Concepedia

Unified Memory Optimization

Unified Memory Optimization is a memory hierarchy optimization framework that integrates disparate memory spaces into a single coherent address space, enabling automatic data migration and coherence management to minimize explicit memory transfer overhead in heterogeneous computing systems.

12

Publications

292

Citations

34

Authors

14

Institutions

Publications per year

2017–2026

12

Parents

Publications

12

Performance Evaluation of Advanced Features in CUDA Unified Memory

2019 · 49 citations · Full text

, , +15

Benchmarking and Evaluating Unified Memory for OpenMP GPU Offloading

Alok Mishra, Lingda Li, Martin Kong et al. · 2017 · 43 citations · Full text

, , +16

Performance evaluation of Unified Memory with prefetching and oversubscription for selected parallel CUDA applications on NVIDIA Pascal and Volta GPUs

Marcin Knap, Paweł Czarnul · The Journal of Supercomputing · 2019 · 43 citations · Full text

, , +17

DeepUM: Tensor Migration and Prefetching in Unified Memory

Jaehoon Jung, Jin-Pyo Kim, Jaejin Lee · 2023 · 29 citations

, , +17

Performance evaluation of unified memory and dynamic parallelism for selected parallel CUDA applications

Łukasz Jarząbek, Paweł Czarnul · The Journal of Supercomputing · 2017 · 25 citations · Full text

, , +17

1–5 of 12

Authors

34

  1. JL
    Jaejin Lee

    Seoul National University, South Korea

    2 publications · 44 citations

    2

    h-index

  2. PC
    Paweł Czarnul

    Gdańsk University of Technology, Poland

    2 publications · 68 citations

    2

    h-index

  3. JJ
    Jaehoon Jung

    Seoul National University, South Korea

    2 publications · 44 citations

    2

    h-index

  4. ŁJ
    Łukasz Jarząbek

    International Institute for Applied Systems Analysis, Austria

    1 publications · 25 citations

    1

    h-index

  5. HF
    Hal Finkel

    Argonne National Laboratory, United States

    1 publications · 43 citations

    1

    h-index

1–5 of 34

Institutions

14

  1. Gdańsk University of Technology

    Gdansk, Poland

    2 h-index

    4 publications

    136 citations

  2. KTH Royal Institute of Technology

    Stockholm, Sweden

    2 h-index

    3 publications

    113 citations

  3. Lawrence Livermore National Laboratory

    Livermore, United States

    2 h-index

    3 publications

    77 citations

  4. Seoul National University

    Seoul, South Korea

    2 h-index

    7 publications

    133 citations

  5. Argonne National Laboratory

    Lemont, United States

    2 h-index

    2 publications

    57 citations

  6. Brookhaven National Laboratory

    Upton, United States

    1 h-index

    3 publications

    129 citations

  7. Politecnico di Torino

    Turin, Italy

    1 h-index

    2 publications

    22 citations

  8. University of California, Davis

    Davis, United States

    1 h-index

    3 publications

    36 citations

1–8 of 14

Venues

  1. The Journal of Supercomputing

    3 publications · 81 citations

    3

    h-index

  2. Applied Sciences

    2 publications · 34 citations

    2

    h-index

  3. arXiv (Cornell University)

    Repository · 1 publications · 12 citations

    1

    h-index

  4. 1

    h-index

  5. Journal of Grid Computing

    1 publications · 13 citations

1–5