SASEPA: Simultaneous Allocation and Scheduling with Exclusion and Precedence Relations Algorithm

Abstract

Abstract. An algorithm for allocating and scheduling tasks in multiprocessor environments is presented. Its main characteristic is its orientation towards machine vision applications. In this sense it deals with the peculiarities of systems which combine generic-type processors with Image Acquisition and Processing Boards. The main goal of the algorithm is total processing time reduction; such are the requirements when we deal with automated industrial inspection applications. By simultaneously tackling the phases of allocation and scheduling, the results obtained are better than those offered by traditional algorithms. The system is applied to a process of citrus fruit inspection, and its performances are also evaluated over randomly generated task graphs.

Static Scheduling with Interruption Costs for Computer Vision Applications

“…The tasks have been scheduled using four different scheduling algorithms considering a target architecture with a CPU and two IAPBs. The four algorithms were the PREC 1 [6], the Critic Path [1], the SASEPA [10] and the SASEPA extension with interruption costs. In order to apply the two first algorithms for the target architecture it was necessary to improve then with several new features (kinds of tasks, sporadic tasks, spatial allocation…).…”

“…References [10] and [2] describe the static algorithm SASEPA (Simultaneous Allocation and Scheduling with Exclusion and Precedence Relations Algorithm), which carries out a spatial allocation and a temporal scheduling over a multiprocessor system considering all of the above-mentioned characteristics for computer vision systems. This algorithm also does a pre-emptive scheduling and considers the task interruptions to make the resulting scheduling better.…”