Romero, N. A.8; Glinsvad, Christian1; Larsen, Ask Hjorth2; Enkovaara, J.9; Shende, S.7; Morozov, V. A.8; Mortensen, Jens Jørgen2
1 Experimental Surface and Nanomaterials Physics, Department of Physics, Technical University of Denmark2 Department of Physics, Technical University of Denmark3 Theoretical Atomic-scale Physics, Department of Physics, Technical University of Denmark4 Center for Atomic-scale Materials Design, Center, Technical University of Denmark5 Argonne National Laboratory6 Aalto University7 Oregon State University8 Argonne National Laboratory9 Aalto University
A case study of GPAW on the Blue Gene/P architecture
Density function theory (DFT) is the most widely employed electronic structure method because of its favorable scaling with system size and accuracy for a broad range of molecular and condensed-phase systems. The advent of massively parallel supercomputers has enhanced the scientific community's ability to study larger system sizes. Ground-state DFT calculations on∼103 valence electrons using traditional O(N3) algorithms can be routinely performed on present-day supercomputers. The performance characteristics of these massively parallel DFT codes on>104 computer cores are not well understood. The GPAW code was ported an optimized for the Blue Gene/P architecture. We present our algorithmic parallelization strategy and interpret the results for a number of benchmark test cases.
Concurrency and Computation: Practice and Experience, 2013, Vol 27, Issue 1, p. 69-93
Blue gene; DFT; Electronic structure; GPAW; High-performance computing; Massive parallelization