Abstract

More effective and scalable techniques for algorithmic optimization are required due to the substantial computational challenges brought about by the quick development of artificial intelligence (AI) and machine learning (ML) applications. In order to overcome these computational obstacles, High-Performance Computing (HPC), which makes use of distributed systems, specialized hardware, and parallelism, has become essential infrastructure. Opportunities to boost AI algorithms beyond the speed of conventional computing have emerged with the arrival of Quantum Computing (QC), especially for challenging jobs in large-scale optimization and data processing. In addition to examining how specialized hardware, such as GPUs, TPUs, FPGAs, and quantum processors, can be utilized to improve AI acceleration, this study also examines the state-of-the-art HPC methodologies used to optimize AI workloads. A thorough examination of the body of work published between 2003 and 2022 is done, and suggestions for how newly developed quantum computing paradigms could improve artificial intelligence algorithms are made. The outcomes show notable gains in scalability, resource efficiency, and performance, despite difficulties with quantum error control and hardware interoperability. In order to optimize AI, the report ends by suggesting future research paths centered on the combination of HPC and quantum computing.

References

1. A. Ashari, N. Sedaghati, J. Eisenlohr, D. Hazelwood, and S. Sengupta, 'Improving GPU performance for compute-intensive applications,' IEEE Transactions on Parallel and Distributed Systems, vol. 28, no. 1, pp. 17-29, Jan. 2017. DOI: 10.1109/TPDS.2016.2582786.
2. M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Kudlur, 'TensorFlow: A system for large-scale machine learning,' in Proc. of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI), Savannah, GA, USA, 2016, pp. 265-283. DOI: 10.5555/3026877.3026899.
3. L. Rokach, O. Maimon, and I. Vidas, 'Data mining with decision trees: Theory and applications,' IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 35, no. 4, pp. 497-509, Aug. 2005. DOI: 10.1109/TSMCC.2004.843228.
4. J. Shalf, S. Dosanjh, and J. Morrison, 'Exascale computing technology challenges,' in Proc. of IEEE 18th International Symposium on High Performance Distributed Computing (HPDC), Munich, Germany, 2009, pp. 13-24. DOI: 10.1109/HPDC.2009.5077067.
5. A. Bhoj, A. Agrawal, P. Kumar, and A. Srinivasan, 'Performance evaluation of deep learning models on GPUs and TPUs for different AI workloads,' in Proc. of the IEEE 24th International Symposium on High-Performance Computing Architecture (HPCA), Vienna, Austria, 2020, pp. 163-172. DOI: 10.1109/HPCA.2020.00038.
6. D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifre, G. Van Den Driessche, and D. Hassabis, 'Mastering the game of Go with deep neural networks and tree search,' Nature, vol. 529, pp. 484-489, 2016. DOI: 10.1038/nature16961.
7. A. Kiani, S. Doroudi, and M. Jamali, 'Tensor Processing Units: Hardware accelerators for AI workloads,' IEEE Transactions on Computers, vol. 68, no. 7, pp. 1123-1135, July 2019. DOI: 10.1109/TC.2019.2893731.
8. D. Wecker, M. B. Hastings, N. Wiebe, B. K. Clark, and C. Nayak, 'Solving strongly correlated electron models on a quantum computer,' Physical Review A, vol. 92, no. 6, pp. 062318, Dec. 2015. DOI: 10.1103/PhysRevA.92.062318.
9. Preskill, 'Quantum computing in the NISQ era and beyond,' Quantum, vol. 2, pp. 79-106, Aug. 2018. DOI: 10.22331/q-2018-08-06-79.
10. M. Schuld, I. Sinayskiy, and F. Petruccione, 'An introduction to quantum machine learning,' Contemporary Physics, vol. 56, no. 2, pp. 172-185, Mar. 2015. DOI: 10.1080/00107514.2014.964942.
11. A. K. Zadeh, M. Farhadi, and T. Banerjee, 'Quantum-inspired reinforcement learning models for optimization,' in Proc. of IEEE International Conference on Quantum Computing and Engineering (QCE), Denver, CO, USA, 2021, pp. 185-193. DOI: 10.1109/QCE52317.2021.00041.
12. V. L. D. Silva, M. C. Perez, J. L. Trammell, and T. W. Maschmeyer, 'High-performance FPGAs for machine learning on the edge: A survey,' IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 10, pp. 4205-4223, Oct. 2021. DOI: 10.1109/TNNLS.2020.3023056.
13. S. Haribara, J. Raymond, and Y. Yamamoto, 'Quantum artificial intelligence and deep learning: Algorithms, architecture, and applications,' in Proc. of the IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Seoul, South Korea, 2019, pp. 167-172. DOI: 10.1109/AICAS.2019.8803350.
14. J. R. McClean, J. Romero, R. Babbush, and A. Aspuru-Guzik, 'The theory of variational hybrid quantum-classical algorithms,' New Journal of Physics, vol. 18, no. 23, pp. 23-35, 2016. DOI: 10.1088/1367-2630/18/2/023023.
15. N. C. Jones, J. D. Whitfield, P. L. McMahon, and M. A. Martin-Delgado, 'Solving the transverse Ising model using a quantum annealer,' Nature Physics, vol. 8, pp. 179-183, Mar. 2012. DOI: 10.1038/nphys2250.
16. M. Cerezo, A. Arrasmith, R. Babbush, S. C. Benjamin, and P. J. Love, 'Variational quantum algorithms,' Nature Reviews Physics, vol. 3, pp. 625-644, Oct. 2021. DOI: 10.1038/s42254-021-00348-9.
17. S. Aaronson and A. Arkhipov, 'The computational complexity of linear optics,' Theory of Computing, vol. 9, no. 1, pp. 143-252, Dec. 2013. DOI: 10.4086/toc.2013.v009a004.
18. M. H. Amin, E. Andriyash, J. Rolfe, and M. Amin, 'Quantum Boltzmann machine,' Physical Review X, vol. 8, no. 1, pp. 011021, Feb. 2018. DOI: 10.1103/PhysRevX.8.011021.
19. G. Carleo, Y. Nomura, and M. Imada, 'Constructing exact representations of quantum many-body systems with deep neural networks,' Nature Communications, vol. 9, pp. 5322, Dec. 2018. DOI: 10.1038/s41467-018-07520-2.
20. S. Lloyd, M. Mohseni, and P. Rebentrost, 'Quantum algorithms for supervised and unsupervised machine learning,' arXiv preprint, arXiv:1307.0411, 2013.

Download PDF
Back