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.

For the fault-tolerance shortage of CFD (Computational Fluid Dynamics)-oriented application development framework, a new fault-tolerance period optimization method was proposed. The method computed the ideal best fault-tolerance period based on the probability model of system's faults, and online determined the occasion of real check points with the consideration of CFD fields output characteristic. The experimental results of three applications show that on the systems with different mean time between faults, compared with the fault-tolerance method based on performing fault-tolerance between fixed steps, the proposed method can always get the best fault-tolerance overheads. Based on this method, user can set the fault-tolerance period with framework interfaces conveniently and reduce the fault-tolerance overheads.

A classifier model based on word terms was proposed to classify Spam Short Messages (SSM). The concept of word-category weight was introduced for representing a word effect of identifying the category a SSM belongs to and a method was put forward to calculate the word-category weight. Based on the word-category weight, a dimension reduction was carried out to get word items set.The Short message-Category Membership Value (SCMV) was used to illustrate how much a SSM belonged to a category, then a classifying algorithm was implemented by computing SCMV and SCMV density. To improve the accuracy of classification and make the word-category weight more reasonable, an word-weight iterative learning procedure was performed. The experimental results show that the proposed model is superior to other classification methods in terms of classification performance and time complexity.