NEM-GNN: DAC/ADC-less, Scalable, Reconfigurable, Graph and Sparsity-Aware Near-Memory Accelerator for Graph Neural Networks.
Siddhartha Raman Sundara RamanLizy Kurian JohnJaydeep P. KulkarniPublished in: ACM Trans. Archit. Code Optim. (2024)
Keyphrases
- neural network
- general purpose
- directed graph
- graph representation
- graph structure
- random walk
- graph theory
- pattern recognition
- graph model
- bipartite graph
- genetic algorithm
- graph construction
- parallel implementation
- associative memory
- connected components
- structured data
- graph theoretic
- low cost
- graph search
- graph based algorithm