Abstract
In this paper, we address the problem of energy-aware heterogeneous data allocation and task scheduling on heterogeneous multiprocessor systems for real-time applications. In a heterogeneous distributed shared-memory multiprocessor system, an important problem is how to assign processors to real-time application tasks, allocate data to local memories, and generate an efficient schedule in such a way that a time constraint can be met and the total system energy consumption can be minimized. We propose an optimal approach, i.e., an integer linear programming method, to solve this problem. As the problem has been conclusively shown to be computationally very complicated, we also present two heuristic algorithms, i.e., task assignment considering data allocation (TAC-DA) and task ratio greedy scheduling (TRGS), to generate near-optimal solutions for real-time applications in polynomial time. We evaluate the performance of our algorithms by comparing them with a greedy algorithm that is commonly used to solve heterogeneous task scheduling problems. Based on our extensive simulation study, we observe that our algorithms exhibit excellent performance. We conducted experimental performance evaluation on two heterogeneous multiprocessor systems. The average reduction rates of the total energy consumption of the TAC-DA and TRGS algorithms to that of the greedy algorithm are 13.72% and 15.76%, respectively, on the first system, and 19.76% and 24.67%, respectively, on the second system. To the best of our knowledge, this is the first study to solve the problem of task scheduling incorporated with data allocation and energy consumption on heterogeneous distributed shared-memory multiprocessor systems.
Highlights
Since it is possible that the time constraint is too tight for task assignment considering data allocation (TAC-DA) to obtain a solution, we propose the task ratio greedy scheduling (TRGS) algorithm in which data assignment is considered in conjunction with task scheduling
The TRGS algorithm is superior to the TAC-DA algorithm
In this paper, we presented an optimal algorithm, i.e., the integer linear programming (ILP) method, and two heuristic algorithms, i.e., the TAC-DA and TRGS algorithms, to solve the heterogeneous data allocation and task scheduling (HDATS) problem that aims to obtain better task scheduling incorporated with data allocation, such that the total system energy consumption is minimized for a given time constraint
Summary
A modern high-performance computing system normally consists of heterogeneous computing and communication resources, including heterogeneous processors, heterogeneous memories, and heterogeneous communication interconnections. The three algorithms aim to obtain an efficient task schedule incorporated with data allocation, so that certain timing requirement can be met and total system (i.e., both processors and memories) energy consumption can be minimized. To obtain an optimal solution, we present an integer linear programming (ILP) formulation to solve the HDATS problem Since it takes a long time for the ILP method to get results even for medium-sized DAGs with no more than 100 nodes, we propose two heuristic algorithms, i.e., the TAC-DA (task assignment considering data allocation) and the TRGS (task ratio greedy scheduling) algorithms. To the best of our knowledge, this is the first study to solve the problem of task scheduling incorporated with data allocation and energy consumption on heterogeneous distributed shared-memory multiprocessor systems.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have