Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 10 of 10 for “"Overlapping communication"”.

  1. Overlapping communication and computation with MPI-2 for Floyd's algorithm

    … overlap of computation with data transfer "communication" through the use of MPI_Bcast as the function to interchange information among participant processes. One of the reasons for the development of non-blocking instructions for MPI was to support the overlap of useful computation with …

    ttu Repository record for Overlapping communication and computation with MPI-2 for Floyd's algorithm (opens in a new tab)

  2. Seismic modeling and imaging with Fourier method : numerical analyses and parallel implementation strategies

    … first algorithm employs non-blocking all-to-all communications to optimize the conventional parallel Fourier modeling workflows by overlapping communication with computation. With a carefully designed communication-computation overlapping mechanism, a large amount of communication overhead can be …

    texas Repository record for Seismic modeling and imaging with Fourier method : numerical analyses and parallel implementation strategies (opens in a new tab)

  3. Adaptive strategy for one-sided communication in MPICH2

    The one-sided communication model (or remote memory access) supported by MPI-2 is more convenient to use than the regular two-sided send/receive communication model, because it allows the sender to specify all data transfer parameters and avoids the receiver to be explicitly involved in data …

    uiuc Repository record for Adaptive strategy for one-sided communication in MPICH2 (opens in a new tab)

  4. Multi-level Parallelism with MPI and OpenACC for CFD Applications

    … cavity flows is accelerated using OpenACC. Overlapping communication with computation improves performance for the multi-GPU implementation by up to 21%, achieving up to 400 times faster performance than a single CPU and 99% weak scalability efficiency with 32 GPUs. The second study ports …

    vt Repository record for Multi-level Parallelism with MPI and OpenACC for CFD Applications (opens in a new tab)

  5. SemCache: Semantics-Aware Caching for Efficient GPU Offloading

    … is very difficult to manually optimize CPU-GPU communication between multiple kernel invocations to avoid redundant communication when using these kernels with complex applications. ^ In this thesis, we introduce SemCache, a semantics-aware GPU cache that automatically manages CPU-GPU …

    purdue-thes Repository record for SemCache: Semantics-Aware Caching for Efficient GPU Offloading (opens in a new tab)

  6. Strained turbulence and low-diffusivity turbulent mixing using high performance computing

    … national supercomputer centers is maintained by overlapping communication and computation through extensive use of shared-memory programming, both in homogeneous and heterogeneous (i.e., GPU-accelerated) computing environments. Simulations of passive scalars maintained under a uniform mean …

    gatech Repository record for Strained turbulence and low-diffusivity turbulent mixing using high performance computing (opens in a new tab)

  7. Scalable non-blocking Krylov solvers for extreme-scale computing

    … systems have many factors that increase communication costs and cause performance variation across cores that can reduce performance at scale. Many Krylov solvers require frequent blocking allreduce collective operations that can limit performance at scale due to the increasing cost of …

    uiuc Repository record for Scalable non-blocking Krylov solvers for extreme-scale computing (opens in a new tab)

  8. Use of multi-GPU systems for large FFTs: with applications in ultrasound simulations

    … we benchmark and model the device-to-device communication potential of an existing multi-GPU system. Four different methods are considered, namely: via CPU, pointer swapping, hybrid-staged, and kernel. The results reveal that the pointer swapping and kernel based methods of managing …

    anu Repository record for Use of multi-GPU systems for large FFTs: with applications in ultrasound simulations (opens in a new tab)