Rev 2 | Go to most recent revision | Blame | Compare with Previous | Last modification | View Log | RSS feed
1999-05-17 fftw <fftw@glauke.lcs.mit.edu>
* NEWS: Noted codelet generator speed.
* gensrc/symmetry.ml, gensrc/genfft.ml, gensrc/fft.ml: Improved
real{even|odd}2 transforms
* doc/fftw.texi: Fixed typo.
* gensrc/exprdag.ml: Improved simplifier for DCT-type transforms.
* TODO: Noted that the transpose routines for MPI could use
improving.
* gensrc/symmetry.ml: Fixed comment.
* gensrc/symmetry.ml, gensrc/genfft.ml, gensrc/fft.ml: Fixed
modified DCT/DST generation (realeven2/realodd2) so that it works
now. The simplifier really sucks for this, at the moment. Why?
1999-05-16 fftw <fftw@glauke.lcs.mit.edu>
* gensrc/genfft.ml: Fixed real[even,odd]2 codelet node type
output.
* gensrc/variable.ml, gensrc/variable.mli, gensrc/symmetry.ml,
gensrc/genfft.ml: Added generators realeven2 and realodd2 for the
modified DCT and DST (i.e. transforms for real data that are
even/odd about n=-1/2, not n=0).
* gensrc/exprdag.ml: Memoized eval for speed reasons.
* gensrc/util.ml, gensrc/exprdag.ml: Implemented better
statistics.
* gensrc/exprdag.ml: Improved complexity of network transposition
from O(n^2)=O(slow) to O(n) [times O(polylog)]
* TODO: Noted that the generator can now output efficient
hard-coded DCT/DST routines of small sizes.
* gensrc/variable.mli, gensrc/variable.ml, gensrc/symmetry.ml,
gensrc/genfft.ml, gensrc/complex.mli, gensrc/complex.ml: Added
realeven and realodd codelet generation options. (They work.)
1999-05-10 fftw <fftw@glauke.lcs.mit.edu>
* doc/fftw.texi: Noted how to force compiler choice via CC
env. variable. Also added "compiler" index entry.
1999-05-07 fftw <fftw@glauke.lcs.mit.edu>
* TODO, NEWS: Updated TODO.
* README: Fixed Cilk URL.
* NEWS: Noted GNU-style long options in the test programs.
1999-05-06 fftw <fftw@glauke.lcs.mit.edu>
* tests/test_main.c: --help option no longer causes an exit with
an error code.
* tests/test_main.c, configure.in, fftw/config.h.in: Test programs
now use GNU-ly correct long options if getopt_long is available.
* FAQ/fftw-faq.bfnn, NEWS: MPICH bug fix is apparently not
specific to Linux (it also fixed the same problem on some
Ultrasparcs).
* fftw.spec: Updated for 2.1.2.
* mpi/fftw_mpi_test.c: --only-parallel argument hack should also
only be accessed by process 0.
1999-05-05 fftw <fftw@glauke.lcs.mit.edu>
* NEWS: Noted addition of omitted fftw_f77_threads_init function.
* FAQ/fftw-faq.bfnn: Bug fix (dates need to have two digits for
the day).
* threads/rfftw_threads_test.c, threads/fftw_threads_test.c,
tests/test_main.c, tests/test_main.h, tests/rfftw_test.c,
tests/fftw_test.c, mpi/rfftw_mpi_test.c, mpi/test_transpose_mpi.c,
FAQ/fftw-faq.bfnn, mpi/fftw_mpi_test.c, NEWS, configure.in: Fixed
bug when running test programs under MPICH; prepared for 2.1.2
release.
1999-04-18 stevenj <stevenj@glauke.lcs.mit.edu>
* fftw.spec: Made package relocatable.
* fftw.spec: Created spec file for generating RPM packages of
FFTW.
* FAQ/fftw-faq.bfnn: Revised linker FAQ entry.
1999-04-12 fftw <fftw@glauke.lcs.mit.edu>
* tests/test_main.c: Added joke.
1999-04-10 fftw <fftw@glauke.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: Added linker FAQ entry.
1999-04-07 stevenj <stevenj@glauke.lcs.mit.edu>
* threads/fftw_f77_threads.c: Added missing fftw_f77_threads_init
function (thanks to V. Sundararajan for pointing out the
omission).
1999-04-06 stevenj <stevenj@glauke.lcs.mit.edu>
* configure.in: Check for hcc in addition to mpicc (hcc is used by
the LAM MPI implementation).
1999-03-31 stevenj <stevenj@glauke.lcs.mit.edu>
* NEWS, doc/fftw.texi, ChangeLog: Fixed credit for 2.1.1 bug fix
(real credit goes to Ming-Chang Liu, according to Jeff
Briedenbach, whose name was misspelled anyway).
1999-03-30 stevenj <stevenj@glauke.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: Moderated language.
* NEWS: This isn't LaTeX, Matteo; an en dash in a monospaced font
is rendered the same as a hyphen (i.e. "-" not "--").
1999-03-29 Matteo Frigo <athena@supertech.lcs.mit.edu>
* ChangeLog: Updated
* NEWS: Minor change.
1999-03-28 Matteo Frigo <athena@supertech.lcs.mit.edu>
* tests/rfftw_test.c, tests/fftw_test.c:
Implemented paranoid check for real->complex and complex->real
transforms
1999-03-28 Matteo Frigo <athena@stern.lcs.mit.edu>
* NEWS:
Moderated language. I do not want to claim that the bug occurs in
`rare' circumstances. A bug is a bug, period.
* tests/fftw_test.c, rfftw/rplanner.c:
Implemented paranoid check for in-place complex planners.
I still don't know how to check real->complex plans,
though (apart from rewriting test_ergun for real->complex
and complex->real)
1999-03-26 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi, FAQ/fftw-faq.bfnn, NEWS:
Updated documentation for FFTW 2.1.1.
* configure.in:
Updated version number for 2.1.1 (as well as shared lib. version).
* threads/Makefile.am, mpi/Makefile.am: Fixed typo in comment.
* threads/fftw_threads_test.c, threads/rfftw_threads_test.c,
mpi/rfftw_mpi_test.c, mpi/fftw_mpi_test.c:
Added definition of enter_paranoid_mode() to threads & MPI test
programs.
* fftw/planner.c:
Slight modification for future safety (not necessary now).
1999-03-25 Matteo Frigo <athena@stern.lcs.mit.edu>
* tests/test_main.c, tests/test_main.h, tests/rfftw_test.c,
tests/fftw_test.c, fftw/planner.c:
Added hooks for paranoid verification of every single plan.
1999-03-23 Matteo Frigo <athena@stern.lcs.mit.edu>
* fftw/generic.c:
Array read out of bounds---fixed. Thanks to Ming-Chang Liu.
1999-03-09 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn:
Noted free-ness in "What is FFTW?" description.
1999-03-08 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* threads/fftw_threads.c:
By default, don't even try to specify PTHREAD_SCOPE_SYSTEM, since
it causes problems on @!#%$ IRIX 6.5 (in which
PTHREAD_SCOPE_SYSTEM is not supported, but pthread_attr_setscope
doesn't return an error!!!). Just use the default attributes
(fftw_pthread_attributes_p == NULL).
* threads/fftw_threads.c: Fixed typo in comment.
* NEWS: Added 2.1 news.
1999-03-08 Matteo Frigo <athena@stern.lcs.mit.edu>
* tests/rfftw_test.c, tests/fftw_test.c:
Fixed pow(8192, x) --> pow(8192.0, x) . This failed on
Digital unix, I don't know why.
1999-03-08 Matteo Frigo <athena@stern.lcs.mit.edu>
* ChangeLog: Updated
* configure.in: Updated version number
1999-03-07 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: a_slow_array --> a_bad_array
* doc/fftw.texi:
Removed all reference to performance from "Dynamic Arrays--The
Wrong Way" section.
* doc/fftw.texi:
Clarified output parameter of Fortran multi-dimensional in-place
transforms.
* NEWS, doc/fftw.texi:
Thanks to Erik Scheirer (boom@sonyx.com) for testing the Mach C
threads code.
1999-03-06 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* mpi/fftw_mpi_test.c: Added undocumented --only-parallel flag.
* threads/rfftw_f77_threads.c, threads/fftw_f77_threads.c,
threads/Makefile.am, doc/fftw.texi, NEWS:
Added Fortran-callable wrappers for the multi-threaded routines.
1999-02-25 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* threads/fftw_threads.c, threads/fftw_threads-int.h:
Made pthreads code more tolerant if user doesn't call
fftw_threads_init.
* tests/rfftw_test.c, tests/fftw_test.c, mpi/rfftw_mpi_test.c,
mpi/fftw_mpi_test.c:
Reduced array sizes somewhat for planner tests.
1999-02-24 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Added user thank-you to acknowledgements.
* doc/fftw.texi: Clarified output format of 1d MPI transforms.
* FAQ/fftw-faq.bfnn: Small change.
1999-02-24 fftw <fftw@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: Changed wording regarding VC++5.0.
