中圖分類號：TP311 文獻標志碼：Ａ DOI: 10.16157/j.issn.0258-7998.244858
中文引用格式： 黃旭東，洪澤，陳振嬌. 稀疏矩陣在C66x上的應用及優化[J]. 電子技術應用，2024，50(11)：23-27.
英文引用格式： Huang Xudong，Hong Ze，Chen Zhenjiao. Application and optimization of sparse matrix vector multiplication on C66x[J]. Application of Electronic Technique，2024，50(11)：23-27.

Application and optimization of sparse matrix vector multiplication on C66x

Abstract： With the explosive development of big data, sparse matrix has become an important part of machine learning and edge computing. In the field of machine learning, sparse matrix of data sets can not only save information but also save memory, which has become an inevitable trend. Sparse matrix vector multiplication (SpMV) is the core of sparse matrix computation. The space complexity and time complexity of its iterative solution process have important research significance. Analyze the compression format of sparse matrix C00, CSR, ELLPACK and DIA, change the sparsity of sparse matrix and the distribution of non-zero elements, and conclude that the SpMV read by COO and calculated by CSR is more universal. Utilizing the VLIW instruction architecture of C66x, using software pipelining to manage SpMV_CSR algorithm for instruction parallel optimization, utilizing SIMD single instruction multiple data instruction set for SpMV_CSR algorithm completes data parallel optimization. The experimental results indicate that the optimized SpMV_CSR algorithm has an average acceleration ratio of over 5 times compared to before optimization.

Key words : sparse matrix；SpMV；CSR；C66x；software pipelining；SIMD