arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.11496cs.DC
收藏

混合MPI + MPI代码中的集合:设计、实践和性能

Collectives in hybrid MPI+MPI code: design, practice and performance

Huan Zhou, Jose Gracia, Naweiluo Zhou, Ralf Schneider

摘要:

结合用于节点间并行性的消息传递编程模型和用于节点级并行性的共享存储器编程模型的混合方案的使用被广泛传播。混合消息传递接口(MPI)加上开放多处理(OpenMP)编程的现有广泛实践说明了它的流行。然而,需要强大的编程工作来从MPI + OpenMP代码中获得性能优势。一种新兴的混合方法,结合MPI和MPI共享内存模型(MPI + MPI)是很有前途的。然而,编写一个高效的混合MPI + MPI程序--特别是当涉及到集体通信操作时--并不是理所当然的。本文提出了一种新的设计方法来实现混合MPI + MPI基于上下文的集体通信操作。我们的方法避免了纯MPI中语义所需的节点上内存复制(节点上通信开销)。我们还提供了对用户隐藏所有设计细节的包装器原语,以及如何使用这些原语构建混合MPI + MPI代码的实践。微基准测试表明,我们的集体是可比的或优于那些在纯MPI的背景。我们进一步验证了混合MPI + MPI模型(使用我们的包装原语)在三个计算内核的有效性,通过比较纯MPI和混合MPI + OpenMP模型。

英文摘要:

The use of hybrid scheme combining the message passing programming models for inter-node parallelism and the shared memory programming models for node-level parallelism is widely spread. Existing extensive practices on hybrid Message Passing Interface (MPI) plus Open Multi-Processing (OpenMP) programming account for its popularity. Nevertheless, strong programming efforts are required to gain performance benefits from the MPI+OpenMP code. An emerging hybrid method that combines MPI and the MPI shared memory model (MPI+MPI) is promising. However, writing an efficient hybrid MPI+MPI program -- especially when the collective communication operations are involved -- is not to be taken for granted. In this paper, we propose a new design method to implement hybrid MPI+MPI context-based collective communication operations. Our method avoids on-node memory replications (on-node communication overheads) that are required by semantics in pure MPI. We also offer wrapper primitives hiding all the design details from users, which comes with practices on how to structure hybrid MPI+MPI code with these primitives. The micro-benchmarks show that our collectives are comparable or superior to those in pure MPI context. We have further validated the effectiveness of the hybrid MPI+MPI model (which uses our wrapper primitives) in three computational kernels, by comparison to the pure MPI and hybrid MPI+OpenMP models.

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。

↑