{"title":"精确分割并行排序","authors":"Fan Dian, Tang Zhizhong","doi":"10.1109/ISPAN.2004.1300464","DOIUrl":null,"url":null,"abstract":"A new algorithm of parallel sorting by exact splitting suitable for MIMD multiprocessors is presented in the paper. The algorithm locates the splitter accurately using a flexible locating splitter algorithm. The time complexity and communication cost is pretty good compared with other con-generic algorithms, and could even be better in particular situations benefitting from the flexibility of its locating splitter algorithm. In addition, experimental results of the algorithm under an MPI environment on LANs are given and compared with those of the PSRS algorithm. According to the theoretical analysis and experimental results, the algorithm is preferable due to its virtues of high efficiency, scalability, low communication cost and good load balancing.","PeriodicalId":198404,"journal":{"name":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Parallel sorting by exact splitting\",\"authors\":\"Fan Dian, Tang Zhizhong\",\"doi\":\"10.1109/ISPAN.2004.1300464\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A new algorithm of parallel sorting by exact splitting suitable for MIMD multiprocessors is presented in the paper. The algorithm locates the splitter accurately using a flexible locating splitter algorithm. The time complexity and communication cost is pretty good compared with other con-generic algorithms, and could even be better in particular situations benefitting from the flexibility of its locating splitter algorithm. In addition, experimental results of the algorithm under an MPI environment on LANs are given and compared with those of the PSRS algorithm. According to the theoretical analysis and experimental results, the algorithm is preferable due to its virtues of high efficiency, scalability, low communication cost and good load balancing.\",\"PeriodicalId\":198404,\"journal\":{\"name\":\"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-05-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISPAN.2004.1300464\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISPAN.2004.1300464","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A new algorithm of parallel sorting by exact splitting suitable for MIMD multiprocessors is presented in the paper. The algorithm locates the splitter accurately using a flexible locating splitter algorithm. The time complexity and communication cost is pretty good compared with other con-generic algorithms, and could even be better in particular situations benefitting from the flexibility of its locating splitter algorithm. In addition, experimental results of the algorithm under an MPI environment on LANs are given and compared with those of the PSRS algorithm. According to the theoretical analysis and experimental results, the algorithm is preferable due to its virtues of high efficiency, scalability, low communication cost and good load balancing.