Performance Optimization and Parallelization of Turbo Decoding for Software-Defined Radio
MetadataShow full item record
Research indicates that multiprocessor-based architectures will provide a flexible alternative to hard-wired application-specific integrated circuits (ASICs) suitable to implement the multitude of wireless standards required by mobile devices, while meeting their strict area and power requirements. This shift in design philosophy has led to the software-defined radio (SDR) paradigm, where a significant portion of a wireless standard's physical layer is implemented in software, allowing multiple standards to share a common architecture. Turbo codes offer excellent error-correcting performance, however, turbo decoders are one of the most computationally complex baseband tasks of a wireless receiver. Next generation wireless standards such as Worldwide Interoperability for Microwave Access (WiMAX), support enhanced double-binary turbo codes, which offer even better performance than the original binary turbo codes, at the expense of additional complexity. Hence, the design of efficient double-binary turbo decoder software is required to support wireless standards in a SDR environment. This thesis describes the optimization, parallelization, and simulated performance of a software double-binary turbo decoder implementation supporting the WiMAX standard suitable for SDR. An adapted turbo decoder is implemented in the C language, and numerous software optimizations are applied to reduce its overall computationally complexity. Evaluation of the software optimizations demonstrated a combined improvement of at least 270% for serial execution, while maintaining good bit-error rate (BER) performance. Using a customized multiprocessor simulator, special instruction support is implemented to speed up commonly performed turbo decoder operations, and is shown to improve decoder performance by 29% to 40%. The development of a flexible parallel decoding algorithm is detailed, with multiprocessor simulations demonstrating a speedup of 10.8 using twelve processors, while maintaining good parallel efficiency (above 89%). A linear-log-MAP decoder implementation using four iterations was shown to have 90% greater throughput than a max-log-MAP decoder implementation using eight iterations, with comparable BER performance. Simulation also shows that multiprocessor cache effects do not have a significant impact on parallel execution times. An initial investigation into the use of vector processing to further enhance performance of the parallel decoder software reveals promising results.