Combined Fragment Molecular Orbital Cluster in Molecule Approach to Massively Parallel Electron Correlation Calculations for Large Systems.

Abstract

The local correlation "cluster-in-molecule" (CIM) method is combined with the fragment molecular orbital (FMO) method, providing a flexible, massively parallel, and near-linear scaling approach to the calculation of electron correlation energies for large molecular systems. Although the computational scaling of the CIM algorithm is already formally linear, previous knowledge of the Hartree-Fock (HF) reference wave function and subsequent localized orbitals is required; therefore, extending the CIM method to arbitrarily large systems requires the aid of low-scaling/linear-scaling approaches to HF and orbital localization. Through fragmentation, the combined FMO-CIM method linearizes the scaling, with respect to system size, of the HF reference and orbital localization calculations, achieving near-linear scaling at both the reference and electron correlation levels. For the 20-residue alanine α helix, the preliminary implementation of the FMO-CIM method captures 99.6% of the MP2 correlation energy, requiring 21% of the MP2 wall time. The new method is also applied to solvated adamantine to illustrate the multilevel capability of the FMO-CIM method. Disciplines Chemistry CommentsReprinted (adapted) ABSTRACT:The local correlation "cluster-in-molecule" (CIM) method is combined with the fragment molecular orbital (FMO) method, providing a flexible, massively parallel, and near-linear scaling approach to the calculation of electron correlation energies for large molecular systems. Although the computational scaling of the CIM algorithm is already formally linear, previous knowledge of the Hartree−Fock (HF) reference wave function and subsequent localized orbitals is required; therefore, extending the CIM method to arbitrarily large systems requires the aid of low-scaling/linear-scaling approaches to HF and orbital localization. Through fragmentation, the combined FMO-CIM method linearizes the scaling, with respect to system size, of the HF reference and orbital localization calculations, achieving near-linear scaling at both the reference and electron correlation levels. For the 20-residue alanine α helix, the preliminary implementation of the FMO-CIM method captures 99.6% of the MP2 correlation energy, requiring 21% of the MP2 wall time. The new method is also applied to solvated adamantine to illustrate the multilevel capability of the FMO-CIM method.

Explicitly correlated local coupled‐cluster methods using pair natural orbitals

“…An alternative approach to computing a large system as a whole is to split the system into smaller pieces (fragments), again based on orbital localization . In the more accurate fragmentation methods the HF reference function is still computed for the whole molecule, and only the correlation treatment is split into independent parts.…”

The Density-Based Many-Body Expansion as an Efficient and Accurate Quantum-Chemical Fragmentation Method: Application to Water Clusters

“…Moreover, as the individual fragment calculations are in general independent of each other, these can be performed in a massively parallel fashion. [7][8][9][10] As they are naturally partitioned into their molecular building blocks, molecular clusters and molecular crystals present ideal use cases for the application of quantum-chemical fragmentation methods. [11][12][13][14] Water clusters provide a particularly interesting and intensely studies test case, as their interaction energies are determined by the hydrogen-bond network, in which considerable polarization and other cooperative effects can be present.…”

Optimization of the linear-scaling local natural orbital CCSD(T) method: Redundancy-free triples correction using Laplace transform

“…70,[107][108][109][110][111][112][113] CCSD(T) implementations are available for the incremental method proposed by Stoll 114,115 and significantly extended by Friedrich, 109,116 the divide-and-conquer (DC) method of Li and Li 117 and Kobayashi and Nakai, 110,118 the divide-expand-consolidate (DEC) approach of Jørgensen, Kristensen, Kjaergaard, and their co-workers, 112,119,120 and the cluster-in-molecule (CIM) approach developed by Li, Piecuch, Gordon, and their co-workers. 113,121,122 Fragmentation-based strategies offer a straightforward route towards not only linear scaling computation time or efficient parallelism but also asymptotically constant memory and, if needed at all, disk requirement. Additionally, highly optimized canonical algorithms and implementations can be taken advantage of with minor modifications.…”