AN EFFICIENT PARALLEL SORTING COMPATIBLE WITH THE STANDARD QSORT

Author:

MAN DUHU1,ITO YASUAKI1,NAKANO KOJI1

Affiliation:

1. Department of Information Engineering, Hiroshima University, 1-4-1 Kagamiyama, Higashihiroshima, Hiroshima 739-8527, Japan

Abstract

The main contribution of this paper is to present an efficient parallel sorting "psort" compatible with the standard qsort. Our parallel sorting "psort" is implemented such that its interface is compatible with "qsort" in C Standard Library. Therefore, any application program that uses standard "qsort" can be accelerated by simply replacing "qsort" call by our "psort". Also, "psort" uses standard "qsort" as a subroutine for local sequential sorting. So, if the performance of "qsort" is improved by anyone in the open source community, then that of our "psort" is also automatically improved. To evaluate the performance of our "psort", we have implemented our parallel sorting in a Linux server with four Intel hexad-core processors (i.e. twenty four processor cores). The experimental results show that our "psort" is approximately 11 times faster than standard "qsort" using 24 processors.

Publisher

World Scientific Pub Co Pte Lt

Subject

Computer Science (miscellaneous)

Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Parallel Multi-Deque Partition Dual-Deque Merge sorting algorithm using OpenMP;Scientific Reports;2023-04-19

2. Analysis and optimization of Dual Parallel Partition Sorting with OpenMP;Applied Computing and Informatics;2022-07-07

3. AQsort: Scalable Multi-Array In-Place Sorting with OpenMP;Scalable Computing: Practice and Experience;2016-10-11

4. Parallel Partition and Merge QuickSort (PPMQSort) on Multicore CPUs;The Journal of Supercomputing;2016-02-18

5. Optimal Parallel Hardware K-Sorter and Top K-Sorter, with FPGA Implementations;2015 14th International Symposium on Parallel and Distributed Computing;2015-06

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3