Node:Guru Execution of Plans, Previous:Guru Real-to-real Transforms, Up:Guru Interface

4.5.6 Guru Execution of Plans

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:

• The array size, strides, etcetera are the same (since those are set by the plan).
• The input and output arrays are the same (in-place) or different (out-of-place) if the plan was originally created to be in-place or out-of-place, respectively.
• For split arrays, the separations between the real and imaginary parts, ii-ri and 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.)
• The alignment of the new input/output arrays is the same as that of the input/output arrays when the plan was created, unless the plan was created with the FFTW_UNALIGNED flag. 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_malloc are 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 plan is not modified, and these routines can be called as many times as desired, or intermixed with calls to the ordinary fftw_execute.

The plan must have been created for the transform type corresponding to the execute function, e.g. it must be a complex-DFT plan for 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.