Journal Article

PreJuSER-4823

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Large-Scale Parallel Multireference-Averaged Quadratic Coupled Cluster: The Ground State of the Chromium Dimer Revisited

Müller, T.FZJ*

2009
Soc. Washington, DC

This record in other databases:      

Please use a persistent id in citations: doi:10.1021/jp905254u

Abstract: The accurate prediction of the potential energy function of the X1Sigmag+ state of Cr2 is a remarkable challenge; large differential electron correlation effects, significant scalar relativistic contributions, the need for large flexible basis sets containing g functions, the importance of semicore valence electron correlation, and its multireference nature pose considerable obstacles. So far, the only reasonable successful approaches were based on multireference perturbation theory (MRPT). Recently, there was some controversy in the literature about the role of error compensation and systematic defects of various MRPT implementations that cannot be easily overcome. A detailed basis set study of the potential energy function is presented, adopting a variational method. The method of choice for this electron-rich target with up to 28 correlated electrons is fully uncontracted multireference-averaged quadratic coupled cluster (MR-AQCC), which shares the flexibility of the multireference configuration interaction (MRCI) approach and is, in addition, approximately size-extensive (0.02 eV in error as compared to the MRCI value of 1.37 eV for two noninteracting chromium atoms). The best estimate for De arrives at 1.48 eV and agrees well with the experimental data of 1.47 +/- 0.056 eV. At the estimated CBS limit, the equilibrium bond distance (1.685 A) and vibrational frequency (459 cm-1) are in agreement with experiment (1.679 A, 481 cm-1). Large basis sets and reference configuration spaces invariably result in huge wave function expansions (here, up to 2.8 billion configuration state functions), and efficient parallel implementations of the method are crucial. Hence, relevant details on implementation and general performance of the parallel program code are discussed as well.

Keyword(s): J

Note: The calculations have been carried out on the supercomputer resources provided by the John-von-Neumann Institute for Computing (NIC) at the Research Centre, Julich. A generous supply of computing time is gratefully acknowledged. This work has been partially supported by the European Community (COST Action D37).

---

Contributing Institute(s):

1. Jülich Supercomputing Centre (JSC)

Research Program(s):

1. Scientific Computing (P41)

Appears in the scientific report 2009

---