I. Introduction
Scientific applications are playing a critical role in improving our daily life. They are designed to solve pressing scientific challenges, including designing new energy-efficient sources [2] and modeling the earth system [4]. To boost the productivity of scientific applications, High-Performance Computing (HPC) community has built many supercomputers [7] to provide unprecedented computation power over the past decade. Meanwhile, computer scientists are also arduously improving parallel file systems [11], [23] and I/O techniques [19], [20] to bridge the gap between fast processors and slow storage systems. However, despite the rapid evolution of HPC infrastructures, the development of scientific applications dramatically lags behind in leveraging the capabilities of the underlying systems, especially the superior I/O performance.