GCN-ABFT: Low-Cost Online Error Checking for Graph Convolutional Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peltekis, Christodoulos, Dimitrakopoulos, Giorgos
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917878886825984
author Peltekis, Christodoulos
Dimitrakopoulos, Giorgos
author_facet Peltekis, Christodoulos
Dimitrakopoulos, Giorgos
contents Graph convolutional networks (GCNs) are popular for building machine-learning application for graph-structured data. This widespread adoption led to the development of specialized GCN hardware accelerators. In this work, we address a key architectural challenge for GCN accelerators: how to detect errors in GCN computations arising from random hardware faults with the least computation cost. Each GCN layer performs a graph convolution, mathematically equivalent to multiplying three matrices, computed through two separate matrix multiplications. Existing Algorithm-based Fault Tolerance(ABFT) techniques can check the results of individual matrix multiplications. However, for a GCN layer, this check should be performed twice. To avoid this overhead, this work introduces GCN-ABFT that directly calculates a checksum for the entire three-matrix product within a single GCN layer, providing a cost-effective approach for error detection in GCN accelerators. Experimental results demonstrate that GCN-ABFT reduces the number of operations needed for checksum computation by over 21% on average for representative GCN applications. These savings are achieved without sacrificing fault-detection accuracy, as evidenced by the presented fault-injection analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18534
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GCN-ABFT: Low-Cost Online Error Checking for Graph Convolutional Networks
Peltekis, Christodoulos
Dimitrakopoulos, Giorgos
Hardware Architecture
Machine Learning
Graph convolutional networks (GCNs) are popular for building machine-learning application for graph-structured data. This widespread adoption led to the development of specialized GCN hardware accelerators. In this work, we address a key architectural challenge for GCN accelerators: how to detect errors in GCN computations arising from random hardware faults with the least computation cost. Each GCN layer performs a graph convolution, mathematically equivalent to multiplying three matrices, computed through two separate matrix multiplications. Existing Algorithm-based Fault Tolerance(ABFT) techniques can check the results of individual matrix multiplications. However, for a GCN layer, this check should be performed twice. To avoid this overhead, this work introduces GCN-ABFT that directly calculates a checksum for the entire three-matrix product within a single GCN layer, providing a cost-effective approach for error detection in GCN accelerators. Experimental results demonstrate that GCN-ABFT reduces the number of operations needed for checksum computation by over 21% on average for representative GCN applications. These savings are achieved without sacrificing fault-detection accuracy, as evidenced by the presented fault-injection analysis.
title GCN-ABFT: Low-Cost Online Error Checking for Graph Convolutional Networks
topic Hardware Architecture
Machine Learning
url https://arxiv.org/abs/2412.18534