About Me

Hello! I’m Arjun, a final-year Ph.D. student in the Computer Science department at the University of California, Merced. I am fortunate to be advised by Prof. Xiaoyi Lu. My interests are in designing efficient networked and storage systems in datacenter environments, focusing on leveraging DPUs/SmartNICs. I have also worked on projects related to storage disaggregation and persistent memory.

News

04/04/2025Our paper DPU-KV: On the Benefits of DPU Offloading for In-Memory Key-Value Stores at the Edge will appear in HPDC'25.
03/10/2025Our paper Understanding the Idiosyncrasies of Emerging BlueField DPUs will appear in ICS'25.
03/29/2022Our paper NVMe-oAF: Towards Adaptive NVMe-oF for IO-Intensive Workloads on HPC Cloud will appear in HPDC'22.
03/29/2021Our paper Towards Offloadable and Migratable Microservices on Disaggregated Architectures: Vision, Challenges, and Research Roadmap got accepted in WORDS'21 (co-located with ASPLOS'21).
12/1/2020Our work "Understanding the Idiosyncrasies of Real Persistent Memory" will appear in VLDB'21.
9/21/2020Our work "Impact of Commodity Networks on Storage Disaggregation with NVMe-oF" will appear in International Symposium on Benchmarking, Measuring and Optimizing (Bench'20) conference. We evaluated the performance of NVMe-oF over TCP, IPoIB, RoCE, and RDMA transports.

Publications

  1. [HPDC’25] DPU-KV: On the Benefits of DPU Offloading for In-Memory Key-Value Stores at the Edge
    Arjun Kashyap, Yuke Li, and Xiaoyi Lu
    International ACM Symposium on High Performance and Distributed Computing (HPDC), July 2025
    (To appear)
  2. [ICS’25] Understanding the Idiosyncrasies of Emerging BlueField DPUs
    Arjun Kashyap, Yuke Li, Darren Ng, and Xiaoyi Lu
    ACM International Conference on Supercomputing (ICS), June 2025
    [Paper]
  3. [IPDPS’24] Accelerating Lossy and Lossless Compression on Emerging BlueField DPU Architectures
    Yuke Li, Arjun Kashyap, Weicong Chen, Yanfei Guo, and Xiaoyi Lu
    IEEE International Parallel and Distributed Processing Symposium (IPDPS), May 2024
    [Paper]
  4. [IPDPS’24] NVMe-oPF: Designing Efficient Priority Schemes for NVMe-over-Fabrics with Multi-Tenancy Support
    Darren Ng, Andrew Lin, Arjun Kashyap, Guanpeng Li, and Xiaoyi Lu
    IEEE International Parallel and Distributed Processing Symposium (IPDPS), May 2024
    [Paper]
  5. [IEEE Micro’24] Compression Analysis for BlueField-2/3 DPUs: Lossy and Lossless Perspectives
    Yuke Li, Arjun Kashyap, Yanfei Guo, and Xiaoyi Lu
    [Paper]
  6. [SC’23] An Early Case Study with Multi-Tenancy Support in SPDK’s NVMe-over-Fabric Designs (Poster)
    Darren Ng, Charles Parkinson, Andrew Lin, Arjun Kashyap, and Xiaoyi Lu
    Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC), November 2023
  7. [ModSim’23] Early Experiences in Modeling Performance Implications of DPU-Offloaded Computation
    Weicong Chen, Yuke Li, Arjun Kashyap, and Xiaoyi Lu
    Workshop on Modeling & Simulation of Systems and Applications (ModSim), August 2023
  8. [HOTI’23] Characterizing Lossy and Lossless Compression on Emerging BlueField DPU Architectures
    Yuke Li, Arjun Kashyap, Yanfei Guo, and Xiaoyi Lu
    IEEE Symposium on High-Performance Interconnects (HOTI), August 2023
    [Paper]
  9. [HPDC’22] NVMe-oAF: Towards Adaptive NVMe-oF for IO-Intensive Workloads on HPC Cloud
    Arjun Kashyap and Xiaoyi Lu
    International ACM Symposium on High Performance and Distributed Computing (HPDC), June 2022
    [Paper]

  10. [WORDS’21] Towards Offloadable and Migratable Microservices on Disaggregated Architectures: Vision, Challenges, and Research Roadmap
    Xiaoyi Lu and Arjun Kashyap
    The Second Workshop On Resource Disaggregation and Serverless (WORDS), April 2021
    [Paper]

  11. [VLDB’21] Understanding the Idiosyncrasies of Real Persistent Memory
    Shashank Gugnani, Arjun Kashyap, and Xiaoyi Lu
    International Conference on Very Large Data Bases (VLDB), Aug 2021
    [Paper] [Code]

  12. [Bench’20] Impact of Commodity Networks on Storage Disaggregation with NVMe-oF
    Arjun Kashyap, Shashank Gugnani, and Xiaoyi Lu
    International Symposium on Benchmarking, Measuring and Optimizing (Bench), Nov 2020
    [Paper] [Video]