Thank you for your answer Marcus. Do you know when support for
fragmentation of big vectors will arrive in RFNoC, are we talking more than
a year or just a couple of months/weeks?

Best regards
Simon

On Thu, Mar 3, 2016 at 5:20 PM, Marcus Müller <[email protected]>
wrote:

> Dear Simon,
>
> it's actually really just a constraint of how RFNoC packages data for
> transport. It doesn't support fragmenting big vectors (yet), so your vector
> has to fit one packet. Since the maximum size a packet can carry is 9000B,
> and a sc16 complex is 8B long, you only get 9000/8-long FFT output, or
> shorter.
>
> > Ok thanks, so it's a limit in the RFNoC software and not related to
> Ettus FPGA hardware or something like that?
> Now, whether our FPGA code having that limitation is a software or an FPGA
> hardware problem is up for discussion, in my opinion :)
>
> A possible workaround would be writing your own wrapper for the Xilinx IP
> core used to actually do the FFT, which would be able to fragment. But then
> again, the question is what you want to do with the output afterwards.
>
> Best regards,
> Marcus
>
>
> On 03/03/2016 05:10 PM, Simon Olvhammar wrote:
>
> Ok thanks, so it's a limit in the RFNoC software and not related to Ettus
> FPGA hardware or something like that?
> I dont see that limit in regular GNURadio and 8192 channels works fine,
> isnt the packet size also max 9000 there?
> Simon
>
> On Thu, Mar 3, 2016 at 3:45 PM, Marcus D. Leech < <[email protected]>
> [email protected]> wrote:
>
>> On 03/03/2016 05:21 AM, Simon Olvhammar wrote:
>>
>>> Hi,
>>>
>>> I'm wondering what it would take to modify the current FFT RFNoC block
>>> to be able to compute a 8192 channel FFT. Someone that can guide me in the
>>> right direction? I'm a quite experienced programmer, however not in HDL.
>>>
>>> Best regards
>>> Simon
>>>
>>>
>>> The main current stumbling block to large FFTs in RFNOC is that the FFT
>> output has to be able to fit into a single transport packet, and
>>   that is limited to 9000 bytes, which pretty-much limits you to 2048-bin
>> FFTs.  There will be work in the future to allow FFT outputs in
>>   RFNOC to span multiple packets.
>>
>>
>>
>>
>> _______________________________________________
>> Discuss-gnuradio mailing list
>> [email protected]
>> https://lists.gnu.org/mailman/listinfo/discuss-gnuradio
>>
>
>
>
> _______________________________________________
> Discuss-gnuradio mailing 
> [email protected]https://lists.gnu.org/mailman/listinfo/discuss-gnuradio
>
>
>
> _______________________________________________
> Discuss-gnuradio mailing list
> [email protected]
> https://lists.gnu.org/mailman/listinfo/discuss-gnuradio
>
>
_______________________________________________
Discuss-gnuradio mailing list
[email protected]
https://lists.gnu.org/mailman/listinfo/discuss-gnuradio

Reply via email to