Home | Back

FFTW 3.3.1 * Changes since 3.3.1-beta1:      - Reduced planning time in estimate mode for sizes with large     prime factors.   - Added AVX autodetection under Visual Studio.  Thanks Carsten     Steger for submitting the necessary code.   - Modern Fortran interface now uses a separate fftw3l.f03 interface     file for the long double interface, which is not supported by     some Fortran compilers.  Provided new fftw3q.f03 interface file     to access the quadruple-precision FFTW routines with recent     versions of gcc/gfortran. * Added support for the NEON extensions to the ARM ISA.  (Note to beta   users: an ARM cycle counter is not yet implemented; please contact   fftw@fftw.org if you know how to do it right.) * MPI code now compiles even if mpicc is a C++ compiler; thanks to   Kyle Spyksma for the bug report. FFTW 3.3 * Changes since 3.3-beta1:   - Compiling OpenMP support (--enable-openmp) now installs a     fftw3_omp library, instead of fftw3_threads, so that OpenMP     and POSIX threads (--enable-threads) libraries can be built     and installed at the same time.   - Various minor compilation fixes, corrections of manual typos, and     improvements to the benchmark test program. * Add support for the AVX extensions to x86 and x86-64.  The AVX code   works with 16-byte alignment (as opposed to 32-byte alignment),   so there is no ABI change compared to FFTW 3.2.2. * Added Fortran 2003 interface, which should be usable on most modern   Fortran compilers (e.g. gfortran) and provides type-checked access   to the the C FFTW interface.  (The legacy Fortran-77 interface is   still included also.) * Added MPI distributed-memory transforms.  Compared to 3.3alpha,   the major changes in the MPI transforms are:     - Fixed some deadlock and crashing bugs.     - Added Fortran 2003 interface.     - Added new-array execute functions for MPI plans.     - Eliminated use of large MPI tags, since Cray MPI requires tags < 2^24;       thanks to Jonathan Bentz for the bug report.     - Expanded documentation.     - 'make check' now runs MPI tests     - Some ABI changes - not binary-compatible with 3.3alpha MPI. * Add support for quad-precision __float128 in gcc 4.6 or later (on x86.   x86-64, and Itanium).  The new routines use the fftwq_ prefix. * Removed support for MIPS paired-single instructions due to lack of   available hardware for testing.  Users who want this functionality   should continue using FFTW 3.2.x.  (Note that FFTW 3.3 still works   on MIPS; this only concerns special instructions available on some   MIPS chips.) * Removed support for the Cell Broadband Engine.  Cell users should   use FFTW 3.2.x. * New convenience functions fftw_alloc_real and fftw_alloc_complex   to use fftw_malloc for real and complex arrays without typecasts   or sizeof. * New convenience functions fftw_export_wisdom_to_filename and   fftw_import_wisdom_from_filename that export/import wisdom   to a file, which don't require you to open/close the file yourself. * New function fftw_cost to return FFTW's internal cost metric for   a given plan; thanks to Rhys Ulerich and Nathanael Schaeffer for the   suggestion. * The --enable-sse2 configure flag now works in both double and single   precision (and is equivalent to --enable-sse in the latter case). * Remove --enable-portable-binary flag: we new produce portable binaries   by default. * Remove the automatic detection of native architecture flag for gcc   which was introduced in fftw-3.1, since new gcc supports -mtune=native.   Remove the --with-gcc-arch flag; if you want to specify a particlar   arch to configure, use ./configure CC="gcc -mtune=...". * --with-our-malloc16 configure flag is now renamed --with-our-malloc. * Fixed build problem failure when srand48 declaration is missing;   thanks to Ralf Wildenhues for the bug report. * Fixed bug in fftw_set_timelimit: ensure that a negative timelimit   is equivalent to no timelimit in all cases.  Thanks to William Andrew   Burnson for the bug report. * Fixed stack-overflow problem on OpenBSD caused by using alloca with   too large a buffer. FFTW 3.2.2 * Improve performance of some copy operations of complex arrays on   x86 machines. * Add configure flag to disable alloca(), which is broken in mingw64. * Planning in FFTW_ESTIMATE mode for r2r transforms became slower   between fftw-3.1.3 and 3.2.  