SC25 Home
Close

Presenter

Hai Jin
Huazhong University of Science and Technology
Presentations
Paper
StraGCN: GPU-Accelerated Strassen’s Sparse-Dense Matrix Multiplication for Graph Convolutional Network Training
4:15pm - 4:37pm CST Tuesday, 18 November 2025 263-264
HPC for Machine Learning
Performance Measurement, Modeling, & Tools
Programming Frameworks
Livestreamed
Recorded
TP
Paper
Bridging the Gap Between Unstructured SpMM and Structured Sparse Tensor Cores
4:37pm - 5:00pm CST Tuesday, 18 November 2025 263-264
HPC for Machine Learning
Performance Measurement, Modeling, & Tools
Programming Frameworks
Livestreamed
Recorded
TP
Paper
TaGNN: An Efficient Topology-Aware Accelerator for High-Performance Dynamic Graph Neural Networks
11:15am - 11:37am CST Tuesday, 18 November 2025 260-267
HPC for Machine Learning
System Software and Cloud Computing
Not Livestreamed
Not Recorded
Partially Livestreamed
Partially Recorded
TP
Paper
DiffMoE: Efficient Batched MoE Inference with Priority-Driven Differential Expert Caching
2:37pm - 3:00pm CST Thursday, 20 November 2025 275
Architectures & Networks
HPC for Machine Learning
Performance Measurement, Modeling, & Tools
Programming Frameworks
Livestreamed
Recorded
TP