发表机构
New York University (NYU) Abu Dhabi（纽约大学阿布扎比分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对光子变压器加速器因有源移相器组件导致的问题，提出MDTransformer软硬件协同设计。利用模分光学数据流等执行复杂矩阵运算，形成紧凑光子张量核。实验表明其在不同工作负载下相比现有技术有面积、功耗、能源节省及延迟相当等优势，为高性能节能变压器系统提供方案。
AI 中文摘要
最近，光子变压器加速器（PTA）在加速Transformer推理方面比电子加速器成功实现了显著的加速和能效提升。然而，由于有源移相器组件，现有技术依赖昂贵的多波长光生成和大型点积单元，使其方法效率低下且不切实际。为解决此问题，我们提出了MDTransformer，一种基于模分光学数据流和操作的新型PTA软硬件协同设计。具体而言，MDTransformer使用空间模式干涉执行复杂矩阵运算，利用逆设计的多模耦合器、交叉点和马赫曾德尔IQ调制器形成一个紧凑的模分光子张量核（MPTC），能够在光域执行矩阵乘法。其每个导模（即TE0 - TE3）充当独立的计算通道，在无光谱滤波或自由光谱范围限制的情况下实现每波导四倍并行度。此外，其相干检测和IQ调制联合编码幅度和相位，实现变压器全范围操作的复数值运算。MDTransformer提供有效精度低于4位的模拟乘法和低于 - 30 dB的模间串扰。其逆设计方法还提供可扩展性并与1550 nm单激光连续波操作完全兼容。实验结果表明，在不同工作负载（即DeiT - Tiny/Small/Base和BERT - Base/Large）下，MDTransformer与现有技术的PTA相比，实现了40.4%的面积减少、63.6%的功耗节省、40.6%的能源节省以及相当的延迟。这些结果表明，MDTransformer为基于变压器的高性能和节能系统提供了一个实用的解决方案。
英文摘要
Recently, photonic transformer accelerators (PTAs) have successfully achieved significant speedup and energy efficiency improvements over electronic accelerators for expediting Transformer inference. However, state-of-the-art rely on expensive multi-wavelength light generation and large dot-product units due to active phase-shifter components, thus making their approach inefficient and impractical. To address this, we propose MDTransformer, a novel hardware-software co-design of PTA based on mode-division optical dataflow and operations. Specifically, MDTransformer performs complex matrix operations using spatial-mode interference, that leverages the inverse-designed multi-mode couplers, crossings, and Mach-Zehnder IQ modulators into a compact mode-division photonic tensor core (MPTC), capable of executing matrix multiplications in the optical domain. Its each guided mode (i.e., TE0-TE3) acts as an independent computational lane, enabling four-fold parallelism-per-waveguide without spectral filtering or free-spectral-range limitations. Moreover, its coherent detection and IQ modulation jointly encode amplitude and phase, realizing complex-valued arithmetic for full-range operations in transformers. MDTransformer offers analog multiplication with sub-4-bit effective precision and inter-modal crosstalk below -30 dB. Its inverse-designed approach also offers scalable and full compatibility with single-laser continuous-wave operation at 1550 nm. Experimental results show that MDTransformer achieves 40.4% area reduction, 63.6% power saving, 40.6% energy saving, and comparable latency over the state-of-the-art PTA across different workloads (i.e., DeiT-Tiny/Small/Base and BERT-Base/Large). These results show that MDTransformer offers a practical solution for high-performance and energy-efficient transformer-based systems.
Comments10 pages, 10 figures, 1 table
