must be ensured for every individual task in real-time systems. Even periodic tasks, providing timing guarantees segmented self-suspending tasks challenging due to anomalies, i.e., the reduction of execution or suspension time some jobs enlarges response another job. The existing worstcase analyses sporadic are only over-approximations lead overly pessimistic results. In this paper, we focus on eliminating anomalies without negative impacts...

The performance of multiprocessor synchronization and locking protocols is a key factor to utilize the computation power systems under real-time constraints. While multiple have been developed in past decades, their highly depends on task partition prioritization. recently proposed Dependency Graph Approach showed its advantages attracted lot interest. It is, however, restricted sets where each has at most one critical section. In this paper, we remove restriction demonstrate how algorithms...

To avoid race conditions and ensure data integrity, resource synchronization protocols have been widely studied in real-time systems for decades, providing systematical policies to guarantee a bound on priority inversion-induced blocking time the avoidance of deadlocks.However, corresponding realization is often based assumed abstractions necessary adaptions operating system, by which theoretically proven properties such protocol may not be delivered, leading potential mismatches.To prevent...

When considering recurrent tasks in real-time systems, concurrent accesses to shared resources, can cause race conditions or data corruptions. Such a problem has been extensively studied since the 1990s, and numerous resource synchronization protocols have developed for both uni-processor multiprocessor with assumption that implementation overheads are negligible. However, practice, may impact performance of different depending upon practiced scenarios, e.g., resources accessed locally...

Multiprocessor resource synchronization and locking protocols are of great importance to utilize the computation power multiprocessor real-time systems. Hence, in past decades a large number have been developed analyzed. The recently proposed dependency graph approach has significantly improved schedulability for frame-based periodic task However, only supports non-nested access, i.e., each critical section can access one shared resource. In this paper, we develop based protocol that allows...