Spiking Transformer Hardware Accelerators in 3D Integration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Boxun, Hwang, Junyoung, Vanna-iampikul, Pruek, Lim, Sung Kyu, Li, Peng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916478120361984
author Xu, Boxun
Hwang, Junyoung
Vanna-iampikul, Pruek
Lim, Sung Kyu
Li, Peng
author_facet Xu, Boxun
Hwang, Junyoung
Vanna-iampikul, Pruek
Lim, Sung Kyu
Li, Peng
contents Spiking neural networks (SNNs) are powerful models of spatiotemporal computation and are well suited for deployment on resource-constrained edge devices and neuromorphic hardware due to their low power consumption. Leveraging attention mechanisms similar to those found in their artificial neural network counterparts, recently emerged spiking transformers have showcased promising performance and efficiency by capitalizing on the binary nature of spiking operations. Recognizing the current lack of dedicated hardware support for spiking transformers, this paper presents the first work on 3D spiking transformer hardware architecture and design methodology. We present an architecture and physical design co-optimization approach tailored specifically for spiking transformers. Through memory-on-logic and logic-on-logic stacking enabled by 3D integration, we demonstrate significant energy and delay improvements compared to conventional 2D CMOS integration.
format Preprint
id arxiv_https___arxiv_org_abs_2411_07397
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Spiking Transformer Hardware Accelerators in 3D Integration
Xu, Boxun
Hwang, Junyoung
Vanna-iampikul, Pruek
Lim, Sung Kyu
Li, Peng
Neural and Evolutionary Computing
Hardware Architecture
Spiking neural networks (SNNs) are powerful models of spatiotemporal computation and are well suited for deployment on resource-constrained edge devices and neuromorphic hardware due to their low power consumption. Leveraging attention mechanisms similar to those found in their artificial neural network counterparts, recently emerged spiking transformers have showcased promising performance and efficiency by capitalizing on the binary nature of spiking operations. Recognizing the current lack of dedicated hardware support for spiking transformers, this paper presents the first work on 3D spiking transformer hardware architecture and design methodology. We present an architecture and physical design co-optimization approach tailored specifically for spiking transformers. Through memory-on-logic and logic-on-logic stacking enabled by 3D integration, we demonstrate significant energy and delay improvements compared to conventional 2D CMOS integration.
title Spiking Transformer Hardware Accelerators in 3D Integration
topic Neural and Evolutionary Computing
Hardware Architecture
url https://arxiv.org/abs/2411.07397