A Critical-Path and Top-Level attributes based Task Scheduling Algorithm for DAG (CPTL) Nidhi Rajak 1 , Ranjit Rajak 2 and Anurag Dixit 3 1,3 School of Computing & Engineering Galgotias University: (U.P. India) 1 nidhi.bathre@gmail.com, 3 anuradixit@gmail.com 2 Department of Computer Science & Applications Dr. Harisingh Gour Central University Sagar: (M.P: India) 2 ranjit.jnu@gmail.com ABSTRACT Parallel computing is an important area of research. It is used from scientific to commercial applications. Task scheduling is one of the important research areas of parallel computing. The major objective of any task scheduling algorithm is to minimize the execution time i.e. to reduce the scheduling length. Here, an application program is represented by a directed acyclic graph (DAG). In this paper, we have proposed an efficient CPTL scheduling algorithm which is based on two well-known attributes: Critical Path (CP), and Top-level (T-level). This algorithm is calculated the difference between CP and t-level, which is called CPT attribute. This attribute used as a priority of the tasks, and allocated these tasks on multiprocessor system. The proposed algorithm outperforms over the existing heuristic algorithms such as HLEFT, MCP, ETF, and DLS. CPTL algorithm gives minimum scheduling length. The comparison has been done based on following metrics: scheduling length, speedup, efficiency, load balancing, and normalized scheduling length. KEYWORDS Scheduling, DAG, Parallel Processing, Speedup, and Efficiency. 1 INTRODUCTION Task scheduling problem is mapping of tasks of an application program onto the processors and its primary objective is to minimize the execution time. It is an important area of research in parallel computing. Here, an application program is represented by a directed acyclic graph (DAG). Task scheduling problem is an NP-hard [1,2]. There are three components [3] of tasks scheduling algorithm:(i) are performance of the processors, (ii) mapping of the tasks on to the processors, and (iii) execution order of the tasks on to the processors. Task scheduling algorithm can be either deterministic or non deterministic. In deterministic algorithm, number of tasks, number of processors, execution time of each task on the processors, and communication time between the tasks that are known at compiled time. But in case of nondeterministic algorithm, all the above information is known at run time. The proposed algorithm is based on deterministic model. In this paper, we present a new approach for task scheduling algorithm in multiprocessor environment which is known as CPTL algorithms. It is based on CPT attribute which is difference of Critical Path (CP) [4], and Top level (t-level) [4]. We find the priority of the tasks of a given DAG using CPT attribute. Also, we present the comparison among proposed algorithm and three task scheduling heuristic algorithms: HLFET, MCP and DLS task scheduling algorithms. We consider four performance metrics for comparison and performance analysis of the task scheduling algorithms. The rest of the paper is organized as follows: Problem formulation have done in section 2. Section 3 consists of proposed algorithm and performance metrics are defined in section 4.The performance analysis and results of the task scheduling algorithms has been done in International Journal of New Computer Architectures and their Applications (IJNCAA) 4(3): 130-136 The Society of Digital Information and Wireless Communications, 2014 (ISSN: 2220-9085) 130