| 一种并行计算平台KD-60上的可实时更新文本搜索 |
| |
| 引用本文： | 龙柏,方维,孙广中,陈国良. 一种并行计算平台KD-60上的可实时更新文本搜索[J]. 小型微型计算机系统, 2012, 33(4): 712-715 |
| |
| 作者姓名： | 龙柏 方维 孙广中 陈国良 |
| |
| 作者单位： | 中国科学技术大学计算机科学与技术学院,合肥230026;安徽省高性能计算重点实验室,合肥230026 |
| |
| 基金项目： | 国家自然科学基金，国家“八六三”高技术研究发展计划项目，中央高校基本科研业务费专项基金项目资助 |
| |
| 摘 要： | 实时性是影响搜索引擎性能的重要因素.针对这个因素,提出一种可实时更新的倒排索引结构并将其应用于国产万亿次高性能计算平台KD-60.该方案采用主、辅倒排索引和内容过滤索引相结合的方式,实现了搜索过程的实时性.同时,我们将其应用于高性能绿色计算平台KD-60,使之在一定的程度上实现了搜索的高效能.实验证明,基于KD-60平台的倒排索引结构有效的解决了搜索引擎的实时性问题,并可作为绿色计算的实际应用的一个典型实例.
|
| 关 键 词： | 搜索引擎 倒排索引 KD-60 绿色计算 效能 |
Real-time Text Search Based on Parallel Computing Platform KD-60 |
| |
| LONG Bai , FANG Wei , SUN Guang-zhong , CHEN Guo-liang. Real-time Text Search Based on Parallel Computing Platform KD-60[J]. Mini-micro Systems, 2012, 33(4): 712-715 |
| |
| Authors: | LONG Bai FANG Wei SUN Guang-zhong CHEN Guo-liang |
| |
| Affiliation: | 1,2 1(School of Computer Science and Technology,University of Science and Technology of China,Hefei 230026,China) 2(Key Laboratory on High Performance Computing of Anhui Province,Hefei 230026,China) |
| |
| Abstract: | Real-time is an important factor which is affect performance of search engines.This paper presents a real-time updating inverted index structure to improve performance of search engines.This structure consists of main/assist inverted index and content filtrating index,instead of the single model of classical inverted index.Based on this inverted index structure,we implement a real BBS Search engine.At the same time,we implement this new inverted index structure on the Tera Flops Domestic high performance green computing platform KD-60 to achieve real-time and energy-efficient performance in search processing.Experiments show that the inverted index structure based on KD-60 system solves the real-time updating problem of inverted index well,and reaches energy-efficient performance on the practical applications of green computing. |
| |
| Keywords: | search engine inverted index KD-60 green computing energy-efficient performance |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
