arXiv 2409.028302024-09-04cs.DCcs.PF

迈向可扩展且高效的基于 PGAS 的分布式 OpenMP

Towards a Scalable and Efficient PGAS-based Distributed OpenMP

Baodi Shan, Mauricio Araya-Polo, Barbara Chapman

AI总结：

本文提出 DiOMP，将 PGAS 概念集成到 OpenMP 中，基于 LLVM 和 GASNet-EX 实现，实验表明其带宽比 MPI+OpenMP 最高提升 25%、延迟最多降低 45%，为分布式内存并行编程提供了更高效的替代方案。

摘要：

MPI+X 一直是分布式内存并行编程的事实标准。它主要作为一种显式的双端通信模型被广泛使用，这往往导致代码复杂且容易出错。相比之下，PGAS 模型利用高效的单端通信和更直观的通信原语。在本文中，我们提出了一种新颖的方法，将 PGAS 概念集成到 OpenMP 编程模型中，利用 LLVM 编译器基础设施和 GASNet-EX 通信库。我们的模型解决了传统 MPI+OpenMP 编程模型相关的复杂性，同时确保了出色的性能和可扩展性。我们使用一组微基准测试和应用程序内核在两个不同的平台上评估了我们的方法：石溪大学的 Ookami 和 NERSC Perlmutter。结果表明，与 MPI+OpenMP 相比，DiOMP 实现了更高的带宽和更低的延迟，带宽最高提高 25%，延迟最多降低 45%。DiOMP 为传统的 MPI+OpenMP 混合编程模型提供了一种有前景的替代方案，朝着为分布式内存系统开发高性能并行应用提供一种更高效、更高效能的方式迈进。

英文摘要：

MPI+X has been the de facto standard for distributed memory parallel programming. It is widely used primarily as an explicit two-sided communication model, which often leads to complex and error-prone code. Alternatively, PGAS model utilizes efficient one-sided communication and more intuitive communication primitives. In this paper, we present a novel approach that integrates PGAS concepts into the OpenMP programming model, leveraging the LLVM compiler infrastructure and the GASNet-EX communication library. Our model addresses the complexity associated with traditional MPI+OpenMP programming models while ensuring excellent performance and scalability. We evaluate our approach using a set of micro-benchmarks and application kernels on two distinct platforms: Ookami from Stony Brook University and NERSC Perlmutter. The results demonstrate that DiOMP achieves superior bandwidth and lower latency compared to MPI+OpenMP, up to 25% higher bandwidth and down to 45% on latency. DiOMP offers a promising alternative to the traditional MPI+OpenMP hybrid programming model, towards providing a more productive and efficient way to develop high-performance parallel applications for distributed memory systems.

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。

AI总结：

摘要：

英文摘要：

相关论文