An implementation and evaluation of the MPI 3.0 one‐sided communication interface
An implementation and evaluation of the MPI 3.0 one‐sided communication interface
复制标题
DOI：
10.1002/cpe.3758
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
James Dinan;P. Balaji;Darius Buntinas;David Goodell;W. Gropp;R. Thakur
中科院分区：
文献类型：
--
作者：
James Dinan;P. Balaji;Darius Buntinas;David Goodell;W. Gropp;R. Thakur
消息传递接口(MPI)3.0标准包括对MPI的远程内存访问(RMA)接口的重大修订，该接口提供对单边通信的支持。MPI-3 RMA有望极大地提升MPI RMA的可用性和性能。我们介绍了MPI-3 RMA的第一个完整实施，并记录了新界面带来的实施技术和性能优化机会。我们的实施目标是基于消息传递的网络，并在MPICH MPI实施的最新版本中公开提供。使用这个实现，我们探索了新的MPI-3功能和语义对性能的影响。结果表明，与MPI-2接口相比，MPI-3 RMA接口具有显著的优势，它通过接口中松散的语义和提供新的窗口类型、同步模式和原子操作的附加例程来增加通信并发性。版权所有©2016 John Wiley&Sons，Ltd.
The Message Passing Interface (MPI) 3.0 standard includes a significant revision to MPI's remote memory access (RMA) interface, which provides support for one‐sided communication. MPI‐3 RMA is expected to greatly enhance the usability and performance of MPI RMA. We present the first complete implementation of MPI‐3 RMA and document implementation techniques and performance optimization opportunities enabled by the new interface. Our implementation targets messaging‐based networks and is publicly available in the latest release of the MPICH MPI implementation. Using this implementation, we explore the performance impact of new MPI‐3 functionality and semantics. Results indicate that the MPI‐3 RMA interface provides significant advantages over the MPI‐2 interface by enabling increased communication concurrency through relaxed semantics in the interface and additional routines that provide new window types, synchronization modes, and atomic operations. Copyright © 2016 John Wiley & Sons, Ltd.