* doc/texi2html: Fixed bug in index generation
1999-02-24 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: moved configure to fpindex, and added more entries.
* doc/fftw.texi: Added more padding index entries.
* doc/fftw.texi: Objective Caml -> Caml in the index.
* doc/fftw.texi: Added @cindex floating-point precision
* doc/fftw.texi: Updated index.
* doc/fftw.texi:
typo fix: rfftwnd_threads_*_one -> rfftwnd_threads_one_*
* doc/fftw.texi:
Print table of contents at the end, as directed by the texinfo
manual, so that pagination is not screwed up when the TOC has an
odd number of pages.
1999-02-23 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Fixed typo.
* doc/fftw.texi: Indentation fix.
1999-02-22 Matteo Frigo <athena@stern.lcs.mit.edu>
* ChangeLog: Updated
1999-02-22 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: Noted workaround for buggy SGI compilers.
* ChangeLog:
Line-wrapped (I wish you would remember to do this, Matteo).
* gensrc/Makefile.rfftw.am, mpi/Makefile.am, threads/Makefile.am,
gensrc/Makefile.fftw.am:
Got rid of hackery in header creation, since circular dependencies are
gone. Also added prefixed headers to CLEANFILES so they get deleted
by 'make clean'.
* configure.in:
Used xyz for prefix1 instead of just x, to make future conflicts less
likely.
1999-02-22 Matteo Frigo <athena@stern.lcs.mit.edu>
* configure.in: Fix for irix didn't work, let's try this
* ChangeLog: Fixed typo
* ChangeLog: Updated
* configure.in: Accounted for irix thread lossage
* tests/test_main.c:
usage() must normally exit, otherwise the test programs tries to
read argv[] out of bounds.
* doc/Makefile.am: fftw.ps used compressed fonts
* gensrc/Makefile.rfftw.am, gensrc/Makefile.fftw.am:
rfftw.h didn't go into distribution. Fixed
* threads/Makefile.am, gensrc/Makefile.rfftw.am, mpi/Makefile.am,
configure.in, gensrc/Makefile.fftw.am:
Removed circular dependencies
* configure.in: Fixed typo
1999-02-22 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* tests/test_main.c:
Added some new jokes. Also, print out floating-point precision
for -v.
* FAQ/fftw-faq.bfnn: Noted workaround for buggy SGI compilers.
* ChangeLog:
Line-wrapped (I wish you would remember to do this, Matteo).
* gensrc/Makefile.rfftw.am, mpi/Makefile.am, threads/Makefile.am, gensrc/Makefile.fftw.am:
Got rid of hackery in header creation, since circular dependencies are
gone. Also added prefixed headers to CLEANFILES so they get deleted
by 'make clean'.
* configure.in:
Used xyz for prefix1 instead of just x, to make future conflicts less
likely.
1999-02-22 Matteo Frigo <athena@stern.lcs.mit.edu>
* configure.in: Fix for irix didn't work, let's try this
* ChangeLog: Fixed typo
* ChangeLog: Updated
* configure.in: Accounted for irix thread lossage
* tests/test_main.c:
usage() must normally exit, otherwise the test programs tries to
read argv[] out of bounds.
* doc/Makefile.am: fftw.ps used compressed fonts
* gensrc/Makefile.rfftw.am, gensrc/Makefile.fftw.am:
rfftw.h didn't go into distribution. Fixed
* threads/Makefile.am, gensrc/Makefile.rfftw.am, mpi/Makefile.am, configure.in, gensrc/Makefile.fftw.am:
Removed circular dependencies
* configure.in: Fixed typo
1999-02-21 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* NEWS: Feature set for 2.1 is now frozen (I think).
* doc/fftw.texi: slight change
* mpi/Makefile.am, threads/Makefile.am, gensrc/Makefile.fftw.am,
gensrc/Makefile.rfftw.am: Whoops! Don't include
XXX_FFTW_PREFIX_XXX header files in CLEANFILES, because that will
cause 'make clean' to delete irreplaceable files when no prefix is
being used.
* mpi/Makefile.am, threads/Makefile.am, gensrc/Makefile.fftw.am,
gensrc/Makefile.rfftw.am: Fixed installed headers to use
FFTW_PREFIX for their own header inclusions.
* configure.in, doc/fftw.texi, NEWS: Documented
--enable-type-prefix.
* mpi/Makefile.am, tests/Makefile.am, threads/Makefile.am,
gensrc/Makefile.fftw.am, gensrc/Makefile.rfftw.am, acinclude.m4,
configure.in: Use FFTW_PREFIX for all installed files.
* configure.in: Use g77 in preference to fort77.
1999-02-21 Matteo Frigo <athena@stern.lcs.mit.edu>
* tests/Makefile.am: Fixed forgotted XXX_FFTW_NAME_XXX
* configure.in: Allowed user specification of [r]fftw-name
1999-02-21 fftw <fftw@stern.lcs.mit.edu>
* tests/Makefile.am, configure.in, gensrc/Makefile.fftw.am,
gensrc/Makefile.rfftw.am, acinclude.m4: (Preliminary) hack: allow
user to change name of fftw library.
* configure.in: Incremented shared library version number.
* configure.in: Added rfftw_mpi.h to list of files to install for
--enable-mpi.
1999-02-20 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: The ascii and info (but not html) versions of
the FAQ were chopping off the answer to the last question. Rather
than fix the bug, I just added a trailing comment like in the
Linux FAQ, which seems to correct the problem.
* FAQ/fftw-faq.bfnn: Minor fixes and updates for 2.1.
* mpi/rfftw_mpi_test.c, mpi/fftw_mpi.h, mpi/fftw_mpi_test.c,
mpi/fftw_mpi.c: Share plans between forward and backward fftw_mpi
plans (and between other fftw_mpi plans of the same size).
* tests/rfftw_test.c, tests/fftw_test.c: In -p test with rank > 1,
reduce the size of the arrays for the plan.
* mpi/transpose_mpi.c: Got rid of compiler warning (code was okay,
though).
* doc/fftw.texi: small fix.
1999-02-20 fftw <fftw@stern.lcs.mit.edu>
* doc/fftw.texi: Minor tweaks
1999-02-20 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/Makefile.am, doc/rfftwnd.gif: fig2dev gif output stinks;
"manually" add better version of gif figure.
* doc/fftw.texi: Added link.
* doc/Makefile.am: Make sure to distribute rfftwnd.fig.
* doc/fftw.texi: Some post-reorganization grooming.
* configure.in: Whoops! Use $enableval, not $withval, in
AC_ARG_ENABLE.
1999-02-19 Matteo Frigo <athena@stern.lcs.mit.edu>
* doc/Makefile.am, doc/fftw.texi: Added picture to postscript
manual
1999-02-19 fftw <fftw@stern.lcs.mit.edu>
* configure.in: Added fort77 to list of fortran compiler (linux
f2c comes with a program with this name)
* doc/rfftwnd.gif, doc/rfftwnd.fig, doc/Makefile.am:
Reverse-engineered rfftwnd picture from postscirpt to fig, so I
can edit it and produce smaller postscript. (Linux rules!)
* doc/fftw.texi: Restructured manual
1999-02-19 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* fftw/config.h.in, threads/fftw_threads-int.h, configure.in,
doc/fftw.texi, NEWS: Added untested support for Mach C threads.
Also changed three --with options to --enable.
1999-02-19 Matteo Frigo <athena@stern.lcs.mit.edu>
* threads/rfftw_threads_test.c, threads/rfftwnd_threads.c,
threads/rexec2_threads.c, threads/rexec_threads.c,
threads/rfftw_threads.h, threads/fftw_threads_test.c,
threads/fftwnd_threads.c, threads/fftw_threads.c,
threads/fftw_threads.h, threads/executor_threads.c,
threads/fftw_threads-int.h, tests/test_main.c, tests/fftw_test.c,
tests/rfftw_test.c, rfftw/rgeneric.c, rfftw/rplanner.c,
rfftw/rfftwf77.c, rfftw/rfftwnd.c, rfftw/rexec2.c, rfftw/rfftw.h,
mpi/transpose_mpi.c, rfftw/rexec.c, mpi/sched.h, mpi/test_sched.c,
mpi/test_transpose_mpi.c, mpi/rfftw_mpi_test.c, mpi/rfftwnd_mpi.c,
mpi/sched.c, mpi/fftwnd_mpi.c, mpi/rfftw_mpi.h, mpi/fftw_mpi.c,
mpi/fftw_mpi.h, mpi/fftw_mpi_test.c, mpi/TOMS_transpose.h,
matlab/fftw.c, mpi/TOMS_transpose.c, gensrc/variable.ml,
gensrc/variable.mli, gensrc/util.mli, gensrc/twiddle.ml,
gensrc/util.ml, gensrc/to_c.mli, gensrc/symmetry.ml,
gensrc/to_c.ml, gensrc/schedule.ml, gensrc/schedule.mli,
gensrc/number.mli, gensrc/rconfig_prelude, gensrc/magic.ml,
gensrc/number.ml, gensrc/fft.ml, gensrc/genfft.ml,
gensrc/exprdag.mli, gensrc/expr.ml, gensrc/expr.mli,
gensrc/exprdag.ml, gensrc/dag.ml, gensrc/dag.mli,
gensrc/complex.ml, gensrc/complex.mli, gensrc/asched.mli,
gensrc/ast.ml, gensrc/asched.ml, fftw/wisdomio.c,
fortran/f77_test.F, fftw/twiddle.c, fftw/wisdom.c, fftw/rader.c,
fftw/timer.c, fftw/planner.c, fftw/putils.c, fftw/generic.c,
fftw/malloc.c, fftw/fftwf77.c, fftw/fftwnd.c, fftw/fftw-int.h,
fftw/fftw.h.in, fftw/executor.c, fftw/f77_func.h,
fftw/config.h.in, cilk/time_cilk.cilk, doc/fftw.texi,
cilk/fftwnd_cilk.cilk, cilk/test_cilk.cilk,
cilk/executor_cilk.cilk, cilk/fftw_cilk.cilkh, COPYRIGHT,
ChangeLog: Fixed copyright year
1999-02-19 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Minor changes.
