FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networks

2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)(2021)

引用 27|浏览11
暂无评分
摘要
We develop a fused matrix multiplication kernel that unifies sampled dense-dense matrix multiplication and sparsedense matrix multiplication under a single operation called FusedMM. By using user-defined functions, FusedMM can capture almost all computational patterns needed by popular graph embedding and GNN approaches.FusedMM is an order of magnitude faster than its equivalent kernels in Deep Gr...
更多
查看译文
关键词
Distributed processing,Program processors,Memory management,Bandwidth,Load management,Libraries,Graph neural networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要