Floating Point to Fixed Point Conversion of C Code

In processors that do not support floating-point instructions, using fixed-point arithmetic instead of floating-point emulation trades off computation accuracy for execution speed. This trade-off is often profitable. In many cases, like embedded systems, low-cost and speed bounds make it the only acceptable option. We present an environment supporting fixed-point code generation from C programs. It allows the user to specify the position of the binary point in the source code and let the converter automatically transform floating-point variables and operations. We demonstrate the validity of our approach on a series of experiments. The results show that, compared to floating-point, fixed-point arithmetic executed on an integer datapath has a limited impact on the accuracy. In the same time the fixed-point code is 3 to 8 times faster than its equivalent floating-point emulation on an integer datapath.