Sparse Matrix-Vector multiplication (SpMV) is one of the most significant yet challenging issues in computational science area. It is a memory-bound application whose performance mostly depends on the input matrix and the underlying architecture. Many researchers have paid more attentions on exploring a variety of optimization techniques to SpMV. One of the most promising respects is how to adapt the storage format to satisfy the underlying architecture. Alterative storage formats can largely lessen memory pressure, however, the computational resources are often underutilized.Therefore, a new storage format, which is called Compressed Sparse Row with Segmented Interleave Combination (SIC), is proposed. Stemming from Compressed Sparse Row format (CSR), SIC format employs an interleave combination pattern that combines certain amount of CSR rows to form a new SIC row. In order to further improve performance, segmented processing is also brought in. According to the empirical data, we also develop an automatic SIC-based SpMV suitable for all the matrices. Experimental results show that our approach outperforms the NVIDIA CSR vector kernel, achieving up to 12.6× speedup. It also demonstrates a comparable performance with the Hybrid format, even with the highest 2.89× speedup.

No abstract

With the development of science and technology, intelligent pavement smoothness detection becomes possible. Intelligent IRI (International Roughness Index) detection is one of the important development directions of pavement performance detection. Different from traditional IRI detection, intelligent IRI detection uses smart phones to collect traffic vibration data. There are many vibration indexes in IRI evaluation unit of driving vibration data, and IRI evaluation can be realized by extracting vibration indexes. In this study, the corresponding relationship between pavement vibration data and IRI is preliminarily proved by driving test. The synthetic vibration acceleration index can reflect the change of IRI. The length of IRI evaluation unit reflects different significance of pavement performance, and the evaluation vibration index extracted is different. When the evaluation unit is short, IRI reflects the local pavement performance of the evaluation unit, and the correlation between the minimum value of vehicle synthetic vibration acceleration and IRI is the best. When the evaluation unit is long, IRI reflects the overall pavement performance of the evaluation unit, and the correlation between the average value of the absolute value of the vehicle synthetic vibration acceleration and IRI is the best.