Why can't double precision data in Unified FFT ip get correct results?

Intel® Quartus® Prime Software

Intel® Quartus® Prime Design Software, Design Entry, Synthesis, Simulation, Verification, Timing Analysis, System Design (Platform Designer, formerly Qsys)

Why can't double precision data in Unified FFT ip get correct results?

386 Views

Hi,

I use the single precision option in unifiedfftip. It works well. (256point ，sampling frequency is 12800hz.The input is 3.14e8*sin2pi50t, and the output of FFT IP is -4.0192e10 , which equal to 3.14e8*(256/2)).

But when I change single precision to double precision and change the input data into double precision floating-point numbers of the same size, it can't get correct results.

Do I need to add other designs to realize Double precision fft or Double precision FFT cannot be realized in unifed fft ip?

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.