arXiv subjects

Thidapat Chantem

Publications and source records attributed to Thidapat Chantem.

4 recordsLinked to original sources

arXiv2025

DARIS: An Oversubscribed Spatio-Temporal Scheduler for Real-Time DNN Inference on GPUs

The widespread use of Deep Neural Networks (DNNs) is limited by high computational demands, especially in constrained environments. GPUs, though effective accelerators, often face underutilization and rely on coarse-grained scheduling. This paper introduces DARIS, a priority-based real-time DNN scheduler for GPUs, utilizing NVIDIA's MPS and CUDA streaming for spatial sharing, and a synchronization-based staging method for temporal partitioning. In particular, DARIS improves GPU utilization and uniquely analyzes GPU concurrency by oversubscribing computing resources. It also supports zero-delay DNN migration between GPU partitions. Experiments show DARIS improves throughput by 15% and 11.5% over batching and state-of-the-art schedulers, respectively, even without batching. All high-priority tasks meet deadlines, with low-priority tasks having under 2% deadline miss rate. High-priority response times are 33% better than those of low-priority tasks.

cs.DC↗

arXiv2024

SGPRS: Seamless GPU Partitioning Real-Time Scheduler for Periodic Deep Learning Workloads

Deep Neural Networks (DNNs) are useful in many applications, including transportation, healthcare, and speech recognition. Despite various efforts to improve accuracy, few works have studied DNN in the context of real-time requirements. Coarse resource allocation and sequential execution in existing frameworks result in underutilization. In this work, we conduct GPU speedup gain analysis and propose SGPRS, the first real-time GPU scheduler considering zero configuration partition switch. The proposed scheduler not only meets more deadlines for parallel tasks but also sustains overall performance beyond the pivot point.

cs.DC↗

arXiv2021

Survey of Control-Flow Integrity Techniques for Embedded and Real-Time Embedded Systems

Computing systems, including real-time embedded systems, are becoming increasingly connected to allow for more advanced and safer operation. Such embedded systems are resource-constrained, such as lower processing capabilities, as compared to general purpose computing systems like desktops or servers. However, allowing external interfaces to such embedded systems increases their exposure to attackers. With an increase in attacks against embedded systems ranging from home appliances to industrial control systems operating critical equipment that have hard real-time requirements, it is imperative that defense mechanisms be created that explicitly consider such resource and real-time constraints constraints. Control-flow integrity (CFI) is a family of defense mechanisms that prevent attackers from modifying the flow of execution. We survey CFI techniques, ranging from the basic to state-of-the-art, that are built for embedded systems and real-time embedded systems and find that there is a dearth, especially for real-time embedded systems, of CFI mechanisms. We then present open challenges to the community to help drive research in this domain.

cs.CR↗

arXiv2020

Secure Traffic Lights: Replay Attack Detection for Model-based Smart Traffic Controllers

Rapid urbanization calls for smart traffic management solutions that incorporate sensors, distributed traffic controllers and V2X communication technologies to provide fine-grained traffic control to mitigate congestion. As in many other cyber-physical systems, smart traffic management systems typically lack security measures. This allows numerous opportunities for adversarial entities to craft attacks on the sensor networks, wireless data sharing and/or the distributed traffic controllers. We show that such vulnerabilities can be exploited to disrupt mobility in a large urban area and cause unsafe conditions for drivers and the pedestrians on the roads. Specifically, in this paper, we look into vulnerabilities in model-based traffic controllers and show that, even with state-of-the-art attack detectors in place, false-data injection can be used to hamper mobility. We demonstrate a replay attack by modeling an isolated intersection in VISSIM, a popular traffic simulator and also discuss countermeasures to thwart such attacks.

cs.CR↗