Benefits of Parallel I/O in Ab Initio Nuclear Physics Calculations

Authors:
Nikhil Laghave;Masha Sosonkina;Pieter Maris;James P. Vary
Affiliations:
Ames Laboratory/DOE, Iowa State University, Ames, USA IA 50011;Ames Laboratory/DOE, Iowa State University, Ames, USA IA 50011;Physics Department, Iowa State University, Ames, USA IA 50011;Physics Department, Iowa State University, Ames, USA IA 50011
Venue:
ICCS '09 Proceedings of the 9th International Conference on Computational Science: Part I
Year:
2009

Citing 2
Cited 0

Accelerating configuration interaction calculations for nuclear structure

Proceedings of the 2008 ACM/IEEE conference on Supercomputing
Integration of Ab Initio Nuclear Physics Calculations with Optimization Techniques

ICCS '08 Proceedings of the 8th international conference on Computational Science, Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many modern scientific applications rely on highly parallel calculations, which scale to 10's of thousands processors. However, most applications do not concentrate on parallelizing input/output operations. In particular, sequential I/O has been identified as a bottleneck for the highly scalable MFDn (Many Fermion Dynamics for nuclear structure) code performing ab initio nuclear structure calculations. In this paper, we develop interfaces and parallel I/O procedures to use a well-known parallel I/O library in MFDn. As a result, we gain efficient input/output of large datasets along with their portability and ease of use in the downstream processing.