Fast Fourier Transforms (FFT)
FFTs for Multiple Needs
FFT functions in one, two, or three dimensions with support for mixed radices (not limited to sizes that are powers of 2). Distributed versions of these FFT functions are used on clusters. Supported functions include:
- One-dimensional versions in single and double precision
- Multidimensional, complex-to-complex, real-to-complex, and real-to-real transforms of arbitrary length
- FFTW interfaces for compatibility with industry-standard APIs
Fourier Transform Functions for Clusters
When single-node performance is insufficient, get support for distributed computation across a cluster of compute nodes.
FFT Performance Boost Benchmarks
Make informed decisions regarding which functions to use in your applications, comparing the performance of Intel® Math Kernel Library to FFTW.