A quantitative analysis of fixed-point LDPC-decoder implementations using hardware-accelerated HDL emulations

Abstract

Using hardware-accelerated HDL emulators of fixed-point implementations has several advantages in comparison to C-based simulations: The high degree of parallelism for example of field-programmable gate-array based hardware accelerators promise an increased emulation throughput. Furthermore, the HDL model of the considered circuit can be used in the following design process making an additional verification dispensable. For a system analysis of different low-density parity-check (LDPC) decoders such an emulator is practically inevitable from a throughput perspective: the outstanding error correction capability of those decoders allowing for bit-error rates (BER) of well below 10-10 requires a simulative decoding of billions of blocks. In this work, an HDL-based emulator is used. The designed HDL model is highly parameterizable and includes an LDPC decoder and high-quality Box-Muller-based white Gaussian-noise generators to create rare error-events. Using this emulator a comparison of the decoding capability of different fixed-point decoder implementations has been performed. Additionally, accurate cost-models are used for estimating the hardware costs of the different decoder implementations which enable an identification of Pareto-optimal decoder implementations. Finally, the achievable emulator throughput is discussed and compared to the simulation throughput of a speed optimized C-model.