Since baseband processors for Multiple Input and Multiple Output (MIMO) equalization require high throughput and high flexibility, a parallel MIMO detector was proposed for 3GPP-LTE standard based on Software Defined Radio (SDR) methodology, which adopted Single Instruction Multiple Data (SIMD) and Very Long Instruction Word (VLIW) technology to exploit the parallelism on both inter-tone and inner-tone MIMO equalization. Each SIMD lane supported both 16 bit fixed-point and 20 bit floating-point complex vector and matrix operations, met the requirements of power, processing delay and precision for different MIMO configurations. The experimental results show that the proposed MIMO detector is much more efficient and 4×4 matrix inversion rate is up to 95 MInversion/s, which satisfies the requirement of 3GPP-LTE standard. Besides, its programmability and configurability support different algorithms of MIMO equalization.
According to the characteristics of traditional multivariate linear regression method for long processing time and limited memory, a parallel multivariate linear regression forecasting model was designed based on MapReduce for the time-series sample data. The model was composed of three MapReduce processes which were used to solve the eigenvector and standard orthogonal vector of cross product matrix composed by historical data, to forecast the future parameter of the eigenvalues and eigenvectors matrix, and to estimate the regression parameters in the next moment respectively. Experiments were designed and implemented to the validity effectiveness of the proposed parallel multivariate linear regression forecasting model. The experimental results show multivariate linear regression prediction model based on MapReduce has good speedup and scaleup, and suits for analysis and forecasting of large data.