Related papers: Interference-free Operating System: A 6 Years' Exp…
Dragonfly class of networks are considered as promising interconnects for next-generation supercomputers. While Dragonfly+ networks offer more path diversity than the original Dragonfly design, they are still prone to performance…
The Robot Operating System (ROS) is rapidly becoming the de facto framework for building robotics systems, thanks to its flexibility and the large acceptance that it has received in the robotics community. With the growth of its popularity,…
Cross-application interference can affect drastically performance of HPC applications when running in clouds. This problem is caused by concurrent access performed by co-located applications to shared and non-sliceable resources such as…
Real-time control systems often require dedicated hardware and software, including real-time operating systems, while many systems are available for off-line computing, mainly based on standard system units (PCs), standard network…
A wireless communication system is studied that operates in the presence of multiple reconfigurable intelligent surfaces (RISs). In particular, a multi-operator environment is considered where each operator utilizes an RIS to enhance its…
Real-time embedded platforms with resource constraints can take the benefits of mixed-criticality system where applications with different criticality-level share computational resources, with isolation in the temporal and spatial domain. A…
Acoustic-sensor-based soft error resilience is particularly promising, since it can verify the absence of soft errors and eliminate silent data corruptions at a low hardware cost. However, the state-of-the-art work incurs a significant…
The potential impact of autonomous robots on everyday life is evident in emerging applications such as precision agriculture, search and rescue, and infrastructure inspection. However, such applications necessitate operation in unknown and…
LLM inference latency critically determines user experience and operational costs, directly impacting throughput under SLO constraints. Even brief latency spikes degrade service quality despite acceptable average performance. However,…
We introduce LinuxArena, a control setting in which agents operate directly on live, multi-service production environments. LinuxArena contains 20 environments, 1,671 main tasks representing legitimate software engineering work, and 184…
Time awareness is critical to a broad range of emerging applications -- in Cyber-Physical Systems and Internet of Things -- running on commodity platforms and operating systems. Traditionally, time is synchronized across devices through a…
In this paper we investigate the feasibility of denial-of-service (DoS) attacks on shared caches in multicore platforms. With carefully engineered attacker tasks, we are able to cause more than 300X execution time increases on a victim task…
Microprocessor roadmaps clearly show a trend towards multiple core CPUs. Modern operating systems already make use of these CPU architectures by distributing tasks between processing cores thereby increasing system performance. This review…
GPUs are vastly underutilized, even when running resource-intensive AI applications, as GPU kernels within each job have diverse resource profiles that may saturate some parts of a device while often leaving other parts idle. Colocating…
In-memory key-value stores (IMKVSes) serve many online applications because of their efficiency. To support data backup, popular industrial IMKVSes periodically take a point-in-time snapshot of the in-memory data with the system call fork.…
Highly configurable systems are highly complex systems, with the Linux kernel arguably being one of the most well-known ones. Since 2007, it has been a frequent target of the research community, conducting empirical studies and building…
Data race conditions in multi-tasking software applications are prevented by serializing access to shared memory resources, ensuring data consistency and deterministic behavior. Traditionally tasks acquire and release locks to synchronize…
Real-time communication applications require consistently low latency, which is often disrupted by latency spikes caused by competing flows, especially Web traffic. We identify the root cause of disruptions in such cases as the mismatch…
We introduce system norms which assess transient behavior of stable Linear Time-Invariant (LTI) systems. This allows us to address undesired responses to initial conditions, finite resource consumption signals, or persistent perturbations.…
Large number of cores and hardware resource sharing are two characteristics on multicore processors, which bring new challenges for the design of operating systems. How to locate and analyze the speedup restrictive factors in operating…