Hamid Arabnejad

List Scheduling Algorithm for Heterogeneous Systems by an Optimistic Cost Table

Efficient application scheduling algorithms are important for obtaining high performance in heterogeneous computing systems. In this paper, we present a novel list-based scheduling algorithm called Predict Earliest Finish Time (PEFT) for heterogeneous computing systems. The algorithm has the same time complexity as the state-of-the-art algorithm for the same purpose, that is, O(v2.p) for v tasks and p processors, but offers significant makespan improvements by introducing a look-ahead feature without increasing the time complexity associated with computation of an optimistic cost table (OCT). The calculated value is an optimistic cost because processor availability is not considered in the computation. Our algorithm is only based on an OCT that is used to rank tasks and for processor selection. The analysis and experiments based on randomly generated graphs with various characteristics and graphs of real-world applications show that the PEFT algorithm outperforms the state-of-the-art list-based algorithms for heterogeneous systems in terms of schedule length ratio, efficiency, and frequency of best results.

A Budget Constrained Scheduling Algorithm for Workflow Applications

Service-oriented computing has enabled a new method of service provisioning based on utility computing models, in which users consume services based on their Quality of Service (QoS) requirements. In such pay-per-use models, users are charged for services based on their usage and on the fulfilment of QoS constraints; execution time and cost are two common QoS requirements. Therefore, to produce effective scheduling maps, service pricing must be considered while optimising execution performance. In this paper, we propose a Heterogeneous Budget Constrained Scheduling (HBCS) algorithm that guarantees an execution cost within the user’s specified budget and that minimises the execution time of the user’s application. The results presented show that our algorithm achieves lower makespans, with a guaranteed cost per application and with a lower time complexity than other budget-constrained state-of-the-art algorithms. The improvements are particularly high for more heterogeneous systems, in which a reduction of 30 % in execution time was achieved while maintaining the same budget level.

Low-time complexity budget-deadline constrained workflow scheduling on heterogeneous resources

The execution of scientific applications, under the utility computing model, is constrained to Quality of Service (QoS) parameters. Commonly, applications have time and cost constraints such that all tasks of an application need to be finished within a user-specified Deadline and Budget. Several algorithms have been proposed for multiple QoS workflow scheduling, but most of them use search-based strategies that generally have a high time complexity, making them less useful in realistic scenarios. In this paper, we present a heuristic scheduling algorithm with quadratic time complexity that considers two important constraints for QoS-based workflow scheduling, time and cost, named Deadline-Budget Constrained Scheduling (DBCS). From the deadline and budget defined by the user, the DBCS algorithm finds a feasible solution that accomplishes both constraints with a success rate similar to other state-of-the-art search-based algorithms in terms of the successful rate of feasible solutions, consuming in the worst case only approximately 4% of the time. The DBCS algorithm has a low-time complexity of O ( n 2 . p ) for n tasks and p processors. A review of multiple QoS parameter workflow scheduling.A new multiple QoS algorithm with quadratic complexity for workflow scheduling.Similar performances of search-based algorithms in a small fraction of the time.Results for randomly generated graphs as well as for real-world applications.

Fairness Resource Sharing for Dynamic Workflow Scheduling on Heterogeneous Systems

For most Heterogeneous Computing Systems (HCS) the completion time of an application is the most important requirement. Many applications are represented by a workflow that is therefore schedule in a HCS system. Recently, researchers have proposed algorithms for concurrent workflow scheduling in order to improve the execution time of several applications in a HCS system. Although, most of these algorithms were designed for static scheduling, that is all application must be submitted at the same time, there are a few algorithms, such as OWM (online workflow Management) and RANK_HYBD, that were presented for dealing with dynamic application scheduling. In this paper, we present a new algorithm for dynamic application scheduling. The algorithm focus on the Quality of Service (QoS) experienced by each application (or user). It reduces the waiting and execution times of each individual workflow, unlike other algorithms that give privilege to average completion time of all workflows. The simulation results show that the proposed approach significantly outperforms the other algorithms in terms of individual response time.

Budget Constrained Scheduling Strategies for On-line Workflow Applications

To execute scientific applications, described by workflows, whose tasks have different execution requirements, efficient scheduling methods are essential for task matching (machine assignment) and scheduling (ordered for execution) on a variety of machines provided by a heterogeneous computing system. Several algorithms for concurrent workflow scheduling have been proposed, being most of them off-line solutions. Recent research attempted to propose on-line strategies for concurrent workflows but only address fairness in resource sharing among applications while minimizing the execution time. In this paper, we propose a new strategy that extends on-line methods by optimizing execution time constrained to the user budget. Experimental results show a significant improvement of the produced schedules when our strategy is applied.

