sci-libs/fftw

FFTW is a C subroutine library for computing the discrete Fourier transform.

Versions

Slot Version Repository Platforms
0 3.3.10-r1 scientific ~amd64 arm? armv7? ~armv8 ~x86

Metadata

Homepage https://www.fftw.org
Summary FFTW is a C subroutine library for computing the discrete Fourier transform
Description FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions, of arbitrary input size, and of both real and complex data (as well as of even/odd data, i.e. the discrete cosine/sine transforms or DCT/DST) FFTW's performance is typically superior to that of other publicly available FFT software, and is even competitive with vendor-tuned codes. In contrast to vendor-tuned codes, however, FFTW's performance is portable: the same program will perform well on most architectures without modification. Hence the name, "FFTW", which stands for the somewhat whimsical title of "Fastest Fourier Transform in the West."
Upstream documentation https://www.fftw.org/faq
Upstream release notes https://www.fftw.org/release-notes.html
Dependencies (
    build:
    sys-devel/cmake
    virtual/pkg-config
    build+run:
    fortran? (
        sys-libs/libgfortran:=
    )
    openmp? (
        sys-libs/libgomp:=
    )
    mpi? (
        sys-cluster/openmpi
    )
    quadmath? (
        sys-libs/libquadmath:=
    )
)
Downloads https://www.fftw.org/fftw-3.3.10.tar.gz
Licences GPL-2

Choices

OPTIONS

fortran Adds support for Fortran (formerly f77)
mpi
openmp
quadmath Add support for quadruple-precision arithmetic libraries

amd64_cpu_features

avx Optimization for Intel "Sandy Bridge", AMD "Bulldozer" processors (See 'flags:' in /proc/cpuinfo)
avx2 Optimization for Intel "Haswell" and Intel "Broadwell" processors (See 'flags:' in /proc/cpuinfo)
avx512 Optimization for Intel "Knights Landing" processors (See 'flags:' in /proc/cpuinfo)