NeuraChip: Accelerating GNN Computations with a Hash-based Decoupled Spatial Accelerator

Graph Neural Networks (GNNs) are emerging as a formidable tool for processing non-euclidean data across various domains, ranging from social network analysis to bioinformatics. Despite their effectiveness, their adoption has not been pervasive because of scalability challenges associated with large-...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) S. 946 - 960
Hauptverfasser:	Shivdikar, Kaustubh, Agostini, Nicolas Bohm, Jayaweera, Malith, Jonatan, Gilbert, Abellan, Jose L., Joshi, Ajay, Kim, John, Kaeli, David
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 29.06.2024
Schlagworte:	Computer architecture Decoupled Computations Graph neural networks Graph Neural Networks (GNN) Hardware-software co-design On-chip Memory Organizations Prefetching Scalability Social networking (online) Source coding Sparse Matrix Multiplication (SpGEMM) Spatial Accelerators
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!