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...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) S. 903 - 914
Hauptverfasser:	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:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 29.06.2024
Schlagworte:	Computational modeling Computer Architecture Diffusion Models Image synthesis Loading Machine Learning Memory architecture Memory management Merging Termination of employment
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!