intel fft ip fixed point with fractional bits

[AlexBeasley]

Hi there, 

I am using the Intel (altera) FFT IP core and I have it configured in fixed-point variable streaming mode. Which lets me set the "data width". 

My data is in a fixed point format but it has both decimal and fractional bits (m.n) format. However, I can not see anywhere in the documentation to tell me if fixed-point mode supports data with fractional bits. Can you clarify on this please? 

Thanks 

[Kshitij_Intel]

Hi,

Sharing the documentation. Please go through it.

https://www.intel.com/content/www/us/en/docs/programmable/683374/17-1/variable-streaming-fft.html

https://www.intel.com/content/www/us/en/docs/programmable/683374/17-1/fixed-point-variable-streaming-ffts.html

If you still do not find the answer you are looking then please elaborate your question.

Thank you

Kshitij Goel

[AlexBeasley]

Hi, 

My understanding from the documentation (and using the IP core), is that fixed-point mode is for 2's complement integer data only. Is this true? I really wanted 2's complement fractional data. 

Many thanks 

[Kshitij_Intel]

Hi,

Let's say for m.n eg. 5.11 and your input is 16bits and you are performing 4096 points FFT the output will be 16 bits +13bits = 29bits you should be able to see the output as 18.11.

Thank you

Kshitij Goel

[Kshitij_Intel]

Hi,

We do not receive any response from you to the previous reply that I have provided. This thread will be transitioned to community support. If you have a new question, feel free to open a new thread to get the support from Intel experts. Otherwise, the community users will continue to help you on this thread.

Thank you

Kshitij Goel