FFTW Frequently Asked Questions with Answers

This is the list of Frequently Asked Questions about FFTW, a collection of fast C routines for computing the Discrete Fourier Transform in one or more dimensions.

Index

Section 1. Introduction and General Information
Q1.1. What is FFTW?
Q1.2. How do I obtain FFTW?
Q1.3. Is FFTW free software?
Q1.4. What is this about non-free licenses?
Q1.5. In the West? I thought MIT was in the East?
Section 2. Installing FFTW
Q2.1. Which systems does FFTW run on?
Q2.2. Does FFTW run on Windows?
Q2.3. My compiler has trouble with FFTW.
Q2.4. FFTW does not compile on Solaris, complaining about const.
Q2.5. What's the difference between --enable-3dnow and --enable-k7?
Q2.6. What's the difference between the fma and the non-fma versions?
Q2.7. Which language is FFTW written in?
Q2.8. Can I call FFTW from Fortran?
Q2.9. Can I call FFTW from C++?
Q2.10. Why isn't FFTW written in Fortran/C++?
Q2.11. How do I compile FFTW to run in single precision?
Q2.12. --enable-k7 does not work on x86-64
Section 3. Using FFTW
Q3.1. Why not support the FFTW 2 interface in FFTW 3?
Q3.2. Why do FFTW 3 plans encapsulate the input/output arrays and not just the algorithm?
Q3.3. FFTW seems really slow.
Q3.4. FFTW slows down after repeated calls.
Q3.5. An FFTW routine is crashing when I call it.
Q3.6. My Fortran program crashes when calling FFTW.
Q3.7. FFTW gives results different from my old FFT.
Q3.8. FFTW gives different results between runs
Q3.9. Can I save FFTW's plans?
Q3.10. Why does your inverse transform return a scaled result?
Q3.11. How can I make FFTW put the origin (zero frequency) at the center of its output?
Q3.12. How do I FFT an image/audio file in foobar format?
Q3.13. My program does not link (on Unix).
Q3.14. I included your header, but linking still fails.
Q3.15. My program crashes, complaining about stack space.
Q3.16. FFTW seems to have a memory leak.
Q3.17. The output of FFTW's transform is all zeros.
Q3.18. How do I call FFTW from the Microsoft language du jour?
Q3.19. Can I compute only a subset of the DFT outputs?
Q3.20. Can I use FFTW's routines for in-place and out-of-place matrix transposition?
Section 4. Internals of FFTW
Q4.1. How does FFTW work?
Q4.2. Why is FFTW so fast?
Section 5. Known bugs
Q5.1. FFTW 1.1 crashes in rfftwnd on Linux.
Q5.2. The MPI transforms in FFTW 1.2 give incorrect results/leak memory.
Q5.3. The test programs in FFTW 1.2.1 fail when I change FFTW to use single precision.
Q5.4. The test program in FFTW 1.2.1 fails for n > 46340.
Q5.5. The threaded code fails on Linux Redhat 5.0
Q5.6. FFTW 2.0's rfftwnd fails for rank > 1 transforms with a final dimension >= 65536.
Q5.7. FFTW 2.0's complex transforms give the wrong results with prime factors 17 to 97.
Q5.8. FFTW 2.1.1's MPI test programs crash with MPICH.
Q5.9. FFTW 2.1.2's multi-threaded transforms don't work on AIX.
Q5.10. FFTW 2.1.2's complex transforms give incorrect results for large prime sizes.
Q5.11. FFTW 2.1.3's multi-threaded transforms don't give any speedup on Solaris.
Q5.12. FFTW 2.1.3 crashes on AIX.

Matteo Frigo and Steven G. Johnson / fftw@fftw.org - 27 July 2011