* doc/fftw.texi: Various updates.
* doc/fftw.texi: Acknowledged Steven's long-suffering advisor. =)
* doc/fftw.texi: Noted that 1d complex MPI transforms are
supported.
* NEWS: Noted rfftwnd illustration.
* README: Moved threads, mpi, and fortran descriptions to be under
"official" header.
* TODO: Removed parallel rfftw from TODO (it's done).
* doc/rfftwnd.gif, doc/fftw.texi, doc/Makefile.am: Added rfftwnd
illustration to the manual (HTML version only).
1999-02-18 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: rfftwnd_mpi documentation bug fix.
1999-02-16 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Noted library requirements of 1D MPI.
* mpi/fftw_mpi.h, mpi/fftw_mpi.c, doc/fftw.texi: Added scrambled
input/output options (flags) for 1d mpi transforms.
* cilk/Makefile: Don't complain if Makefile.common doesn't exist.
* mpi/fftw_mpi_test.c: Fixed printf.
* mpi/Makefile.am: Made sure headers are included in make dist.
* doc/fftw.texi: Documented 1D MPI transforms in manual.
* mpi/fftw_mpi.c, mpi/fftw_mpi.h, mpi/fftw_mpi_test.c,
mpi/Makefile.am, NEWS: Added MPI 1D FFT for those crazy guys at
Caltech.
* NEWS, doc/fftw.texi: Documented real MPI transforms.
* mpi/rfftw_mpi_test.c: Small fix.
1999-02-15 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* mpi/rfftw_mpi_test.c, mpi/rfftwnd_mpi.c, mpi/fftw_mpi_test.c,
mpi/rfftw_mpi.h, configure.in, mpi/Makefile.am: Added rfftw MPI
transforms.
* mpi/transpose_mpi.h: this header file is now part of fftw_mpi.h
* doc/fftw.texi: fixed quote marks.
* doc/fftw.texi: Fixed typo.
* doc/fftw.texi: Fixed parallel ref. in intro.
* doc/fftw.texi: fixed typo
* doc/fftw.texi: Noted stupid Fortran identifier length
limitation.
* doc/fftw.texi: hyphenation fix
* doc/fftw.texi: Fixed cross-reference.
* doc/fftw.texi: small fix
* doc/fftw.texi: Clarifications in the MPI section.
* doc/fftw.texi: bug fix.
* doc/fftw.texi: Fixed @uref tags.
* NEWS: Noted MPI updates.
* doc/fftw.texi: Added documentation reference to MPI FFTW in
parallel overview.
* mpi/README, doc/fftw.texi: Folded MPI documentation into main
manual.
* mpi/transpose_mpi.c: bug fix: when a process didn't have any
local data, we weren't able to distinguish between in-place and
out-of-place transposes, and were also incorrectly thinking that
all block sizes were equal.
1999-02-14 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* tests/test_main.h, tests/test_main.c, mpi/test_fftwnd_mpi.c,
mpi/time_fftwnd_mpi.c, mpi/fftw_mpi_test.c, configure.in,
mpi/Makefile.am: Use standard fftw test program template for MPI
tests.
* fftw/malloc.c: Whoops!
* fftw/malloc.c: fixed omission from last checkin.
* configure.in: Fixed typo and updated version number to 2.1.
* mpi/transpose_mpi.c, mpi/time_fftwnd_mpi.c,
mpi/test_transpose_mpi.c, mpi/test_fftwnd_mpi.c, mpi/fftwnd_mpi.c,
mpi/fftw_mpi.h: Added option of doing out-of-place transpose, so
that we can take advantage of MPI_Alltoall primitive if the user
provides enough space.
* threads/fftw_threads.c: Don't require system to support
PTHREAD_SCOPE_SYSTEM (although we prefer this over
PTHREAD_SCOPE_PROCESS).
* gensrc/Makefile.fftw.am, gensrc/Makefile.rfftw.am: Include f77
wrapper files in sources.
* mpi/transpose_mpi.c, mpi/test_transpose_mpi.c,
mpi/time_fftwnd_mpi.c, mpi/fftwnd_mpi.h, mpi/sched.c,
mpi/test_fftwnd_mpi.c, mpi/fftw_mpi.h, mpi/fftwnd_mpi.c,
mpi/Makefile.am, mpi/TOMS_transpose.c, mpi/TOMS_transpose.h,
mpi/Makefile, Makefile.am, configure.in: Integrated mpi stuff into
automake/autoconf.
* threads/Makefile.am: Fixed typo in comment.
1999-02-13 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* mpi/transpose_mpi.c, mpi/transpose_mpi.h,
mpi/test_transpose_mpi.c, mpi/time_fftwnd_mpi.c, mpi/sched.h,
mpi/test_fftwnd_mpi.c, mpi/test_sched.c, mpi/fftwnd_mpi.h,
mpi/sched.c, mpi/TOMS_transpose.c, mpi/TOMS_transpose.h,
mpi/fftwnd_mpi.c, mpi/Makefile: Updated MPI routines. The new
implementation is almost completely rewritten from before, and
should (hopefully) be easier to manage and (maybe) faster in some
cases.
* configure.in: Check for pthread_create outside of -lpthread,
since some systems may have threads built into the standard C
libraries.
* fftw/malloc.c: Allow allocation/freeing of 0-size blocks/NULL
pointers (since that is ANSI-okay, after all).
* cilk/executor_cilk.cilk: Use ntwiddle instead of r-1 in case
twiddle policy changes.
* mpi/time_fftwnd_mpi.c: Whoops! don't pass uninitialized out
parameter (shouldn't be a problem in any case since transform is
in-place, but better safe than sorry).
1999-02-11 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Noted necessity of linking threads-using code
with -lpthread or whatever.
* rfftw/rfftwf77.c, fortran/rfftw_f77.c, fortran/fortranize.h,
fortran/fftw_f77.c, fortran/fftw_f77.i, fortran/README,
fortran/f77_test.F, fftw/f77_func.h, fftw/fftwf77.c,
fftw/config.h.in, configure.in, doc/fftw.texi, NEWS, acinclude.m4:
Fortran wrapper functions are now automatically included in the
main FFTW libraries, unless the --without-fortran option is passed
to configure. They are also documented in the main manual.
* doc/fftw.texi: Fixed broken cross-reference.
1999-02-10 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Small fixes to multi-threaded FFTW section.
* threads/README, doc/fftw.texi, NEWS: Documented threads routines
in the main FFTW manual.
* threads/fftw_threads.c: Make sure spawn_loop handles nthreads ==
0.
* threads/fftw_threads-int.h, threads/rfftwnd_threads.c,
threads/executor_threads.c: Set things up so that we could pass
workspace to fftw_many_inplace_threads.
* threads/fftw_threads.c: Improved load-balancing of threads
slightly, although in practice it doesn't seem to make much
difference.
* threads/rfftwnd_threads.c, threads/rexec_threads.c,
threads/rfftw_threads.h, threads/rfftw_threads_test.c: For greater
consistency, make sure "threads" suffix always directly follows
rfftw or rfftwnd.
* threads/rfftwnd_threads.c, threads/rexec2_threads.c,
threads/rexec_threads.c, threads/rfftw_threads.h,
threads/fftw_threads-int.h, threads/fftw_threads.c,
threads/fftwnd_threads.c, threads/executor_threads.c: Cleaned up
loop-parallelizing interface considerably.
* threads/rfftwnd_threads.c, threads/rfftw_threads.h,
threads/rfftw_threads_test.c, threads/rexec2_threads.c,
threads/rexec_threads.c, threads/executor_threads.c,
threads/fftw_threads-int.h, threads/fftw_threads.h, configure.in,
threads/Makefile.am, NEWS: Added first stab at parallel (threads)
rfftw.
* rfftw/rfftwnd.c, rfftw/rexec.c: Slight stride/dist fix (to make
behavior in in-place transforms more in line with what the manual
says),
1999-02-05 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* tests/test_main.c: Noted -x and -f options in -h help.
* threads/executor_threads.c: Yikes! Use ntwiddle instead of r-1
in twiddle_thread. (This would have been a problem if we ever
changed the twiddle policy.)
