Definition at line 196 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...
|
| |
| real(real32), dimension(:,:,:,:), pointer, public, contiguous | srs_data |
| | Single-precision buffers, used only when single is .true. (FFTW path; the accelerator transforms operate on caller-provided device buffers). More...
|
| |
| complex(real32), dimension(:,:,:,:), pointer, public, contiguous | crs_data |
| | complex32 real-space buffer More...
|
| |
| complex(real32), dimension(:,:,:,:), pointer, public, contiguous | cfs_data |
| | complex32 Fourier-space buffer More...
|
| |
| logical, public | single = .false. |
| | single-precision FFT (FFTW and accelerator only) 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 |
| |
1.9.4