A 28.6 mJ/iter Stable Diffusion Processor for Text-to-Image Generation with Patch Similarity-based Sparsity Augmentation and Text-based Mixed-Precision
This paper presents an energy-efficient stable diffusion processor for text-to-image generation. While stable diffusion attained attention for high-quality image synthesis results, its inherent characteristics hinder its deployment on mobile platforms. The proposed processor achieves high throughput and energy efficiency with three key features as solutions: 1) Patch similarity-based sparsity augmentation (PSSA) to reduce external memory access (EMA) energy of self-attention score by 60.3 %, leading to 37.8 % total EMA energy reduction. 2) Text-based important pixel spotting (TIPS) to allow 44.8 % of the FFN layer workload to be processed with low-precision activation. 3) Dual-mode bit-slice core (DBSC) architecture to enhance energy efficiency in FFN layers by 43.0 %. The proposed processor is implemented in 28 nm CMOS technology and achieves 3.84 TOPS peak throughput with 225.6 mW average power consumption. In sum, 28.6 mJ/iteration highly energy-efficient text-to-image generation processor can be achieved at MS-COCO dataset.
@article{arxiv.2403.04982,
title = {A 28.6 mJ/iter Stable Diffusion Processor for Text-to-Image Generation with Patch Similarity-based Sparsity Augmentation and Text-based Mixed-Precision},
author = {Jiwon Choi and Wooyoung Jo and Seongyon Hong and Beomseok Kwon and Wonhoon Park and Hoi-Jun Yoo},
journal= {arXiv preprint arXiv:2403.04982},
year = {2024}
}
Comments
Accepted at 2024 IEEE International Symposium on Circuits and Systems (ISCAS)