As another naive note, since sincosf seems to be the dominating
function by a large factor, this website might be worth a read:
http://www.devmaster.net/forums/showthread.php?t=5784
I know there is a fast sine and cosine somewhere for filtering, but I
also thought those caused some issues recently with GMSK demodulation?
When converted from floating -> fixed point for transmission, the
error might be swamped by the quantization noise?
The last section of the forum post really is interesting since we
generally do work on more than 1 piece of data at a time, the SIMD
version of calculating sines or cosines might come in handy.
Brian
_______________________________________________
Discuss-gnuradio mailing list
Discuss-gnuradio@gnu.org
http://lists.gnu.org/mailman/listinfo/discuss-gnuradio
