Jean-Marc, <br><br>in regards to your oversampling idea, the extra processing required may nullify the gains from using DSPLIB over kissfft. <br><br>To be honest, I have not measured the MIPS difference between DSPLIB and kiss FFT, I will try to do that sometime soon to see how much of a difference the intrinsic libraries make. Do you have those numbers already?<br>
<br><br><br><div class="gmail_quote">2010/5/18 Jean-Marc Valin <span dir="ltr"><<a href="mailto:Jean-Marc.Valin@usherbrooke.ca">Jean-Marc.Valin@usherbrooke.ca</a>></span><br><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
<div class="im">Hi Bob,<br>
<br>
A few questions/comments:<br>
<br>
1) It may be possible to use the TI DSP for all of the radix-2 steps in the FFT<br>
and then only apply the radix 3 and 5 in C.<br>
<br>
2) I assume that the sampling is done on the TI chip, so couldn't you just<br>
configure it to work at 51.2 kHz? This would produce frames that are powers of<br>
two and the resulting bit-stream would be perfectly compatible with a decoder<br>
running with the same frame duration (hence 15/16 the actual number of samples)<br>
at 48 kHz.<br>
<br>
Cheers,<br>
<br>
Jean-Marc<br>
</div><div><div></div><div class="h5">Quoting Bob Bang <<a href="mailto:bob.bang2@gmail.com">bob.bang2@gmail.com</a>>:<br>
<br>
> Hello Jean-Marc, I appreciate you taking our feedback in this change.<br>
><br>
> I would be against this new input frame size change as I am developing on<br>
> the TI 55x platform. On this platform it benefits to use the DSPLIB which<br>
> REQUIRES a power of 2 frame size.<br>
><br>
> My current setup is using a 48kHz sample rate and a 128 sample frame size<br>
> (~2.5ms).<br>
<br>
<br>
<br>
<br>
</div></div></blockquote></div><br>