A composite sub-optimal approach for hardware implementation of turbo decoder

In Log-MAP turbo decoding, the complicated log exponential sum is often simplified with the Jacobian logarithm which consists of the max operation along with a log-exponential correction function. Although the Max-Log-MAP reduces the complexity of the Jacobian logarithm implementation by omitting the correction function, its performance is inferior to the LogMAP algorithm. Hence, a simple approximation to the correction function is needed to complement the Max-Log-MAP algorithm. In this paper, a combination of Linear Approximation and LUT based implementation is proposed for the correction function to be applied in the Log-MAP algorithm. This method is applied along with 6 bit precision fixed point for decimal values in view of hardware implementation. The performance of this algorithm is compared with Log-MAP and Max-Log-MAP and is shown to have a close approximation to the Log-MAP solution especially at low SNR.