Re: [Discuss-gnuradio] am reception examples

[Matteo Campanella]

I digged into the usrp c code, and I have found the following code, that 
basically says we could use 32 bits for tuning on the fpga, but we truncate 
it to 14 - unless there's a good reason for that, we could be much more 
precise in tuning the NCO... again, unless Matt has a good reason for that.

ciao
Matteo

// The FPGA NCOs use a signed 32-bit frequency tuning word,
// but we keep only the most significant 14 bits.

static unsigned int
compute_freq_control_word_fpga (double master_freq, double target_freq,
                               double *actual_freq, bool verbose)
{
 static const int NBITS = 14;

 int   v = (int) rint (target_freq / master_freq * pow (2.0, 32.0));
 // v += 1 << (32 - NBITS - 1);                // add 1/2
 v = (v >> (32 - NBITS)) << (32 - NBITS);      // keep only top NBITS

 *actual_freq = v * master_freq / pow (2.0, 32.0);

 if (verbose)
   fprintf (stderr,
            "compute_freq_control_word_fpga: target = %g  actual = %g
delta = %g\n",
            target_freq, *actual_freq, *actual_freq - target_freq);

 return (unsigned int) v;
}
----- Original Message ----- 
From: "Eric Blossom" <address@hidden>
To: "Matteo Campanella" <address@hidden>
Cc: <address@hidden>
Sent: Sunday, March 05, 2006 3:22 AM
Subject: Re: [Discuss-gnuradio] am reception examples


> On Fri, Mar 03, 2006 at 12:06:01AM +0100, Matteo Campanella wrote:
> > In another script, usrp_wfm_rcv.pl, another method has been used, the
> > usrp.tune, that, according to the tests, does not need any successive
> > adjustment - is there any reason why the am receiver is not written using
> > this method?
>
> usrp_wfm_rcv was written later in the game, and uses the prefered
> method (works with all daughterboards).  Whether or not you need to
> the final software DDS depends on how precisely you need to be on
> frequency.  The WFM signal is > 100 kHz wide, thus an offset of a few
> kHz makes no difference.  For narrow band FM, or AM, etc, you probably
> want to be closer.  Take a look at usrp_nbfm_rcv.py, it uses the
> preferred technique.  Note that if you really are trying to handle AM
> properly you're probably better off building a synchronous receiver or
> some other method that tracks the carrier.
>
> > Another doubt is about optfir.low_pass versus gr.firdes.low_pass - from 
> > the
> > tests I have run, the first one is much faster of the second - is there 
> > any
> > reason to use the second instead of the faster optfir?
>
> optfir uses the Remez / Parks-McClellan design method.
> gr.firdes.low_pass designs filters using the window method.  It all
> depends on what you want.  See any DSP book for details.
>
> Eric