Results 1 
9 of
9
PerformanceEffective and LowComplexity Task Scheduling for Heterogeneous Computing
 IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
, 2002
"... Efficient application scheduling is critical for achieving high performance in heterogeneous computing environments. The application scheduling problem has been shown to be NPcomplete in general cases as well as in several restricted cases. Because of its key importance, this problem has been exte ..."
Abstract

Cited by 255 (0 self)
 Add to MetaCart
Efficient application scheduling is critical for achieving high performance in heterogeneous computing environments. The application scheduling problem has been shown to be NPcomplete in general cases as well as in several restricted cases. Because of its key importance, this problem has been extensively studied and various algorithms have been proposed in the literature which are mainly for systems with homogeneous processors. Although there are a few algorithms in the literature for heterogeneous processors, they usually require significantly high scheduling costs and they may not deliver good quality schedules with lower costs. In this paper, we present two novel scheduling algorithms for a bounded number of heterogeneous processors with an objective to simultaneously meet high performance and fast scheduling time, which are called the Heterogeneous EarliestFinishTime (HEFT) algorithm and the CriticalPathonaProcessor (CPOP) algorithm. The HEFT algorithm selects the task with the highest upward rank value at each step and assigns the selected task to the processor, which minimizes its earliest finish time with an insertionbased approach. On the other hand, the CPOP algorithm uses the summation of upward and downward rank values for prioritizing tasks. Another difference is in the processor selection phase, which schedules the critical tasks onto the processor that minimizes the total execution time of the critical tasks. In order to provide a robust and unbiased comparison with the related work, a parametric graph generator was designed to generate weighted directed acyclic graphs with various characteristics. The comparison study, based on both randomly generated graphs and the graphs of some real applications, shows that our scheduling algorithms significantly surpass previous approaches in terms of both quality and cost of schedules, which are mainly presented with schedule length ratio, speedup, frequency of best results, and average scheduling time metrics.
Scheduling workflow applications on processors with different capabilities
, 2006
"... Efficient scheduling of workflow applications represented by weighted directed acyclic graphs (DAG) on a set of heterogeneous processors is essential for achieving high performance. The optimization problem is NPcomplete in general. A few heuristics for scheduling on heterogeneous systems have been ..."
Abstract

Cited by 26 (1 self)
 Add to MetaCart
Efficient scheduling of workflow applications represented by weighted directed acyclic graphs (DAG) on a set of heterogeneous processors is essential for achieving high performance. The optimization problem is NPcomplete in general. A few heuristics for scheduling on heterogeneous systems have been proposed recently. However, few of them consider the case where processors have different capabilities. In this paper, we present a novel list scheduling based algorithm to deal with this situation. The algorithm (SDC) has two distinctive features. First, the algorithm takes into account the effect of Percentage of Capable Processors (PCP) when assigning the task node weights. For two task nodes with same average computation cost, our weight assignment policy tends to give higher weight to the task with small PCP. Secondly, during the processor selection phase, the algorithm adjusts the effective Earliest Finish Time strategy by incorporating the average communication cost between the current scheduling node and its children. Comparison study shows that our algorithm performs better than related work overall.
Improved Static Multiprocessor Scheduling using Cyclic Task Graphs: A Genetic Approach
 Parallel Computing: Fundamentals, Applications and New Directions, NorthHolland
, 1997
"... Genetic algorithms have successfully been applied to multiprocessor task graph scheduling. In these previous attempts the schedules are constructed from directed acyclic task graphs. However, recurrent applications such as realtime control and digital signal processing can be expressed as directed ..."
Abstract

