# Research paper: Sustainable Transformer Neural Network Acceleration with Stochastic Photonic Computing — retained record

> Retained semantic-scholar record from semantic-scholar.

Canonical: https://highsignal.app/data/records/d1c54b6e1d9a974d

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


source: [semantic-scholar](https://highsignal.app/data/semantic-scholar) published 2026-04-10 00:00 ingested 2026-06-01 11:16

[Lightmatter Inc.](https://highsignal.app/entities/LIGHTMATTER)[original source ↗](https://www.semanticscholar.org/paper/700b284615418ee0fab1990f14a587467eaa7bc8)

## extract

Query: photonic computing transformer accelerator
Authors: S. Afifi, O. Alo, I. Thakkar, S. Pasricha
Citations: 0
Transformers achieve state-of-the-art performance in natural language processing, vision, and scientific computing, but demand high computation and memory. To address these challenges, we present ASTRA, the first silicon-photonic accelerator leveraging stochastic computing for transformers. ASTRA employs novel optical stochastic multipliers and unary/analog homodyne accumulation in a crosstalk-minimal organization to efficiently process dynamic tensor computations. Evaluations show at least 7.6x speedup and 1.3x lower energy overheads compared to state-of-the-art accelerators, highlighting ASTRA's potential for efficient, scalable, and sustainable transformer inference.

## retained text

No document body was retained for this record — only its metadata was stored.