* threads/fftwnd_threads.c, threads/executor_threads.c,
threads/fftw_threads-int.h, fftw/config.h.in: Use autoconf to
determine if alloca is available and use malloc/free if it is not.
* threads/fftw_threads_test.c: Call fftw_threads_init when
starting up.
* threads/time_threads.c, threads/fftwnd_threads.c,
threads/test_threads.c, threads/fftw_threads.h,
threads/fftw_threads_test.c, threads/executor_threads.c,
threads/fftw_threads-int.h, threads/fftw_threads.c,
threads/Makefile.am, threads/README, tests/test_main.c,
tests/test_main.h, tests/rfftw_test.c, configure.in,
tests/fftw_test.c: Made the threads test program follow the model
of the uniprocessor test programs.
* doc/fftw.texi: Documented --with-threads configure option.
* threads/time_threads.c, threads/Makefile.am, threads/README,
threads/fftw_threads.h, threads/test_threads.c, threads/Makefile,
configure.in, fftw/config.h.in, Makefile.am, NEWS: Autoconfiscated
threads stuff.
1999-02-01 fftw <fftw@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: Added entry about VC++ 5.0
1999-01-29 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* NEWS: Noted improvements to <n> argument for test programs.
* tests/fftw_test.c: Removed unnecessary testing of both real and
imaginary impulses--this is unnecessary since we check linearity
under multiplication by complex scalars.
* tests/test_main.c: (Whoops!) Turn interactive mode back off
when getopt is available.
* tests/test_main.c: Added support for new <n> format to
interactive mode.
1999-01-29 Matteo Frigo <athena@stern.lcs.mit.edu>
* tests/test_main.c, tests/test_main.h, tests/rfftw_test.c,
tests/fftw_test.c, tests/Makefile.am, tests/README, ChangeLog:
Allow specification of dimensions in ND test program.
1998-12-11 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* fftw/malloc.c: Use typedefs consistently for fftw_*_hook.
1998-12-09 Matteo Frigo <athena@stern.lcs.mit.edu>
* gensrc/dag.ml: Changed to avoid warning from ocaml-2.01
1998-11-17 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Updated Cilk URL.
1998-11-11 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* tests/test_main.c: Print FFTW version on -v.
* tests/Makefile.am: Removed explicit -lm -- it is added
automatically by configure when it is available.
1998-10-19 Matteo Frigo <athena@stern.lcs.mit.edu>
* tests/test_main.c: Replaced 2x2 linear system with fib() in
timer iteration. The linear system was converging to 0 in
floating point, and it caused underflow problems.
1998-10-07 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* configure.in: Fixed usage of ` in echo.
1998-10-06 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* configure.in: Got rid of message about enabling the x86 cycle
counter--why are we loudly suggesting a deprecated option?
Interested users can read the manual.
1998-10-01 Matteo Frigo <athena@stern.lcs.mit.edu>
* gensrc/genfft.ml: Changed <athfft.h> -> "athfft.h"
1998-09-29 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn, README: Don't mention the current version
number, so that we don't have to keep updating these files with
each new version.
* README.hacks: Postponed computation of the phase of the moon
until FFTW 17.0.
* doc/fftw.texi: Explained "out of place" in tutorial.
* doc/fftw.texi: Added a couple of clarifications to the
installation on non-Unix section.
* NEWS: Fixed typo.
1998-09-28 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* tests/test_main.c: Deleted some unused variables.
1998-09-28 Matteo Frigo <athena@stern.lcs.mit.edu>
* fftw/wisdom.c, fftw/config.h.in, fftw/executor.c, Makefile.am,
configure.in: Moved version number to configure.in and tweaked
make dist to change config.h with the right version number.
1998-09-27 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn, NEWS: Noted bug fixes for large rfftwnd
transforms in 2.0.1.
* tests/rfftw_test.c: Fixed bug in -s for large multi-dimensional
transforms.
* tests/test_main.c: Added -b flag for testing really large
transforms.
* fftw/fftwnd.c: Initialize nwork to zero (not really necessary,
but it doesn't hurt to make sure things are initialized).
* rfftw/rfftwnd.c: Fixed another parenthesization problem which
caused overflow problems with rank > 2 transforms.
1998-09-26 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* rfftw/rfftwnd.c: Yeow! Integer precision overflow occurs for
final dim. >= 2^16 due to inauspicious parenthesization. Fixed.
1998-09-25 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* NEWS: Some small changes to 2.0.1 release notes.
1998-09-25 Matteo Frigo <athena@stern.lcs.mit.edu>
* gensrc/Makefile.rfftw.am, gensrc/exprdag.ml,
gensrc/Makefile.fftw.am, NEWS, configure.in, ChangeLog: Changed
version numbers for 2.0.1 release.
* tests/fftw_test.c: Added FFTW_OUT_OF_PLACE to flags just in case
we forget it again in the header file.
* gensrc/magic.ml, gensrc/genfft.ml, gensrc/exprdag.ml: Added a
couple of hacks useful for athenafft
1998-09-24 Matteo Frigo <athena@theory.lcs.mit.edu>
* gensrc/magic.ml, gensrc/genfft.ml: Added experimental `athena'
mode
1998-09-23 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Fixed another typo.
1998-09-23 Matteo Frigo <athena@theory.lcs.mit.edu>
* fftw/fftw.h.in, doc/fftw.texi: Added definition of
FFTW_OUT_OF_PLACE and fixed typo.
1998-09-23 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Noted how to compile in single precision in
installation for non-unix section.
1998-09-18 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* fftw/fftwnd.c: Modified buffered transforms to use a skew
(padding) between buffers, and also to do contigous writes instead
of reads when copying result from buffers back to array. Thanks
to Geert van Kempen for the tips.
* fftw/fftw.h.in: Added Andrew Sterian's patch to allow FFTW to be
used as a shared library more easily on Win32.
1998-09-17 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* tests/test_main.c, tests/test_main.h, tests/rfftw_test.c,
tests/fftw_test.c: Added -e flag to use FFTW_ESTIMATE in speed
tests.
1998-09-16 Matteo Frigo <athena@theory.lcs.mit.edu>
* rfftw/rplanner.c, fftw/planner.c: Do not use twiddle(1)
codelets, even if somebody (like me :-)) includes them
accidentally in [r]config.c.
1998-09-15 Matteo Frigo <athena@theory.lcs.mit.edu>
* doc/fftw.texi: Fixed typo 0 <= i instead of 0 < i
1998-09-15 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Added hyphen.
1998-09-15 Matteo Frigo <athena@theory.lcs.mit.edu>
* gensrc/variable.ml, gensrc/number.ml, gensrc/exprdag.ml: Better
hashing scheme for variables. Removed caching of float value of
Numbers since it makes little difference with the new hashing
scheme.
1998-09-15 Matteo Frigo <athena@theory.lcs.mit.edu>
* gensrc/number.ml, gensrc/exprdag.ml: Made oracle smarter (as it
was in 2.0)
1998-09-14 Matteo Frigo <athena@theory.lcs.mit.edu>
* gensrc/variable.mli, gensrc/number.ml, gensrc/variable.ml,
gensrc/Makefile.genfft, gensrc/exprdag.ml: Many, many speed
improvements
1998-09-14 Matteo Frigo <athena@theory.lcs.mit.edu>
* gensrc/Makefile.genfft, gensrc/util.ml: Added timestamp to info
messages
* gensrc/util.ml, gensrc/util.mli, gensrc/genfft.ml,
gensrc/magic.ml, gensrc/exprdag.ml, gensrc/Makefile.genfft: Added
informative messages
* gensrc/variable.mli, gensrc/to_c.ml, gensrc/variable.ml,
gensrc/fft.ml, gensrc/exprdag.ml, gensrc/exprdag.mli,
gensrc/expr.ml, gensrc/expr.mli, gensrc/complex.mli,
gensrc/asched.ml, gensrc/complex.ml: Added LittleSimplifier to do
a first quick simplification pass. This speeds up the algebraic
simplifier a lot.
1998-09-14 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Fixed library ordering for -lrfftw.
1998-09-13 Matteo Frigo <athena@theory.lcs.mit.edu>
* gensrc/number.mli, gensrc/fft.ml, gensrc/number.ml,
gensrc/exprdag.mli, gensrc/complex.mli, gensrc/exprdag.ml,
gensrc/complex.ml: Improved speed of generator
1998-09-11 Matteo Frigo <athena@theory.lcs.mit.edu>
* acinclude.m4: Dec's compiler does not like -malign-double.
1998-09-11 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* acinclude.m4: Make sure ACX_PROG_CC_EGCS is called.
1998-09-11 Matteo Frigo <athena@theory.lcs.mit.edu>
* Makefile.am: Added COPYRIGHT to distribution
* tests/Makefile.am: Added missing dependency
* threads/Makefile, cilk/Makefile, configure.in, ChangeLog,
acinclude.m4: Disabled egcs scheduler.
1998-09-10 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* acinclude.m4: Added ppc/linux flags.
