Xpikeformer: Hybrid Analog-Digital Hardware Acceleration for Spiking Transformers
This paper introduces Xpikeformer, a hybrid analog-digital hardware architecture designed to accelerate spiking neural network (SNN)-based transformer models. By combining the energy efficiency and temporal dynamics of SNNs with the powerful sequence modeling capabilities of transformers, Xpikeforme...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | This paper introduces Xpikeformer, a hybrid analog-digital hardware
architecture designed to accelerate spiking neural network (SNN)-based
transformer models. By combining the energy efficiency and temporal dynamics of
SNNs with the powerful sequence modeling capabilities of transformers,
Xpikeformer leverages mixed analog-digital computing techniques to enhance
performance and energy efficiency. The architecture integrates analog in-memory
computing (AIMC) for feedforward and fully connected layers, and a stochastic
spiking attention (SSA) engine for efficient attention mechanisms. We detail
the design, implementation, and evaluation of Xpikeformer, demonstrating
significant improvements in energy consumption and computational efficiency.
Through an image classification task and a wireless communication symbol
detection task, we show that Xpikeformer can achieve software-comparable
inference accuracy. Energy evaluations reveal that Xpikeformer achieves up to a
$17.8$--$19.2\times$ reduction in energy consumption compared to
state-of-the-art digital ANN transformers and up to a $5.9$--$6.8\times$
reduction compared to fully digital SNN transformers. Xpikeformer also achieves
a $12.0\times$ speedup compared to the GPU implementation of spiking
transformers. |
---|---|
DOI: | 10.48550/arxiv.2408.08794 |