Non-collective parallel I/O for global address space programming models

Abstract

Achieving high performance for out-of-core applications typically involves explicit management of the movement of data between the disk and the physical memory. We are developing a programming environment in which the different levels of the memory hierarchy are handled efficiently in a unified transparent framework. In this paper, we present our experiences with implementing efficient non-collective I/O (GPCIO) as part of this framework. As a generalization of the remote procedure call (RPC) that was used as a foundation for the Sun NFS system, we developed a global procedure call (GPC) to invoke procedures on a remote node to handle non-collective I/O. We consider alternative approaches that can be employed in implementing this functionality. The approaches are evaluated using a representative computation from quantum chemistry. The results demonstrate that GPC-IO achieves better absolute execution times, strong-scaling, and weak-scaling than the alternatives considered.

DOI: 10.1109/CLUSTR.2007.4629215

Extracted Key Phrases

7 Figures and Tables

Cite this paper

@article{Krishnamoorthy2007NoncollectivePI, title={Non-collective parallel I/O for global address space programming models}, author={Sriram Krishnamoorthy and Juan Piernas and Vinod Tipparaju and Jarek Nieplocha and P. Sadayappan}, journal={2007 IEEE International Conference on Cluster Computing}, year={2007}, pages={41-49} }