Yifeng Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yifeng Chen has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Kun Li
Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China
4 shared publications - Ting Cao
Tsinghua University
4 shared publications - Yunquan Zhang
Chinese Academy of Sciences
4 shared publications - Haozhi Han
School of Computer Science, Peking University, Beijing, China
3 shared publications - Mao Yang
Microsoft Research, Beijing, China
3 shared publications David A. Hills
Department of Engineering Science, Oxford University, OX1 3PJ, Oxford, UK
2 shared publications
Latest Publications
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 23 (1) , 1-24
MatXtract: Sparsity-Aware Matrix Transformation via Cascaded Compute Density EXtraction for SpMV
Sparse Matrix-Vector multiplication (SpMV) is a fundamental kernel across scientific computing and graph analytics. Modern GPUs feature specialized processing units such as Tensor Core Units (TCUs) for accelerating dense matrix operations. While recent efforts leverage TCUs for SpMV acceleration, direct TCU-only mappings suffer from poor cache utilization and limited performance generalization across diverse sparse matrices. This article presents MatXtract, 1 a sparsity-aware matrix transformation framework that restructures sparse matrices through cascaded compute density extraction, enabling efficient TCU-accelerated SpMV. MatXtract introduces three key components: (1) Compute Density Extraction optimizes memory hierarchy utilization while creating Tensor Core- and CUDA core-friendly computation substrates to enhance TCU compute density and CUDA core load balancing; (2) Cascaded Execution Kernel employs a two-stage cascaded compression that systematically exploits hierarchical sparsity to maximize GPU computational throughput; and (3) Sparsity-Aware Predictor mitigates the mismatch between fixed TCU computation and diverse sparsity through Bayesian optimization for enhanced performance generalization. Extensive evaluations on 2,059 matrices show that MatXtract outperforms cuSPARSE, DASP, CSR5, and Merge-SpMV, achieving higher performance on 96.64% of matrices, with an average 1.98× and up to 8.83× speedup over cuSPARSE on NVIDIA A100 GPUs.
- 22 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 23 (1) , 1-24
Open AccessMatXtract: Sparsity-Aware Matrix Transformation via Cascaded Compute Density EXtraction for SpMV
Sparse Matrix-Vector multiplication (SpMV) is a fundamental kernel across scientific computing and graph analytics. Modern GPUs feature specialized processing units such as Tensor Core Units (TCUs) for accelerating dense matrix operations. While recent efforts leverage TCUs for SpMV acceleration, direct TCU-only mappings suffer from poor cache utilization and limited performance generalization across diverse sparse matrices. This article presents MatXtract, 1 a sparsity-aware matrix transformation framework that restructures sparse matrices through cascaded compute density extraction, enabling efficient TCU-accelerated SpMV. MatXtract introduces three key components: (1) Compute Density Extraction optimizes memory hierarchy utilization while creating Tensor Core- and CUDA core-friendly computation substrates to enhance TCU compute density and CUDA core load balancing; (2) Cascaded Execution Kernel employs a two-stage cascaded compression that systematically exploits hierarchical sparsity to maximize GPU computational throughput; and (3) Sparsity-Aware Predictor mitigates the mismatch between fixed TCU computation and diverse sparsity through Bayesian optimization for enhanced performance generalization. Extensive evaluations on 2,059 matrices show that MatXtract outperforms cuSPARSE, DASP, CSR5, and Merge-SpMV, achieving higher performance on 96.64% of matrices, with an average 1.98× and up to 8.83× speedup over cuSPARSE on NVIDIA A100 GPUs.
