Node:Guru Execution of Plans, Previous:Guru Real-to-real Transforms, Up:Guru Interface
Normally, one executes a plan for the arrays with which the plan was
created, by calling
fftw_execute(plan) as described in Using Plans.
However, it is possible to apply a given plan to a different
array using the guru functions detailed below, provided that the
following conditions are met:
io-ro, are the same as they were for the input and output arrays when the plan was created. (This condition is automatically satisfied for interleaved arrays.)
FFTW_UNALIGNEDflag. Here, the alignment is a platform-dependent quantity (for example, it is the address modulo 16 if SSE SIMD instructions are used, but the address modulo 4 for non-SIMD single-precision FFTW on the same machine). In general, only arrays allocated with
fftw_mallocare guaranteed to be equally aligned.
If you are tempted to use this guru interface because you want to transform a known bunch of arrays of the same size, stop here and go use the advanced interface instead (see Advanced Interface)).
The guru execute functions are:
void fftw_execute_dft( const fftw_plan p, fftw_complex *in, fftw_complex *out); void fftw_execute_split_dft( const fftw_plan p, double *ri, double *ii, double *ro, double *io); void fftw_execute_dft_r2c( const fftw_plan p, double *in, fftw_complex *out); void fftw_execute_split_dft_r2c( const fftw_plan p, double *in, double *ro, double *io); void fftw_execute_dft_c2r( const fftw_plan p, fftw_complex *in, double *out); void fftw_execute_split_dft_c2r( const fftw_plan p, double *ri, double *ii, double *out); void fftw_execute_r2r( const fftw_plan p, double *in, double *out);
These execute the
plan to compute the corresponding transform on
the input/output arrays specified by the subsequent arguments. The
input/output array arguments have the same meanings as the ones passed
to the guru planner routines in the preceding sections. The
is not modified, and these routines can be called as many times as
desired, or intermixed with calls to the ordinary
plan must have been created for the transform type
corresponding to the execute function, e.g. it must be a complex-DFT
fftw_execute_dft. Any of the planner routines for that
transform type, from the basic to the guru interface, could have been
used to create the plan, however.