This regression has now been fixed. FFTW 3.2.1 * Performance improvements for some multidimensional r2c/c2r transforms;   thanks to Eugene Miloslavsky for his benchmark reports. * Compile with icc on MacOS X, use better icc compiler flags. * Compilation fixes for systems where snprintf is defined as a macro;   thanks to Marcus Mae for the bug report. * Fortran documentation now recommends not using dfftw_execute,   because of reports of problems with various Fortran compilers;   it is better to use dfftw_execute_dft etcetera. * Some documentation clarifications, e.g. of fact that --enable-openmp   and --enable-threads are mutually exclusive (thanks to Long To),   and document slightly odd behavior of plan_guru_r2r in Fortran   (thanks to Alexander Pozdneev). * FAQ was accidentally omitted from 3.2 tarball. * Remove some extraneous (harmless) files accidentally included in   a subdirectory of the 3.2 tarball. FFTW 3.2 * Worked around apparent glibc bug that leads to rare hangs when freeing   semaphores. * Fixed segfault due to unaligned access in certain obscure problems   that use SSE and multiple threads. * MPI transforms not included, as they are still in alpha; the alpha   versions of the MPI transforms have been moved to FFTW 3.3alpha1. FFTW 3.2alpha3 * Performance improvements for sizes with factors of 5 and 10. * Documented FFTW_WISDOM_ONLY flag, at the suggestion of Mario   Emmenlauer and Phil Dumont. * Port Cell code to SDK2.1 (libspe2), as opposed to the old libspe1 code. * Performance improvements in Cell code for N < 32k, thanks to Jan Wagner   for the suggestions. * Cycle counter for Sun x86_64 compiler, and compilation fix in cycle   counter for AIX/xlc (thanks to Jeff Haferman for the bug report). * Fixed incorrect type prefix in MPI code that prevented wisdom routines   from working in single precision (thanks to Eric A. Borisch for the report). * Added 'make check' for MPI code (which still fails in a couple corner   cases, but should be much better than in alpha2). * Many other small fixes. FFTW 3.2alpha2 * Support for the Cell processor, donated by IBM Research; see README.Cell   and the Cell section of the manual. * New 64-bit API: for every "plan_guru" function there is a new "plan_guru64"   function with the same semantics, but which takes fftw_iodim64 instead of   fftw_iodim.  fftw_iodim64 is the same as fftw_iodim, except that it takes   ptrdiff_t integer types as parameters, which is a 64-bit type on   64-bit machines.  This is only useful for specifying very large transforms   on 64-bit machines.  (Internally, FFTW uses ptrdiff_t everywhere   regardless of what API you choose.) * Experimental MPI support.  Complex one- and multi-dimensional FFTs,   multi-dimensional r2r, multi-dimensional r2c/c2r transforms, and   distributed transpose operations, with 1d block distributions.   (This is an alpha preview: routines have not been exhaustively   tested, documentation is incomplete, and some functionality is   missing, e.g. Fortran support.)  See mpi/README and also the MPI   section of the manual. * Significantly faster r2c/c2r transforms, especially on machines with SIMD. * Rewritten multi-threaded support for better performance by   re-using a fixed pool of threads rather than continually   respawning and joining (which nowadays is much slower). * Support for MIPS paired-single SIMD instructions, donated by   Codesourcery. * FFTW_WISDOM_ONLY planner flag, to create plan only if wisdom is   available and return NULL otherwise. * Removed k7 support, which only worked in 32-bit mode and is   becoming obsolete.  Use --enable-sse instead. * Added --with-g77-wrappers configure option to force inclusion   of g77 wrappers, in addition to whatever is needed for the   detected Fortran compilers.  This is mainly intended for GNU/Linux   distros switching to gfortran that wish to include both   gfortran and g77 support in FFTW. * In manual, renamed "guru execute" functions to "new-array execute"   functions, to reduce confusion with the guru planner interface.   (The programming interface is unchanged.) * Add missing __declspec attribute to threads API functions when compiling   for Windows; thanks to Robert O. Morris for the bug report. * Fixed missing return value from dfftw_init_threads in Fortran;   thanks to Markus Wetzstein for the bug report. FFTW 3.1.1 * Performance improvements for Intel EMT64. * Performance improvements for large-size transforms with SIMD. * Cycle counter support for Intel icc and Visual C++ on x86-64. * In fftw-wisdom tool, replaced obsolete --impatient with --measure. * Fixed compilation failure with AIX/xlc; thanks to Joseph Thomas. * Windows DLL support for Fortran API (added missing __declspec(dllexport)). * SSE/SSE2 code works properly (i.e. disables itself) on older 