Quantum-based Molecular Dynamics Simulations Using Tensor Cores

• URL: http://arxiv.org/abs/2107.02737v2
• Date: Fri, 10 Sep 2021 23:01:50 GMT
• Title: Quantum-based Molecular Dynamics Simulations Using Tensor Cores
• Authors: Joshua Finkelstein, Justin S. Smith, Susan M. Mniszewski, Kipton Barros, Christian F. A. Negre, Emanuel H. Rubensson, Anders M. N. Niklasson
• Abstract summary: We show how tensor cores can be applied with high efficiency to the Born-Oppenheimer molecular dynamics problem. The interatomic forces are calculated on-the-fly from an electronic structure that is obtained from a generalized deep neural network. A canonical ensemble simulation scheme is also presented, where the additional numerical noise in the calculated forces is absorbed into a Langevin-like dynamics.
• Score: 2.3551989288556774
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tensor cores, along with tensor processing units, represent a new form of hardware acceleration specifically designed for deep neural network calculations in artificial intelligence applications. Tensor cores provide extraordinary computational speed and energy efficiency, but with the caveat that they were designed for tensor contractions (matrix-matrix multiplications) using only low-precision floating point operations. In spite of this, we demonstrate how tensor cores can be applied with high efficiency to the challenging and numerically sensitive problem of quantum-based Born-Oppenheimer molecular dynamics, which requires highly accurate electronic structure optimizations and conservative force evaluations. The interatomic forces are calculated on-the-fly from an electronic structure that is obtained from a generalized deep neural network, where the computational structure naturally takes advantage of the exceptional processing power of the tensor cores and allows for high performance in excess of 100 Tflops on the tensor cores of a single Nvidia A100 GPU. Stable molecular dynamics trajectories are generated using the framework of extended Lagrangian Born-Oppenheimer molecular dynamics, which combines computational efficiency with long-term stability, even when using approximate charge relaxations and force evaluations that are limited in accuracy by the numerically noisy conditions caused by the low precision tensor core floating-point operations. A canonical ensemble simulation scheme is also presented, where the additional numerical noise in the calculated forces is absorbed into a Langevin-like dynamics.

Related papers

• Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems [77.88054335119074]
  We use FNOs to model the evolution of random quantum spin systems. We apply FNOs to a compact set of Hamiltonian observables instead of the entire $2n$ quantum wavefunction.
  arXiv  Detail & Related papers  (2024-09-05T07:18:09Z)
• Speed Limits for Deep Learning [67.69149326107103]
  Recent advancement in thermodynamics allows bounding the speed at which one can go from the initial weight distribution to the final distribution of the fully trained network. We provide analytical expressions for these speed limits for linear and linearizable neural networks. Remarkably, given some plausible scaling assumptions on the NTK spectra and spectral decomposition of the labels -- learning is optimal in a scaling sense.
  arXiv  Detail & Related papers  (2023-07-27T06:59:46Z)
• Faster spectral density calculation using energy moments [77.34726150561087]
  We reformulate the recently proposed Gaussian Integral Transform technique in terms of Fourier moments of the system Hamiltonian. One of the main advantages of this framework is that it allows for an important reduction of the computational cost.
  arXiv  Detail & Related papers  (2022-11-01T23:57:58Z)
• Predictive Scale-Bridging Simulations through Active Learning [43.48102250786867]
  We use an active learning approach to optimize the use of local fine-scale simulations for informing coarse-scale hydrodynamics. Our approach addresses three challenges: forecasting continuum coarse-scale trajectory, dynamically updating coarse-scale from fine-scale calculations, and quantifying uncertainty in neural network models.
  arXiv  Detail & Related papers  (2022-09-20T15:58:50Z)
• Quantum perturbation theory using Tensor cores and a deep neural network [0.0]
  Time-independent quantum response calculations are performed using floating cores. We demonstrate a peak performance of almost 200 Tflops using the cores of two Nvidia A100 GPUs.
  arXiv  Detail & Related papers  (2022-03-17T21:24:10Z)
• Efficient quantum computation of molecular forces and other energy gradients [0.4696310509745634]
  We introduce new quantum algorithms for computing molecular energy derivatives with significantly lower complexity than prior methods. Our results suggest that the calculation of forces on a single nucleus may be of similar cost to estimating energies of chemical systems.
  arXiv  Detail & Related papers  (2021-11-24T11:37:13Z)
• Quantum-Classical Hybrid Algorithm for the Simulation of All-Electron Correlation [58.720142291102135]
  We present a novel hybrid-classical algorithm that computes a molecule's all-electron energy and properties on the classical computer. We demonstrate the ability of the quantum-classical hybrid algorithms to achieve chemically relevant results and accuracy on currently available quantum computers.
  arXiv  Detail & Related papers  (2021-06-22T18:00:00Z)
• Solving the electronic Schr\"odinger equation for multiple nuclear geometries with weight-sharing deep neural networks [4.1201966507589995]
  We introduce a weight-sharing constraint when optimizing neural network-based models for different molecular geometries. We find that this technique can accelerate optimization when considering sets of nuclear geometries of the same molecule by an order of magnitude.
  arXiv  Detail & Related papers  (2021-05-18T08:23:09Z)
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations [86.41674945012369]
  We develop a scalable and expressive Graph Neural Networks model, ForceNet, to approximate atomic forces. Our proposed ForceNet is able to predict atomic forces more accurately than state-of-the-art physics-based GNNs.
  arXiv  Detail & Related papers  (2021-03-02T03:09:06Z)
• Microcanonical and finite temperature ab initio molecular dynamics simulations on quantum computers [0.0]
  Ab initio molecular dynamics (AIMD) is a powerful tool to predict properties of molecular and condensed matter systems. We provide solutions for the alleviation of the statistical noise associated to the measurements of the expectation values of energies and forces. We also propose a Langevin dynamics algorithm for the simulation of canonical, i.e., constant temperature, dynamics.
  arXiv  Detail & Related papers  (2020-08-18T20:24:27Z)
• Variational Monte Carlo calculations of $\mathbf{A\leq 4}$ nuclei with an artificial neural-network correlator ansatz [62.997667081978825]
  We introduce a neural-network quantum state ansatz to model the ground-state wave function of light nuclei. We compute the binding energies and point-nucleon densities of $Aleq 4$ nuclei as emerging from a leading-order pionless effective field theory Hamiltonian.
  arXiv  Detail & Related papers  (2020-07-28T14:52:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.