Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (17) · 18476-18484
DOI: 10.1609/aaai.v39i17.34033 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Weikai Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).
Abstract (Originalsprache)
High-level synthesis (HLS) is a widely used tool in designing Field Programmable Gate Array (FPGA). HLS enables FPGA design with software programming languages by compiling the source code into an FPGA circuit. The source code includes a program (called ``kernel'') and several pragmas that instruct hardware synthesis, such as parallelization, pipeline, etc. While it is relatively easy for software developers to design the program, it heavily relies on hardware knowledge to design the pragmas, posing a big challenge for software developers. Recently, different machine learning algorithms, such as GNNs, have been proposed to automate the pragma design via performance prediction. However, when applying the trained model on new kernels, the significant domain shift often leads to unsatisfactory performance. We propose a more domain-generalizable model structure: a two-level hierarchical Mixture of Experts (MoE), that can be flexibly adapted to any GNN model. Different expert networks can learn to deal with different regions in the representation space, and they can utilize similar patterns between the old kernels and new kernels. In the low-level MoE, we apply MoE on three natural granularities of a program: node, basic block, and graph. The high-level MoE learns to aggregate the three granularities for the final decision. To stably train the hierarchical MoE, we further propose a two-stage training method. Extensive experiments verify the effectiveness of the hierarchical MoE.
Zitieren
APA
Li, W., Wang, D., Ding, Z., Sohrabizadeh, A., Qin, Z., Cong, J., & Sun, Y. (2025). Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence, 39(17), 18476-18484. https://doi.org/10.1609/aaai.v39i17.34033
Vancouver
Li W, Wang D, Ding Z, Sohrabizadeh A, Qin Z, Cong J, et al. Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(17):18476-18484. doi:10.1609/aaai.v39i17.34033
BibTeX
@article{Li2025,
author = {Li, Weikai and Wang, Ding and Ding, Zijian and Sohrabizadeh, Atefeh and Qin, Zongyue and Cong, Jason and Sun, Yizhou},
title = {Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {17},
pages = {18476--18484},
doi = {10.1609/aaai.v39i17.34033}
}
EUVIMED