Chris@10: Next: Installation and Customization, Chris@10: Previous: Calling FFTW from Legacy Fortran, Chris@10: Up: Top Chris@10:
In this chapter, we outline the process for updating codes designed for Chris@10: the older FFTW 2 interface to work with FFTW 3. The interface for FFTW Chris@10: 3 is not backwards-compatible with the interface for FFTW 2 and earlier Chris@10: versions; codes written to use those versions will fail to link with Chris@10: FFTW 3. Nor is it possible to write “compatibility wrappers” to Chris@10: bridge the gap (at least not efficiently), because FFTW 3 has different Chris@10: semantics from previous versions. However, upgrading should be a Chris@10: straightforward process because the data formats are identical and the Chris@10: overall style of planning/execution is essentially the same. Chris@10: Chris@10:
Unlike FFTW 2, there are no separate header files for real and complex
Chris@10: transforms (or even for different precisions) in FFTW 3; all interfaces
Chris@10: are defined in the <fftw3.h> header file.
Chris@10:
Chris@10:
The main difference in data types is that fftw_complex in FFTW 2
Chris@10: was defined as a struct with macros c_re and c_im
Chris@10: for accessing the real/imaginary parts. (This is binary-compatible with
Chris@10: FFTW 3 on any machine except perhaps for some older Crays in single
Chris@10: precision.) The equivalent macros for FFTW 3 are:
Chris@10:
Chris@10:
#define c_re(c) ((c)[0]) Chris@10: #define c_im(c) ((c)[1]) Chris@10:Chris@10:
This does not work if you are using the C99 complex type, however,
Chris@10: unless you insert a double* typecast into the above macros
Chris@10: (see Complex numbers).
Chris@10:
Chris@10:
Also, FFTW 2 had an fftw_real typedef that was an alias for
Chris@10: double (in double precision). In FFTW 3 you should just use
Chris@10: double (or whatever precision you are employing).
Chris@10:
Chris@10:
The major difference between FFTW 2 and FFTW 3 is in the Chris@10: planning/execution division of labor. In FFTW 2, plans were found for a Chris@10: given transform size and type, and then could be applied to any Chris@10: arrays and for any multiplicity/stride parameters. In FFTW 3, Chris@10: you specify the particular arrays, stride parameters, etcetera when Chris@10: creating the plan, and the plan is then executed for those arrays Chris@10: (unless the guru interface is used) and those parameters Chris@10: only. (FFTW 2 had “specific planner” routines that planned for Chris@10: a particular array and stride, but the plan could still be used for Chris@10: other arrays and strides.) That is, much of the information that was Chris@10: formerly specified at execution time is now specified at planning time. Chris@10: Chris@10:
Like FFTW 2's specific planner routines, the FFTW 3 planner overwrites
Chris@10: the input/output arrays unless you use FFTW_ESTIMATE.
Chris@10:
Chris@10:
FFTW 2 had separate data types fftw_plan, fftwnd_plan,
Chris@10: rfftw_plan, and rfftwnd_plan for complex and real one- and
Chris@10: multi-dimensional transforms, and each type had its own ‘destroy’
Chris@10: function. In FFTW 3, all plans are of type fftw_plan and all are
Chris@10: destroyed by fftw_destroy_plan(plan).
Chris@10:
Chris@10:
Where you formerly used fftw_create_plan and fftw_one to
Chris@10: plan and compute a single 1d transform, you would now use
Chris@10: fftw_plan_dft_1d to plan the transform. If you used the generic
Chris@10: fftw function to execute the transform with multiplicity
Chris@10: (howmany) and stride parameters, you would now use the advanced
Chris@10: interface fftw_plan_many_dft to specify those parameters. The
Chris@10: plans are now executed with fftw_execute(plan), which takes all
Chris@10: of its parameters (including the input/output arrays) from the plan.
