cuda_poisson_110_t Derived Type

public subroutine base_init(self, mesh, xdirps, ydirps, zdirps, n_spec, n_sp_st)

Sets up the state every case shares. The backend's init calls it once it has set bc_code, which the spectral extents it passes in already depend on. The supported BC codes are the cases of the backend factories, create_omp_poisson_fft and create_cuda_poisson_fft.

Arguments

public subroutine solve_poisson(self, f, temp)

Gathers each non-periodic line into a periodic one, so that a plain FFT can stand in for the cosine transform, solves in spectral space, and scatters the result back. The 000 case has nothing to reorder and overrides this to transform f in place.

Arguments

public subroutine stretching_matrix(self, geo, xdirps, ydirps, zdirps)

Stretching necessitates a special operation in spectral space. The coefficients for the operation are stored in matrix form.

Arguments

public subroutine waves_set(self, geo, xdirps, ydirps, zdirps)

Spectral equivalence constants

Arguments

public function get_km(self, i, j, k) result(km)

Arguments

Return Value complex(kind=dp)

public function get_km_re(self, i, j, k) result(re)

Arguments

Return Value real(kind=dp)

public function get_km_im(self, i, j, k) result(re)

Arguments

Return Value real(kind=dp)

private subroutine init_cuda(self, mesh, xdirps, ydirps, zdirps, lowmem)

Arguments

public subroutine init_dim2_mirror(self, mesh)

The 010, 100 and 110 cases pair each dim2 spectral mode with its mirror, which cuFFTMp may place on another rank. Slab index r of P owns global dim2 modes [rm + 1, (r + 1)m] with m = ny_spec, and the mirror of that range is slab P - 1 - r shifted up by one plane, so the extra plane comes from slab P - r. Both partners are symmetric. A single rank holds every partner itself and allocates nothing. This is the only place c_mirror_dev is allocated, see the cuFFTMp check in init_cuda.

Arguments

public subroutine exchange_dim2_mirror(self, c_dev)

Fills c_mirror_dev and c_plane_recv_dev with the dim2 mirror of the local spectral slab, so that the paired split can read its partner mode without going looking for it in another rank's memory.

Arguments

public subroutine init_case_110(self, mesh)

Arguments

public subroutine create_plans_110(self, mesh, fft_n, fft_n_loc, fw_plan_type, bw_plan_type)

R2C with Z-transpose, on (nz, nx, ny). A single rank keeps the plain cuFFT path; on multiple ranks cuFFTMp distributes the transform, and the physical Z-slab is redistributed into its Y-slab input through an MPI_Alltoall (see redistribute_110_to_yslab).

Arguments

public subroutine fft_forward_110_cuda(self, f)

Forward FFT for 110 case: transpose (nx,ny,nz)->(nz,nx,ny) then R2C

Arguments

public subroutine fft_backward_110_cuda(self, f)

Backward FFT for 110 case: C2R then transpose (nz,nx,ny)->(nx,ny,nz)

Arguments

public subroutine fft_postprocess_110_cuda(self)

Spectral post-processing for 110 case (R2C Z-transpose). Spectral array is (nz/2+1, nx, ny) = (nx_spec, ny_spec, nz_spec). Thread i->X (ny_spec), blockIdx%y k->Y (nz_spec), serial j->Z (nx_spec). On a single rank X and Y are both whole, so 7 kernel launches avoid cross-block race conditions. On multiple ranks cuFFTMp splits X across ranks, so the X pairing reaches its partner through the dim2 mirror exchange (see exchange_dim2_mirror) instead, adding two more launches.

Arguments

public subroutine enforce_periodicity_xy_cuda(self, f_out, f_in)

Arguments

public subroutine undo_periodicity_xy_cuda(self, f_out, f_in)

Arguments

public subroutine redistribute_110_to_yslab(self, zslab, yslab)

Redistributes the 110 field from the physical Z-slab (nx, ny, nz_l) to the cuFFTMp Y-slab real view (2*(nz/2+1), nx, ny_l), ahead of the forward transform. See the comment above pack_110_xyz_to_yslab.

Arguments

public subroutine redistribute_110_to_zslab(self, yslab, zslab)

Inverse of redistribute_110_to_yslab, after the backward transform.

Arguments