![]() |
Dendro
5.01
Dendro in Greek language means tree. The Dendro library is a large scale (262K cores on ORNL's Titan) distributed memory adaptive octree framework. The main goal of Dendro is to perform large scale multiphysics simulations efficeiently in mordern supercomputers. Dendro consists of efficient parallel data structures and algorithms to perform variational ( finite element) methods and finite difference mthods on 2:1 balanced arbitary adaptive octrees which enables the users to perform simulations raning from black holes (binary black hole mergers) to blood flow in human body, where applications ranging from relativity, astrophysics to biomedical engineering.
|
▼ examples | |
► include | |
▼ FEM | |
► examples | |
► include | |
▼ include | |
► cuda | |
► test | |
asyncExchangeContex.h | |
binUtils.h | A set of efficient functions that use binary operations to perform some small computations |
block.h | |
colors.h | A set of colors useful for debugging |
cudaUtils.h | |
daUtils.h | |
dendro.h | |
dendroIO.h | |
dendroProfileParams.h | |
dollar.hpp | |
dtypes.h | Traits to determine MPI_DATATYPE from a C++ datatype |
genPts_par.h | |
hcurvedata.h | |
key.h | |
mathUtils.h | |
matRecord.h | |
memory_pool.h | |
mesh.h | |
node.h | |
nufft.h | Interface to non-uniform FFT library by L. Greengard |
nuts.h | Spatially adaptive non uniform time stepping framework |
octUtils.h | |
oda.h | The class that manages the octree mesh that support FEM computations. Note that this file is a refactored version from Dendro4 which is changed to support Dendro-5.0 Currently we use mesh based FEM computations but in future we will move towards the mesh - free FEM computation methods |
odaUtils.h | |
ompUtils.h | |
parUtils.h | A set of parallel utilities |
point.h | |
pointT.h | |
profiler.h | |
radix.h | |
sc_flops.h | |
seqUtils.h | A set of sequential utilities |
sfcSearch.h | |
sfcSort.h | |
simd_derivs.h | |
skey.h | |
stencil.h | |
sub_oda.h | |
subscattermap.h | Sub scatter map for partial MPI communications. This is an abstract version of the full scatter map to perform partial data exchanges. (Note that this is implemented for block wise scatter map, which will be used in non uniform timestepping ) |
TreeNode.h | |
treenode2vtk.h | |
wavelet.h | |
▼ IO | |
► include | |
► vtk | |
► zlib | |
▼ LinAlg | |
► include | |
▼ NLSigma | |
► include | |
▼ ODE | |
► include | |
▼ src | |
oda.cpp | The class that manages the octree mesh that support FEM computations. Note that this file is a refactored version from Dendro4 which is changed to support Dendro-5.0 Currently we use mesh based FEM computations but in future we will move towards the mesh - free FEM computation methods. Distributed Array (DA) methods currently uses ot::Mesh class to provide interface to write FEM loops |