The previous study introduced the N-Conjugate Shuffle Cluster (NCSC), a router-less Interconnection Network (IN) designed to link multiple multi-core clusters, enabling the construction of a scalable many-core system. To ensure efficient intra- cluster communication, the system utilizes a Multi-Port Content-Addressable Memory (MPCAM) architecture. This paper presents a mathematical analysis of NCSC, demonstrating a linear relationship between bandwidth and the number of cores. Numerical results show that NCSC achieves a bandwidth of up to 2n Probability (PR) per cluster, where PR=r+p-rp, outperforming Grid crossbar and multi-cluster crossbar networks by 20-35% across various core counts (e.g., N<1024N). Static performance metrics further highlight NCSC’s advantages: it maintains a constant diameter of 2, a degree of 4, and a bisection width of K2/2, ensuring low latency, high scalability, and strong reliability. Comparative analysis with mesh, hypercube, and tree topologies confirms NCSC’s superior scalability and cost-effectiveness, particularly as a router-less solution.

[1] Abdullah M., Abuelrub E., and Mahafzah B., “The Chained-Cubic Tree Interconnection Network,” The International Arab Journal of Information Technology, vol. 8, no. 3, pp. 334-343, 2011. https://C:/Users/acit2k/Downloads/The_chained- cubic_tree_interconnection_network%20(1).pdf

[2] Abumwais A. and Ayyad A., “The MPCAM Based Multi-Core Processor Architecture: A Contention Free Architecture,” WSEAS Transactions on Electronics, vol. 9, pp. 105-111, 2018. https://wseas.com/journals/articles.php?id=2706

[3] Abumwais A. and Obaid M., “Shared Cache Based on Content Addressable Memory in a Multi-Core Architecture,” Computers, Materials and Continuavol, vol. 74, pp. 4951-4963, 2023. https://doi.org/10.32604/cmc.2023.032822 An Analytical Model of Many-Core System Using N-Conjugate Shuffle Cluster (NCSC) 11

[4] Abumwais A., Amirjanov A., Uyar K., and Eleyat M., “Dual-Port Content Addressable Memory for Cache Memory Applications,” Computers, Materials and Continua, vol. 70, pp. 4583-4597, 2022. https://doi.org/10.32604/cmc.2022.020529

[5] Alam M. and Varshney A., “A Comparative Study of Interconnection Network,” International Journal of Computer Applications, vol. 127, pp. 37-43, 2015. DOI: 10.5120/ijca2015906378

[6] Awal R., Rahman H., Nor R., Sembok T., and Akhand M., “Architecture and Network-on-Chip Implementation of a New Hierarchical Interconnection Network,” Journal of Circuits, Systems and Computers, vol. 24, pp. 1540006, 2015. https://doi.org/10.1142/S021812661540006X

[7] Eleyat M. and Abumwais A., “A Scalable Interconnection Scheme in Many-Core Systems,” Computers, Materials and Continua, vol. 77, pp. 615-632, 2023. https://doi.org/10.32604/cmc.2023.038810

[8] Hamid N., Walters R., and Wills G., “An Analytical Model of Multi-Core Multi-Cluster Architecture,” Open Journal of Cloud Computing, vol. 2, pp. 4-15, 2023. https://www.ronpub.com/OJCC_2015v2i1n02_H amid.pdf

[9] Hamid N., Walters R., and Wills G., “An Architecture for Measuring Network Performance in Multi-Core Multi-Cluster Architecture,” International Journal of Computer Theory and Engineering, vol. 7, no. 1, pp. 57-61, 2015. https://www.ijcte.org/vol7/930-AC0023.pdf

[10] Hoskote Y., Vangal S., Singh A., Borkar N., and Borkar S., “A 5-GHz Mesh Interconnect for a Teraflops Processor,” IEEE Micro, vol. 27, pp. 51- 61, 2007. https://doi.org/10.1109/MM.2007.4378783

[11] Krishnan S., Yazdanbakhsh A., Prakash S., Jabbour J., and et al., “Archgym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design,” in Proceedings of the 50th Annual International Symposium on Computer Architecture, Orlando, pp. 1-16, 2023. https://doi.org/10.1145/3579371.3589049

[12] Li W., Guo B., Li X., Yin S., and et al., “Nesting Ring Architecture of Multichip Optical Network on Chip for Many-Core Processor Systems,” Optical Engineering, vol. 56, no. 3, pp. 1-10, 2017. https://doi.org/10.1117/1.OE.56.3.035106

[13] Ou Y., Agwa S., and Batten C., “Implementing Low-Diameter On-Chip Networks for Manycore Processors Using a Tiled Physical Design Methodology,” in Proceedings of the 14th IEEE/ACM International Symposium on Networks-on-Chip, Hamburg, pp. 1-8, 2020. https://doi.org/10.1109/NOCS50636.2020.92417 10

[14] Patterson D. and Hennessy J., Computer Organization and Design ARM Edition: The Hardware Software Interface, The Morgan Kaufmann Series in Computer Architecture and Design, 2016. http://home.ustc.edu.cn/~louwenqi/reference_boo ks_tools/Computer%20Organization%20and%20 Design%20ARM%20edition.pdf

[15] Penney D., Machine Learning for Computer Architecture Design and Optimization, Ph.D. Thesis, Oregon State University, 2023. https://ir.library.oregonstate.edu/concern/graduate _thesis_or_dissertations/70795h33q

[16] Ruaro M., Velloso N., Jantsch A., and Moraes F., “Distributed SDN Architecture for NoC-based Many-Core SoCs,” in Proceedings of the 13th IEEE/ACM International Symposium on Networks-on-Chip, New York, pp, 1-8, 2019. https://doi.org/10.1145/3313231.3352361

[17] Udipi A., Muralimanohar N., and Balasubramonian R., “Towards Scalable, Energy- Efficient, Bus-based On-Chip Networks,” in Proceedings of the HPCA-16 the 6th International Symposium on High-Performance Computer Architecture, Bangalore, pp. 1-12, 2010. https://doi.org/10.1109/HPCA.2010.5416639

[18] Wang J., Li Y., and Peng Q., “A Novel Analytical Model for Network-on-Chip Using Semi-Markov Process,” Advances in Electrical and Computer Engineering, vol. 11, no. 1, pp. 111-118, 2011. https://www.aece.ro/abstractplus.php?year=2011 &number=1&article=18

[19] Wang K., Zheng H., Li Y., and Louri A., “SecureNoC: A Learning-Enabled, High- Performance, Energy-Efficient, and Secure On- Chip Communication Framework Design,” IEEE Transactions on Sustainable Computing, vol. 7, pp. 709-723, 2021. https://doi.org/10.1109/TSUSC.2021.3138279 12