1998-09-10 Matteo Frigo <athena@theory.lcs.mit.edu>
* Makefile.am: Added bootstrap.sh to distributed files
* ChangeLog: Formatted The Right Way
* gensrc/to_c.mli, gensrc/fft.ml, gensrc/to_c.ml,
gensrc/exprdag.ml, gensrc/exprdag.mli, gensrc/Makefile.sources,
gensrc/codelet_prelude, gensrc/Makefile.genfft: Tweaked generator
to print fused mult/add count and more revision infos
1998-09-09 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* threads/README, threads/fftw_threads.h, threads/Makefile,
doc/fftw.texi: Noted that Win32 threads code has been reported as
working.
1998-09-09 Matteo Frigo <athena@theory.lcs.mit.edu>
* threads/executor_threads.c, cilk/executor_cilk.cilk,
gensrc/magic.ml: Fixed parallel transform after X_codelet ->
fftw_X_codelet conversion
1998-09-08 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* ChangeLog: Line-wrapped.
1998-09-08 Matteo Frigo <athena@theory.lcs.mit.edu>
* gensrc/magic.ml, gensrc/genfft.ml, gensrc/Makefile.sources,
gensrc/exprdag.ml, ChangeLog: More experiments with generation of
twiddle factors (disabled by default)
1998-09-08 fftw <fftw@stern.lcs.mit.edu>
* doc/fftw.texi: Added reference to ocaml 2.00
1998-09-07 Matteo Frigo <athena@theory.lcs.mit.edu>
* gensrc/Makefile.sources: Disabled fused madd flags for now
* gensrc/magic.ml, gensrc/genfft.ml, gensrc/Makefile.sources,
gensrc/exprdag.ml: Added option to expand all FMA's explicitly,
even at the cost of increasing the operation count.
* gensrc/number.ml, gensrc/number.mli, gensrc/magic.ml,
gensrc/genfft.ml, gensrc/Makefile.sources, gensrc/exprdag.ml:
Implemented fused-multiply-add rules
1998-09-07 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* fftw/malloc.c: Got rid of COMMA hack.
1998-09-07 Matteo Frigo <athena@theory.lcs.mit.edu>
* rfftw/rgeneric.c, rfftw/rplanner.c, rfftw/rexec2.c,
rfftw/rfftwnd.c, rfftw/.indent.pro, rfftw/rexec.c,
gensrc/genfft.ml, fftw/putils.c, gensrc/.indent.pro,
fftw/planner.c, fftw/fftw-int.h, fftw/fftw.h.in, fftw/.indent.pro,
fftw/executor.c: Alpha-converted X_codelet => fftw_X_codelet to
avoid namespace pollution. Replaced ``for (i = 0; i < m; ++i)''
with ``for (i = m; i > 0; --i)'' in twiddle codelets.
1998-09-05 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* configure.in: Removed redundant inclusion of acinclude.m4.
* acinclude.m4, configure.in: Moved max. optimization checking
into acinclude.m4.
* ChangeLog: Line-wrapped.
* gensrc/codelet_prelude, gensrc/Makefile.fftw.am,
gensrc/Makefile.rfftw.am: Changed from perfect to past tense in
notices about being automatically generated.
* FAQ/fftw-faq.bfnn: Slight change.
* fftw/putils.c, fftw/fftw.h.in: added fftw_sizeof_fftw_real().
1998-09-03 Steven G. Johnson <stevenj@stern.lcs.mit.edu>
* doc/fftw.texi: Fixed bug in documentation of how factors of 11
and 13 may be efficiently handled.
1998-09-02 fftw <fftw@stern.lcs.mit.edu>
* configure.in: Respect existing CFLAGS in the environment if any
1998-09-02 Matteo Frigo <athena@theory.lcs.mit.edu>
* cilk/Makefile, configure.in, acinclude.m4: Added -cpu=pentium et
al. for latest egcs
1998-09-02 fftw <fftw@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: Added FAQ antry about the darned ucbcc
1998-09-01 fftw <fftw@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: Mentioned that matlab computes normalized
FFTs
* fortran/f77_test.F: Used 'implicit none' to be sure to catch
Fortran compilers that don't call cpp.
1998-08-31 fftw <fftw@stern.lcs.mit.edu>
* ChangeLog: Updated changelog
* gensrc/Makefile.rfftw.am, gensrc/Makefile.fftw.am: Added
`automatically generated' notice
* rfftw/rplanner.c, rfftw/rgeneric.c, rfftw/rfftwnd.c,
rfftw/rexec2.c, rfftw/rexec.c, gensrc/rconfig_prelude,
gensrc/config_prelude, configure.in: Tried to be more tolerant of
systems with nonworking ``const''.
1998-08-30 fftw <fftw@stern.lcs.mit.edu>
* gensrc/Makefile.rfftw.am, gensrc/Makefile.fftw.am: Switched
version number of shared library to 2.0.0.
1998-08-28 fftw <fftw@stern.lcs.mit.edu>
* fftw/fftwnd.c: Removed redundant include.
* doc/fftw.texi: Recommend using GNU make.
* cilk/Makefile: use rm -f for make clean.
* doc/fftw.texi: Various small changes.
* Makefile.am: Fixed bug: CVS dir was not removed from
distribution
* threads/Makefile, tests/Makefile.am, mpi/Makefile,
gensrc/Makefile.rfftw.am, gensrc/Makefile.fftw.am,
gensrc/Makefile, cilk/Makefile, Makefile.am: Minor fixes for
distribution
* Makefile.am: Polished `make dist'.
* doc/fftw.texi: Fixed missing word.
* doc/fftw.texi: Changed @detailmenu label. There must be some
bug in emacs, I believe.
* doc/equation-4.gif: Grabbed equation-4.gif again
* fftw/fftwnd.c: Yikes! Bug fix.
* doc/fftw.texi: Minor fixes.
* FAQ/fftw-faq.bfnn: Rewrote answer to "What is FFTW?" question.
* doc/fftw.texi: More fixes.
* doc/fftw.texi: Fixed messed-up equation.
1998-08-27 fftw <fftw@stern.lcs.mit.edu>
* doc/fftw.texi: Slight changes.
* doc/fftw.texi: "What RFFTWND Really Computes" was missing a
complex conjugate in the description of Hermitian symmetry.
* threads/Makefile: Link libraries in the correct order.
* configure.in: Renamed 2.0 to 2.0-beta1 for the release
* doc/fftw.texi, doc/equation-4.gif, doc/Makefile.am: Added html
definition of rfftwnd.
* doc/fftw.texi: Fixed a few typos.
* fftw/putils.c: Fixed improper reference to planner.c (which
causes the whole complex package to be loaded for real transforms)
* ChangeLog: Line-wrapped.
* README.hacks, TODO, README, INSTALL: Updated README and similar
files for 2.0.
* threads/executor_threads.c: Align stack on Linux/x86 with gcc.
* doc/fftw.texi: Noted that complex-to-real transforms overwrite
their input arrays.
* gensrc/makemakefile.sh, gensrc/Makefile.fftw.am,
gensrc/Makefile.am: Makefile.am -> Makefile.fftw.am, for
consistency.
* gensrc/Makefile.rfftw.am: rfftwint.h is gone.
* doc/fftw.texi: More stylistic changes
* doc/fftw.texi: Stylistic changes
* doc/fftw.texi: Added What RFFTWND Really Computes section.
* rfftw/rplanner.c, rfftw/rgeneric.c, rfftw/rfftwnd.c,
rfftw/rfftwint.h, rfftw/rexec2.c, rfftw/rexec.c, fftw/executor.c:
Inlined i386 hacks. This is almost completely portable because of
the new alloca() trick. Code is much cleaner now.
* doc/fftw.texi: Described rfftwnd complex format, and discussed
meaning of stride/dist for in-place transforms.
1998-08-26 fftw <fftw@stern.lcs.mit.edu>
* fftw/rader.c, fftw/planner.c, cilk/test_cilk.cilk,
cilk/executor_cilk.cilk, cilk/Makefile, ChangeLog: Upgraded Cilk
version to 2.0
* doc/fftw.texi: Fixed a couple of typos
* doc/fftw.texi: Added most of rfftwnd reference.
* NEWS: Noted FFTW_THREADSAFE and corresponding new section of the
manual.
* doc/fftw.texi: More changes in the introduction of the
halfcomplex format.
* doc/fftw.texi: Made it clear that halfcomplex applies to
one-dimensional rfftw only.
* doc/texi2html: There is no <MATH> tag in HTML 4.0.
* doc/fftw.texi: Fixed html versions of halfcomplex dfn.
* doc/texi2html, doc/fftw.texi: Added a few missing html formulas
* doc/fftw.texi: Some minor changes. Removed mention of
"halfcomplex" in reference to rfftwnd outputs, since we define
that word in terms of the rfftw output format.
* doc/fftw.texi: Added What RFFTW Really Computes section
* doc/fftw.texi, doc/Makefile.am: Added index
* doc/fftw.texi: Added description of halfcomplex storage.
* tests/README: Noted rfftw_test, and pointed user to manual for
compilation instructions.
