FPGA Intellectual Property
PCI Express*, Networking and Connectivity, Memory Interfaces, DSP IP, and Video IP
Announcements
Intel Support hours are Monday-Fridays, 8am-5pm PST, except Holidays. Thanks to our community members who provide support during our down time or before we get to your questions. We appreciate you!

Need Forum Guidance? Click here
Search our FPGA Knowledge Articles here.
5881 Discussions

output data format of FFT IP core

ElizabethJaison
Beginner
217 Views

Hi,

I was doing the simulation of FFT IP in Quartus Prime (Board selected: intel Altera Arria10GX). The IP configuration is given as shown in the attached snippet. The input data to the IP is in Q17 format. What would be the output data format? would it be also Q17?

0 Kudos
4 Replies
CheePin_C_Intel
Employee
194 Views

Hi,


As I understand it, you have some inquiries related to the FFT IP. For your information, it is recommended for you to perform a Modelsim simulation with your targeted configuration and input data to verify the expected output. Also, Modelsim simulation will help to isolate any functional problem prior to hardware testing. 


By the way, just to ensure we are on the same page, would you mind to further elaborate on the following:


1. What is the Quartus edition that you are using? I understand from the screenshot that you are using version 18.1.


2. Mind further elaborate one the "Q17 format" that you are referring to? 


Please let me know if there is any concern. Thank you.


ElizabethJaison
Beginner
184 Views

Hi,

Thank you for the reply

Like you said i am doing simulation in modelsim and

 1. Version of Quartus prime is 18.1.

 2. In fixed point representation, Q17 format means out of 18 bits of data, MSB bit(18th bit) will be the sign bit and rest of the data will be fractional bits. So if i give the data like this what would be the output format?

 

CheePin_C_Intel
Employee
168 Views

Hi,


Thanks for your clarification. As I look at your IP configuration, you seems to be pruning the output width to 18 bits. With this, configuration, the format should be Q17 as well. You can perform a Modelsim simulation to further verify on this. Note that normally after the FFT operation, there will be bit growth. With pruning to 18 bits output, you should expect magnitude truncation as well as low magnitude samples being pruned off.


Please let me know if there is any concern. Thank you.


CheePin_C_Intel
Employee
151 Views

Hi,


As I understand it, it has been some time since I last heard from you. 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.


Reply