|
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. |