1998-08-25 fftw <fftw@stern.lcs.mit.edu>
* NEWS: Noted version 2.0.
* doc/fftw.texi: Slight change.
* doc/fftw.texi: Wrote non-Unix installation section and made a
few other minor changes.
* doc/fftw.texi: Fixed references to "What FFTWND Really
Computes".
* rfftw/rexec.c, fftw/fftw-int.h, fftw/executor.c,
fftw/config.h.in, configure.in: I386_HACK Done Right. The hack
now should work across all generations of gcc/egcs, whether
building a shared library or not.
* doc/fftw.texi: Noted use of fast algorithm for prime sizes in
complex transforms. Got rid of <MATH> tag everywhere (doesn't
seem to be well-defined in the HTML standard).
* rfftw/rfftw.h: Changed rfftw.h to reflect the manual.
* rfftw/rexec.c, fftw/fftw-int.h, fftw/executor.c,
fftw/config.h.in, configure.in: Changed the x86 hack to work also
with the shared library.
* doc/texi2html: @math used to translate to italics, which looked
ugly in HTML; now does nothing.
* doc/fftw.texi: Several small changes. Gave uref's readable
titles. Removed @inforef, which looked ugly in non-info docs.
* doc/fftw.texi: Fixed screwed-up master menu
* doc/fftw.texi: Worked on installation guide
* doc/fftw.texi: Added draft or real-complex reference.
* doc/texi2html, doc/fftw.texi: Upgraded to latest texi2html.
* configure.in: Use -qansialias on RS/6000 (seems to cause a
miniscule improvement).
* doc/fftw.texi: Several small changes.
1998-08-24 fftw <fftw@stern.lcs.mit.edu>
* doc/fftw.texi: Separate wisdom is now used for real-complex.
* doc/fftw.texi: Fixed typo.
* doc/fftw.texi: Noted link requirements for rfftw.
* doc/fftw.texi: Quick Start -> Tutorial. Updated introduction to
reflect extra sections.
* NEWS: Noted dropped op-count routines.
* threads/README: Updated; noted FFTW_THREADSAFE flag.
* threads/time_threads.c, threads/test_threads.c,
threads/fftwnd_threads.c, threads/executor_threads.c: Updated for
FFTW 2.0.
* doc/fftw.texi: Slight changes to introduction.
* doc/fftw.texi: Removed reference to operation counts from
manual.
* rfftw/rplanner.c, rfftw/rfftwnd.c, rfftw/rfftw.h,
gensrc/genfft.ml, fftw/rader.c, fftw/putils.c, fftw/fftwnd.c,
fftw/fftw.h.in, fftw/fftw-int.h: Removed op counts, until we find
a decent way to incorporate them back.
* FAQ/fftw-faq.bfnn: Added entry for broken linuxthreads.
* doc/fftw.texi: Updated introduction
* doc/fftw.texi: Written draft of reference section.
1998-08-23 fftw <fftw@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: My middle initial is "G," not "J."
1998-08-22 fftw <fftw@stern.lcs.mit.edu>
* fftw/malloc.c: Added more paranoia to debugging malloc/free.
* doc/fftw.texi: Changed some wording in threads section and noted
that wisdom import/forget is not threadsafe.
* gensrc/fft.ml: More cosmetic changes
* gensrc/fft.ml, gensrc/complex.mli, gensrc/complex.ml: Cosmetic
changes
* doc/fftw.texi: Started re-adding installation section.
* doc/fftw.texi: Noted that plan destruction is not safe either.
* doc/fftw.texi: Cross-reference and line-length fixes.
* doc/fftw.texi: Updated menus and node references. Emacs
texinfo-mode is great!
* doc/fftw.texi: Re-added "Words of Wisdom" and "Multi-Dimensional
Array Formats" chapters Added chapter on parallel transforms &
thread-safety.
* doc/texi2html: @url{} tags are now converted into hyperlinks.
1998-08-21 fftw <fftw@stern.lcs.mit.edu>
* gensrc/util.mli, gensrc/util.ml, gensrc/symmetry.ml,
gensrc/fft.ml: Fixes to improve speed of generator and op count
for n not squarefree.
1998-08-20 fftw <fftw@stern.lcs.mit.edu>
* doc/fftw.texi: Grammar fix.
* doc/fftw.texi: Don't need to say the number of args.
* doc/fftw.texi: Recommend that quick starts be read in order.
* rfftw/rfftwnd.c: dist parameter for in-place transforms now
works more closely like what you might expect.
* doc/fftw.texi: Various fixes and modifications.
* doc/fftw.texi: Added rfftwnd quick start.
* doc/fftw.texi: public-domain -> freely-available (FFTW, along
with many other FFT routines, is not "public-domain").
* doc/fftw.texi: Minor additions.
* doc/fftw.texi: Wrote rfftw quick start.
* fftw/twiddle.c, fftw/rader.c: Use FFTW_FORWARD instead of a
hard-coded negative sign, in case someone ever needs to change
this sign.
* rfftw/rfftw.h: Recreated rfftw_plan and rfftwnd_plan types.
* doc/fftw.texi: Some more changes to the multi-dimensional
quick-start.
* doc/fftw.texi: Added quick-start for multi-dimensional
transforms.
* doc/fftw.texi: Added 1d complex quick start.
1998-08-19 fftw <fftw@stern.lcs.mit.edu>
* doc/fftw.texi: Changed reference in the introduction--an
introductory book is a better reference for people who don't know
anything about DFTs. Also some minor changes. Alluded to a
License and Copyright section.
* gensrc/symmetry.ml, gensrc/magic.ml, gensrc/fft.ml,
gensrc/exprdag.mli, gensrc/exprdag.ml, gensrc/expr.mli,
gensrc/expr.ml: Implemented three-phase simplifier.
* gensrc/symmetry.ml, gensrc/magic.ml, gensrc/fft.ml: Reset
rader_min to 13, until I understand how to simplify the code
properly.
* gensrc/number.ml, gensrc/magic.ml, gensrc/genfft.ml,
gensrc/fft.ml, gensrc/exprdag.mli, gensrc/exprdag.ml,
gensrc/Makefile.sources, gensrc/Makefile.genfft: Disabled new
convolution hack for n >= 17, since the naive algorithm is better.
The hack is similar to Rader's variant 4 in Tolimieri's book, and
the growth of the operation count is also documented in that book.
* TODO: Updated to reflect the fact that we have now rewritten
rfftw.
* fortran/README: Fixed erroneous listing of rfftwnd.
* fortran/fortranize.h, fortran/README: Various improvements.
* NEWS: Added rfftw Fortran wrappers.
* fortran/fortranize.h, fortran/rfftw_f77.c, fortran/fftw_f77.i,
fortran/fftw_f77.c, fortran/README: Added rfftw wrappers.
1998-08-18 fftw <fftw@stern.lcs.mit.edu>
* gensrc/exprdag.ml, gensrc/expr.ml, gensrc/Makefile.genfft:
Another horrible hack in the generator speeds up n=13 by a lot.
* rfftw/rfftwint.h: Whoops! Deleted extraneous characters.
* rfftw/rplanner.c, rfftw/rgeneric.c, rfftw/rfftwnd.c,
rfftw/rfftwint.h, rfftw/rfftw.h, rfftw/rexec2.c, rfftw/rexec.c,
gensrc/Makefile.rfftw.am: Added invoke_many routine for rfftw, and
split hacks into separate header file (rfftwint.h).
* gensrc/magic.ml, gensrc/genfft.ml, gensrc/fft.ml,
gensrc/exprdag.ml, gensrc/Makefile.sources: Implemented new way of
doing Rader's algorithm.
* NEWS: Noted fftw_one, etcetera.
* ChangeLog: Line-wrapped entries.
* tests/rfftw_test.c, rfftw/rfftwnd.c: Yikes! Bug fix. In the
future, be sure to try running the test program with the -m
option, since the rfftwnd specific planner operates signficantly
differently under FFTW_MEASURE than under FFTW_ESTIMATE.
1998-08-17 fftw <fftw@stern.lcs.mit.edu>
* tests/test_main.c: Also sprach g++: the `gets' function is
dangerous and should not be used.
* rfftw/rfftwnd.c, fftw/rader.c, fftw/malloc.c: Made g++ happy
* rfftw/rplanner.c, fftw/putils.c, ChangeLog: Fixed wrong
arguments in make_node_rgeneric. (Ouch!)
* tests/rfftw_test.c, tests/fftw_test.c, rfftw/rfftwnd.c,
fftw/fftwnd.c, fftw/fftw.h.in, fftw/fftw-int.h: Added
FFTW_THREADSAFE flag, which is intended to guarantee that the plan
be read-only, making it safe to use the same plan in parallel from
multiple threads. Currently, it only has an effect in the
multi-dimensional transforms (the 1d plans are already read-only).
* tests/Makefile.am, rfftw/rfftw.h, rfftw/rexec2.c, rfftw/rexec.c,
fftw/executor.c: Optimized the aligned _many loop. Fixed
alignments in rexec2.c
* rfftw/rexec.c, fftw/fftw-int.h, fftw/executor.c: Reorganized
alignment hacks to be more robust with different compilers and
compiler flags.
