mirror of
https://github.com/tildearrow/furnace.git
synced 2024-12-05 18:57:27 +00:00
166 lines
7.6 KiB
Text
166 lines
7.6 KiB
Text
|
@node Introduction, Tutorial, Top, Top
|
||
|
@chapter Introduction
|
||
|
This manual documents version @value{VERSION} of FFTW, the
|
||
|
@emph{Fastest Fourier Transform in the West}. FFTW is a comprehensive
|
||
|
collection of fast C routines for computing the discrete Fourier
|
||
|
transform (DFT) and various special cases thereof.
|
||
|
@cindex discrete Fourier transform
|
||
|
@cindex DFT
|
||
|
@itemize @bullet
|
||
|
@item FFTW computes the DFT of complex data, real data, even-
|
||
|
or odd-symmetric real data (these symmetric transforms are usually
|
||
|
known as the discrete cosine or sine transform, respectively), and the
|
||
|
discrete Hartley transform (DHT) of real data.
|
||
|
|
||
|
@item The input data can have arbitrary length.
|
||
|
FFTW employs @Onlogn{} algorithms for all lengths, including
|
||
|
prime numbers.
|
||
|
|
||
|
@item FFTW supports arbitrary multi-dimensional data.
|
||
|
|
||
|
@item FFTW supports the SSE, SSE2, AVX, AVX2, AVX512, KCVI, Altivec, VSX, and
|
||
|
NEON vector instruction sets.
|
||
|
|
||
|
@item FFTW includes parallel (multi-threaded) transforms
|
||
|
for shared-memory systems.
|
||
|
@item Starting with version 3.3, FFTW includes distributed-memory parallel
|
||
|
transforms using MPI.
|
||
|
@end itemize
|
||
|
|
||
|
We assume herein that you are familiar with the properties and uses of
|
||
|
the DFT that are relevant to your application. Otherwise, see
|
||
|
e.g. @cite{The Fast Fourier Transform and Its Applications} by E. O. Brigham
|
||
|
(Prentice-Hall, Englewood Cliffs, NJ, 1988).
|
||
|
@uref{http://www.fftw.org, Our web page} also has links to FFT-related
|
||
|
information online.
|
||
|
@cindex FFTW
|
||
|
|
||
|
@c TODO: revise. We don't need to brag any longer
|
||
|
@c
|
||
|
@c FFTW is usually faster (and sometimes much faster) than all other
|
||
|
@c freely-available Fourier transform programs found on the Net. It is
|
||
|
@c competitive with (and often faster than) the FFT codes in Sun's
|
||
|
@c Performance Library, IBM's ESSL library, HP's CXML library, and
|
||
|
@c Intel's MKL library, which are targeted at specific machines.
|
||
|
@c Moreover, FFTW's performance is @emph{portable}. Indeed, FFTW is
|
||
|
@c unique in that it automatically adapts itself to your machine, your
|
||
|
@c cache, the size of your memory, your number of registers, and all the
|
||
|
@c other factors that normally make it impossible to optimize a program
|
||
|
@c for more than one machine. An extensive comparison of FFTW's
|
||
|
@c performance with that of other Fourier transform codes has been made,
|
||
|
@c and the results are available on the Web at
|
||
|
@c @uref{http://fftw.org/benchfft, the benchFFT home page}.
|
||
|
@c @cindex benchmark
|
||
|
@c @fpindex benchfft
|
||
|
|
||
|
In order to use FFTW effectively, you need to learn one basic concept
|
||
|
of FFTW's internal structure: FFTW does not use a fixed algorithm for
|
||
|
computing the transform, but instead it adapts the DFT algorithm to
|
||
|
details of the underlying hardware in order to maximize performance.
|
||
|
Hence, the computation of the transform is split into two phases.
|
||
|
First, FFTW's @dfn{planner} ``learns'' the fastest way to compute the
|
||
|
transform on your machine. The planner
|
||
|
@cindex planner
|
||
|
produces a data structure called a @dfn{plan} that contains this
|
||
|
@cindex plan
|
||
|
information. Subsequently, the plan is @dfn{executed}
|
||
|
@cindex execute
|
||
|
to transform the array of input data as dictated by the plan. The
|
||
|
plan can be reused as many times as needed. In typical
|
||
|
high-performance applications, many transforms of the same size are
|
||
|
computed and, consequently, a relatively expensive initialization of
|
||
|
this sort is acceptable. On the other hand, if you need a single
|
||
|
transform of a given size, the one-time cost of the planner becomes
|
||
|
significant. For this case, FFTW provides fast planners based on
|
||
|
heuristics or on previously computed plans.
|
||
|
|
||
|
FFTW supports transforms of data with arbitrary length, rank,
|
||
|
multiplicity, and a general memory layout. In simple cases, however,
|
||
|
this generality may be unnecessary and confusing. Consequently, we
|
||
|
organized the interface to FFTW into three levels of increasing
|
||
|
generality.
