DFT verses FFT performance for non 2^ sizes

Intel® oneAPI Math Kernel Library

Ask questions and share information with other developers who use Intel® Math Kernel Library.

DFT verses FFT performance for non 2^ sizes

428 Views

I am migrating from the MKLFFT calls to the MKL DFT calls using C++. I have a fft size that is 700K long that requires me to use a fft length of 2^20th. With the DFT call in MKL vs the FFT call will I see a 25% speed increase because I can use the 700K sample fft in the DFT instead of the 2^20th for the MKL FFT?

Link Copied

0 Replies

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.