#include <iostream>
#include "Kokkos_Core.hpp"
#include "Stokhos_Multiply.hpp"
#include "Stokhos_BlockCrsMatrix.hpp"
#include "Stokhos_CrsProductTensor.hpp"
#include "Stokhos_Cuda_DeviceProp.hpp"
#include "Stokhos_Cuda_WarpShuffle.hpp"
#include "Teuchos_TestForException.hpp"
#include "cuda_profiler_api.h"
Go to the source code of this file.
|
class | Stokhos::Multiply< BlockCrsMatrix< CrsProductTensor< TensorScalar, Kokkos::Cuda >, MatrixScalar, Kokkos::Cuda >, Kokkos::View< VectorScalar **, Kokkos::LayoutLeft, Kokkos::Cuda >, Kokkos::View< VectorScalar **, Kokkos::LayoutLeft, Kokkos::Cuda > > |
|
class | Stokhos::Multiply< BlockCrsMatrix< CrsProductTensor< TensorScalar, Kokkos::Cuda >, MatrixScalar, Kokkos::Cuda >, Kokkos::View< VectorScalar **, Kokkos::LayoutLeft, Kokkos::Cuda >, Kokkos::View< VectorScalar **, Kokkos::LayoutLeft, Kokkos::Cuda > >::MultiplyKernel |
|
struct | Stokhos::Multiply< BlockCrsMatrix< CrsProductTensor< TensorScalar, Kokkos::Cuda >, MatrixScalar, Kokkos::Cuda >, Kokkos::View< VectorScalar **, Kokkos::LayoutLeft, Kokkos::Cuda >, Kokkos::View< VectorScalar **, Kokkos::LayoutLeft, Kokkos::Cuda > >::TensorReadEntry |
|
◆ USE_LDG
◆ USE_FIXED_BLOCKSIZE
#define USE_FIXED_BLOCKSIZE 0 |