Logo image
Wireless enabled Inter-Chiplet Communication in DNN Hardware Accelerators
Conference proceeding

Wireless enabled Inter-Chiplet Communication in DNN Hardware Accelerators

M Palesi, E Russo, A Das and J Jose
ispartofbook:IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)
2023

Abstract

Deep Neural Network (DNN) Hardware Accelerator Domain Specific Architecture (DSA) Multi-Chip-Module (MCM) Network-on-Package (NoP) Wireless-enabled NoP
Inter-chiplet communication is a fundamental bottleneck in scale-out Homogeneous Multi-Chip-Module-based Hardware Accelerators (HMCMHAs). This paper focuses on the problem of many-to-many communication traffic generated when dispatching output feature map tiles among chiplets. Such traffic has a strong impact on the latency and energy metrics of the HMCMHAs as it exposes the limitations of the existing wire-based Network-on-Package (NoP). This paper investigates augmenting the existing NoP with emerging wireless in-package communication links. The intrinsic single-hop and broadcastcapable technology is exploited to tackle the many-to-many communication traffic in question. We show that the proposed wireless-enabled NoP can significantly improve the latency and energy of Deep Neural Network (DNN) inference on HMCMHAs.

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
International collaboration
Web of Science research areas
Computer Science, Hardware & Architecture
Computer Science, Interdisciplinary Applications
Computer Science, Theory & Methods
Logo image