Yuetao Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yuetao Chen has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Daxin Jiang
StepFun, Shanghai, China
1 shared publication - Donglin Bai
Microsoft Research, Beijing, China
1 shared publication - Hong Xu
The Chinese University of Hong Kong, Hong Kong, Hong Kong
1 shared publication - Kun Li
Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China
1 shared publication - Kun Yan
SKLSDE Lab, Beihang University
1 shared publication - Lei Wang
Peking University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 11 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 101-116
Dynamic Sparsity in Large-Scale Video DiT Training
- 11 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 101-116
Open AccessDynamic Sparsity in Large-Scale Video DiT Training
- Open Access
- 20 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 333-347
ConvStencil: Transform Stencil Computation to Matrix Multiplication on Tensor Cores
Tensor Core Unit (TCU) is increasingly integrated into modern high-performance processors to enhance matrix multiplication performance. However, constrained to its over-specification, its potential for improving other critical scientific operations like stencil computations remains untapped. This paper presents ConvStencil1, a novel stencil computing system designed to efficiently transform stencil computation to matrix multiplication on Tensor Cores. We first develop a performance model for ConvStencil to guide algorithm design and optimization on TCUs. Based on this model, we propose three techniques: (1) Memory-efficient Layout Transformation using the stencil2row method; (2) Computation-dense Compute Adaptation with Dual Tessellation and kernel fusion; and (3) Performance-boosting Conflict Removal using a Lookup Table and Dirty Bits Padding. ConvStencil outperforms other stencil optimization frameworks, achieving significant speedups compared to solutions like AMOS, cuDNN, Brick, DRStencil, and TCStencil. By transforming stencil computation on Tensor Cores, ConvStencil promises to improve the performance of various scientific and engineering applications.
- 20 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 333-347
Open AccessConvStencil: Transform Stencil Computation to Matrix Multiplication on Tensor Cores
Tensor Core Unit (TCU) is increasingly integrated into modern high-performance processors to enhance matrix multiplication performance. However, constrained to its over-specification, its potential for improving other critical scientific operations like stencil computations remains untapped. This paper presents ConvStencil1, a novel stencil computing system designed to efficiently transform stencil computation to matrix multiplication on Tensor Cores. We first develop a performance model for ConvStencil to guide algorithm design and optimization on TCUs. Based on this model, we propose three techniques: (1) Memory-efficient Layout Transformation using the stencil2row method; (2) Computation-dense Compute Adaptation with Dual Tessellation and kernel fusion; and (3) Performance-boosting Conflict Removal using a Lookup Table and Dirty Bits Padding. ConvStencil outperforms other stencil optimization frameworks, achieving significant speedups compared to solutions like AMOS, cuDNN, Brick, DRStencil, and TCStencil. By transforming stencil computation on Tensor Cores, ConvStencil promises to improve the performance of various scientific and engineering applications.