Cambricon-D: Full-Network Differential Acceleration for Diffusion Models

Diffusion models have made significant progress in current image generation tasks, thus becoming a prominent area of research. Diffusion models necessitate repetitive iterations on minimally altered input data across timesteps, each timestep requiring the recalculation of the entire model, resulting...

Full description

Bibliographic Details

Published in:	2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) pp. 903 - 914
Main Authors:	Kong, Weihao, Hao, Yifan, Guo, Qi, Zhao, Yongwei, Song, Xinkai, Li, Xiaqing, Zou, Mo, Du, Zidong, Zhang, Rui, Liu, Chang, Wen, Yuanbo, Jin, Pengwei, Hu, Xing, Li, Wei, Xu, Zhiwei, Chen, Tianshi
Format:	Conference Proceeding
Language:	English
Published:	IEEE 29.06.2024
Subjects:	Computational modeling Computer Architecture Diffusion Models Image synthesis Loading Machine Learning Memory architecture Memory management Merging Termination of employment
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!