MODEL PARALELISASI MENGGUNAKAN DIVIDE AND CONQUER, PIPELINE, DAN MAP-REDUCE
DOI:
https://doi.org/10.71282/jurmie.v3i1.1596Keywords:
Parallel Algorithms, Divide and Conquer, Pipeline, Map-ReduceAbstract
This study discusses a computational parallelization model that integrates the divide and conquer, pipeline processing, and map-reduce approaches as strategies to improve data processing efficiency and the performance of modern computing systems. The background of this study is based on the growing need to optimize increasingly complex computational processes, particularly in large-scale data processing scenarios and applications that require fast execution times. The literature review covers the fundamental concepts, functions, and main roles of each parallel algorithm in creating more efficient processing structures. The research method adopts a qualitative approach with descriptive analysis, focusing on the interpretation of literature, mapping of operational mechanisms, and comparative evaluation of the three parallelization models within the context of practical implementation. The results indicate that combining the three models can enhance scalability, reduce bottlenecks, and significantly accelerate computation time. This study confirms that the appropriate selection and integration of parallel strategies can effectively support the demands of modern computing in both distributed environments and multi-core architectures.
Downloads
References
Agrawal, P., & Singh, R. (2021). Performance optimization techniques in distributed computing. Journal of Computer Systems, 14(3), 115–128.
Al-Farisi, M. (2022). Pemrograman Paralel untuk Aplikasi Data Besar. Bandung: Informatika.
Arifin, H. (2021). Analisis penerapan model komputasi paralel dalam pengolahan citra digital. Jurnal Teknologi Informasi Nasional, 6(2), 44–53.
Chen, L., & Zhao, Q. (2020). A hybrid parallel model combining divide-and-conquer and map-reduce. International Journal of High Performance Computing, 34(1), 55–70.
Dewi, S. (2023). Implementasi pipeline processing pada sistem rekomendasi real-time. Jurnal Sistem Cerdas Indonesia, 5(1), 77–89.
Fahrudi, R. (2021). Arsitektur Komputasi Paralel. Jakarta: Andi.
Gopal, A., & Mehta, D. (2023). Efficiency analysis of pipeline-based processing systems in large-scale computation. International Journal of Distributed Algorithms, 11(2), 201–219.
Hendrawan, B. (2020). Studi komparatif model paralelisasi pada big data analytics. Jurnal Informatika Nusantara, 9(4), 301–310.
Kurniawan, Y. (2022). Map-reduce sebagai model komputasi terdistribusi pada data tidak terstruktur. Jurnal Teknologi dan Sistem Informasi, 12(3), 188–197.
Liang, X., & Sun, J. (2024). Improving computational throughput using structured pipeline parallelism. Journal of Parallel Processing Research, 18(2), 90–101.
Mahendra, A. (2023). Optimalisasi kinerja pemrosesan data melalui divide and conquer. Jurnal Sains Komputasi Indonesia, 7(1), 56–66.
Nugroho, T. (2021). Analisis performa algoritma paralel pada lingkungan multi-core. Jurnal Komputasi dan Aplikasi, 8(2), 100–112.
Rahman, I., & Putra, G. (2024). Hybrid parallel computation on distributed environments. International Journal of Computer Science Review, 16(1), 33–48.
Satria, D. (2020). Pemanfaatan model map-reduce pada aplikasi e-commerce lokal. Jurnal Teknologi Digital, 4(2), 67–79.
Wang, Z., & Liu, H. (2022). Parallel algorithm design using divide and conquer for high-density data processing. Global Journal of Computing Systems, 19(3), 142–158.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Bayu Endru Subiyakto, Fawwaz Muzakkty, Alfi Muiz, Muhammad Faiz Fairuz (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
