Design and testing of a Software Defined Radio based transceiver on a Graphics Processing Unit

High transmission bit rate in wireless channels gives rise to severe inter-symbol interference (ISI) and this makes the detection task very challenging. In such cases, Near-Maximum-Likelihood (NML) detection gives good performance. This paper describes the Design and Testing of a QPSK transceiver using NML detection on an NVIDIA Graphics Processing Unit (GPU) for Software Defined Radio (SDR) systems. Recent advances in programmable, highly parallel GPUs have enabled high performance general purpose computation. NVIDIA GPU is used for realizing this application. The data is transmitted over a frequency selective channel and experimental results are obtained. All the processing is done onto the NVIDIA GPU and the results obtained are compared for varying Signal to Noise Ratios (SNR) for different channel configurations.