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2126-2142
Matrix Is All You Need: Rearchitecting Quantum Chemistry to Scale on AI Accelerators
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2126-2142
Open AccessMatrix Is All You Need: Rearchitecting Quantum Chemistry to Scale on AI Accelerators
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1495-1509
SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1495-1509
Open AccessSparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation
- Open Access
- 28 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 355-368
FlashFFTStencil: Bridging Fast Fourier Transforms to Memory-Efficient Stencil Computations on Tensor Core Units
While Tensor Core Units (TCUs) excel in AI tasks, their application to HPC algorithms like stencil computations faces significant challenges due to sparsity, which leads to underutilization and exacerbates memory-bound limitations. This paper introduces FlashFFTStencil1, a memory-efficient stencil computing system designed to bridge FFT to fully-dense stencil computations on TCUs. Aimed at bound shifting, FlashFFTStencil comprises three key techniques: Kernel Tailoring on HBM fuses distinct kernels to enhance parallelism while reducing memory transfer and footprint; Architecture Aligning on SMEM restructures FFT-based stencil computations into dense matrix multiplications tailored for shared memory architecture; Computation Streamlining on TCU optimizes TCU utilization and thread parallelism by minimizing pipeline stalls and maximizing register reuse. Notably, a distinctive extension is FlashFFTStencil's ability to enable theoretically unrestricted temporal fusion by FFT. Results show that FlashFFTStencil achieves effective sparsity-free bound shifting, with an average speedup of 2.57x over the state-of-the-art. FlashFFTStencil pioneers a new era in unifying computational patterns within the HPC landscape and bridges them with cutting-edge AI-driven hardware innovations like TCUs.
- 28 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 355-368
Open AccessFlashFFTStencil: Bridging Fast Fourier Transforms to Memory-Efficient Stencil Computations on Tensor Core Units
While Tensor Core Units (TCUs) excel in AI tasks, their application to HPC algorithms like stencil computations faces significant challenges due to sparsity, which leads to underutilization and exacerbates memory-bound limitations. This paper introduces FlashFFTStencil1, a memory-efficient stencil computing system designed to bridge FFT to fully-dense stencil computations on TCUs. Aimed at bound shifting, FlashFFTStencil comprises three key techniques: Kernel Tailoring on HBM fuses distinct kernels to enhance parallelism while reducing memory transfer and footprint; Architecture Aligning on SMEM restructures FFT-based stencil computations into dense matrix multiplications tailored for shared memory architecture; Computation Streamlining on TCU optimizes TCU utilization and thread parallelism by minimizing pipeline stalls and maximizing register reuse. Notably, a distinctive extension is FlashFFTStencil's ability to enable theoretically unrestricted temporal fusion by FFT. Results show that FlashFFTStencil achieves effective sparsity-free bound shifting, with an average speedup of 2.57x over the state-of-the-art. FlashFFTStencil pioneers a new era in unifying computational patterns within the HPC landscape and bridges them with cutting-edge AI-driven hardware innovations like TCUs.
- 22 December 2023
- Published by Elsevier in Journal of the Mechanics and Physics of Solids
- Vol. 184, 105528
Non-slipping adhesive contact between dissimilar elastic solids under normal and tangential loads
- 22 December 2023
- Published by Elsevier in Journal of the Mechanics and Physics of Solids
- Vol. 184, 105528
Non-slipping adhesive contact between dissimilar elastic solids under normal and tangential loads
- 5 October 2023
- Published by Elsevier in International Journal of Solids and Structures
- Vol. 284
Investigation of stress states around a finite-height crack
- 5 October 2023
- Published by Elsevier in International Journal of Solids and Structures
- Vol. 284
Investigation of stress states around a finite-height crack
- 27 March 2023
- Published by SAGE Publications in The Journal of Strain Analysis for Engineering Design
- Vol. 58 (8) , 684-694
Shakedown of a plate with a circular hole: An educational problem
The shakedown limit for an infinite plate containing a circular hole and subject to oscillatory arbitrary remote loading is found, first by using Melan’s lower bound theorem, and secondly by using a finite element model. It is shown that in some cases the limit found from the Melan theorem using the solution for the residual state of stress for an over-pressurized hole provides the exact solution, specifically when the limiting factor is the reversal of the state of stress at a particular point, while in other cases the shakedown limit is rather higher.
- 27 March 2023
- Published by SAGE Publications in The Journal of Strain Analysis for Engineering Design
- Vol. 58 (8) , 684-694
Shakedown of a plate with a circular hole: An educational problem
The shakedown limit for an infinite plate containing a circular hole and subject to oscillatory arbitrary remote loading is found, first by using Melan’s lower bound theorem, and secondly by using a finite element model. It is shown that in some cases the limit found from the Melan theorem using the solution for the residual state of stress for an over-pressurized hole provides the exact solution, specifically when the limiting factor is the reversal of the state of stress at a particular point, while in other cases the shakedown limit is rather higher.