# Research paper: MDTransformer: A Hardware-Software Co-Design of Mode-Division Photonic Transformer Accelerator with Inverse-Designed Coherent Crossbar — retained record

> Retained semantic-scholar record from semantic-scholar.

Canonical: https://highsignal.app/data/records/b4e8346a5d6d920f

[← sources](https://highsignal.app/data)


source: [semantic-scholar](https://highsignal.app/data/semantic-scholar) published 2026-07-28 00:00 ingested 2026-08-12 07:13

[Lightmatter Inc.](https://highsignal.app/entities/LIGHTMATTER)[original source ↗](https://www.semanticscholar.org/paper/8f027a4cf071023b8ec47d53564e823cdea7a75a)

## retained text



```
Query: photonic computing transformer accelerator
Authors: S. Serunjogi, Rachmad Vidya Wicaksana Putra, Ayat M. Taha, Muhammad Shafique, Mahmoud S. Rasras
Citations: 0
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.
```



document fetched 2026-08-12 07:13 · canonical https://semanticscholar.org/paper/8f027a4cf071023b8ec47d53564e823cdea7a75a
