Table Of Contents

Floating-Point to Fixed-Point Conversion

Last Modified: August 8, 2018

To conserve FPGA resources and reduce power consumption, convert the floating-point data types in your design to fixed-point for use on an FPGA.

Quickly convert your floating-point designs to fixed-point to save resources on an FPGA and optimize the performance of your application. The fixed-point data type allows you to specify the exact size and precision of numbers so that an FPGA can use the numbers more efficiently. An interactive conversion tool evaluates your code and provides fixed-point data type suggestions depending on your configuration.

Converting your floating-point design to fixed-point consists of the following phases:

  1. Adapting a Testbench for Fixed-Point ConversionWhen converting a floating-point design to fixed-point, you can adapt an existing testbench, such as the testbench used to test the original floating-point design, to test the output of the converted fixed-point design and make sure it sufficiently represents the output of the original floating-point design.
  2. Converting Data Types to Fixed-Point for Implementation on an FPGABecause resources are limited on an FPGA, convert floating-point data types in your application to fixed-point to conserve resources when you implement the application on an FPGA.

Recently Viewed Topics