cannam@95: Next: MPI Plan Creation, cannam@95: Previous: Using MPI Plans, cannam@95: Up: FFTW MPI Reference cannam@95:
As described above (see MPI Data Distribution), in order to
cannam@95: allocate your arrays, before creating a plan, you must first
cannam@95: call one of the following routines to determine the required
cannam@95: allocation size and the portion of the array locally stored on a given
cannam@95: process. The MPI_Comm communicator passed here must be
cannam@95: equivalent to the communicator used below for plan creation.
cannam@95:
cannam@95:
The basic interface for multidimensional transforms consists of the cannam@95: functions: cannam@95: cannam@95:
ptrdiff_t fftw_mpi_local_size_2d(ptrdiff_t n0, ptrdiff_t n1, MPI_Comm comm, cannam@95: ptrdiff_t *local_n0, ptrdiff_t *local_0_start); cannam@95: ptrdiff_t fftw_mpi_local_size_3d(ptrdiff_t n0, ptrdiff_t n1, ptrdiff_t n2, cannam@95: MPI_Comm comm, cannam@95: ptrdiff_t *local_n0, ptrdiff_t *local_0_start); cannam@95: ptrdiff_t fftw_mpi_local_size(int rnk, const ptrdiff_t *n, MPI_Comm comm, cannam@95: ptrdiff_t *local_n0, ptrdiff_t *local_0_start); cannam@95: cannam@95: ptrdiff_t fftw_mpi_local_size_2d_transposed(ptrdiff_t n0, ptrdiff_t n1, MPI_Comm comm, cannam@95: ptrdiff_t *local_n0, ptrdiff_t *local_0_start, cannam@95: ptrdiff_t *local_n1, ptrdiff_t *local_1_start); cannam@95: ptrdiff_t fftw_mpi_local_size_3d_transposed(ptrdiff_t n0, ptrdiff_t n1, ptrdiff_t n2, cannam@95: MPI_Comm comm, cannam@95: ptrdiff_t *local_n0, ptrdiff_t *local_0_start, cannam@95: ptrdiff_t *local_n1, ptrdiff_t *local_1_start); cannam@95: ptrdiff_t fftw_mpi_local_size_transposed(int rnk, const ptrdiff_t *n, MPI_Comm comm, cannam@95: ptrdiff_t *local_n0, ptrdiff_t *local_0_start, cannam@95: ptrdiff_t *local_n1, ptrdiff_t *local_1_start); cannam@95:cannam@95:
These functions return the number of elements to allocate (complex
cannam@95: numbers for DFT/r2c/c2r plans, real numbers for r2r plans), whereas
cannam@95: the local_n0 and local_0_start return the portion
cannam@95: (local_0_start to local_0_start + local_n0 - 1) of the
cannam@95: first dimension of an n0 × n1 × n2 × … × nd-1 array that is stored on the local
cannam@95: process. See Basic and advanced distribution interfaces. For
cannam@95: FFTW_MPI_TRANSPOSED_OUT plans, the ‘_transposed’ variants
cannam@95: are useful in order to also return the local portion of the first
cannam@95: dimension in the n1 × n0 × n2 ×…× nd-1 transposed output. See Transposed distributions. The advanced interface for multidimensional
cannam@95: transforms is:
cannam@95:
cannam@95:
ptrdiff_t fftw_mpi_local_size_many(int rnk, const ptrdiff_t *n, ptrdiff_t howmany, cannam@95: ptrdiff_t block0, MPI_Comm comm, cannam@95: ptrdiff_t *local_n0, ptrdiff_t *local_0_start); cannam@95: ptrdiff_t fftw_mpi_local_size_many_transposed(int rnk, const ptrdiff_t *n, ptrdiff_t howmany, cannam@95: ptrdiff_t block0, ptrdiff_t block1, MPI_Comm comm, cannam@95: ptrdiff_t *local_n0, ptrdiff_t *local_0_start, cannam@95: ptrdiff_t *local_n1, ptrdiff_t *local_1_start); cannam@95:cannam@95:
These differ from the basic interface in only two ways. First, they
cannam@95: allow you to specify block sizes block0 and block1 (the
cannam@95: latter for the transposed output); you can pass
cannam@95: FFTW_MPI_DEFAULT_BLOCK to use FFTW's default block size as in
cannam@95: the basic interface. Second, you can pass a howmany parameter,
cannam@95: corresponding to the advanced planning interface below: this is for
cannam@95: transforms of contiguous howmany-tuples of numbers
cannam@95: (howmany = 1 in the basic interface).
cannam@95:
cannam@95:
The corresponding basic and advanced routines for one-dimensional cannam@95: transforms (currently only complex DFTs) are: cannam@95: cannam@95:
ptrdiff_t fftw_mpi_local_size_1d( cannam@95: ptrdiff_t n0, MPI_Comm comm, int sign, unsigned flags, cannam@95: ptrdiff_t *local_ni, ptrdiff_t *local_i_start, cannam@95: ptrdiff_t *local_no, ptrdiff_t *local_o_start); cannam@95: ptrdiff_t fftw_mpi_local_size_many_1d( cannam@95: ptrdiff_t n0, ptrdiff_t howmany, cannam@95: MPI_Comm comm, int sign, unsigned flags, cannam@95: ptrdiff_t *local_ni, ptrdiff_t *local_i_start, cannam@95: ptrdiff_t *local_no, ptrdiff_t *local_o_start); cannam@95:cannam@95:
As above, the return value is the number of elements to allocate
cannam@95: (complex numbers, for complex DFTs). The local_ni and
cannam@95: local_i_start arguments return the portion
cannam@95: (local_i_start to local_i_start + local_ni - 1) of the
cannam@95: 1d array that is stored on this process for the transform
cannam@95: input, and local_no and local_o_start are the
cannam@95: corresponding quantities for the input. The sign
cannam@95: (FFTW_FORWARD or FFTW_BACKWARD) and flags must
cannam@95: match the arguments passed when creating a plan. Although the inputs
cannam@95: and outputs have different data distributions in general, it is
cannam@95: guaranteed that the output data distribution of an
cannam@95: FFTW_FORWARD plan will match the input data distribution
cannam@95: of an FFTW_BACKWARD plan and vice versa; similarly for the
cannam@95: FFTW_MPI_SCRAMBLED_OUT and FFTW_MPI_SCRAMBLED_IN flags.
cannam@95: See One-dimensional distributions.
cannam@95:
cannam@95:
cannam@95: