SC25 Home
Close

Session

Paper
: Algorithms: Matrix Multiplication and GEMM Optimization
Session Chair
Qinglei Cao
Saint Louis University
Event Type
Paper
give feedback
TimeThursday, 20 November 202510:30am - 12:00pm CST
Location260-267
Tags
Algorithms
HPC for Machine Learning
Programming Frameworks
Recordings
Livestreamed
Recorded
Registration Categories
TP
Similar Sessions
Auto-Tuning, Compilation, and Code Generation
Machine Learning: Methods
Performance: Sparse Matrix and Tensor Computation
Presentations
10:30am - 10:52am CSTKAMI: Communication-Avoiding General Matrix Multiplication Within a Single GPU
Authors
Hemeng Wang
Yang Du
Sidu Li
Xiaowen Tian
Qingxiao Sun
Weifeng Liu
Algorithms
10:52am - 11:15am CSTMXBLAS: Accelerating 8-Bit Deep Learning with a Unified Micro-Scaled GEMM Library
Authors
Weihu Wang
Yaqi Xia
Donglin Yang
Xiaobo Zhou
Dazhao Cheng
HPC for Machine Learning
11:15am - 11:37am CSTHyTiS: Hybrid Tile Scheduling for GPU GEMM with Enhanced Wave Utilization and Cache Locality
Authors
Zheng Zhang
Hulin Wang
Hongming Xu
Donglin Yang
Xiaobo Zhou
Dazhao Cheng
Programming Frameworks
11:37am - 12:00pm CSTLiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving
Authors
Huanqi Hu
Bowen Xiao
Shixuan Sun
Jianian Yin
Zhexi Zhang
Xiang Luo
Chengquan Jiang
Weiqi Xu
Xiaoying Jia
Xin Liu
Minyi Guo
HPC for Machine Learning