All Stories

  1. System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

    Article • June 2024, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  2. TEA+ : A Novel Temporal Graph Random Walk Engine with Hybrid Storage Architecture

    Article • ACM Transactions on Architecture and Code Optimization, May 2024, ACM (Association for Computing Machinery)

    Heng Zhang, Shuaiwen Leon Song

  3. Mitigating Coupling Map Constrained Correlated Measurement Errors on Quantum Devices

    Article • November 2023, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  4. NAS-SE: Designing A Highly-Efficient In-Situ Neural Architecture Search Engine for Large-Scale Deployment

    Article • October 2023, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  5. HEAT: A Highly Efficient and Affordable Training System for Collaborative Filtering Based Recommendation on CPUs

    Article • June 2023, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  6. TEA: A General-Purpose Temporal Graph Random Walk Engine

    Article • May 2023, ACM (Association for Computing Machinery)

    Jinlei Jiang, Shuaiwen Leon Song

  7. DynamAP: Architectural Support for Dynamic Graph Traversal on the Automata Processor

    Article • ACM Transactions on Architecture and Code Optimization, December 2022, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song, Yiding Liu

  8. T-GCN

    Article • October 2022, ACM (Association for Computing Machinery)

    Heng Zhang, Jinlei Jiang, Shuaiwen Leon Song

  9. Vapro

    Article • March 2022, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  10. AStitch: enabling a new multi-dimensional optimization space for memory-intensive ML training and inference on modern SIMT architectures

    Article • February 2022, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  11. MAPA

    Article • November 2021, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  12. Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrieving

    Article • October 2021, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  13. Toward efficient interactions between Python and native libraries

    Article • August 2021, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  14. Fast and Scalable Sparse Triangular Solver for Multi-GPU Based HPC Architectures

    Article • August 2021, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  15. ClickTrain

    Article • June 2021, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song, Geng Yuan

  16. η-LSTM: Co-Designing Highly-Efficient Large LSTM Training via Exploiting Memory-Saving and Architectural Design Opportunities

    Article • June 2021, Institute of Electrical & Electronics Engineers (IEEE)

    Shuaiwen Leon Song

  17. Designing Future Planet-Scale Virtual Reality System via Software-Hardware Co-design

    Article • April 2021, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song

  18. An efficient uncertain graph processing framework for heterogeneous architectures

    Article • February 2021, ACM (Association for Computing Machinery)

    Heng Zhang, Shuaiwen Leon Song

  19. A novel memory-efficient deep learning training framework via error-bounded lossy compression

    Article • February 2021, ACM (Association for Computing Machinery)

    Shuaiwen Leon Song