Definition at line 192 of file fft.F90.
|
| integer, public | type |
| | is the fft real or complex More...
|
| |
| integer, public | library |
| | what library are we using More...
|
| |
| integer, dimension(1:3), public | stride_rs |
| | GPU strides for the (spatial) cube packing. More...
|
| |
| integer, dimension(1:3), public | stride_fs |
| |
| real(real64), dimension(:,:,:,:), pointer, public, contiguous | drs_data |
| | The following arrays have to be stored here and allocated in the initialization routine because of PFFT These arrays are also used for FFTW, as we want to have aligned memory. More...
|
| |
| complex(real64), dimension(:,:,:,:), pointer, public, contiguous | zrs_data |
| | array used to store the function in real space. More...
|
| |
| complex(real64), dimension(:,:,:,:), pointer, public, contiguous | fs_data |
| | array used to store the function in Fourier space. More...
|
| |
| type(pnfft_t), public | pnfft |
| |
| logical, public | aligned_memory |
| |
|
| integer | slot = 0 |
| | in which slot do we have this fft More...
|
| |
| integer | howmany |
| | Number of FFTs performed at once. Batched transforms (howmany > 1) are supported by FFTW and cuFFT; PFFT, NFFT and PNFFT require howmany == 1. More...
|
| |
| type(mpi_comm) | comm |
| | The batch always occupies the trailing (slowest-varying, rank-4) axis of the data arrays ("batch-last"), so each transform is contiguous. The spatial dimension arrays below stay rank-3; fft_pack() builds the rank-4 shape where it is needed. More...
|
| |
| integer, dimension(3) | rs_n_global |
| | total size of the fft in each direction in real space More...
|
| |
| integer, dimension(3) | fs_n_global |
| | total size of the fft in each direction in fourier space More...
|
| |
| integer, dimension(3) | rs_n |
| | local size of the fft in in each direction real space More...
|
| |
| integer, dimension(3) | fs_n |
| | local size of the fft in in each direction fourier space More...
|
| |
| integer, dimension(1:3) | rs_istart |
| | where does the local portion of the function start in real space More...
|
| |
| integer, dimension(1:3) | fs_istart |
| | where does the local portion of the function start in fourier space More...
|
| |
| type(c_ptr) | planf |
| | plan for forward transform More...
|
| |
| type(c_ptr) | planb |
| | plan for backward transform More...
|
| |
| type(c_ptr) | cuda_plan_fw |
| |
| type(c_ptr) | cuda_plan_bw |
| |
◆ slot
| integer fft_oct_m::fft_t::slot = 0 |
|
private |
in which slot do we have this fft
Definition at line 194 of file fft.F90.
◆ type
| integer, public fft_oct_m::fft_t::type |
is the fft real or complex
Definition at line 196 of file fft.F90.
◆ library
| integer, public fft_oct_m::fft_t::library |
what library are we using
Definition at line 197 of file fft.F90.
◆ howmany
| integer fft_oct_m::fft_t::howmany |
|
private |
Number of FFTs performed at once. Batched transforms (howmany > 1) are supported by FFTW and cuFFT; PFFT, NFFT and PNFFT require howmany == 1.
Definition at line 198 of file fft.F90.
◆ comm
The batch always occupies the trailing (slowest-varying, rank-4) axis of the data arrays ("batch-last"), so each transform is contiguous. The spatial dimension arrays below stay rank-3; fft_pack() builds the rank-4 shape where it is needed.
MPI communicator
Definition at line 204 of file fft.F90.
◆ rs_n_global
| integer, dimension(3) fft_oct_m::fft_t::rs_n_global |
|
private |
total size of the fft in each direction in real space
Definition at line 205 of file fft.F90.
◆ fs_n_global
| integer, dimension(3) fft_oct_m::fft_t::fs_n_global |
|
private |
total size of the fft in each direction in fourier space
Definition at line 206 of file fft.F90.
◆ rs_n
| integer, dimension(3) fft_oct_m::fft_t::rs_n |
|
private |
local size of the fft in in each direction real space
Definition at line 207 of file fft.F90.
◆ fs_n
| integer, dimension(3) fft_oct_m::fft_t::fs_n |
|
private |
local size of the fft in in each direction fourier space
Definition at line 208 of file fft.F90.
◆ rs_istart
| integer, dimension(1:3) fft_oct_m::fft_t::rs_istart |
|
private |
where does the local portion of the function start in real space
Definition at line 209 of file fft.F90.
◆ fs_istart
| integer, dimension(1:3) fft_oct_m::fft_t::fs_istart |
|
private |
where does the local portion of the function start in fourier space
Definition at line 210 of file fft.F90.
◆ stride_rs
| integer, dimension(1:3), public fft_oct_m::fft_t::stride_rs |
GPU strides for the (spatial) cube packing.
Definition at line 213 of file fft.F90.
◆ stride_fs
| integer, dimension(1:3), public fft_oct_m::fft_t::stride_fs |
◆ planf
| type(c_ptr) fft_oct_m::fft_t::planf |
|
private |
plan for forward transform
Definition at line 216 of file fft.F90.
◆ planb
| type(c_ptr) fft_oct_m::fft_t::planb |
|
private |
plan for backward transform
Definition at line 217 of file fft.F90.
◆ drs_data
| real(real64), dimension(:,:,:,:), pointer, public, contiguous fft_oct_m::fft_t::drs_data |
The following arrays have to be stored here and allocated in the initialization routine because of PFFT These arrays are also used for FFTW, as we want to have aligned memory.
array used to store the function in real space.
Definition at line 223 of file fft.F90.
◆ zrs_data
| complex(real64), dimension(:,:,:,:), pointer, public, contiguous fft_oct_m::fft_t::zrs_data |
array used to store the function in real space.
Definition at line 224 of file fft.F90.
◆ fs_data
| complex(real64), dimension(:,:,:,:), pointer, public, contiguous fft_oct_m::fft_t::fs_data |
array used to store the function in Fourier space.
Definition at line 225 of file fft.F90.
◆ cuda_plan_fw
| type(c_ptr) fft_oct_m::fft_t::cuda_plan_fw |
|
private |
◆ cuda_plan_bw
| type(c_ptr) fft_oct_m::fft_t::cuda_plan_bw |
|
private |
◆ pnfft
◆ aligned_memory
| logical, public fft_oct_m::fft_t::aligned_memory |
The documentation for this type was generated from the following file:
1.9.4