Supporting Soft Real-Time Parallel Applications on Multicore Processors

Liu, Cong; Anderson, James H.

doi:10.1109/rtcsa.2012.55

Cited by 25 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A capacity augmentation bound of 4 − 2 m was proved in [35] for tasks with for implicit deadlines. Liu et al [36] provide a response time analysis for G-EDF.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Federated and Global Scheduling for Parallel Real-Time Tasks

Chen

Agrawal

et al. 2014

2014 26th Euromicro Conference on Real-Time Systems

175

119

View full text Add to dashboard Cite

This paper considers the scheduling of parallel realtime tasks with implicit deadlines. Each parallel task is characterized as a general directed acyclic graph (DAG). We analyze three different real-time scheduling strategies: two well known algorithms, namely global earliestdeadline-first and global rate-monotonic, and one new algorithm, namely federated scheduling. The federated scheduling algorithm proposed in this paper is a generalization of partitioned scheduling to parallel tasks. In this strategy, each high-utilization task (utilization ≥ 1) is assigned a set of dedicated cores and the remaining low-utilization tasks share the remaining cores. We prove capacity augmentation bounds for all three schedulers. In particular, we show that if on unit-speed cores, a task set has total utilization of at most m and the criticalpath length of each task is smaller than its deadline, then federated scheduling can schedule that task set on m cores of speed 2; G-EDF can schedule it with speed 3+ √ 5 2 ≈ 2.618; and G-RM can schedule it with speed 2 + √ 3 ≈ 3.732. We also provide lower bounds on the speedup and show that the bounds are tight for federated scheduling and G-EDF when m is sufficiently large.

show abstract

“…A capacity augmentation bound of 4 − 2 m was proved in [35] for tasks with for implicit deadlines. Liu et al [36] provide a response time analysis for G-EDF.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Federated and Global Scheduling for Parallel Real-Time Tasks

Chen

Agrawal

et al. 2014

2014 26th Euromicro Conference on Real-Time Systems

175

119

View full text Add to dashboard Cite

show abstract

“…Many strategies for parallel synchronous tasks decompose parallel tasks into sets of sequential tasks [1,[13][14][15][16]. Without decomposition, researchers have studied both synchronous tasks [17] and general DAG tasks [18][19][20][21][22]. For hard real-time tasks with worst-case parameters, the best capacity augmentation bound known for general DAGs is 2 using federated scheduling (a partition-like strategy) without decomposition [2]; 2.6 using GEDF without decomposition [2]; 3.73 for rate-monotonic with and without decompostion [1,2]; and 3.42 for a more restricted class of synchronous tasks [13].…”

Section: Related Workmentioning

confidence: 99%

“…Lateness guarantees also have been studied for GEDF-like scheduling [28]. For parallel tasks, Liu et al [18] for the first time provide a soft real-time response time analysis for GEDF.…”

Section: Related Workmentioning

confidence: 99%

Federated scheduling for stochastic parallel real-time tasks

Agrawal

Gill

et al. 2014

2014 IEEE 20th International Conference on Embedded and Real-Time Computing Systems and Applications

View full text Add to dashboard Cite

Abstract-Federated scheduling is a strategy to schedule parallel real-time tasks: It allocates a dedicated cluster of cores to each high-utilization task (utilization ≥ 1); It uses a multiprocessor scheduling algorithm to schedule and execute all low-utilization tasks sequentially, on a shared cluster of the remaining cores. Prior work has shown that federated scheduling has the best known capacity augmentation bound of 2 for parallel tasks with implicit deadlines. In this paper, we explore the soft realtime performance of federated scheduling and address averagecase workloads instead of worst-case ones. In particular, we consider stochastic tasks -tasks for which execution time and critical-path length are random variables. In this case, we use bounded expected tardiness as the schedulability criterion. We define a stochastic capacity augmentation bound and prove that federated scheduling algorithms guarantee the same bound of 2 for stochastic tasks. We present three federated mapping algorithms with different complexities for core allocation. All of them guarantee bounded expected tardiness and provide the same capacity augmentation bound. In practice, however, we expect them to provide different performance, both in terms of the task sets they can schedule and the actual tardiness they guarantee. Therefore, we present numerical evaluations using randomly generated task sets to examine the practical differences between the three algorithms.

show abstract

“…Many theoretical scheduling algorithms have been designed and analyzed for various task models in both hard real time [9, 10, 16, 26-30, 35, 37] and soft real time [32,36] contexts. There has not been as much work on building platforms that support real-time parallelism.…”

Section: Related Workmentioning

confidence: 99%

Real-time system support for hybrid structural simulation

Ferry

Bunting

Maghareh

et al. 2014

Proceedings of the 14th International Conference on Embedded Software

View full text Add to dashboard Cite

Real-time hybrid simulation (RTHS) is an important tool in the design and testing of civil and mechanical structures when engineers and scientists wish to understand the performance of an isolated component within the context of a larger structure. Performing full-scale physical experimentation with a large structure can be prohibitively expensive. Instead, a hybrid testing framework connects part of a physical structure within a closed loop (through sensors and actuators) to a numerical simulation of the rest of the structure. If we wish to understand the dynamic response of the combined structure, this testing must be done in real-time, which significantly restricts both the size of the simulation and the rate at which it can be conducted.Adding parallelism to the numerical simulation can enable both larger and higher frequency real-time simulations, potentially increasing both the accuracy and the control stability of the test. We present a proof-of-concept exploration of the execution of real-time hybrid simulations (an exemplar of a more general class of cyber-mechanical systems) with parallel computations. We execute large numerical simulations within tight timing constraints and provide a reasonable assurance of timeliness and usability. We detail the operation of our system, its design features, and show how parallel execution could enable qualitatively better experimentation within the discipline of structural engineering.

show abstract

Supporting Soft Real-Time Parallel Applications on Multicore Processors

Cited by 25 publications

References 15 publications

Analysis of Federated and Global Scheduling for Parallel Real-Time Tasks

Analysis of Federated and Global Scheduling for Parallel Real-Time Tasks

Federated scheduling for stochastic parallel real-time tasks

Real-time system support for hybrid structural simulation

Contact Info

Product

Resources

About