近年來，隨著人工智慧計算需求的急速增長，計算硬體設計正持續進步與創新。本研究專注於探討多層級指令在動態多型加速器中的應用。我們提出了一種包含三個階段指令的設計框架：首先是任務階層指令，負責高層次的任務規劃和調度，包括選擇適當的計算流程和資源配置；其次是執行硬體運作的低階層指令，用於實際的計算操作和資料讀取；最後是情境指令，用於精細的硬體控制，特別是在資料路徑的架構決策上。這種多層級指令結構旨在增強動態多型加速器處理複雜人工智慧計算任務的效率和應用靈活性。本研究深入探討了這一設計框架的概念和實踐方法，並探索了其在實際應用中的可行性和挑戰。

In recent years, driven by the rapid growth in demand for artificial intelligence computations, the field of computational hardware design has been experiencing continuous innovation and advancement. This study focuses on exploring the application of multi-level instruction sets in dynamic polymorphic accelerators. We propose a design framework comprising three stages of instructions: firstly, task-level instructions responsible for high-level task planning and scheduling, including selecting appropriate computation flows and resource configurations; secondly, execution-level instructions used for actual computation operations and data retrieval within the hardware; and finally, context instructions employed for precise hardware control, particularly in decisions regarding the architecture of the data path. This multi-level instruction structure aims to enhance the efficiency and application flexibility of dynamic polymorphic accelerators in handling complex artificial intelligence computing tasks. The study delves into the conceptualization and practical methods of this design framework, exploring its feasibility and potential challenges in real-world applications.

[1] E. Cambria and B. White, "Jumping NLP curves: A review of natural language processing research," IEEE Computational Intelligence Magazine, vol. 9, no. 2, pp. 48-57, 2014, doi: 10.1109/MCI.2014.2307227.
[2] "Advances in Neural Information Processing Systems," in 31st Annual Conference on Neural Information Processing Systems, NIPS 2017, December 4, 2017 - December 9, 2017, Long Beach, CA, United states, 2017, vol. 2017-December: Neural information processing systems foundation, in Advances in Neural Information Processing Systems.
[3] C. Lattner and V. Adve, "LLVM: A compilation framework for lifelong program analysis & transformation," in International Symposium on Code Generation and Optimization, CGO 2004, March 20, 2004 - March 24, 2004, San Jose, CA, United states, 2004: Institute of Electrical and Electronics Engineers Computer Society, in International Symposium on Code Generation and Optimization, CGO, pp. 75-86, doi: 10.1109/CGO.2004.1281665. [Online]. Available: http://dx.doi.org/10.1109/CGO.2004.1281665
[4] L. Dagum and R. Menon, "OpenMP: an industry standard API for shared-memory programming," IEEE computational science and engineering, vol. 5, no. 1, pp. 46-55, 1998.
[5] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," Commun. ACM, vol. 60, no. 6, pp. 84-90, 2017, doi: 10.1145/3065386.
[6] M. T. Camacho Olmedo, M. Paegelow, J.-F. o. Mas, and F. Escobar, "Geomatic approaches for modeling land change scenarios. An introduction," Geomatic Approaches for Modeling Land Change Scenarios, pp. 1-8, 2018.
[7] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," in 3rd International Conference on Learning Representations, ICLR 2015, May 7, 2015 - May 9, 2015, San Diego, CA, United states, 2015: International Conference on Learning Representations, ICLR, in 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings.
[8] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, June 26, 2016 - July 1, 2016, Las Vegas, NV, United states, 2016, vol. 2016-December: IEEE Computer Society, in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 770-778, doi: 10.1109/CVPR.2016.90. [Online]. Available: http://dx.doi.org/10.1109/CVPR.2016.90
[9] C. Szegedy et al., "Going deeper with convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9.
[10] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
[11] K. Xu et al., "Show, attend and tell: Neural image caption generation with visual attention," in International conference on machine learning, 2015: PMLR, pp. 2048-2057.
[12] F. Yu and V. Koltun, "Multi-scale context aggregation by dilated convolutions," arXiv preprint arXiv:1511.07122, 2015.
[13] W. Ouyang et al., "Deepid-net: Deformable deep convolutional neural networks for object detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 2403-2412.
[14] Z.-Q. Zhao, P. Zheng, S.-t. Xu, and X. Wu, "Object detection with deep learning: A review," IEEE transactions on neural networks and learning systems, vol. 30, no. 11, pp. 3212-3232, 2019.
[15] J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 3431-3440.
[16] D. Shen, G. Wu, and H.-I. Suk, "Deep learning in medical image analysis," Annual review of biomedical engineering, vol. 19, no. 1, pp. 221-248, 2017.
[17] D. W. Ruck, S. K. Rogers, and M. Kabrisky, "Feature selection using a multilayer perceptron," Journal of neural network computing, vol. 2, no. 2, pp. 40-48, 1990.
[18] H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena, "Self-attention generative adversarial networks," in International conference on machine learning, 2019: PMLR, pp. 7354-7363.
[19] G. Bebis and M. Georgiopoulos, "Feed-forward neural networks," Ieee Potentials, vol. 13, no. 4, pp. 27-31, 1994.
[20] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for language understanding," arXiv preprint arXiv:1810.04805, 2018.
[21] Y. Liu et al., "Roberta: A robustly optimized bert pretraining approach," arXiv preprint arXiv:1907.11692, 2019.
[22] V. Sanh, L. Debut, J. Chaumond, and T. Wolf, "DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter," arXiv preprint arXiv:1910.01108, 2019.
[23] A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever, "Improving language understanding by generative pre-training," 2018.
[24] A. Dosovitskiy et al., "An image is worth 16x16 words: Transformers for image recognition at scale," arXiv preprint arXiv:2010.11929, 2020.