FFTW is a comprehensive collection of fast C routines for computing the Discrete Fourier Transform (DFT) and various special cases thereof, copyrighted by MIT and distributed under the GNU General Public License. For more information, refer to the FFTW website (fftw.org).
FFTW can compute transforms of real and complex-value arrays of arbitrary size and dimension. AOCL-FFTW is an AMD optimized version of FFTW implementation targeted for AMD EPYC™ CPUs.
Highlights of AOCL-FFTW 5.0
- Support added for using the wisdom feature by default under the –enable-amd-app-opt option
Documentation
- Prior versions: AOCL-FFTW Archive
- Source code: GitHub
Downloads
| File Name | Version | Size | Launch Date | OS | Bitness | Description |
| Binary Packages Compiled with AOCC 5.0 | ||||||
| aocl-fftw-linux-aocc-5.0.0.tar.gz | 5.0 | 17MB | 10/10/2024 | RHEL, Ubuntu, SLES | 64-bit | AOCC compiled AOCL-FFTW library binary package sha256 Checksum: 853e2bd99fafb348a1c1a7a6da1dc57762402193882c1b775409021d8e688abe |
| Binary Packages Compiled with GCC 13.2.1 | ||||||
| aocl-fftw-linux-gcc-5.0.0.tar.gz | 5.0 | 17MB | 10/10/2024 | RHEL, Ubuntu, SLES | 64-bit | GCC compiled AOCL-FFTW library binary package sha256 Checksum: 83fc9fa87c4a72572c3d2f0067a61e15a8851571f591351ab92790d8db20aa83 |