* tests/Makefile.am: automake TESTS variable expects the names of
actual executables, not simple 'make' dependencies. Fixed by
overriding 'make check' behavior instead of using TESTS.
* tests/test_main.c, tests/Makefile.am: Added 'make check'
feature, along with flag to test programs to limit the number of
iterations.
* tests/test_main.h, tests/test_main.c, tests/rfftw_test.c,
tests/fftw_test.c, rfftw/rfftwnd.c, rfftw/rfftw.h, rfftw/rexec.c,
fftw/fftwnd.c, fftw/fftw.h.in, fftw/executor.c: Added fftw_one and
friends, and modified the test programs to check them.
* doc/fftw.texi: Capitalization changes, clarifications, and other
minor changes.
* doc/texi2html, doc/fftw.texi: Restructured manual (still
incomplete)
* rfftw/rplanner.c, rfftw/rgeneric.c, rfftw/rfftw.h,
rfftw/rexec.c, fftw/twiddle.c, fftw/timer.c, fftw/rader.c,
fftw/putils.c, fftw/planner.c, fftw/malloc.c, fftw/generic.c,
fftw/fftwnd.c, fftw/fftw-int.h, fftw/executor.c, fftw/config.h.in:
Many cosmetic changes. ``optimized'' rexecutor slightly.
* fftw/rader.c: Calls fftw_executor_simple directly instead of
calling fftw().
* tests/test_main.h, tests/test_main.c, tests/rfftw_test.c: Fixed
(hopefully) a problem with roundoff errors sometimes exceeding the
tolerance.
1998-08-16 fftw <fftw@stern.lcs.mit.edu>
* rfftw/rgeneric.c: ``optimized'' rgeneric codelets (kind of)
* fftw/fftw-int.h, fftw/config.h.in, configure.in: Added separate
--enable-debug-alignment flags for debugging x86 alignments (the
--enable-debug flag also changes the compiler flags, which we
don't want to do).
* rfftw/rplanner.c, fftw/putils.c: Bug fix--make sure to only call
rgeneric codelets for odd n.
* rfftw/rexec2.c, gensrc/Makefile.sources: Fixed x86 alignments.
* tests/test_main.c: -s now interacts with -d 1 in the same way
that -c and -a do.
* NEWS: Slight clarification.
* rfftw/rplanner.c: Planner can now decide on the best place to
use generic codelets.
* fftw/planner.c: Planner now decides the best place to put
generic/Rader codelets.
* fftw/putils.c: Changed message for Rader print_plan.
* tests/rfftw_test.c, fftw/rader.c, fftw/putils.c, fftw/fftw.h.in:
Modified Rader to use only a single plan for forward and backward
transforms of the convolution.
1998-08-15 fftw <fftw@stern.lcs.mit.edu>
* NEWS: Noted the news.
* threads/Makefile, tests/Makefile.am, mpi/Makefile,
matlab/Makefile, gensrc/config, gensrc/README, fftw/fftw-int.h,
doc/fftw.texi, cilk/README, cilk/Makefile, FAQ/fftw-faq.bfnn,
configure.in, README.hacks, Makefile.am, INSTALL: The great
directory renaming: src -> fftw.
* src/twiddle.c, src/rader.c, src/putils.c, src/fftw.h.in,
src/fftw-int.h, src/executor.c: Added sharing of Rader data and
twiddles between different plans (and within the same plan).
* tests/test_main.c, src/malloc.c, src/fftw.h.in: When debugging
is enabled, keep track of the peak memory usage (and report it in
the test programs).
* src/rader.c: Rader is now prepared to share data between forward
and backward transforms.
* src/rader.c, src/fftw.h.in, src/fftw-int.h, src/executor.c:
Whoops, forgot to add rader.c to the repository. Also got rid of
an unused variable and include prototypes for the *_ops functions
in fftw-int.h.
* src/twiddle.c, src/putils.c, src/planner.c, src/fftw.h.in,
src/fftw-int.h, src/executor.c, gensrc/Makefile.am: Added Rader
codelets to handle large prime factors.
1998-08-14 fftw <fftw@stern.lcs.mit.edu>
* rfftw/rgeneric.c: rgeneric seems to work!
* rfftw/rgeneric.c: Fixed yet another bug in rgeneric.
* rfftw/rexec.c: Fixed wrong union field.
* src/putils.c, src/planner.c, src/fftw.h.in, src/fftw-int.h,
rfftw/rplanner.c, rfftw/rgeneric.c, rfftw/rexec.c,
gensrc/Makefile.rfftw.am: Implemented generic codelet. (inverse
does not work yet)
* src/putils.c, src/generic.c, src/fftw.h.in, src/fftw-int.h,
rfftw/rplanner.c, rfftw/rfftw.h, rfftw/rexec2.c, rfftw/rexec.c:
Split NOTW from HC2REAL and TWIDDLE from HC2HC, to avoid horrible
type confusion and let me modify the various codelts type
separately
* tests/rfftw_test.c: Fixed bug in in-place testnd. (It's working
now...hooray!)
* tests/test_main.h: CHECK now calls fftw_die instead of exit
(mainly to make it easier to breakpoint).
* src/wisdom.c, src/twiddle.c, src/timer.c, src/putils.c,
src/planner.c, src/malloc.c, src/generic.c, src/fftwnd.c,
src/fftw.h.in, src/fftw-int.h, src/config.h.in, src/.indent.pro,
rfftw/rplanner.c, rfftw/rfftwnd.c, rfftw/rfftw.h,
rfftw/.indent.pro, gensrc/.indent.pro: Moved code around to avoid
unnecessary linking dependencies.
* tests/rfftw_test.c, src/putils.c, src/planner.c, src/generic.c,
src/fftw-int.h, src/.indent.pro, rfftw/rplanner.c,
rfftw/rfftwnd.c, rfftw/rfftw.h, rfftw/rexec2.c, rfftw/rexec.c,
rfftw/.indent.pro, gensrc/Makefile.am, gensrc/.indent.pro:
Splitted planner.c into two files, so that the liker does not load
the complex codelets if only rfftw is used. Renamed
rfftw_plan->fftw_plan, since they are the same and we do not seem
able to maintain consistency internally.
* ChangeLog: Updated changelog
* src/executor.c, rfftw/rexec2.c: Removed redundant test
* tests/rfftw_test.c, rfftw/rfftwnd.c: Fixed more bugs in in-place
rfftwnd (not done yet...sigh).
* rfftw/rfftwnd.c, rfftw/rexec2.c, rfftw/rexec.c: Fixed bug in
rfftwnd for ((n+1)/2)%4 == 0.
1998-08-13 fftw <fftw@stern.lcs.mit.edu>
* rfftw/rexec2.c: Removed redundant statement.
* tests/test_main.c: test -d 1 -a now uses nd routines, consistent
with -d 1 -c <n>.
* src/malloc.c: Need to flush(stdout) before printing to stderr,
or messages sometimes come in the wrong order. Also, should pass
EXIT_FAILURE instead of 1 to exit().
* src/executor.c, rfftw/rexec.c: Fixed those damned alignments.
* tests/test_main.h, tests/test_main.c, tests/rfftw_test.c,
tests/fftw_test.c: Multi-dimensional tests are getting closer to
working...
* rfftw/rfftwnd.c, rfftw/rexec2.c: Bug fixes.
* src/fftw-int.h, src/executor.c, rfftw/rexec.c, gensrc/to_c.ml,
gensrc/magic.ml, gensrc/genfft.ml, gensrc/Makefile.sources: Added
automatic alignment checker --- this will make life easier on the
x86
* src/wisdom.c: Fixed incorrect order of arguments.
* src/wisdom.c, src/twiddle.c, src/planner.c, src/fftw-int.h,
src/executor.c, src/.indent.pro, rfftw/rplanner.c,
rfftw/rfftwnd.c, rfftw/rexec2.c, rfftw/rexec.c, rfftw/.indent.pro,
configure.in: Added extra wisdom flag. Renamed to V2.0.
* tests/Makefile.am: Registered testmain.h with automake, so that
it gets distributed
* Makefile.am: Compile rfftw before tests (otherwise make fails)
* tests/rfftw_test.c: Fixed in-place testing bug.
* tests/rfftw_test.c: Fixed bug in test.
* tests/rfftw_test.c: First version of rfftw_test (incomplete).
* tests/test_main.h, tests/test_main.c, tests/fftw_test.c,
tests/Makefile.am, rfftw/rfftwnd.c: Initial version of rfftw_test
(incomplete).
* gensrc/Makefile: 'make clean' now gets rid of files from aborted
make install.
* gensrc/Makefile.rfftw.am: Added rfftwnd & friends to makefile.
* tests/test_main.h, tests/test_main.c, tests/fftw_test.c,
tests/Makefile.am: Split off main portion of fftw_test.c so that
it can be reused for rfftw_test.
* src/fftwnd.c, src/fftw-int.h, rfftw/rfftwnd.c, rfftw/rfftw.h,
rfftw/rexec2.c, rfftw/rexec.c: Added preliminary rfftwnd.c,
modifying other files as necessary.