Performance evaluation of list based scheduling on heterogeneous systems

This paper addresses the problem of evaluating the schedules produced by list based scheduling algorithms, with metaheuristic algorithms. Task scheduling in heterogeneous systems is a NP-problem, therefore several heuristic approaches were proposed to solve it. These heuristics are categorized into several classes, such as list based, clustering and task duplication scheduling. Here we consider the list scheduling approach. The objective of this study is to assess the solutions obtained by list based algorithms to verify the space of improvement that new heuristics can have considering the solutions obtained with metaheuritcs that are higher time complexity approaches. We concluded that for a low Communication to Computation Ratio (CCR) of 0.1, the schedules given by the list scheduling approach is in average close to metaheuristic solutions. And for CCRs up to 1 the solutions are below 11% worse than the metaheuristic solutions, showing that it may not be worth to use higher complexity approaches and that the space to improve is narrow.

Maximizing the completion rate of concurrent scientific applications under time and budget constraints

Abstract In many domains of science, scientific applications are represented by workflows. In this paper, we introduce a resource management strategy to maximize the success rate of concurrent workflow applications constrained by individual deadline and budget values. The Multi-Workflow Deadline-Budget Scheduling (MW-DBS) algorithm can schedule multiple workflows that can arrive in the system at any time, with the aim of satisfying individual job requirements. MW-DBS produces schedules without performing optimizations but guarantees that the deadline and budget defined for each job are not exceeded. Experimental results show that our strategy increases the scheduling success rate of finding valid solutions.

Multi-workflow QoS-Constrained Scheduling for Utility Computing

In this paper, we introduce a utility driven strategy to schedule concurrent workflows constrained to users QoS parameters, namely Deadline and Budget. The Multi-Workflow Deadline-Budget Scheduling algorithm (MW-DBS) can schedule multiple workflows that can arrive to the system at any instant of time, with the aim of satisfying individual QoS requirements. Common approaches optimize one factor, e.g. processing time, constrained to the other factor, e.g. cost. MW-DBS produces schedules without optimizing any of the parameters but guaranteeing that the deadline and budget defined for each workflow are not exceeded. We study the scalability of the algorithm with different types of workflows and service providers. Experimental results show that our strategy is able to increase the scheduling success rate of finding valid solutions.

Multi-QoS constrained and Profit-aware scheduling approach for concurrent workflows on heterogeneous systems

Abstract The execution of a workflow application can result in an imbalanced workload among allocated processors, ultimately resulting in a waste of resources and a higher cost to the user. Here, we consider a dynamic resource management system in which processors are reserved not for a job but only to run a task, thus allowing a higher resource usage rate. This paper presents a scheduling algorithm that manages concurrent workflows in a dynamic environment in which jobs are submitted by users at any moment in time, on shared heterogeneous resources, and constrained to a specified budget and deadline for each job. Recent research attempted to propose dynamic strategies for concurrent workflows but only addressed fairness in resource sharing among applications while minimizing the execution time. The Multi-QoS Profit-Aware scheduling algorithm (MQ-PAS) proposed here is able to increase the profit achieved by the provider by considering the budget available for each job to define tasks priorities. We study the scalability of the algorithm with different types of workflows and infrastructures. The experimental results show that our strategy improves provider revenue significantly and obtains comparable successful rates of completed jobs.

AutoPar-Clava: An Automatic Parallelization source-to-source tool for C code applications

Automatic parallelization of sequential code has become increasingly relevant in multicore programming. In particular, loop parallelization continues to be a promising optimization technique for scientific applications, and can provide considerable speedups for program execution. Furthermore, if we can verify that there are no true data dependencies between loop iterations, they can be easily parallelized. This paper describes Clava AutoPar, a library for the Clava weaver that performs automatic and symbolic parallelization of C code. The library is composed of two main parts, parallel loop detection and source-to-source code parallelization. The system is entirely automatic and attempts to statically detect parallel loops for a given input program, without any user intervention or profiling information. We obtained a geometric mean speedup of 1.5 for a set of programs from the C version of the NAS benchmark, and experimental results suggest that the performance obtained with Clava AutoPar is comparable or better than other similar research and commercial tools.