publications
2025
- IPDPSGIFTS: Efficient GCN Inference Framework on PyTorch-CPU via Exploring the SparsityIn Proceedings of the IEEE International Parallel & Distributed Processing Symposium (IPDPS), 2025
- DACSAGA: A Memory-Efficient Accelerator for GANN Construction via Harnessing Vertex SimilarityIn Design Automation Conference (DAC), 2025
2024
- HPCADifferential-Matching Prefetcher for Indirect Memory AccessIn The 30-th IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2024
2022
- TPDSA Comprehensive Performance Model of Sparse Matrix-Vector Multiplication to Guide Kernel OptimizationIEEE Transactions on Parallel and Distributed Systems, 2022