TNNGen: Automated Design of Neuromorphic Sensory Processing Units for Time-Series Clustering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vellaisamy, Prabhu, Nair, Harideep, Ratnakaram, Vamsikrishna, Gupta, Dhruv, Shen, John Paul
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912168762408960
author Vellaisamy, Prabhu
Nair, Harideep
Ratnakaram, Vamsikrishna
Gupta, Dhruv
Shen, John Paul
author_facet Vellaisamy, Prabhu
Nair, Harideep
Ratnakaram, Vamsikrishna
Gupta, Dhruv
Shen, John Paul
contents Temporal Neural Networks (TNNs), a special class of spiking neural networks, draw inspiration from the neocortex in utilizing spike-timings for information processing. Recent works proposed a microarchitecture framework and custom macro suite for designing highly energy-efficient application-specific TNNs. These recent works rely on manual hardware design, a labor-intensive and time-consuming process. Further, there is no open-source functional simulation framework for TNNs. This paper introduces TNNGen, a pioneering effort towards the automated design of TNNs from PyTorch software models to post-layout netlists. TNNGen comprises a novel PyTorch functional simulator (for TNN modeling and application exploration) coupled with a Python-based hardware generator (for PyTorch-to-RTL and RTL-to-Layout conversions). Seven representative TNN designs for time-series signal clustering across diverse sensory modalities are simulated and their post-layout hardware complexity and design runtimes are assessed to demonstrate the effectiveness of TNNGen. We also highlight TNNGen's ability to accurately forecast silicon metrics without running hardware process flow.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17977
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TNNGen: Automated Design of Neuromorphic Sensory Processing Units for Time-Series Clustering
Vellaisamy, Prabhu
Nair, Harideep
Ratnakaram, Vamsikrishna
Gupta, Dhruv
Shen, John Paul
Hardware Architecture
Artificial Intelligence
Neural and Evolutionary Computing
Temporal Neural Networks (TNNs), a special class of spiking neural networks, draw inspiration from the neocortex in utilizing spike-timings for information processing. Recent works proposed a microarchitecture framework and custom macro suite for designing highly energy-efficient application-specific TNNs. These recent works rely on manual hardware design, a labor-intensive and time-consuming process. Further, there is no open-source functional simulation framework for TNNs. This paper introduces TNNGen, a pioneering effort towards the automated design of TNNs from PyTorch software models to post-layout netlists. TNNGen comprises a novel PyTorch functional simulator (for TNN modeling and application exploration) coupled with a Python-based hardware generator (for PyTorch-to-RTL and RTL-to-Layout conversions). Seven representative TNN designs for time-series signal clustering across diverse sensory modalities are simulated and their post-layout hardware complexity and design runtimes are assessed to demonstrate the effectiveness of TNNGen. We also highlight TNNGen's ability to accurately forecast silicon metrics without running hardware process flow.
title TNNGen: Automated Design of Neuromorphic Sensory Processing Units for Time-Series Clustering
topic Hardware Architecture
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2412.17977