doxygen/moose/TorchPreKernel_8h_source.html

//* This file is part of the MOOSE framework

//* https://mooseframework.inl.gov

//*

//* All rights reserved, see COPYRIGHT for full restrictions

//* https://github.com/idaholab/moose/blob/master/COPYRIGHT

//*

//* Licensed under LGPL 2.1, please see LICENSE for details

//* https://www.gnu.org/licenses/lgpl-2.1.html


#pragma once


// NEML2_ENABLED implies MOOSE_LIBTORCH_ENABLED (neml2 is built against libtorch), so the

// TorchKernel base is available here.

#ifdef NEML2_ENABLED


// MOOSE includes

#include "TorchKernel.h"

#include "MOOSEToNEML2.h"


class TorchPreKernel : public TorchKernel, public MOOSEToNEML2

{

public:

  static InputParameters validParams();


  TorchPreKernel(const InputParameters & parameters);


  at::Tensor gatheredData() const override { return _output; }

};


#endif // NEML2_ENABLED

MOOSEToNEML2.h

TorchKernel.h

InputParameters
The main MOOSE class responsible for handling user-defined parameters in almost every MOOSE system.
Definition InputParameters.h:68

MOOSEToNEML2
Common interface for inserting gathered MOOSE data into the NEML2 material model.
Definition MOOSEToNEML2.h:28

MooseBase::parameters
const InputParameters & parameters() const
Get the parameters of the object.
Definition MooseBase.h:131

TorchKernel
TorchKernel is a conceptual extension of a MOOSE kernel that operates on batched libtorch tensors.
Definition TorchKernel.h:37

TorchKernel::_output
at::Tensor _output
The output of the forward operator.
Definition TorchKernel.h:59

TorchPreKernel
Base class for Torch FEM kernels that operate before the constitutive update, feeding their gathered ...
Definition TorchPreKernel.h:23

TorchPreKernel::validParams
static InputParameters validParams()
Definition TorchPreKernel.C:16

TorchPreKernel::gatheredData
at::Tensor gatheredData() const override
Convert data gathered from MOOSE into an at::Tensor (shape (batch, *base_shape))
Definition TorchPreKernel.h:29