Principles and Practice of Parallel Programming

• ElasGNN: An Elastic Training Framework for Distributed GNN Training
• APERTURE: Algorithm-System Co-optimization for Temporal Graph Network Inference
• Accelerating Sparse Transformer Inference on GPU
• Exploiting Efficient Mapping and Pipelined Execution for Accelerating SpMV on Tensor Cores
• Session Chair of ML Inference (part of Main Conference)