Analyzing the Next Generation Software Defined Radio for Future Architectures

Abstract

Commercial and research work in the field of software defined radio (SDR) has produced designs which have been able to deliver the efficiency and computational power needed to process 3G wireless technologies. Though efficient 3G processing has been achieved by these designs, next generation 4G SDR technology requires 10---1000x more computational performance but limits the power budget increase to 2---5x. In this paper, we present a breakdown of the major 4G kernels and analyze two methods of increasing performance and reducing power consumption. Specifically, we consider the effect of SIMD width and reduction in number of register file accesses on the performance and energy consumption of a SDR architecture, SODA. We show that by increasing SIMD width we can gain almost 2---8x performance increase while increasing total energy used by 1---2x for different SIMD widths. We also show that by reducing SIMD register accesses we can reduce the total energy used by 5---20% for the 4G kernels.