Publications

Sehyeon Kim, Minkwan Kim, Chanho Park, Hanmok Park, Seonghoon Kim, Taigon Song, and William J. Song, “NPUWattch: ML-based Power, Area, and Timing Modeling for Neural Accelerators,” IEEE International Symposium on High-Performance Computer Architecture (HPCA), Jan. 2026.
Hyeonjin Kim, Taesoo Lim, and William J. Song, “Graphite: Hardware-Aware GNN Reshaping for Acceleration with GPU Tensor Cores,” IEEE Transactions on Parallel and Distributed Systems (TPDS), vol. 36, no. 5, May 2025, pp. 918-931.
Taesoo Lim, Hyeonjin Kim, Jingu Park, Bogil Kim, and William J. Song, “RoTA: Rotational Torus Accelerator for Wear Leveling of Neural Processing Elements,” Design, Automation and Test in Europe Conference and Exhibition (DATE), Mar. 2025, pp. 1-7.
Youngin Kim and William J. Song, “Genie Cache: Non-blocking Miss Handling and Replacement in Page-Table-based DRAM Cache,” IEEE/ACM International Symposium on Microarchitecture (MICRO), Nov. 2024, pp. 983-996.
HoSun Choi, Chanho Park, Euijun Kim, and William J. Song, “Nona: Accurate Power Prediction Model Using Neural Networks,” ACM/IEEE Design Automation Conference (DAC), no. 38, June 2024, pp. 1-6.
Chanho Park, Bogil Kim, Sungmin Ryu, and William J. Song, “NeuroSpector: Systematic Optimization of Dataflow Scheduling in DNN Accelerators,” IEEE Transactions on Parallel and Distributed Systems (TPDS), vol. 34, no. 8, Aug. 2023, pp. 2279-2294.
Hyeonjin Kim and William J. Song, “LAS: Locality-Aware Scheduling for GEMM-Accelerated Convolutions in GPUs,” IEEE Transactions on Parallel and Distributed Systems (TPDS), vol. 34, no. 5, May 2023, pp. 1479-1494.
Youngin Kim, Hyeonjin Kim, and William J. Song, “NOMAD: Enabling Non-blocking OS-Managed DRAM Cache via Tag-Data Decoupling,” IEEE International Symposium on High-Performance Computer Architecture (HPCA), Feb. 2023, pp. 193-205.
Jiwon Lee, Ju Min Lee, Yunho Oh, William J. Song, and Won Woo Ro, “SnakeByte: A TLB Design with Adaptive and Recursive Page Merging in GPUs,” IEEE International Symposium on High-Performance Computer Architecture (HPCA), Feb. 2023, pp. 1195-1207.
Bogil Kim, Sungjae Lee, Chanho Park, Hyeonjin Kim, and William J. Song, “The Nebula Benchmark Suite: Implications of Lightweight Neural Networks,” IEEE Transactions on Computers (TC), vol. 70, no. 11, Nov. 2021, pp. 1887-1900.
William J. Song, “Hardware Accelerator Systems for Embedded Systems,” Hardware Accelerator Systems for Artificial Intelligence and Machine Learning, Elsevier Advances in Computers, vol. 122, Mar. 2021, pp. 23-49.
Changsu Kim, Shinnung Jeong, Sungjun Cho, Yongwoo Lee, William J. Song, Youngsok Kim, and Hanjun Kim, “Thread-Aware Area-Efficient High-Level Synthesis Compiler for Embedded Devices,” International Symposium on Code Generation and Optimization (CGO), Mar. 2021, pp. 327-339.
Bogil Kim, Sungjae Lee, Amit Ranjan Trivedi, William J. Song, “Energy-Efficient Acceleration of Deep Neural Networks on Realtime-Constrained Embedded Edge Devices,” IEEE Access, vol. 8, Nov. 2020, pp. 216259-216270.
Hyeonjin Kim, Sungwoo Ahn, Yunho Oh, Bogil Kim, Won Woo Ro, and William J. Song, “Duplo: Lifting Redundant Memory Accesses of Deep Neural Networks for GPU Tensor Cores,” IEEE/ACM International Symposium on Microarchitecture (MICRO), Oct. 2020, pp. 725-737.
Yunho Oh, Myung Kuk Yoon, William J. Song, and Won Woo Ro, “FineReg: Fine-Grained Register File Management for Augmenting GPU Throughput,” IEEE/ACM International Symposium on Microarchitecture (MICRO), Oct. 2018, pp. 364-379.

