Next: 2d MPI example, Previous: FFTW MPI Installation, Up: Distributed-memory FFTW with MPI [Contents][Index]
Programs using the MPI FFTW routines should be linked with
-lfftw3_mpi -lfftw3 -lm
on Unix in double precision,
-lfftw3f_mpi -lfftw3f -lm
in single precision, and so on
(see Precision). You will also need to link with whatever library
is responsible for MPI on your system; in most MPI implementations,
there is a special compiler alias named mpicc
to compile and
link MPI code.
Before calling any FFTW routines except possibly
fftw_init_threads
(see Combining MPI and Threads), but after calling
MPI_Init
, you should call the function:
void fftw_mpi_init(void);
If, at the end of your program, you want to get rid of all memory and other resources allocated internally by FFTW, for both the serial and MPI routines, you can call:
void fftw_mpi_cleanup(void);
which is much like the fftw_cleanup()
function except that it
also gets rid of FFTW’s MPI-related data. You must not execute
any previously created plans after calling this function.