News

May. 2024Our paper "Characterizing In-Kernel Observability of Latency-Sensitive Request-level Metrics with eBPF," has been nominated for the Best Paper Award at the IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) 2024.
Mar. 2024Our paper "Characterizing In-Kernel Observability of Latency-Sensitive Request-level Metrics with eBPF," has been accepted in IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2024.
Aug. 2023Our paper "WattWiser: Power Resource-Efficient Scheduling for Multi-Model Multi-GPU Inference Servers," has been accepted in IEEE International Green and Sustainable Computing (IGSC), 2023.
Dec. 2022Our paper "KRISP: Enabling Kernel-wise Right-sizing for Spatial Partitioned GPU Inference Servers," has been accepted in IEEE International Symposium on High Performance Computer Architecture (HPCA), 2023.
July 2022I will be joining NVIDIA as Research Intern (Hyperscale Graphics Systems Group) in Fall 2022.
Apr. 2022Our work-in-progress "ScaleServe: A Scalable Multi-GPU Machine Learning Inference System and Benchmarking Suite," has been published in the 14th workshop on General Purpose Processing Using GPU (GPGPU), 2022.
Feb. 2022I will be joining Motional as Machine Learning Intern (Lidar Group) in Spring 2022.
Jan. 2022Our paper "PowerMorph: QoS-aware Server Power Reshaping for Data Center Regulation Service," has been accepted in ACM Transactions on Architecture and Code Optimization (TACO), 2022.
Sep. 2021Our paper "Inf4Edge: Automatic Resource-aware Generation of Energy-efficient CNN Inference Accelerator for Edge Embedded FPGAs," has been accepted in IEEE Workshop on Energy-Efficient Machine Learning (E2ML), 2021.
July. 2021Our paper "Deflection-aware Routing Algorithm in Network on Chip against Soft Errors and Crosstalk Faults," has been accepted in the 15th IEEE International Conference on Networking, Architecture, and Storage (NAS), 2021.
July. 2021Our paper "ICAP: Designing Inrush Current Aware Power Gating Switch for GPGPU," has been accepted in the 15th IEEE International Conference on Networking, Architecture, and Storage (NAS), 2021.
Mar. 2021Our paper "BlockMaestro: Enabling Programmer-Transparent Task-based Execution in GPU Systems," has been accepted in the IEEE/ACM International Symposium on Computer Architecture (ISCA), 2021.
Dec. 2020I will be joining Motional as Software Engineer Intern (Virtual World Infrastructure Group), in Winter 2021.
Sep. 2020Our paper "GPU-NEST: Characterizing Energy Efficiency of Multi-GPU Inference Servers," has been accepted in IEEE Computer Architecture Letters (CAL), 2020.