2
* experiment with compiler flags
3
Special thanks to Oscar Lesta. He suggested some compiler flags
4
for gcc that make a big difference. They shave 10-15% off
5
execution time on some systems. Try some combination of:
10
* If the input data has no imaginary component, use the kiss_fftr code under tools/.
11
Real ffts are roughly twice as fast as complex.
14
* remove some of the butterflies. There are currently butterflies optimized for radices
15
2,3,4,5. It is worth mentioning that you can still use FFT sizes that contain
16
these factors, they just won't be quite as fast. You can decide for yourself
17
whether to keep radix 2 or 4. If you do some work in this area, let me
20
* For platforms where ROM/code space is more plentiful than RAM,
21
consider creating a hardcoded kiss_fft_state. In other words, decide which
22
FFT size(s) you want and make a structure with the correct factors and twiddles.