Cited by 9 (5 self)
 Add to MetaCart
(Show Context)
Genetic algorithms have successfully been applied to multiprocessor task graph scheduling. In these previous attempts the schedules are constructed from directed acyclic task graphs. However, recurrent applications such as realtime control and digital signal processing can be expressed as directed cyclic task graphs. This paper presents a method for transforming a cyclic task graph into several alternate acyclic task graphs, The benefits of this are demonstrated through an example where the task graphs become easier to schedule through restructuring. Thus, the new task graphs result in better load balancing and less interprocessor traffic than the "standard" acyclic task graphs. A genetic algorithm has been used to search for the task graph and schedule that best fit a particular application and hardware configuration. The results are encouraging. 1 Introduction Static multiprocessor task graph scheduling is a combinatorial optimisation problem [20] that involves assigning processin...
Static multiprocessor task graph scheduling in the genetic paradigm: A comparison of genotype representations
, 1998
"... In the NPhard multiprocessor scheduling problem a set of precedence constrained tasks are allocated onto processors in a processing order in order to minimise the makespan. Many heuristic methods for nding solutions exist, but they are all suboptimal on general task graphs. To improve these soluti ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
(Show Context)
In the NPhard multiprocessor scheduling problem a set of precedence constrained tasks are allocated onto processors in a processing order in order to minimise the makespan. Many heuristic methods for nding solutions exist, but they are all suboptimal on general task graphs. To improve these solutions, genetic algorithms have successfully been applied to the problem and the results reported have been superior to the listscheduling approaches. However, the application of genetic algorithms to the multiprocessor scheduling problem have predominantly followed two main paths of developments, namely the use of direct and indirect representations. In the direct chromosome representation the schedule is represented and manipulated directly by the genetic operators, and the genotype is identical to the phenotype. In the indirect representation only the decisions on how to build the schedule is encoded in the chromosome. The genetic operators a ect the schedules implicitly, and the genotype is different
Static Task Scheduling with a Unified Objective on Time and Resource Domains
, 2006
"... Task scheduling for parallel and distributed systems is an NPcomplete problem, which is well documented and studied in the literature. A large set of proposed heuristics for this problem mainly target to minimize the completion time or the schedule length of the output schedule for a given task gra ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Task scheduling for parallel and distributed systems is an NPcomplete problem, which is well documented and studied in the literature. A large set of proposed heuristics for this problem mainly target to minimize the completion time or the schedule length of the output schedule for a given task graph. An additional objective, which is not much studied, is the minimization of number of processors allocated for the schedule. These two objectives are both conflicting and complementary, where the former is on the time domain targeting to improve task utilization and the latter is on the resource domain targeting to improve processor utilization. In this paper, we unify these two objectives with a weighting scheme that allows to personalize the importance of the objectives. In this paper, we present a new genetic search framework for task scheduling problem by considering the new objective. The performance of our genetic algorithm is compared with the scheduling algorithms in the literature that consider the heterogeneous processors. The results of the synthetic benchmarks and task graphs that are extracted from wellknown applications clearly show that our genetic algorithmbased framework outperforms the related work with respect to normalized cost values, for various task graph characteristics.
Local Search Techniques for Scheduling Problems A Tutorial
"... Abstract Although it is not a newcomer in the combinatorial optimization literature, Local Search is an emerging paradigm for combinatorial search, which has been recently shown to be very effective for a large number of scheduling problems. A number of metaheuristics based on local search have been ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Abstract Although it is not a newcomer in the combinatorial optimization literature, Local Search is an emerging paradigm for combinatorial search, which has been recently shown to be very effective for a large number of scheduling problems. A number of metaheuristics based on local search have been also proposed to address with success a variety of scheduling problems. In this tutorial, we survey the basic local search techniques proposed in the literature and implemented in many industrial scheduling systems: Simulated Annealing, Tabu Search, and various forms of Hill Climbing. We also illustrate some of the most promising improvements and variations of such basic techniques which are currently investigated. Finally, we propose the combination of local search with other solution paradigms, such as genetic algorithms and constructive heuristics. Throughout the tutorial we illustrate three case studies of successful applications of these techniques to real life problems: school timetabling, frequency assignment in mobile radio systems, and sport scheduling.
Examining Branch and Bound Strategy on Multiprocessor Task Scheduling
"... The multiprocessor task graph scheduling problem has been extensively studied as academic optimization problem which occurs in optimizing the execution time of parallel algorithm with parallel computer. The problem is already being known as one ofthe NPhard problems. There are many good approaches ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
The multiprocessor task graph scheduling problem has been extensively studied as academic optimization problem which occurs in optimizing the execution time of parallel algorithm with parallel computer. The problem is already being known as one ofthe NPhard problems. There are many good approaches made with many optimizing algorithm to find out the optimum solution for this problem with less computational time. One of them is branch and bound algorithm. In this paper, we studied the branch and bound algorithm for the multiprocessor schedulingproblem.
Noname manuscript No. (will be inserted by the editor) Learning Optimal Metric for Image Alignment
"... Abstract Image alignment has been a long standing problem ..."
(Show Context)