Abstract
The design and optimization of deep neural network accelerators should sufficiently consider numerous design parameters and physical constraints that render their design spaces massive in scale and complicated in distribution. When confronted with the massive and complicated design spaces, previous works on design space exploration suffer from the exploration-exploitation dilemma and are unable to simultaneously assure optimization efficiency and stability. In order to solve the exploration-exploitation dilemma, we present a novel design space exploration method named CSDSE. CSDSE implements heterogeneous agents separately responsible for exploration or exploitation to search the design space cooperatively and introduces a weighted compact buffer that encourages agents to search in diverse directions and bolsters their global exploration ability. CSDSE is implemented to enhance accelerator design. Compared to former methods, it achieves latency speedups of up to 6.1x and energy reductions of up to 1.3x in different constraint scenarios.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdelfattah, M.S., Dudziak, Ł., Chau, T., Lee, R., Kim, H., Lane, N.D.: Best of both worlds: AutoML codesign of a CNN and its hardware accelerator. In: 2020 57th ACM/IEEE Design Automation Conference (DAC), pp. 1–6. IEEE (2020)
Badia, A.P., et al.: Never give up: learning directed exploration strategies. arXiv preprint arXiv:2002.06038 (2020)
Bergstra, J., Yamins, D., Cox, D.: Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures. In: International Conference on Machine Learning, pp. 115–123. PMLR (2013)
Chen, Y.H., Krishna, T., Emer, J.S., Sze, V.: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid-State Circuits 52(1), 127–138 (2016)
Cong, J., Wang, J.: PolySA: polyhedral-based systolic array auto-compilation. In: 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), pp. 1–8. IEEE (2018)
Dave, S., Kim, Y., Avancha, S., Lee, K., Shrivastava, A.: dMazeRunner: executing perfectly nested loops on dataflow accelerators. ACM Trans. Embed. Comput. Syst. 18(5s), 70 (2019). https://doi.org/10.1145/3358198
Feng, K., Fan, X., An, J., Li, C., Di, K., Li, J.: ACDSE: a design space exploration method for CNN accelerator based on adaptive compression mechanism. ACM Trans. Embed. Comput. Syst. (2022). https://doi.org/10.1145/3545177, Just Accepted
Feng, K., et al.: ERDSE: efficient reinforcement learning based design space exploration method for CNN accelerator on resource limited platform. Graph. Vis. Comput. 4, 200024 (2021)
Gao, Y., Chen, L., Li, B.: Spotlight: optimizing device placement for training deep neural networks. In: International Conference on Machine Learning, pp. 1676–1684. PMLR (2018)
Guo, Y., et al.: Memory based trajectory-conditioned policies for learning from sparse rewards. Adv. Neural. Inf. Process. Syst. 33, 4333–4345 (2020)
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861–1870. PMLR (2018)
Jazzbin, et al.: geatpy: the genetic and evolutionary algorithm toolbox with high performance in Python (2020)
Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1–12 (2017)
Kao, S.C., Jeong, G., Krishna, T.: ConfuciuX: autonomous hardware resource assignment for DNN accelerators using reinforcement learning. In: 2020 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), pp. 622–636. IEEE (2020)
Kao, S.C., Krishna, T.: GAMMA: automating the HW mapping of DNN models on accelerators via genetic algorithm. In: 2020 IEEE/ACM International Conference on Computer Aided Design (ICCAD), pp. 1–9. IEEE (2020)
Krishnan, S., et al.: Multi-agent reinforcement learning for microprocessor design space exploration (2022)
Kwon, H., Chatarasi, P., Pellauer, M., Parashar, A., Sarkar, V., Krishna, T.: Understanding reuse, performance, and hardware cost of DNN dataflow: a data-centric approach. In: Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture, pp. 754–768 (2019)
Lin, Y., Yang, M., Han, S.: NAAS: neural accelerator architecture search. In: 2021 58th ACM/IEEE Design Automation Conference (DAC), pp. 1051–1056. IEEE (2021)
Muñoz-Martínez, F., Abellán, J.L., Acacio, M.E., Krishna, T.: STONNE: enabling cycle-level microarchitectural simulation for DNN inference accelerators. IEEE Comput. Archit. Lett. 20(2), 122–125 (2021). https://doi.org/10.1109/LCA.2021.3097253
NVIDIA: Nvidia deep learning accelerator (2017). http://nvdla.org/
Oh, J., Guo, Y., Singh, S., Lee, H.: Self-imitation learning. In: International Conference on Machine Learning, pp. 3878–3887. PMLR (2018)
Reagen, B., et al.: A case for efficient accelerator design space exploration via Bayesian optimization. In: 2017 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), pp. 1–6. IEEE (2017)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Shao, Y.S., Xi, S.L., Srinivasan, V., Wei, G.Y., Brooks, D.: Co-designing accelerators and SoC interfaces using gem5-Aladdin. In: 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), pp. 1–12. IEEE (2016)
Tan, M., et al.: MnasNet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2820–2828 (2019)
Zheng, S., Liang, Y., Wang, S., Chen, R., Sheng, K.: FlexTensor: an automatic schedule exploration and optimization framework for tensor computation on heterogeneous system, ASPLOS 2020, pp. 859–873. Association for Computing Machinery, New York, NY, USA (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Feng, K., Fan, X., An, J., Wang, H., Li, C. (2024). CSDSE: Apply Cooperative Search to Solve the Exploration-Exploitation Dilemma of Design Space Exploration. In: Tari, Z., Li, K., Wu, H. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2023. Lecture Notes in Computer Science, vol 14490. Springer, Singapore. https://doi.org/10.1007/978-981-97-0859-8_1
Download citation
DOI: https://doi.org/10.1007/978-981-97-0859-8_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0858-1
Online ISBN: 978-981-97-0859-8
eBook Packages: Computer ScienceComputer Science (R0)