publications
2025
- HPCADitto: Accelerating Diffusion Model via Temporal Value SimilarityIn 2025 IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2025
- JournalREC: Enhancing fine-grained cache coherence protocol in multi-GPU systemsJournal of Systems Architecture, 2025
2024
- ICCDAirGun: Adaptive Granularity Quantization for Accelerating Large Language Models (Accepted)In International Conference on Computer Design (ICCD), 2024
- ISLPEDGUMSO: Gating Unnecessary On-Chip Memory Slices for Power Optimization on GPUsIn International Symposium on Low Power Electronics and Design (ISLPED), 2024
- Journal
2023
- MICROExploiting Inherent Properties of Complex Numbers for Accelerating Complex Valued Neural NetworksIn 2023 56th IEEE/ACM International Symposium on Microarchitecture (MICRO), 2023
- ISPASSEarly-Adaptor: An Adaptive Framework forProactive UVM Memory ManagementIn 2023 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2023
2022
- US PatentMemory device including a plurality of area having different refresh periods, memory controller controlling the same and memory system including the sameMar 2022US Patent 11,276,452
2021
- Book