JASAG: A Gridification Tool for Agricultural Simulation Applications [JCR]

MAURICIO ARROQUI; JUAN RODRIGUEZ ALVAREZ; HERNAN VAZQUEZ; CLAUDIO MACHADO; CRISTIAN MATEOS; ALEJANDRO ZUNINO

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE

JOHN WILEY & SONS LTD

Lugar: LOndres; Año: 2015 vol. 27 p. 4716 - 4740

1532-0626

Abstract The Grid Computing paradigm aims to create a "virtual" and powerful single computer with many distributed resources to solve resource intensive problems. The term "gridification" involves the process of transforming a conventional application to run in a Grid environment. In that sense, the more automatic this process is, the easier is for developers with low expertise in parallel and distributed computing to take advantage of these resources. To date, many semi automatic gridifiers were built to support different gridification approaches and application code structures or anatomies. Furthermore, agricultural simulation applications have a particular common anatomy based on biophysical entities, such as animals, crops and pastures, which are updated by actions, such as growing animals, growing crops and growing pasture, along simulation execution. However, this anatomy is not fully supported by any of the existing gridifiers. Thus, this paper presents ASAG, a method for easy gridification of agricultural simulation applications, and its Java implementation, named JASAG. The main design drivers of JASAG are middleware independence, separation of business logic and Grid behavior, and performance increase. An experimental evaluation showing the feasibility of the gridification method and its implementation is also reported, which resulted in speedups of up to 25 by using a real agricultural simulation application.