furnace/extern/fftw/doc/FAQ/fftw-faq.html/section5.html

149 lines
5.8 KiB
HTML
Raw Normal View History

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">
<html>
<head><title>
FFTW FAQ - Section 5
</title>
<link rev="made" href="mailto:fftw@fftw.org">
<link rel="Contents" href="index.html">
<link rel="Start" href="index.html">
<link rel="Previous" href="section4.html"><link rel="Bookmark" title="FFTW FAQ" href="index.html">
</head><body text="#000000" bgcolor="#FFFFFF"><h1>
FFTW FAQ - Section 5 <br>
Known bugs
</h1>
<ul>
<li><a href="#rfftwndbug" rel=subdocument>Q5.1. FFTW 1.1 crashes in rfftwnd on Linux.</a>
<li><a href="#fftwmpibug" rel=subdocument>Q5.2. The MPI transforms in FFTW 1.2 give incorrect results/leak
memory.</a>
<li><a href="#testsingbug" rel=subdocument>Q5.3. The test programs in FFTW 1.2.1 fail when I change FFTW to use single
precision.</a>
<li><a href="#teststoobig" rel=subdocument>Q5.4. The test program in FFTW 1.2.1 fails for n &gt;
46340.</a>
<li><a href="#linuxthreads" rel=subdocument>Q5.5. The threaded code fails on Linux Redhat 5.0</a>
<li><a href="#bigrfftwnd" rel=subdocument>Q5.6. FFTW 2.0's rfftwnd fails for rank &gt; 1 transforms with a final
dimension &gt;= 65536.</a>
<li><a href="#primebug" rel=subdocument>Q5.7. FFTW 2.0's complex transforms give the wrong results with prime
factors 17 to 97.</a>
<li><a href="#mpichbug" rel=subdocument>Q5.8. FFTW 2.1.1's MPI test programs crash with
MPICH.</a>
<li><a href="#aixthreadbug" rel=subdocument>Q5.9. FFTW 2.1.2's multi-threaded transforms don't work on
AIX.</a>
<li><a href="#bigprimebug" rel=subdocument>Q5.10. FFTW 2.1.2's complex transforms give incorrect results for large prime
sizes.</a>
<li><a href="#solaristhreadbug" rel=subdocument>Q5.11. FFTW 2.1.3's multi-threaded transforms don't give any speedup on
Solaris.</a>
<li><a href="#aixflags" rel=subdocument>Q5.12. FFTW 2.1.3 crashes on AIX.</a>
</ul><hr>
<h2><A name="rfftwndbug">
Question 5.1. FFTW 1.1 crashes in rfftwnd on
Linux.
</A></h2>
This bug was fixed in FFTW 1.2. There was a bug in
<code>rfftwnd</code> causing an incorrect amount of memory to be allocated. The bug showed
up in Linux with libc-5.3.12 (and nowhere else that we know of).
<h2><A name="fftwmpibug">
Question 5.2. The MPI transforms in FFTW 1.2 give incorrect
results/leak memory.
</A></h2>
These bugs were corrected in FFTW 1.2.1. The MPI transforms (really,
just the transpose routines) in FFTW 1.2 had bugs that could cause
errors in some situations.
<h2><A name="testsingbug">
Question 5.3. The test programs in FFTW 1.2.1 fail when I change FFTW
to use single precision.
</A></h2>
This bug was fixed in FFTW 1.3. (Older versions of FFTW did
work in single precision, but the test programs didn't--the error
tolerances in the tests were set for double precision.)
<h2><A name="teststoobig">
Question 5.4. The test program in FFTW 1.2.1 fails for n &gt;
46340.
</A></h2>
This bug was fixed in FFTW 1.3. FFTW 1.2.1 produced the right answer,
but the test program was wrong. For large n, n*n in the naive
transform that we used for comparison overflows 32 bit integer
precision, breaking the test.
<h2><A name="linuxthreads">
Question 5.5. The threaded code fails on Linux Redhat
5.0
</A></h2>
We had problems with glibc-2.0.5. The code should work with
glibc-2.0.7.
<h2><A name="bigrfftwnd">
Question 5.6. FFTW 2.0's rfftwnd fails for rank &gt; 1 transforms
with a final dimension &gt;= 65536.
</A></h2>
This bug was fixed in FFTW 2.0.1. (There was a 32-bit integer
overflow due to a poorly-parenthesized expression.)
<h2><A name="primebug">
Question 5.7. FFTW 2.0's complex transforms give the wrong results
with prime factors 17 to 97.
</A></h2>
There was a bug in the complex transforms that could cause incorrect
results under (hopefully rare) circumstances for lengths with
intermediate-size prime factors (17-97). This bug was fixed in FFTW
2.1.1.
<h2><A name="mpichbug">
Question 5.8. FFTW 2.1.1's MPI test programs crash with
MPICH.
</A></h2>
This bug was fixed in FFTW 2.1.2. The 2.1/2.1.1 MPI test programs
crashed when using the MPICH implementation of MPI with the
<code>ch_p4</code> device (TCP/IP); the transforms themselves worked fine.
<h2><A name="aixthreadbug">
Question 5.9. FFTW 2.1.2's multi-threaded transforms don't work on
AIX.
</A></h2>
This bug was fixed in FFTW 2.1.3. The multi-threaded transforms in
previous versions didn't work with AIX's
<code>pthreads</code> implementation, which idiosyncratically creates threads in detached
(non-joinable) mode by default.
<h2><A name="bigprimebug">
Question 5.10. FFTW 2.1.2's complex transforms give incorrect results
for large prime sizes.
</A></h2>
This bug was fixed in FFTW 2.1.3. FFTW's complex-transform algorithm
for prime sizes (in versions 2.0 to 2.1.2) had an integer overflow
problem that caused incorrect results for many primes greater than
32768 (on 32-bit machines). (Sizes without large prime factors are
not affected.)
<h2><A name="solaristhreadbug">
Question 5.11. FFTW 2.1.3's multi-threaded transforms don't give any
speedup on Solaris.
</A></h2>
This bug was fixed in FFTW 2.1.4. (By default, Solaris creates
threads that do not parallelize over multiple processors, so one has
to request the proper behavior specifically.)
<h2><A name="aixflags">
Question 5.12. FFTW 2.1.3 crashes on AIX.
</A></h2>
The FFTW 2.1.3 <code>configure</code> script picked incorrect compiler flags for the <code>xlc</code> compiler on newer IBM processors. This
is fixed in FFTW 2.1.4. <hr>
Back: <a href="section4.html" rev=precedes>Internals of FFTW</a>.<br>
<a href="index.html" rev=subdocument>Return to contents</a>.<p>
<address>
<A href="http://www.fftw.org">Matteo Frigo and Steven G. Johnson</A> / <A href="mailto:fftw@fftw.org">fftw@fftw.org</A>
- 14 September 2021
</address><br>
Extracted from FFTW Frequently Asked Questions with Answers,
Copyright &copy; 2021 Matteo Frigo and Massachusetts Institute of Technology.
</body></html>