TRON: Transformer Neural Network Acceleration with Non-Coherent Silicon Photonics

Salma Afifi, Febin Sunny, Mahdi Nikdast, Sudeep Pasricha
3/22/2023
cs.LGcs.AR

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Accelerating Neural Networks for Large Language Models and Graph Processing with Silicon Photonics

87% match2024

Optical Transformers

82% match2023

ARTEMIS: A Mixed Analog-Stochastic In-DRAM Accelerator for Transformer Neural Networks

82% match2024

A Survey of Techniques for Optimizing Transformer Inference

81% match2023

FAMOUS: Flexible Accelerator for the Attention Mechanism of Transformer on UltraScale+ FPGAs

81% match2024

ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers

80% match2023

Cite this paper

@article{afifi2023tron,
  title  = {TRON: Transformer Neural Network Acceleration with Non-Coherent Silicon Photonics},
  author = {Salma Afifi and Febin Sunny and Mahdi Nikdast and Sudeep Pasricha},
  year   = {2023},
  eprint = {2303.12914},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.12914v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.12914.svg)](https://codeofpaper.com/paper/2303.12914)

Discussion