386 and 486   CPUs lacking a CPUID instruction; thanks to Eric Korpela. FFTW 3.1 * Faster FFTW_ESTIMATE planner. * New (faster) algorithm for REDFT00/RODFT00 (type-I DCT/DST) of odd size. * "4-step" algorithm for faster FFTs of very large sizes (> 2^18). * Faster in-place real-data DFTs (for R2HC and HC2R r2r formats). * Faster in-place non-square transpositions (FFTW uses these internally   for in-place FFTs, and you can also perform them explicitly using   the guru interface). * Faster prime-size DFTs: implemented Bluestein's algorithm, as well   as a zero-padded Rader variant to limit recursive use of Rader's algorithm. * SIMD support for split complex arrays. * Much faster Altivec/VMX performance. * New fftw_set_timelimit function to specify a (rough) upper bound to the   planning time (does not affect ESTIMATE mode). * Removed --enable-3dnow support; use --enable-k7 instead. * FMA (fused multiply-add) version is now included in "standard" FFTW,   and is enabled with --enable-fma (the default on PowerPC and Itanium). * Automatic detection of native architecture flag for gcc.  New   configure options: --enable-portable-binary and --with-gcc-arch=<arch>,   for people distributing compiled binaries of FFTW (see manual). * Automatic detection of Altivec under Linux with gcc 3.4 (so that   same binary should work on both Altivec and non-Altivec PowerPCs). * Compiler-specific tweaks/flags/workarounds for gcc 3.4, xlc, HP/UX,   Solaris/Intel. * Various documentation clarifications. * 64-bit clean.  (Fixes a bug affecting the split guru planner on   64-bit machines, reported by David Necas.) * Fixed Debian bug #259612: inadvertent use of SSE instructions on   non-SSE machines (causing a crash) for --enable-sse binaries. * Fixed bug that caused HC2R transforms to destroy the input in   certain cases, even if the user specified FFTW_PRESERVE_INPUT. * Fixed bug where wisdom would be lost under rare circumstances,   causing excessive planning time. * FAQ notes bug in gcc-3.4.[1-3] that causes FFTW to crash with SSE/SSE2. * Fixed accidentally exported symbol that prohibited simultaneous   linking to double/single multithreaded FFTW (thanks to Alessio Massaro). * Support Win32 threads under MinGW (thanks to Alessio Massaro). * Fixed problem with building DLL under Cygwin; thanks to Stephane Fillod. * Fix build failure if no Fortran compiler is found (thanks to Charles   Radley for the bug report). * Fixed compilation failure with icc 8.0 and SSE/SSE2.  Automatic   detection of icc architecture flag (e.g. -xW). * Fixed compilation with OpenMP on AIX (thanks to Greg Bauer). * Fixed compilation failure on x86-64 with gcc (thanks to Orion Poplawski). * Incorporated patch from FreeBSD ports (FreeBSD does not have memalign,   but its malloc is 16-byte aligned). * Cycle-counter compilation fixes for Itanium, Alpha, x86-64, Sparc,   MacOS (thanks to Matt Boman, John Bowman, and James A. Treacy for   reports/fixes).  Added x86-64 cycle counter for PGI compilers,   courtesy Cristiano Calonaci. * Fix compilation problem in test program due to C99 conflict. * Portability fix for import_system_wisdom with djgpp (thanks to Juan   Manuel Guerrero). * Fixed compilation failure on MacOS 10.3 due to getopt conflict. * Work around Visual C++ (version 6/7) bug in SSE compilation;   thanks to Eddie Yee for his detailed report. Changes from FFTW 3.1 beta 2: * Several minor compilation fixes. * Eliminate FFTW_TIMELIMIT flag and replace fftw_timelimit global with   fftw_set_timelimit function.  Make wisdom work with time-limited plans. Changes from FFTW 3.1 beta 1: * Fixes for creating DLLs under Windows; thanks to John Pavel for his feedback. * Fixed more 64-bit problems, thanks to John Pavel for the bug report. * Further speed improvements for Altivec/VMX. * Further speed improvements for non-square transpositions. * Many minor tweaks. FFTW 3.0.1 * Some speed improvements in SIMD code. * --without-cycle-counter option is removed.  If no cycle counter is found,   then the estimator is always used.  