Contention-aware optimal scheduling of real-time precedence-constrained task graphs on heterogeneous distributed systems

Roy, Sanjit Kumar; Devaraj, Rajesh; Sarkar, Arnab; Maji, Kankana; Sinha, Sayani

doi:10.1016/j.sysarc.2019.101706

Cited by 36 publications

(25 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Real-time scheduling aims to complete tasks within specific time constraints and avoiding simultaneous access to resources shared amongst application tasks. To guarantee real-time performance while meeting all timing, precedence and resource usage specifications requires employment of efficient scheduling algorithms supported by accurate schedulability analysis techniques [ 104 ]. Real-time scheduling algorithms can be implemented for uniprocessor or multiprocessor systems [ 105 – 107 ].…”

Section: Required Software Components For Real-time Implementationmentioning

confidence: 99%

“…The Arduino Uno uses the ATMEGA 328P processor (uni-processor), whereas embedded computers like the Rasberry-Pi uses a quad core ARM Cortex-A72 processor (multi-processor). Scheduling algorithms can be broadly divided into two major subsets: offline scheduling and online scheduling algorithms [ 104 ]. In offline scheduling algorithms, task scheduling is carried out before system execution, also known as pre-run time scheduling.…”

Section: Required Software Components For Real-time Implementationmentioning

confidence: 99%

See 1 more Smart Citation

A review on drones controlled in real-time

Kangunde

Jamisola

Theophilus

2021

Int. J. Dynam. Control

View full text Add to dashboard Cite

This paper presents related literature review on drones or unmanned aerial vehicles that are controlled in real-time. Systems in real-time control create more deterministic response such that tasks are guaranteed to be completed within a specified time. This system characteristic is very much desirable for drones that are now required to perform more sophisticated tasks. The reviewed materials presented were chosen to highlight drones that are controlled in real time, and to include technologies used in different applications of drones. Progress has been made in the development of highly maneuverable drones for applications such as monitoring, aerial mapping, military combat, agriculture, etc. The control of such highly maneuverable vehicles presents challenges such as real-time response, workload management, and complex control. This paper endeavours to discuss real-time aspects of drones control as well as possible implementation of real-time flight control system to enhance drones performance.

show abstract

Section: Required Software Components For Real-time Implementationmentioning

confidence: 99%

Section: Required Software Components For Real-time Implementationmentioning

confidence: 99%

A review on drones controlled in real-time

Kangunde

Jamisola

Theophilus

2021

Int. J. Dynam. Control

View full text Add to dashboard Cite

show abstract

“…The former aims to minimize the number of used processors, while the latter aims to minimize the execution latency while keeping the deadline constraints. The latter is extended to consider heterogeneous processors and shared bus contention in [27].…”

Section: ) Scheduling Of a Single Sdf Graphmentioning

confidence: 99%

Parallel Scheduling of Multiple SDF Graphs Onto Heterogeneous Processors

et al. 2021

View full text Add to dashboard Cite

Parallel scheduling of multiple real-time applications onto heterogeneous processors is needed in the emerging embedded systems such as self-driving cars, smart cameras, and smartphones. Assuming that an embedded application is specified as a synchronous dataflow (SDF) graph or its extension, we propose a novel parallel scheduling methodology based on an evolutionary algorithm where the mapping of tasks onto processors is evolved to optimize a given objective function in an iterative fashion. In each iteration, we use an existing worst-case response time (WCRT) analysis tool to check if all applications satisfy their real-time requirements by translating each SDF graph into a directed acyclic graph (DAG) that is assumed in the WCRT analysis tool. Since the WCRT analysis must be performed in each iteration of evolution, we propose a clustering technique to reduce drastically the analysis time that depends on the number of nodes and their dependency. We formally prove that the proposed clustering technique does not change the estimated WCRT of each application. The effectiveness of the proposed scheduling methodology with the clustering technique is verified with extensive experiments using real-life benchmarks, randomly generated graphs, and the comparison with the existing technique.

show abstract

“…In recent years, a large number of scheduling algorithms that combine time and other system qualities of service (QoS), such as reliability, budget, deadline, energy consumption, have been emerged in the field of heterogeneous computing systems [16]- [19], [34], [39], [40]. Dogan and Özgüner [40] analyzed the task execution reliability on heterogeneous computing systems, and combined this into applications dynamic level to implemented the scheduling algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…Dogan and Özgüner [40] analyzed the task execution reliability on heterogeneous computing systems, and combined this into applications dynamic level to implemented the scheduling algorithm. Roy et al studied the real-time precedence-constrained task scheduling problem on heterogeneous systems with multiple service levels (such as performance, reliability, cost) [34]- [36]. Zhang et al first built the heterogeneous systems communication contention and task execution reliability model.…”

Section: Related Workmentioning

confidence: 99%

CPU–GPU Utilization Aware Energy-Efficient Scheduling Algorithm on Heterogeneous Computing Systems

Tang

2020

IEEE Access

View full text Add to dashboard Cite

Nowadays, heterogeneous computing systems have proven to be a good solution for processing computation intensive high-performance applications. The main challenges for such large-scale systems are energy consumption, computing node CPU-GPU utilization dynamic variability, and so on. In response to these challenges, this study first provides heterogeneous computing systems architecture and parallel application job model. Then, we build system computing node CPU-GPU utilization model and analyze job execution energy consumption. We also deduce the optimal CPU-GPU utilization and job deadline scheduling constraint. Third, we propose a systems CPU-GPU utilization aware and energy-efficient heuristic greedy strategy (UEJS) to solve this job scheduling problem. To improve the algorithm global optimization ability, we design a hybrid particle swarm optimization algorithm (H-PSO), which incorporates the heuristic greedy strategy into the bio-inspired search optimization technique. The rigorous experimental results clearly demonstrate that our proposed H-PSO outperforms heuristic greedy strategy, Max-EAMin, and Genetic Algorithm in terms of the average energy consumption of jobs and system job rejection rate. In particular, H-PSO is better than UEJS by 36.5%, Max-EAMin by 36.3%, and GA by 46.7% in term of the job average energy consumption for heterogeneous system with high workload.

show abstract

Contention-aware optimal scheduling of real-time precedence-constrained task graphs on heterogeneous distributed systems

Cited by 36 publications

References 27 publications

A review on drones controlled in real-time

A review on drones controlled in real-time

Parallel Scheduling of Multiple SDF Graphs Onto Heterogeneous Processors

CPU–GPU Utilization Aware Energy-Efficient Scheduling Algorithm on Heterogeneous Computing Systems

Contact Info

Product

Resources

About