Cloud Computing for Parameter Sweep Experiments

ELINA PACINI; MELISA RIBERO; CRISTIAN MATEOS; ANIBAL MIRASSO; CARLOS GARCÍA GARINO

New Horizons in Creative Open Software, Multimedia, Human Factors and Software Engineering

Blue Herons

Lugar: Bergamo; Año: 2012; p. 101 - 118

<!-- @page { margin: 0.79in } P { margin-bottom: 0.08in } -->Nowadays, scientists and engineers are more and more faced to the need of computational power to satisfy the ever-increasing resource intensive nature of their experiments. Traditionally, to cope with this, users have relied on conventional computing infrastructures such as clusters and Grids. A recent computing paradigm that is gaining momentum is Cloud Computing, which offers a simpler administration mechanism compared to those conventional infrastructures. However, there is a lack of studies in the literature about the viability of using Cloud Computing to execute scientific and engineering applications from a performance standpoint. We present an empirical study on the employment of Cloud infrastructures to run parameter sweep experiments (PSEs), particularly studies of viscoplastic solids together with simulations by using the CloudSim toolkit. In general, we obtained very good speedups, which suggest that disciplinary users could benefit from Cloud Computing for executing resource intensive PSEs.