Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution Networks

Graph Convolutional Networks (GCNs) are pivotal in extracting latent information from graph data across various domains, yet their acceleration on mainstream GPUs is challenged by workload imbalance and memory access irregularity. To address these challenges, we present Accel-GCN, a GPU accelerator...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Digest of technical papers - IEEE/ACM International Conference on Computer-Aided Design S. 01 - 09
Hauptverfasser:	Xie, Xi, Peng, Hongwu, Hasan, Amit, Huang, Shaoyi, Zhao, Jiahui, Fang, Haowen, Zhang, Wei, Geng, Tong, Khan, Omer, Ding, Caiwen
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 28.10.2023
Schlagworte:	Accelerator architectures Bandwidth Benchmark testing Convolution GPUs Graph Convolution Network Graphics processing units Memory management parallel computing Parallel processing sparse matrix multiplication (SpMM)
ISSN:	1558-2434
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!