Chris@42: Chris@42: Chris@42: Chris@42: FFTW FAQ - Section 5 Chris@42: Chris@42: Chris@42: Chris@42: Chris@42: Chris@42:

Chris@42: FFTW FAQ - Section 5
Chris@42: Known bugs Chris@42:

Chris@42: Chris@42:
Chris@42: Chris@42:

Chris@42: Question 5.1. FFTW 1.1 crashes in rfftwnd on Chris@42: Linux. Chris@42:

Chris@42: Chris@42: This bug was fixed in FFTW 1.2. There was a bug in Chris@42: rfftwnd causing an incorrect amount of memory to be allocated. The bug showed Chris@42: up in Linux with libc-5.3.12 (and nowhere else that we know of). Chris@42: Chris@42:

Chris@42: Question 5.2. The MPI transforms in FFTW 1.2 give incorrect Chris@42: results/leak memory. Chris@42:

Chris@42: Chris@42: These bugs were corrected in FFTW 1.2.1. The MPI transforms (really, Chris@42: just the transpose routines) in FFTW 1.2 had bugs that could cause Chris@42: errors in some situations. Chris@42:

Chris@42: Question 5.3. The test programs in FFTW 1.2.1 fail when I change FFTW Chris@42: to use single precision. Chris@42:

Chris@42: Chris@42: This bug was fixed in FFTW 1.3. (Older versions of FFTW did Chris@42: work in single precision, but the test programs didn't--the error Chris@42: tolerances in the tests were set for double precision.) Chris@42: Chris@42:

Chris@42: Question 5.4. The test program in FFTW 1.2.1 fails for n > Chris@42: 46340. Chris@42:

Chris@42: Chris@42: This bug was fixed in FFTW 1.3. FFTW 1.2.1 produced the right answer, Chris@42: but the test program was wrong. For large n, n*n in the naive Chris@42: transform that we used for comparison overflows 32 bit integer Chris@42: precision, breaking the test. Chris@42:

Chris@42: Question 5.5. The threaded code fails on Linux Redhat Chris@42: 5.0 Chris@42:

Chris@42: Chris@42: We had problems with glibc-2.0.5. The code should work with Chris@42: glibc-2.0.7. Chris@42:

Chris@42: Question 5.6. FFTW 2.0's rfftwnd fails for rank > 1 transforms Chris@42: with a final dimension >= 65536. Chris@42:

Chris@42: Chris@42: This bug was fixed in FFTW 2.0.1. (There was a 32-bit integer Chris@42: overflow due to a poorly-parenthesized expression.) Chris@42:

Chris@42: Question 5.7. FFTW 2.0's complex transforms give the wrong results Chris@42: with prime factors 17 to 97. Chris@42:

Chris@42: Chris@42: There was a bug in the complex transforms that could cause incorrect Chris@42: results under (hopefully rare) circumstances for lengths with Chris@42: intermediate-size prime factors (17-97). This bug was fixed in FFTW Chris@42: 2.1.1. Chris@42:

Chris@42: Question 5.8. FFTW 2.1.1's MPI test programs crash with Chris@42: MPICH. Chris@42:

Chris@42: Chris@42: This bug was fixed in FFTW 2.1.2. The 2.1/2.1.1 MPI test programs Chris@42: crashed when using the MPICH implementation of MPI with the Chris@42: ch_p4 device (TCP/IP); the transforms themselves worked fine. Chris@42: Chris@42:

Chris@42: Question 5.9. FFTW 2.1.2's multi-threaded transforms don't work on Chris@42: AIX. Chris@42:

Chris@42: Chris@42: This bug was fixed in FFTW 2.1.3. The multi-threaded transforms in Chris@42: previous versions didn't work with AIX's Chris@42: pthreads implementation, which idiosyncratically creates threads in detached Chris@42: (non-joinable) mode by default. Chris@42:

Chris@42: Question 5.10. FFTW 2.1.2's complex transforms give incorrect results Chris@42: for large prime sizes. Chris@42:

Chris@42: Chris@42: This bug was fixed in FFTW 2.1.3. FFTW's complex-transform algorithm Chris@42: for prime sizes (in versions 2.0 to 2.1.2) had an integer overflow Chris@42: problem that caused incorrect results for many primes greater than Chris@42: 32768 (on 32-bit machines). (Sizes without large prime factors are Chris@42: not affected.) Chris@42:

Chris@42: Question 5.11. FFTW 2.1.3's multi-threaded transforms don't give any Chris@42: speedup on Solaris. Chris@42:

Chris@42: Chris@42: This bug was fixed in FFTW 2.1.4. (By default, Solaris creates Chris@42: threads that do not parallelize over multiple processors, so one has Chris@42: to request the proper behavior specifically.) Chris@42: Chris@42:

Chris@42: Question 5.12. FFTW 2.1.3 crashes on AIX. Chris@42:

Chris@42: Chris@42: The FFTW 2.1.3 configure script picked incorrect compiler flags for the xlc compiler on newer IBM processors. This Chris@42: is fixed in FFTW 2.1.4.
Chris@42: Back: Internals of FFTW.
Chris@42: Return to contents.

Chris@42:

Chris@42: Matteo Frigo and Steven G. Johnson / fftw@fftw.org Chris@42: - 30 July 2016 Chris@42:

Chris@42: Extracted from FFTW Frequently Asked Questions with Answers, Chris@42: Copyright © 2016 Matteo Frigo and Massachusetts Institute of Technology. Chris@42: