Evolutionary Scheduling of Parallel Tasks Graphs onto Homogeneous Clusters

Hunold, Sascha; Lepping, Joachim

doi:10.1109/cluster.2011.45

Cited by 6 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we also include the meta-heuristic EMTS that performs an evolutionary schedule optimization [17]. Here, we also include the meta-heuristic EMTS that performs an evolutionary schedule optimization [17].…”

Section: Results With Run-time Modelmentioning

confidence: 99%

“…The synthetic (random) DAGs are generated with DAGGEN [20] and contain 25, 50, or 100 nodes. For the purpose of better comparability, we used the same set of DAGs that has been used in the experiments in [16,17]. The number of operations per task depend on the data size d (number of elements) and a function applied to the data, which were both randomly selected.…”

Section: Dags and Platformsmentioning

confidence: 99%

“…Thus, to obtain the speedup of a moldable task using Amdahl's law, we pick the non-parallelizable (sequential) fractionˇ(discussed below) of f .d / randomly from a uniform distribution between 0 and 0.25. For the purpose of better comparability, we used the same set of DAGs that has been used in the experiments in [16,17]. The Cartesian product of the following values was used as parameter set to generate the irregular DAGs: width D ¹0:2; 0:5; 0:8º, regularity D ¹0:2; 0:8º, density D ¹0:2; 0:8º, and jump D ¹1; 2; 4º.…”

Section: Dags and Platformsmentioning

confidence: 99%

“…In the previous work, we already addressed the challenge of dealing with arbitrary run‐time functions by using an evolutionary algorithm (EA) to find short schedules . The proposed Evolutionary Moldable Task Scheduling (EMTS) algorithm takes solutions to the allotment problem produced by several heuristics, such as CPA and MCPA, and optimizes them using an ( μ + λ )‐EA, where μ and λ denote the number of parents and offspring, respectively.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

One step toward bridging the gap between theory and practice in moldable task scheduling with precedence constraints

Hunold

2014

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Because of the increasing number of cores of current parallel machines and the growing need for a concurrent execution of tasks, the problem of parallel task scheduling is more relevant than ever, especially under the moldable task model, in which tasks are allocated to a fixed number of processors before execution. Much research has been conducted to develop efficient scheduling algorithms for moldable tasks, both in theory and practice. The problem is that theoretical and practical approaches expose shortcomings, for example, many approximation algorithms only guarantee bounds under assumptions, which are unrealistic in practice, or most heuristics have not been rigorously compared with competing approximation algorithms. In particular, it is often assumed that the speedup function of moldable tasks is either non-decreasing, sublinear, or concave. In practice, however, the resulting speedup of parallel programs on current hardware with deep memory hierarchies is most often neither non-decreasing nor concave. We present a new algorithm for the problem of scheduling moldable tasks with precedence constraints for the makespan objective and for arbitrary speedup functions. We show through simulation that the algorithm not only creates competitive schedules for moldable tasks with arbitrary speedup functions but also outperforms other published heuristics and approximation algorithms for non-decreasing speedup functions.We have conducted three different simulation studies, which are part of the overall evaluation. First, we compare the schedules produced by CPA13 and its competitors for the non-increasing and convex run-time model. Second, we address the scalability of these algorithms by increasing the number

show abstract

Section: Results With Run-time Modelmentioning

confidence: 99%

Section: Dags and Platformsmentioning

confidence: 99%

Section: Dags and Platformsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

One step toward bridging the gap between theory and practice in moldable task scheduling with precedence constraints

Hunold

2014

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, new algorithms are designed to accept any arbitrary graph [9]. It is also applicable as parallel [10].…”

Section: Introductionmentioning

confidence: 99%

Genetic Algorithm with Descendants Idea for Scheduling Tasks Graph in the Multi-Processor Architecture

Mahi¹,

Kodaz²

2014

JACN

View full text Add to dashboard Cite

Abstract-Nowadays, multi-processor systems are being used extensively in parallel computing. The effective scheduling system for implementing parallel programs to achieve high performance is crucial. The timing should be done in such a way that the total execution time of the program with according to time and tasks to be minimize communication between processors. This is a NP-Hard problem which tasks graph scheduling approaches based on deterministic methods are not effective in this context while the use of evolutionary computing and genetic algorithms to solve this problem effectively are mainly. In this paper, a new genetic algorithm is proposed for the problem of scheduling tasks graph which is able to spend less time to get. This algorithm is based on a new approach to minimize the length of the critical path and the cost of communication between processors. In this paper, we calculate the number of descendants for each node in which tries to minimize the total execution time of the program.

show abstract

SEED: solar energy‐aware efficient scheduling for data centers

Jing

Zhu

2013

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYIt is well known that data centers are consuming a large amount of energy that incurs significant financial and environmental costs. Recently, there has been an increasing interest in utilizing green energy for data centers, where green energy sources include solar and wind. This paper studies the crucial problem of maximizing the utilization of green energy through scheduling complex jobs in data centers in order to reduce the use of traditional brown energy. However, it is highly challenging for data centers to make use of green energy. First, the availability of typical green energy is variable to dynamic changes of natural environments, for example, weather. Second, although predictions can be made for the future availability of green energy, it is inevitable that such predictions have errors. Third, jobs are associated with strict deadlines, and it is required that jobs are completed before their deadlines. Finally, because the reliability in a data center relies upon temperature, the awareness of temperature should be taken into account while maximizing the green energy. In this paper, we consider online scheduling of jobs whose arrivals to the data center system dynamically. In addition, we explicitly take the power consumption of switches into account when scheduling jobs onto computing nodes. Two solar energy-aware algorithms called SEEDMin and SEEDMax have been proposed. Then, we extend SEED to RSEED with the awareness of reliability. To evaluate the effectiveness of the proposed algorithms, comprehensive simulations have been conducted, and the proposed algorithms are compared with other state-of-art algorithms. Experimental results demonstrate that both SEEDMin and SEEDMax can significantly increase the utilization of solar energy without violating job deadlines and overall energy budget. The amount of solar energy utilized by SEEDMin and SEEDMax is 33.4%and 35.3% larger than that of two traditional scheduling algorithms, MinMin and MinMax, respectively. Also, it can be seen that RSEED greatly improves the reliability by decreasing the temperature.

show abstract

Evolutionary Scheduling of Parallel Tasks Graphs onto Homogeneous Clusters

Cited by 6 publications

References 18 publications

One step toward bridging the gap between theory and practice in moldable task scheduling with precedence constraints

One step toward bridging the gap between theory and practice in moldable task scheduling with precedence constraints

Genetic Algorithm with Descendants Idea for Scheduling Tasks Graph in the Multi-Processor Architecture

SEED: solar energy‐aware efficient scheduling for data centers

Contact Info

Product

Resources

About