Towards 3D Acceleration for low-power Mixture-of-Experts and Multi-Head Attention Spiking Transformers

Guardado en:

Detalles Bibliográficos
Publicado en:	arXiv.org (Dec 7, 2024), p. n/a
Autor principal:	Xu, Boxun
Otros Autores:	Hwang, Junyoung, Vanna-iampikul, Pruek, Yin, Yuxuan, Lim, Sung Kyu, Li, Peng
Publicado:	Cornell University Library, arXiv.org
Materias:	Brain Circuits Neural networks Mixtures Hardware Spiking Distributed processing Logic Network latency
Acceso en línea:	Citation/Abstract Full text outside of ProQuest
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Descripción
Resumen:	Spiking Neural Networks(SNNs) provide a brain-inspired and event-driven mechanism that is believed to be critical to unlock energy-efficient deep learning. The mixture-of-experts approach mirrors the parallel distributed processing of nervous systems, introducing conditional computation policies and expanding model capacity without scaling up the number of computational operations. Additionally, spiking mixture-of-experts self-attention mechanisms enhance representation capacity, effectively capturing diverse patterns of entities and dependencies between visual or linguistic tokens. However, there is currently a lack of hardware support for highly parallel distributed processing needed by spiking transformers, which embody a brain-inspired computation. This paper introduces the first 3D hardware architecture and design methodology for Mixture-of-Experts and Multi-Head Attention spiking transformers. By leveraging 3D integration with memory-on-logic and logic-on-logic stacking, we explore such brain-inspired accelerators with spatially stackable circuitry, demonstrating significant optimization of energy efficiency and latency compared to conventional 2D CMOS integration.
ISSN:	2331-8422
Fuente:	Engineering Database