* gensrc/number.mli, gensrc/number.ml, gensrc/exprdag.ml,
gensrc/expr.mli, gensrc/expr.ml: Added post-optimization pass to
simplify K1*(K2*A+K3*B), where Ki is a number
* rfftw/rfftw.h, rfftw/rexec2.c, rfftw/rexec.c: Added rexec2 in
preparation for rfftwnd transforms.
* rfftw/README: Removed out-of-date rfftw/README. We will need to
add a couple of sections to the main manual.
1998-08-12 fftw <fftw@stern.lcs.mit.edu>
* src/twiddle.c, src/planner.c, src/fftw.h.in, src/fftw-int.h,
src/executor.c, rfftw/test_rfftw.c, rfftw/time_rfftw.c,
rfftw/rfftw.h, rfftw/rplanner.c, rfftw/rfftw.c, rfftw/rexec.c,
rfftw/Makefile.am, gensrc/rconfig_prelude, gensrc/makesources.sh,
gensrc/makerconfig.sh, gensrc/makemakefile.sh,
gensrc/makeconfig.sh, gensrc/install.sh, gensrc/config,
gensrc/config_prelude, gensrc/Makefile.rfftw.am,
gensrc/Makefile.am, gensrc/Makefile, configure.in: First version
of rfftw executor and friends.
* gensrc/config, gensrc/Makefile.sources: Updated for real
transforms
* gensrc/polygen.ml, gensrc/poly.ml, gensrc/factorizer.ml,
gensrc/Makefile.genfft: Removed old unused files
* gensrc/variable.mli, gensrc/variable.ml, gensrc/symmetry.ml,
gensrc/genfft.ml, gensrc/fft.ml, gensrc/complex.mli,
gensrc/complex.ml, gensrc/Makefile.genfft: Added hc2hc_backward
codelets.
INCOMPATIBLE CHANGE: hc2hc codelets are marked FFTW_HC2HC instead
of FFTW_HC2HC_FORWARD and FFTW_HC2HC_BACKWARD. The direction is
given by the dir flag.
* gensrc/schedule.ml: Added some comments
* gensrc/schedule.ml, gensrc/dag.mli, gensrc/dag.ml: Changed
scheduler to work properly with DIF codelets.
* gensrc/variable.mli, gensrc/variable.ml, gensrc/magic.ml,
gensrc/genfft.ml, gensrc/dag.ml, gensrc/Makefile.genfft: Removed
old junk code.
* gensrc/twiddle.ml, gensrc/genfft.ml, gensrc/fft.ml,
gensrc/Makefile.genfft: Separated twiddle policies into new file.
Added DIF twiddle code.
1998-08-11 fftw <fftw@stern.lcs.mit.edu>
* gensrc/variable.mli, gensrc/variable.ml, gensrc/makeconfig.sh,
gensrc/genfft.ml, gensrc/fft.ml: Added hc2real codelets
* gensrc/variable.ml, gensrc/fft.ml: Fixed a couple of bugs in the
generator
1998-08-10 fftw <fftw@stern.lcs.mit.edu>
* gensrc/variable.mli, gensrc/variable.ml, gensrc/to_c.mli,
gensrc/to_c.ml, gensrc/genfft.ml, gensrc/fft.ml,
gensrc/complex.mli, gensrc/complex.ml: Implemented hc2hc-forward
pass (not tested yet)
* gensrc/to_c.mli, gensrc/to_c.ml, gensrc/genfft.ml: renamed
confusing function `make_unparser'
* gensrc/variable.mli, gensrc/variable.ml, gensrc/genfft.ml,
gensrc/fft.ml, gensrc/.indent.pro: genfft now generates real2hc
codelets
1998-08-08 fftw <fftw@stern.lcs.mit.edu>
* threads/fftwnd_threads.c, tests/fftw_test.c, src/wisdom.c,
src/twiddle.c, src/planner.c, src/malloc.c, rfftw/rfftw.c,
gensrc/genfft.ml: Reverted NULL -> (foo *) 0
* threads/fftwnd_threads.c, tests/fftw_test.c, src/wisdom.c,
src/twiddle.c, src/planner.c, src/malloc.c, rfftw/rfftw.c,
gensrc/makeconfig.sh, gensrc/genfft.ml: (foo *) 0 -> NULL, since
the former is technically non-portable (it assumes that a NULL
pointer is equivalent to the cast of an integer 0).
1998-08-07 fftw <fftw@stern.lcs.mit.edu>
* ChangeLog: Updated changelog
* configure.in: test $CC is incorrect if CC contains a space.
Fixed to test "$CC"
* doc/fftw.texi: configure -> ./configure
1998-08-06 fftw <fftw@stern.lcs.mit.edu>
* src/wisdomio.c, src/common_io.c, gensrc/Makefile.am: Changed
common_io.c -> wisdomio.c to meet 8.3 filename restriction.
(sigh)
1998-08-02 fftw <fftw@stern.lcs.mit.edu>
* src/fftw-int.h: Got rid of PASTE(x,FFTW_REAL_SUFFIX) since
invoking macros with empty arguments (e.g. the default value of
FFTW_REAL_SUFFIX) produces undefined behavior in ANSI C (the 1989
ISO standard). (The C9X standard will fix this.)
1998-07-31 fftw <fftw@stern.lcs.mit.edu>
* tests/fftw_test.c: main() now returns 0 instead of calling
exit(0).
1998-07-28 fftw <fftw@stern.lcs.mit.edu>
* configure.in: Note default CFLAGS in configure message when
machine is unknown.
* doc/fftw.texi: Added more concrete example of how to save &
restore plans using wisdom.
1998-07-03 fftw <fftw@stern.lcs.mit.edu>
* threads/fftw_threads.h: Noted that nthreads is modified by the
spawn_loop macro.
1998-06-25 fftw <fftw@stern.lcs.mit.edu>
* FAQ/fftw-faq.bfnn: Noted that you shouldn't recreate the plan
before every transform.
1998-06-15 fftw <fftw@stern.lcs.mit.edu>
* src/fftw-int.h: Fixed bug in pentium timer runes
1998-06-14 fftw <fftw@stern.lcs.mit.edu>
* doc/fftw.texi: Fixed em-dash bugs introduced in last revision.
1998-06-13 fftw <fftw@stern.lcs.mit.edu>
* AUTHORS: Added newline to end of file.
1998-06-12 fftw <fftw@stern.lcs.mit.edu>
* doc/Makefile.am, configure.in, Makefile.am: Minor fixes
* doc/fftw.texi, doc/Makefile.am, Makefile.am: Added html docs to
make dist
* doc/fftw.texi: Fixed for latest version of texinfo (3.12)
* bootstrap.sh: Fixed bootstrap.sh to interact properly with
automake
* doc/Makefile.am, Makefile.am, ChangeLog: Fixed distribution
policy
* doc/fftw.texi, doc/Makefile.am, doc/Makefile, configure.in,
Makefile.am: Put documentation under automake control.
1998-06-11 fftw <fftw@stern.lcs.mit.edu>
* NEWS: V, V. -> Version
* INSTALL: Added FFTW-specific introduction. I'm still not happy
with this file.
* Makefile.am: Added cilk/ to list of distributed directories
* doc/fftw.texi: Minor fixes.
* tests/fftw_test.c: Used the word "consistency" rather than
"accuracy" when describing the output of fftw_test -t.
* threads/time_threads.c, threads/test_threads.c,
threads/fftwnd_threads.c, threads/fftw_threads.h,
threads/executor_threads.c, threads/README, tests/fftw_test.c,
src/twiddle.c, src/timer.c, src/planner.c, src/generic.c,
src/fftwnd.c, src/fftw.h.in, src/fftw-int.h, src/executor.c,
rfftw/time_rfftw.c, rfftw/test_rfftw.c, rfftw/rfftwnd.c,
rfftw/rfftw.c, rfftw/rfftw.h, rfftw/README,
mpi/transpose_mpi/README, mpi/time_fftwnd_mpi.c,
mpi/test_fftwnd_mpi.c, mpi/fftwnd_mpi.h, mpi/fftwnd_mpi.c,
mpi/README, matlab/fftw.c, gensrc/to_c.ml, gensrc/genfft.ml,
fortran/fftw_f77.c, fortran/README, doc/fftw.texi,
cilk/time_cilk.cilk, cilk/test_cilk.cilk, cilk/fftwnd_cilk.cilk,
cilk/fftw_cilk.cilkh, cilk/executor_cilk.cilk, NEWS: Renamed
FFTW_COMPLEX, FFTW_REAL -> fftw_complex, fftw_real.
* src/malloc.c, src/config.h.in, configure.in: Added
--enable-debug option; supercedes old MALLOC_DEBUG flag in
malloc.c.
* gensrc/Makefile.am: Fixed bug in makefile
* tests/Makefile.am, rfftw/Makefile.am, configure.in, ChangeLog:
Added libtool support
1998-06-11 Matteo Frigo <athena@glauke.lcs.mit.edu>
* Added libtool support for shared libraries