Actions
Forum Thread Details
  • State Not Answered
  • Replies 2 replies
  • Subscribers 353 subscribers
  • Views 314 views
  • Users 0 members are here
Related

Floating Point Operator

Former Member

Hello ,

I have 32 bit std_logic_vector signal and want to multiply it by floating point .

e.g

         signal Input : std_logic_vector (31 downto 0 );
         signal number = 0.2 ;
         signal Output: std_logic_vector (31 downto 0 );

          Output <= 0.2 * Input ;



What can be the best solution to do this kind of multiplication ? i have read somewhere that floating point arithmetic operation is not synthesizable so better to use fixed point numbers .
I have used Floating Point Operator . I added in my Block design and connected via DMA. I set the option "float to Fixed " in that IP (assuming I will send floating point value from SDK ). After generating bitstream, I used the DMA function to send the value float 0.2 to TxBufferPtr, But unfortunately I see only 0 input and 0 output :( So floating point cannot be the input for sending value to DMA. What should I do to complete my required task :(
Which operation has to be selected for that IP ?

It would be appreciated if anyone can tell me the proper idea to do that sort of operation .



Thanks

  • 0


      

    Further , I have read that " binary32 (Single Precision Format) u2013 Uses 32 bits, with a 24-bit fraction and 8-bit exponent. " . So I send the value to DMA for S_AXIS for Floating Point IP "Value = 0x1001011". I can see the input on waveform ILA but my output of Floating Point is still "0000000". (Note I select the option in IP float to fixed point "

  • 0

    It might make sense to simplify the design initially so that you can debug one thing at a time. You might start by skipping the DMA and just connecting the floating point IP to the AXI bus. Make sure that you are using the AXI Stream interface. Then try exercising the IP in a simple manner. Once you can verify that the IP core is performing the floating point function you want then you can add the DMA function.

     

    Since this is a Xilinx IP core you may want to take advantage of the Xilinx Community Forums as well.

     

    -Gary