Transformer neural networks are rapidly being integrated into state-of-the-art solutions for natural language processing (NLP) and computer vision. However, the complex structure of these models creates challenges for accelerating their execution on conventional electronic platforms. We propose the first silicon photonic hardware neural network accelerator called TRON for transformer-based models such as BERT, and Vision Transformers. Our analysis demonstrates that TRON exhibits at least 14x better throughput and 8x better energy efficiency, in comparison to state-of-the-art transformer accelerators.

翻译：Transformer神经网络正迅速被整合到自然语言处理（NLP）和计算机视觉的最先进解决方案中。然而，这些模型的复杂结构给在传统电子平台上加速其执行带来了挑战。我们提出了首个名为TRON的硅光子硬件神经网络加速器，专为基于Transformer的模型（如BERT和Vision Transformers）设计。我们的分析表明，与最先进的Transformer加速器相比，TRON在吞吐量上至少提升14倍，能效上至少提升8倍。