Effects of Multi-Core Processors on Sequential Divide and Conquer Algorithms

被引：0
|
作者：
Alhaidari, Fahd A. [1 ]
Al Metrik, Maissa A. [2 ]
机构：
[1] Imam Abdulrahman Bin Faisal Univ, Coll Comp Sci & Informat Technol, Networks & Commun Dept, PO 1982, Dammam, Saudi Arabia
[2] Imam Abdulrahman Bin Faisal Univ, Coll Comp Sci & Informat Technol, Comp Sience Dept, PO 1982, Dammam, Saudi Arabia
来源：
2021 IEEE NATIONAL COMPUTING COLLEGES CONFERENCE (NCCC 2021) | 2021年
关键词：
Multi-core; Divide and conquer; Sequential; Speedup; parallelism;
D O I：
10.1109/NCCC49330.2021.9428867
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
With the spread of multi-core systems, parallel programming increased in popularity. However, parallelizing algorithms in some cases yield negative results due to overhead. Additionally, implementing parallel algorithms is not always an easy or achievable task. Therefore, finding out to what extent a multi-core architecture can aid in the enhancement of the algorithm's speedup could become extremely beneficial. This paper studies and calculates the execution time and speedup of three of the most popular divide and conquer algorithms (Merge sort, quick sort, and matrix multiplication), the conducted experiments tested against various array sizes. The experiments take place on three different multi-core machines ranging from a dual-core CPU to a hexa-core CPU. The obtained results conclude that speedup is directly proportional to the number of CPU cores, such that using a hexa-core CPU in lieu of a dual-core CPU can achieve a speedup up to twice as fast. Thus, utilizing powerful multi-core CPU's could rival the use of parallelism on a standard CPU.
引用
收藏
页码：1023 / +
页数：6
相关论文
共 50 条
  • [1] An evaluation of double Divide and Conquer on a multi-core
    Konda, Taro
    Toyokawa, Hiroki
    Nakamura, Yoshimasa
    [J]. INTERNATIONAL CONFERENCE ON INFORMATICS EDUCATION AND RESEARCH FOR KNOWLEDGE-CIRCULATING SOCIETY, PROCEEDINGS, 2008, : 201 - 204
  • [2] A highly optimized skeleton for unbalanced and deep divide-and-conquer algorithms on multi-core clusters
    Millán A. Martínez
    Basilio B. Fraguela
    José C. Cabaleiro
    [J]. The Journal of Supercomputing, 2022, 78 : 10434 - 10454
  • [3] A highly optimized skeleton for unbalanced and deep divide-and-conquer algorithms on multi-core clusters
    Martinez, Millan A.
    Fraguela, Basilio B.
    Cabaleiro, Jose C.
    [J]. JOURNAL OF SUPERCOMPUTING, 2022, 78 (08): : 10434 - 10454
  • [4] Parallel Lexical Analysis on Multi-Core Machines using Divide and Conquer
    Barve, Amit
    Joshi, Brijendra Kumar
    [J]. 3RD NIRMA UNIVERSITY INTERNATIONAL CONFERENCE ON ENGINEERING (NUICONE 2012), 2012,
  • [5] Performance optimisation of sequential programs on multi-core processors
    Tristram, Waide
    Bradshaw, Karen
    [J]. PROCEEDINGS OF THE SOUTH AFRICAN INSTITUTE FOR COMPUTER SCIENTISTS AND INFORMATION TECHNOLOGISTS CONFERENCE, 2012, : 119 - 128
  • [6] Accelerating sequential programs on commodity multi-core processors
    Zhang, Yuanming
    Xiao, Gang
    Baba, Takanobu
    [J]. JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2014, 74 (04) : 2257 - 2265
  • [7] A general and efficient divide-and-conquer algorithm framework for multi-core clusters
    Carlos H. González
    Basilio B. Fraguela
    [J]. Cluster Computing, 2017, 20 : 2605 - 2626
  • [8] A general and efficient divide-and-conquer algorithm framework for multi-core clusters
    Gonzalez, Carlos H.
    Fraguela, Basilio B.
    [J]. CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2017, 20 (03): : 2605 - 2626
  • [9] Using multi-core processors for mining frequent sequential patterns
    Huynh, Bao
    Vo, Bay
    [J]. ICIC Express Letters, 2015, 9 (11): : 3071 - 3079
  • [10] On developing B-spline registration algorithms for multi-core processors
    Shackleford, J. A.
    Kandasamy, N.
    Sharp, G. C.
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2010, 55 (21): : 6329 - 6351
12345