Chris@10:
Chris@10:
In-place transforms no longer interpret their output argument as scratch
Chris@10: space, nor is there an FFTW_IN_PLACE flag. You simply pass the
Chris@10: same pointer for both the input and output arguments. (Previously, the
Chris@10: output ostride and odist parameters were ignored for
Chris@10: in-place transforms; now, if they are specified via the advanced
Chris@10: interface, they are significant even in the in-place case, although they
Chris@10: should normally equal the corresponding input parameters.)
Chris@10:
Chris@10:
The FFTW_ESTIMATE and FFTW_MEASURE flags have the same
Chris@10: meaning as before, although the planning time will differ. You may also
Chris@10: consider using FFTW_PATIENT, which is like FFTW_MEASURE
Chris@10: except that it takes more time in order to consider a wider variety of
Chris@10: algorithms.
Chris@10:
Chris@10:
For multi-dimensional complex DFTs, instead of fftwnd_create_plan
Chris@10: (or fftw2d_create_plan or fftw3d_create_plan), followed by
Chris@10: fftwnd_one, you would use fftw_plan_dft (or
Chris@10: fftw_plan_dft_2d or fftw_plan_dft_3d). followed by
Chris@10: fftw_execute. If you used fftwnd to to specify strides
Chris@10: etcetera, you would instead specify these via fftw_plan_many_dft.
Chris@10:
Chris@10:
The analogues to rfftw_create_plan and rfftw_one with
Chris@10: FFTW_REAL_TO_COMPLEX or FFTW_COMPLEX_TO_REAL directions
Chris@10: are fftw_plan_r2r_1d with kind FFTW_R2HC or
Chris@10: FFTW_HC2R, followed by fftw_execute. The stride etcetera
Chris@10: arguments of rfftw are now in fftw_plan_many_r2r.
Chris@10:
Chris@10:
Instead of rfftwnd_create_plan (or rfftw2d_create_plan or
Chris@10: rfftw3d_create_plan) followed by
Chris@10: rfftwnd_one_real_to_complex or
Chris@10: rfftwnd_one_complex_to_real, you now use fftw_plan_dft_r2c
Chris@10: (or fftw_plan_dft_r2c_2d or fftw_plan_dft_r2c_3d) or
Chris@10: fftw_plan_dft_c2r (or fftw_plan_dft_c2r_2d or
Chris@10: fftw_plan_dft_c2r_3d), respectively, followed by
Chris@10: fftw_execute. As usual, the strides etcetera of
Chris@10: rfftwnd_real_to_complex or rfftwnd_complex_to_real are no
Chris@10: specified in the advanced planner routines,
Chris@10: fftw_plan_many_dft_r2c or fftw_plan_many_dft_c2r.
Chris@10:
Chris@10:
In FFTW 2, you had to supply the FFTW_USE_WISDOM flag in order to
Chris@10: use wisdom; in FFTW 3, wisdom is always used. (You could simulate the
Chris@10: FFTW 2 wisdom-less behavior by calling fftw_forget_wisdom after
Chris@10: every planner call.)
Chris@10:
Chris@10:
The FFTW 3 wisdom import/export routines are almost the same as before Chris@10: (although the storage format is entirely different). There is one Chris@10: significant difference, however. In FFTW 2, the import routines would Chris@10: never read past the end of the wisdom, so you could store extra data Chris@10: beyond the wisdom in the same file, for example. In FFTW 3, the Chris@10: file-import routine may read up to a few hundred bytes past the end of Chris@10: the wisdom, so you cannot store other data just beyond it.1 Chris@10: Chris@10:
Wisdom has been enhanced by additional humility in FFTW 3: whereas FFTW Chris@10: 2 would re-use wisdom for a given transform size regardless of the Chris@10: stride etc., in FFTW 3 wisdom is only used with the strides etc. for Chris@10: which it was created. Unfortunately, this means FFTW 3 has to create Chris@10: new plans from scratch more often than FFTW 2 (in FFTW 2, planning Chris@10: e.g. one transform of size 1024 also created wisdom for all smaller Chris@10: powers of 2, but this no longer occurs). Chris@10: Chris@10:
FFTW 3 also has the new routine fftw_import_system_wisdom to
Chris@10: import wisdom from a standard system-wide location.
