AutoSAGE: Input-Aware CUDA Scheduling for Sparse GNN Aggregation (SpMM/SDDMM) and CSR Attention

Documenti analoghi

• iSpLib: A Library for Accelerating Graph Neural Networks using Auto-tuned Sparse Operations
  di: Anik, Md Saidul Hoque, et al.
  Pubblicazione: (2024)
• DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs
  di: Liu, Jiahui, et al.
  Pubblicazione: (2024)
• Block Sparse Flash Attention
  di: Ohayon, Daniel, et al.
  Pubblicazione: (2025)
• One Size Does Not Fit All: Architecture-Aware Adaptive Batch Scheduling with DEBA
  di: Belias, François, et al.
  Pubblicazione: (2025)
• FuseSampleAgg: Fused Neighbor Sampling and Aggregation for Mini-batch GNNs
  di: Stanković, Aleksandar
  Pubblicazione: (2025)