All Stories

  1. M^2 -DFU: Multi-Mode Dataflow Architecture for Adaptive and High-Efficiency Data Processing

    Article • ACM Transactions on Computer Systems, August 2026, ACM (Association for Computing Machinery)

    Zhihua Fan

  2. Making AI Text Generation Faster and More Energy Efficient on Mobile Devices

    Article • July 2026, ACM (Association for Computing Machinery)

    Zhihua Fan, Zirui Ma

  3. UniNL: Unifying Fragmented Non-Linear Operators for Efficient Edge LLM Inference

    Article • July 2026, ACM (Association for Computing Machinery)

    Shantian Qin, Zhihua Fan

  4. TOSCA: A Dataflow Architecture with Semi-Centralized Dynamic Scheduling

    Article • ACM Transactions on Architecture and Code Optimization, July 2026, ACM (Association for Computing Machinery)

    Shantian Qin, Zhihua Fan

  5. BitRed: Taming Non-Uniform Bit-Level Sparsity with a Programmable RISC-V ISA for DNN Acceleration

    Article • March 2026, ACM (Association for Computing Machinery)

    Zhihua Fan

  6. Compressing and Accelerating Sparse CNNs Using Sign-Reserved Toeplitz Filters and Input Activation Density-aware Dataflow

    Article • ACM Transactions on Architecture and Code Optimization, December 2025, ACM (Association for Computing Machinery)

    Zhihua Fan

  7. DFGAS: Exploring the Balance of HW-SW Scheduling through the DFG-Aware Scheme

    Article • ACM Transactions on Architecture and Code Optimization, December 2025, ACM (Association for Computing Machinery)

    Zhihua Fan

  8. GenCNN: A Partition-Aware Multi-Objective Mapping Framework for CNN Accelerators Based on Genetic Algorithm

    Article • ACM Transactions on Architecture and Code Optimization, September 2025, ACM (Association for Computing Machinery)

    Zhihua Fan

  9. PANDA: A Dataflow Chip with Adaptive Prefetching and Decentralized Scheduling

    Article • ACM Transactions on Architecture and Code Optimization, June 2025, ACM (Association for Computing Machinery)

    Shantian Qin, Zhihua Fan

  10. LeakageFreeSpec: Applying the Wiping Approach to Defend Against Transient Execution Attacks

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

    Zhihua Fan

  11. Improving Utilization of Dataflow Unit for Multi-Batch Processing.

    Article • ACM Transactions on Architecture and Code Optimization, December 2023, ACM (Association for Computing Machinery)

    Zhihua Fan