|
||
|
@itemize @bullet
|
||
|
@item The @dfn{basic interface} computes a single
|
||
|
transform of contiguous data.
|
||
|
@item The @dfn{advanced interface} computes transforms
|
||
|
of multiple or strided arrays.
|
||
|
@item The @dfn{guru interface} supports the most general data
|
||
|
layouts, multiplicities, and strides.
|
||
|
@end itemize
|
||
|
We expect that most users will be best served by the basic interface,
|
||
|
whereas the guru interface requires careful attention to the
|
||
|
documentation to avoid problems.
|
||
|
@cindex basic interface
|
||
|
@cindex advanced interface
|
||
|
@cindex guru interface
|
||
|
|
||
|
|
||
|
Besides the automatic performance adaptation performed by the planner,
|
||
|
it is also possible for advanced users to customize FFTW manually. For
|
||
|
example, if code space is a concern, we provide a tool that links only
|
||
|
the subset of FFTW needed by your application. Conversely, you may need
|
||
|
to extend FFTW because the standard distribution is not sufficient for
|
||
|
your needs. For example, the standard FFTW distribution works most
|
||
|
efficiently for arrays whose size can be factored into small primes
|
||
|
(@math{2}, @math{3}, @math{5}, and @math{7}), and otherwise it uses a
|
||
|
slower general-purpose routine. If you need efficient transforms of
|
||
|
other sizes, you can use FFTW's code generator, which produces fast C
|
||
|
programs (``codelets'') for any particular array size you may care
|
||
|
about.
|
||
|
@cindex code generator
|
||
|
@cindex codelet
|
||
|
For example, if you need transforms of size
|
||
|
@ifinfo
|
||
|
@math{513 = 19 x 3^3},
|
||
|
@end ifinfo
|
||
|
@tex
|
||
|
$513 = 19 \cdot 3^3$,
|
||
|
@end tex
|
||
|
@html
|
||
|
513 = 19*3<sup>3</sup>,
|
||
|
@end html
|
||
|
you can customize FFTW to support the factor @math{19} efficiently.
|
||
|
|
||
|
For more information regarding FFTW, see the paper, ``The Design and
|
||
|
Implementation of FFTW3,'' by M. Frigo and S. G. Johnson, which was an
|
||
|
invited paper in @cite{Proc. IEEE} @b{93} (2), p. 216 (2005). The
|
||
|
code generator is described in the paper ``A fast Fourier transform
|
||
|
compiler'',
|
||
|
@cindex compiler
|
||
|
by M. Frigo, in the @cite{Proceedings of the 1999 ACM SIGPLAN Conference
|
||
|
on Programming Language Design and Implementation (PLDI), Atlanta,
|
||
|
Georgia, May 1999}. These papers, along with the latest version of
|
||
|
FFTW, the FAQ, benchmarks, and other links, are available at
|
||
|
@uref{http://www.fftw.org, the FFTW home page}.
|
||
|
|
||
|
The current version of FFTW incorporates many good ideas from the past
|
||
|
thirty years of FFT literature. In one way or another, FFTW uses the
|
||
|
Cooley-Tukey algorithm, the prime factor algorithm, Rader's algorithm
|
||
|
for prime sizes, and a split-radix algorithm (with a
|
||
|
``conjugate-pair'' variation pointed out to us by Dan Bernstein).
|
||
|
FFTW's code generator also produces new algorithms that we do not
|
||
|
completely understand.
|
||
|
@cindex algorithm
|
||
|
The reader is referred to the cited papers for the appropriate
|
||
|
references.
|
||
|
|
||
|
The rest of this manual is organized as follows. We first discuss the
|
||
|
sequential (single-processor) implementation. We start by describing
|
||
|
the basic interface/features of FFTW in @ref{Tutorial}.
|
||
|
Next, @ref{Other Important Topics} discusses data alignment
|
||
|
(@pxref{SIMD alignment and fftw_malloc}),
|
||
|
the storage scheme of multi-dimensional arrays
|
||
|
(@pxref{Multi-dimensional Array Format}), and FFTW's mechanism for
|
||
|
storing plans on disk (@pxref{Words of Wisdom-Saving Plans}). Next,
|
||
|
@ref{FFTW Reference} provides comprehensive documentation of all
|
||
|
FFTW's features. Parallel transforms are discussed in their own
|
||
|
chapters: @ref{Multi-threaded FFTW} and @ref{Distributed-memory FFTW
|
||
|
with MPI}. Fortran programmers can also use FFTW, as described in
|
||
|
@ref{Calling FFTW from Legacy Fortran} and @ref{Calling FFTW from
|
||
|
Modern Fortran}. @ref{Installation and Customization} explains how to
|
||
|
install FFTW in your computer system and how to adapt FFTW to your
|
||
|
needs. License and copyright information is given in @ref{License and
|
||
|
Copyright}. Finally, we thank all the people who helped us in
|
||
|
@ref{Acknowledgments}.
|
||
|
|