Patents

William J. Song, Taesoo Lim, Hyeonjin Kim, Jingu Park, and Bogil Kim, “Neural Network Accelerator and Method for Operating the Same,” Application #US19/293,729, Aug. 2025.
Eunju Hwang, William J. Song, Chanho Park, and Euijun Kim, “System-on-Chip for Predicting Power Consumption of Processor and Managing Power Supplied to Processor and Operating Method Thereof,” Application #US19/172,181, Mar. 2025.
William J. Song, Youngin Kim, and Hyeonjin Kim, “DRAM Cache System and Operating Method of the Same,” Application #US18/627,459, Apr. 2024.
William J. Song and Hyeonjin Kim, “Neural Network Accelerator and Method of Controlling Same,” Application #US18/435,422, Feb. 2024.
William J. Song, Bogil Kim, Chanho Park, Semin Koong, and Taesoo Lim, “Deep Neural Network Accelerator for Optimized Data Processing and Control Method of the Deep Neural Network Accelerator,” Application #US18/127,875, Mar. 2023; Publication #US12,124,879, Oct. 2024.
William J. Song, Chanho Park, Bogil Kim, and Sungmin Ryu, “Neural Network Computing Device and Control Method Thereof,” Application #US17/883,010, Aug. 2022.
William J. Song, Won Woo Ro, Hyeonjin Kim, Sungwoo Ahn, Yunho Oh, and Bogil Kim, “Operation Device of Convolutional Neural Network, Operation Method of Convolutional Neural Network and Computer Program Stored in A Recording Medium to Execute the Method Thereof,” Application #US17/752,235, May 2022.
Seongil O, Won Woo Ro, William J. Song, and Jiwon Lee, “Controller, Computing System including the Same, and Method of Creating and Searching Page Table Entry for the Same,” Application #US17/526,391, Nov. 2021; Publication #US11,860,793, Jan. 2024.

Workshops, Tutorials, and More

Taesoo Lim, Hyeonjin Kim, Jingu Park, Bogil Kim, and William J. Song, “Wear Leveling of Processing Elements Array in Deep Neural Network Accelerators,” Design Automation Conference (DAC) – Work in Progress, July 2023.
Chanho Park, Semin Koong, Bogil Kim, Taesoo Lim, and William J. Song, “Fornax: Lightweight Energy-Efficient DNN Accelerator Architecture for Edge Devices,” Design Automation Conference (DAC) – Work in Progress, July 2023.
Bogil Kim, Chanho Park, Taesoo Lim, and William J. Song, “NPUsim: Full-System, Cycle-Accurate, Functional Simulations of Deep Neural Network Accelerators,” Workshop on Modeling and Simulation of Systems and Applications, Oct. 2021.
William J. Song, “Deep Learning Hardware Acceleration: Current Trends and Future Directions,” SK Hynix, Oct. 2020.
Bogil Kim, Sungjae Lee, and William J. Song, “Nebula: Lightweight Neural Network Benchmarks,” Workshop on Modeling and Simulation of Systems and Applications, Aug. 2020.
William J. Song, “NPUsim: Cycle-Accurate Architecture Simulation Framework for Neural Network Accelerators,” Samsung Advanced Institute of Technology, Jan. 2020.

Software Copyrights

Chanho Park, Bogil Kim, and Sungmin Ryu, and William J. Song, “NeuroSpector: Dataflow and Mapping Optimizer for Deep Neural Network Accelerators,” Korea Copyright Commission C-2025-010190, Mar. 2025.
Suan Jung, Yebin Chon, Jeongmin Hwang, and William J. Song, “RelSim: Computational Framework for Lifetime Reliability Modeling of Heterogeneous Accelerator Systems,” Korea Copyright Commission C-2022-054360, Dec. 2022.
Bogil Kim, Sungjae Lee, Chanho Park, Hyeonjin Kim, and William J. Song, “Nebula: Lightweight Neural Network Benchmarks,” Korea Copyright Commission C-2021-014465, Mar. 2021.