Metraipolis › archive › dc_f33ef4c7e35e
Green Light: Carbon-Aware Design of Photonic Transformer Accelerators at the Edge — arXiv:2610.27376
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.27376
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:11:31.105Z
- SHA-256 of the archived text
6f9bd531be339da745ed641540a3e897d1b9abe2ec0a56e414893a64a2d644bd- Stable URL of this page
https://metraipolis.com/documento/dc_f33ef4c7e35e
How to cite
Green Light: Carbon-Aware Design of Photonic Transformer Accelerators at the Edge — arXiv:2610.27376 — arXiv (en), https://arxiv.org/abs/2610.27376 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f33ef4c7e35e (Metraipolis archive dc_f33ef4c7e35e, sha256 6f9bd531be339da745ed641540a3e897d1b9abe2ec0a56e414893a64a2d644bd)
BibTeX
@misc{dcf33ef4c7e35e,
title = {Green Light: Carbon-Aware Design of Photonic Transformer Accelerators at the Edge — arXiv:2610.27376},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.27376},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f33ef4c7e35e; sha256 6f9bd531be339da745ed641540a3e897d1b9abe2ec0a56e414893a64a2d644bd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27376. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Migrating transformer inference to the edge requires sustainability considerations that encompass both operation and manufacturing, rather than operational energy alone. Silicon photonics enables high-bandwidth, low-energy matrix multiplication; however, existing microring-resonator-based Dot Product Unit (DPU) organizations have been tailored to convolutional computations and evaluated using analog signaling without accounting for embodied carbon footprints. We adapt three DPU organizations (AMW, MAW, and MWA) to transformer inference workloads and extend each organization to stochastic signaling, yielding six organizations in total. We then calculate their embodied and operational carbon per inference. Across five transformer models and four foundry grids, the photonic system achieves improvements of four, four, and six orders of magnitude in Energy-Delay, Carbon-Delay, and Carbon-Energy Product, respectively, relative to CPUs, while also being compared against H100 SXM5 GPU and TPU v5p baseline systems. Analog-to-stochastic conversion increases die area by 4.3-4.6x and embodied carbon by 4.4-4.8x, while reducing operational energy by approximately 91% and causing embodied carbon to equal or exceed operational carbon per inference. Importantly, the DPU organization and signaling scheme, rather than the foundry grid, are the key determinants of carbon impact. Consequently, the fastest organization (MWA) is not necessarily the most carbon-efficient, whereas MAW-Stochastic offers a favorable balance between sustainability and performance. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.AR, nuovi lavori del giorno). Categorie arXiv: Hardware Architecture (cs.AR) ; Emerging Technologies (cs.ET). Pagina del lavoro: https://arxiv.org/abs/2610.27376 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-21T07:06:28.112Z dalla pagina https://arxiv.org/list/cs.AR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).