Blocking optimized SIMD tree search on modern processors

• Published in: Journal of Shanghai University Vol. 15; no. 5; pp. 437 - 444
• Main Author: 张倬 陆宇凡 沈文枫 徐炜民 郑衍衡
• Format: Journal Article
• Language: English
• Published: Heidelberg Shanghai University Press 01.10.2011; School of Computer Engineering and Science, Shanghai University, Shanghai 200072, P.R.China
• Subjects: Algorithms; Classical Mechanics; Engineering; Environment; Information Technology; Life Sciences; Materials Science; Mathematical and Computational Engineering; Mechatronics; Nonlinearity; Processors; Search algorithms; Searching; SIMD; Time response; Trees; Vector processing (computers); 优化算法; 内存访问; 向量处理; 处理器; 搜索算法; 树搜索; 计算能力; binary search; single instruction multiple date (SIMD); Cell broadband engine (BE); tree search; streaming SIMD extensions (SSE); single instruction multiple date(SIMD); streaming SIMD extensions(SSE); Cell broadband engine(BE)
• ISSN: 1007-6417; 1863-236X
• DOI: 10.1007/s11741-011-0765-2

Tree search is a widely used fundamental algorithm. Modern processors provide tremendous computing power by integrating multiple cores, each with a vector processing unit. This paper reviews some studies on exploiting single instruction multiple date （SIMD） capacity of processors to improve the performance of tree search, and proposes several improvement methods on reported SIMD tree search algorithms. Based on blocking tree structure, blocking for memory alignment and dynamic blocking prefetch are proposed to optimize the overhead of memory access. Furthermore, as a way of non-linear loop unrolling, the search branch unwinding shows that the number of branches can exceed the data width of SIMD instructions in the SIMD search algorithm. The experiments suggest that blocking optimized SIMD tree search algorithm can achieve 1.6 times response speed faster than the un-optimized algorithm.