Implementation and Evaluation of an MPI-IO Interface for GPFS in ROMIO

This paper presents an implementation of the MPI-IO interface for GPFS inside ROMIO distribution. The experimental section presents a performance comparison among three collective I/O implementations: two-phase I/O, the default file system independent method of ROMIO, view-based I/O, a file system-independent method we developed in a previous work and a GPFS specific collective I/O implementation based on data-shipping. The results show that data shipping-based collective I/O performs better for writing, while view-based I/O for reading.