首页> 外文期刊>Parallel and Distributed Systems, IEEE Transactions on >Processing MPI Derived Datatypes on Noncontiguous GPU-Resident Data
【24h】

Processing MPI Derived Datatypes on Noncontiguous GPU-Resident Data

机译:在非连续GPU驻留数据上处理MPI派生数据类型

获取原文
获取原文并翻译 | 示例
           

摘要

Driven by the goals of efficient and generic communication of noncontiguous data layouts in GPU memory, for which solutions do not currently exist, we present a parallel, noncontiguous data-processing methodology through the MPI datatypes specification. Our processing algorithm utilizes a kernel on the GPU to pack arbitrary noncontiguous GPU data by enriching the datatypes encoding to expose a fine-grained, data-point level of parallelism. Additionally, the typically tree-based datatype encoding is preprocessed to enable efficient, cached access across GPU threads. Using CUDA, we show that the computational method outperforms DMA-based alternatives for several common data layouts as well as more complex data layouts for which reasonable DMA-based processing does not exist. Our method incurs low overhead for data layouts that closely match best-case DMA usage or that can be processed by layout-specific implementations. We additionally investigate usage scenarios for data packing that incur resource contention, identifying potential pitfalls for various packing strategies. We also demonstrate the efficacy of kernel-based packing in various communication scenarios, showing multifold improvement in point-to-point communication and evaluating packing within the context of the SHOC stencil benchmark and HACC mesh analysis.
机译:为了实现GPU内存中不连续数据布局的高效通用通信的目标(目前尚无解决方案),我们通过MPI数据类型规范提出了一种并行,不连续数据处理方法。我们的处理算法利用GPU上的内核,通过丰富数据类型编码来封装任意不连续的GPU数据,以暴露出细粒度的数据点级别的并行性。此外,通常对基于树的数据类型编码进行预处理,以实现跨GPU线程的高效,缓存访问。使用CUDA,我们表明对于几种常见的数据布局以及不存在基于DMA的合理处理的更复杂的数据布局,该计算方法的性能优于基于DMA的替代方法。对于与最佳情况下的DMA使用非常匹配的数据布局,或者可以通过特定于布局的实现进行处理的数据布局,我们的方法会产生较低的开销。我们还将调查数据打包的使用场景,这些场景会引起资源争用,并确定各种打包策略的潜在陷阱。我们还展示了基于内核的填充在各种通信场景中的功效,显示了点对点通信的多重改进,并在SHOC模具基准测试和HACC网格分析的背景下评估了填充。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号