Reference documentation for deal.II version GIT 4efb66ecd0 2023-02-07 13:45:02+00:00
\(\newcommand{\dealvcentcolon}{\mathrel{\mathop{:}}}\) \(\newcommand{\dealcoloneq}{\dealvcentcolon\mathrel{\mkern-1.2mu}=}\) \(\newcommand{\jump}[1]{\left[\!\left[ #1 \right]\!\right]}\) \(\newcommand{\average}[1]{\left\{\!\left\{ #1 \right\}\!\right\}}\)
Namespaces | Functions
cuda_kernels.cc File Reference
#include <deal.II/lac/cuda_kernels.templates.h>

Go to the source code of this file.

Namespaces

 LinearAlgebra
 
 LinearAlgebra::CUDAWrappers
 
 LinearAlgebra::CUDAWrappers::kernel
 

Functions

template __global__ void LinearAlgebra::CUDAWrappers::kernel::vec_scale< float > (float *, const float a, const size_type)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::vector_bin_op< float, Binop_Addition > (float *v1, const float *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::vector_bin_op< float, Binop_Subtraction > (float *v1, const float *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::masked_vector_bin_op< float, Binop_Addition > (const unsigned int *mask, float *v1, const float *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::masked_vector_bin_op< float, Binop_Subtraction > (const unsigned int *mask, float *v1, const float *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::reduction< float, ElemSum< float > > (float *result, const float *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::reduction< float, L1Norm< float > > (float *result, const float *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::reduction< float, LInfty< float > > (float *result, const float *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::double_vector_reduction< float, DotProduct< float > > (float *result, const float *v1, const float *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::vec_add< float > (float *val, const float, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::add_aV< float > (float *val, const float a, const float *V_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::add_aVbW< float > (float *val, const float a, const float *V_val, const float b, const float *W_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::sadd< float > (const float s, float *val, const float a, const float *V_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::sadd< float > (const float s, float *val, const float a, const float *V_val, const float b, const float *W_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::scale< float > (float *val, const float *V_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::equ< float > (float *val, const float a, const float *V_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::equ< float > (float *val, const float a, const float *V_val, const float b, const float *W_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::add_and_dot< float > (float *res, float *v1, const float *v2, const float *v3, const float a, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::set< float > (float *val, const float s, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::set_permutated< float, size_type > (const size_type *indices, float *val, const float *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::gather< float, size_type > (float *val, const size_type *indices, const float *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::add_permutated< float > (const size_type *indices, float *val, const float *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::vec_scale< double > (double *, const double a, const size_type)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::vector_bin_op< double, Binop_Addition > (double *v1, const double *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::vector_bin_op< double, Binop_Subtraction > (double *v1, const double *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::masked_vector_bin_op< double, Binop_Addition > (const unsigned int *mask, double *v1, const double *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::masked_vector_bin_op< double, Binop_Subtraction > (const unsigned int *mask, double *v1, const double *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::reduction< double, ElemSum< double > > (double *result, const double *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::reduction< double, L1Norm< double > > (double *result, const double *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::reduction< double, LInfty< double > > (double *result, const double *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::double_vector_reduction< double, DotProduct< double > > (double *result, const double *v1, const double *v2, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::vec_add< double > (double *val, const double, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::add_aV< double > (double *val, const double a, const double *V_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::add_aVbW< double > (double *val, const double a, const double *V_val, const double b, const double *W_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::sadd< double > (const double s, double *val, const double a, const double *V_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::sadd< double > (const double s, double *val, const double a, const double *V_val, const double b, const double *W_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::scale< double > (double *val, const double *V_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::equ< double > (double *val, const double a, const double *V_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::equ< double > (double *val, const double a, const double *V_val, const double b, const double *W_val, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::add_and_dot< double > (double *res, double *v1, const double *v2, const double *v3, const double a, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::set< double > (double *val, const double s, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::set_permutated< double, size_type > (const size_type *indices, double *val, const double *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::gather< double, size_type > (double *val, const size_type *indices, const double *v, const size_type N)
 
template __global__ void LinearAlgebra::CUDAWrappers::kernel::add_permutated< double > (const size_type *indices, double *val, const double *v, const size_type N)