A --with-slow-timer option is provided   to force the use of lower-resolution timers. * Several fixes for compilation under Visual C++, with help from Stefane Ruel. * Added x86 cycle counter for Visual C++, with help from Morten Nissov. * Added S390 cycle counter, courtesy of James Treacy. * Added missing static keyword that prevented simultaneous linkage   of different-precision versions; thanks to Rasmus Larsen for the bug report. * Corrected accidental omission of f77_wisdom.f file; thanks to Alan Watson. * Support -xopenmp flag for SunOS; thanks to John Lou for the bug report. * Compilation with HP/UX cc requires -Wp,-H128000 flag to increase   preprocessor limits; thanks to Peter Vouras for the bug report. * Removed non-portable use of 'tempfile' in fftw-wisdom-to-conf script;   thanks to Nicolas Decoster for the patch. * Added 'make smallcheck' target in tests/ directory, at the request of   James Treacy. FFTW 3.0 Major goals of this release: * Speed: often 20% or more faster than FFTW 2.x, even without SIMD (see below). * Complete rewrite, to make it easier to add new algorithms and transforms. * New API, to support more general semantics. Other enhancements: * SIMD acceleration on supporting CPUs (SSE, SSE2, 3DNow!, and AltiVec). (With special thanks to Franz Franchetti for many experimental prototypes   and to Stefan Kral for the vectorizing generator from fftwgel.) * True in-place 1d transforms of large sizes (as well as compressed   twiddle tables for additional memory/cache savings). * More arbitrary placement of real & imaginary data, e.g. including   interleaved (as in FFTW 2.x) as well as separate real/imag arrays. * Efficient prime-size transforms of real data. * Multidimensional transforms can operate on a subset of a larger matrix,   and/or transform selected dimensions of a multidimensional array. * By popular demand, simultaneous linking to double precision (fftw),   single precision (fftwf), and long-double precision (fftwl) versions   of FFTW is now supported. * Cycle counters (on all modern CPUs) are exploited to speed planning. * Efficient transforms of real even/odd arrays, a.k.a. discrete   cosine/sine transforms (types I-IV).  (Currently work via pre/post   processing of real transforms, ala FFTPACK, so are not optimal.) * DHTs (Discrete Hartley Transforms), again via post-processing   of real transforms (and thus suboptimal, for now). * Support for linking to just those parts of FFTW that you need,   greatly reducing the size of statically linked programs when   only a limited set of transform sizes/types are required. * Canonical global wisdom file (/etc/fftw/wisdom) on Unix, along   with a command-line tool (fftw-wisdom) to generate/update it. * Fortran API can be used with both g77 and non-g77 compilers   simultaneously. * Multi-threaded version has optional OpenMP support. * Authors' good looks have greatly improved with age. Changes from 3.0beta3: * Separate FMA distribution to better exploit fused multiply-add instructions   on PowerPC (and possibly other) architectures. * Performance improvements via some inlining tweaks. * fftw_flops now returns double arguments, not int, to avoid overflows   for large sizes. * Workarounds for automake bugs. Changes from 3.0beta2: * The standard REDFT00/RODFT00 (DCT-I/DST-I) algorithm (used in   FFTPACK, NR, etcetera) turns out to have poor numerical accuracy, so   we replaced it with a slower routine that is more accurate. * The guru planner and execute functions now have two variants, one that   takes complex arguments and one that takes separate real/imag pointers. * Execute and planner routines now automatically align the stack on x86,   in case the calling program is misaligned. * README file for test program. * Fixed bugs in the combination of SIMD with multi-threaded transforms. * Eliminated internal fftw_threads_init function, which some people were   calling accidentally instead of the fftw_init_threads API function. * Check for -openmp flag (Intel C compiler) when --enable-openmp is used. * Support AMD x86-64 SIMD and cycle counter. * Support SSE2 intrinsics in forthcoming gcc 3.3. Changes from 3.0beta1: * Faster in-place 1d transforms of non-power-of-two sizes. * SIMD improvements for in-place, multi-dimensional, and/or non-FFTW_PATIENT   transforms. * Added support for hard-coded DCT/DST/DHT codelets of small sizes; the   default distribution only includes hard-coded size-8 DCT-II/III, however. * Many minor improvements to the manual.  Added section on using the   codelet generator to customize and enhance FFTW. * The default 'make check' should now only take a few minutes; for more   strenuous tests (which may take a day or so), do 'cd tests; make bigcheck'. * fftw_print_plan is split into fftw_fprint_plan and fftw_print_plan, where   the latter uses stdout. * Fixed ability to compile with a C++ compiler. * Fixed support for C99 complex type under glibc. * Fixed problems with alloca under MinGW, AIX. * Workaround for gcc/SPARC bug. * Fixed multi-threaded initialization failure on IRIX due to lack of   user-accessible PTHREAD_SCOPE_SYSTEM there.