arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1506.00907physics.comp-phphysics.geo-ph
收藏

GPU团簇逆时迁移的节块间断Galerkin模拟

Nodal Discontinuous Galerkin Simulations for Reverse-Time Migration on GPU Clusters

Axel Modave, Amik St-Cyr, Wim A. Mulder, Tim Warburton

摘要:

提高数值工具的精度和计算性能是地震成像的主要挑战,通常需要专门的实现来充分利用现代并行架构。我们提出了一个计算策略的逆时偏移(RTM)与加速器辅助集群。介绍了一种由压力场和速度场计算的新的成像条件。模型求解器是基于高阶间断Galerkin时域(DGTD)方法的压力-速度系统与非结构化网格和多速率局部时间推进。我们采用MPI+X方法进行分布式编程,其中X是一个线程编程模型。在这项工作中,我们选择了OCCA,这是一个统一的框架,它使用了主要的多线程语言(例如CUDA和OpenCL),并提供了在多种硬件架构上运行的灵活性。DGTD方案适用于加速器的高效计算,这要归功于局部化的单元到单元耦合和每个单元所需的密集代数运算。此外,高阶有限差分格式相比,薄晕固有的DGTD方法减少了MPI过程和RTM程序的存储要求之间交换的数据量。通过只将边界值存储在内存中而不是磁盘上并重新创建前向波场,减少了模拟过程中要记录的数据量。计算结果表明,这些方法是强大的可扩展到至少32个GPU的三维RTM的情况下。

英文摘要:

Improving both accuracy and computational performance of numerical tools is a major challenge for seismic imaging and generally requires specialized implementations to make full use of modern parallel architectures. We present a computational strategy for reverse-time migration (RTM) with accelerator-aided clusters. A new imaging condition computed from the pressure and velocity fields is introduced. The model solver is based on a high-order discontinuous Galerkin time-domain (DGTD) method for the pressure-velocity system with unstructured meshes and multi-rate local time-stepping. We adopted the MPI+X approach for distributed programming where X is a threaded programming model. In this work we chose OCCA, a unified framework that makes use of major multi-threading languages (e.g. CUDA and OpenCL) and offers the flexibility to run on several hardware architectures. DGTD schemes are suitable for efficient computations with accelerators thanks to localized element-to-element coupling and the dense algebraic operations required for each element. Moreover, compared to high-order finite-difference schemes, the thin halo inherent to DGTD method reduces the amount of data to be exchanged between MPI processes and storage requirements for RTM procedures. The amount of data to be recorded during simulation is reduced by storing only boundary values in memory rather than on disk and recreating the forward wavefields. Computational results are presented that indicate that these methods are strong scalable up to at least 32 GPUs for a three-dimensional RTM case.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