Chris@10:
Chris@10:
In FFTW 3, we recommend allocating your arrays with fftw_malloc
Chris@10: and deallocating them with fftw_free; this is not required, but
Chris@10: allows optimal performance when SIMD acceleration is used. (Those two
Chris@10: functions actually existed in FFTW 2, and worked the same way, but were
Chris@10: not documented.)
Chris@10:
Chris@10:
In FFTW 2, there were fftw_malloc_hook and fftw_free_hook
Chris@10: functions that allowed the user to replace FFTW's memory-allocation
Chris@10: routines (e.g. to implement different error-handling, since by default
Chris@10: FFTW prints an error message and calls exit to abort the program
Chris@10: if malloc returns NULL). These hooks are not supported in
Chris@10: FFTW 3; those few users who require this functionality can just
Chris@10: directly modify the memory-allocation routines in FFTW (they are defined
Chris@10: in kernel/alloc.c).
Chris@10:
Chris@10:
In FFTW 2, the subroutine names were obtained by replacing ‘fftw_’ Chris@10: with ‘fftw_f77’; in FFTW 3, you replace ‘fftw_’ with Chris@10: ‘dfftw_’ (or ‘sfftw_’ or ‘lfftw_’, depending upon the Chris@10: precision). Chris@10: Chris@10:
In FFTW 3, we have begun recommending that you always declare the type
Chris@10: used to store plans as integer*8. (Too many people didn't notice
Chris@10: our instruction to switch from integer to integer*8 for
Chris@10: 64-bit machines.)
Chris@10:
Chris@10:
In FFTW 3, we provide a fftw3.f “header file” to include in
Chris@10: your code (and which is officially installed on Unix systems). (In FFTW
Chris@10: 2, we supplied a fftw_f77.i file, but it was not installed.)
Chris@10:
Chris@10:
Otherwise, the C-Fortran interface relationship is much the same as it Chris@10: was before (e.g. return values become initial parameters, and Chris@10: multi-dimensional arrays are in column-major order). Unlike FFTW 2, we Chris@10: do provide some support for wisdom import/export in Fortran Chris@10: (see Wisdom of Fortran?). Chris@10: Chris@10:
Like FFTW 2, only the execution routines are thread-safe. All planner
Chris@10: routines, etcetera, should be called by only a single thread at a time
Chris@10: (see Thread safety). Unlike FFTW 2, there is no special
Chris@10: FFTW_THREADSAFE flag for the planner to allow a given plan to be
Chris@10: usable by multiple threads in parallel; this is now the case by default.
Chris@10:
Chris@10:
The multi-threaded version of FFTW 2 required you to pass the number of
Chris@10: threads each time you execute the transform. The number of threads is
Chris@10: now stored in the plan, and is specified before the planner is called by
Chris@10: fftw_plan_with_nthreads. The threads initialization routine used
Chris@10: to be called fftw_threads_init and would return zero on success;
Chris@10: the new routine is called fftw_init_threads and returns zero on
Chris@10: failure. See Multi-threaded FFTW.
Chris@10:
Chris@10:
There is no separate threads header file in FFTW 3; all the function
Chris@10: prototypes are in <fftw3.h>. However, you still have to link to
Chris@10: a separate library (-lfftw3_threads -lfftw3 -lm on Unix), as well as
Chris@10: to the threading library (e.g. POSIX threads on Unix).
Chris@10:
Chris@10:
[1] We Chris@10: do our own buffering because GNU libc I/O routines are horribly slow for Chris@10: single-character I/O, apparently for thread-safety reasons (whether you Chris@10: are using threads or not).
Chris@10: Chris@10: