Photonic Memory & Storage: A Paradigm Shift for Next-Generation Computing
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V6I1P108Keywords:
Photonic memory, optical storage, phase-change materials, non-volatile memory, data processing, nanophotonicsAbstract
The rapid growth of data in recent years due to modern technologies like Artificial Intelligence, IoT, Cloud computing, big data analytics, etc., has put a lot of pressure on modern storage and processing systems. Current e-memory systems like DRAM and NAND flash storage lag behind in the market demands of faster operating speed, better efficiency, and greater scalability. These limitations have originated from the first principles associated with electronic charge-based storage, such as energy dissipation, latency and bandwidth limitations. When extending computing architectures towards the exascale level and neuromorphic computing, new memory paradigms are needed to close the gap between data processing and data storage. Such technologies include photonic memory and storage; this is because photonic memory and storage is a relatively new field of computation that uses light-based methods of storing data. Photonic systems contrast with conventional electronic counterparts in that they involve much less power consumption during standby conditions, perform data accesses with high speed, and cannot be affected by electromagnetic interferences. Optical memory devices are, therefore, based on this concept of optically encodable data, light pulses or Phase Change Materials (PCMs). Some of the materials, like chalcogenide-based phase change compounds, have the ability to undergo phase change both in optical and structural characteristics, providing a solid basis for optoelectronic applications like non-volatile storage with high switching rates. These can also be coupled with silicon photonics, which ensures that they are fully compatible with the current semiconductor processing technology. Furthermore, the architecture of photonic memory has multi-level storage, high endurance and stability in the long run than the charge storage. As a novel leading-edge technology for data centres, HPC, and AI applications, photonic memory stands capable of changing the trends of Information technology systems. In this paper, the background highlights the fundamentals, materials, and technologies based on one and two-port device architectures and real-world applications of PM. It presents a review of the state-of-the-art of its implications for future computing and data storage
References
[1] Goi, E., Zhang, Q., Chen, X., Luan, H., & Gu, M. (2020). Perspective on photonic memristive neuromorphic computing. PhotoniX, 1, 1-26.
[2] Alexoudi, T., Kanellos, G. T., & Pleros, N. (2020). Optical RAM and integrated optical memories: a survey. Light: Science & Applications, 9(1), 91.
[3] Han, H. (2022). High-Performance and Energy-Efficient Computing Systems Using Photonics (Doctoral dissertation, Northwestern University).
[4] Narayan, A., Thonnart, Y., Vivet, P., Coskun, A., & Joshi, A. (2022). Architecting optically controlled phase change memory. ACM Transactions on Architecture and Code Optimization, 19(4), 1-26.
[5] Yoo, S. B. (2021). Prospects and challenges of photonic switching in data centres and computing systems. Journal of Lightwave Technology, 40(8), 2214-2243.
[6] Shacham, A., Bergman, K., & Carloni, L. P. (2008). Photonic networks-on-chip for future generations of chip multiprocessors. IEEE Transactions on Computers, 57(9), 1246-1260.
[7] Wei, J., & Zhang, X. (2022, May). How much storage do we need for a high-performance server? In 2022 IEEE 38th International Conference on Data Engineering (ICDE) (pp. 3221-3225). IEEE.
[8] DeWitt, D., & Gray, J. (1992). Parallel database systems: The future of high-performance database systems. Communications of the ACM, 35(6), 85-98.
[9] Xu, D., Ma, Y., Jin, G., & Cao, L. (2024). Intelligent Photonics: a disruptive technology to shape the present and redefine the future. Engineering.
[10] Cox, N., Murray, J., Hart, J., & Redding, B. (2024). Photonic next-generation reservoir computer based on distributed feedback in optical fibre. Chaos: An Interdisciplinary Journal of Nonlinear Science, 34(7).
[11] Wang, W., Gao, S., Wang, Y., Li, Y., Yue, W., Niu, H., ... & Shen, G. (2022). Advances in emerging photonic memristive and memristive‐like devices. Advanced Science, 9(28), 2105577.
[12] Beamer, S., Sun, C., Kwon, Y. J., Joshi, A., Batten, C., Stojanović, V., & Asanović, K. (2010). Re-architecting DRAM memory systems with monolithically integrated silicon photonics. ACM SIGARCH Computer Architecture News, 38(3), 129-140.
[13] Cheng, Z., Ríos, C., Youngblood, N., Wright, C. D., Pernice, W. H., & Bhaskaran, H. (2018). Device‐level photonic memories and logic applications using phase‐change materials. Advanced Materials, 30(32), 1802435.
[14] Zhai, Y., Yang, J. Q., Zhou, Y., Mao, J. Y., Ren, Y., Roy, V. A., & Han, S. T. (2018). Toward non-volatile photonic memory: concept, material and design. Materials Horizons, 5(4), 641-654.
[15] Wang, J., Wang, L., & Liu, J. (2020). Overview of phase-change materials-based photonic devices. IEEE Access, 8, 121211-121245.
[16] Wuttig, M., Bhaskaran, H., & Taubner, T. (2017). Phase-change materials for non-volatile photonic applications. Nature Photonics, 11(8), 465-476.
[17] Lian, C., Vagionas, C., Alexoudi, T., Pleros, N., Youngblood, N., & Ríos, C. (2022). Photonic (computational) memories: tunable nanophotonics for data storage and computing. Nanophotonics, 11(17), 3823-3854.
[18] Dong, P., Chen, Y. K., Duan, G. H., & Neilson, D. T. (2014). Silicon photonic devices and integrated circuits. Nanophotonics, 3(4-5), 215-228.
[19] In-memory photonic dot-product engine with electrically programmable weight banks, Nature, 2023. online. https://www.nature.com/articles/s41467-023-38473-x
[20] Bogaerts, W., & Chrostowski, L. (2018). Silicon photonics circuit design: methods, tools and challenges. Laser & Photonics Reviews, 12(4), 1700237.
[21] Shih, C. C., Chiang, Y. C., Hsieh, H. C., Lin, Y. C., & Chen, W. C. (2019). Multilevel photonic transistor memory devices using conjugated/insulated polymer blend electrets. ACS applied materials & interfaces, 11(45), 42429-42437.
[22] Zhu, Z., Guglielmo, G. D., Cheng, Q., Glick, M., Kwon, J., Guan, H., ... & Bergman, K. (2020). Photonic switched optically connected memory: An approach to address memory challenges in deep learning. Journal of Lightwave Technology, 38(10), 2815-2825.
[23] Ríos, C., Youngblood, N., Cheng, Z., Le Gallo, M., Pernice, W. H., Wright, C. D., ... & Bhaskaran, H. (2019). In-memory computing on a photonic platform. Science advances, 5(2), eaau5759.
[24] Udkar S. Emerging Advanced Packaging Technologies and Their Impact on Modern Computer Architecture. IJETCSIT:6(1):56-63.Availablefrom: https://ijetcsit.org/index.php/ijetcsit/article/view/97.
[25] Udkar S. Harnessing Photonic Computing for Next-Generation CPUs and GPUs in High-Performance Computing. IJETCSIT; 5(4):23-36. Available from: https://ijetcsit.org/index.php/ijetcsit/article/view/94.
[26] Udkar S. Multi-Domain IVRs for Chiplet-Based Processors: Towards Energy-Efficient Power Delivery. IJAIBDCMS, 6(1):52-62. Available from: https://ijaibdcms.org/index.php/ijaibdcms/article/view/68.
