MPC-MPI: An MPI Implementation Reducing the Overall Memory Consumption
MPC-MPI: An MPI Implementation Reducing the Overall Memory Consumption
复制标题
MPC-MPI：减少总体内存消耗的 MPI 实现
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
H. Jourdren
中科院分区：
文献类型：
--
作者：
Marc Pérache;Patrick Carribault;H. Jourdren
消息传递接口（Message-Passing Interface， MPI）已经成为高性能计算中并行应用程序的标准。在单个集群节点中，MPI实现受益于共享内存来加速节点内部通信，同时利用底层网络协议在节点之间进行通信。但是，它需要分配额外的缓冲区，从而导致内存消耗开销。这可能会成为未来每个核心内存量减少的集群的一个问题。在本文中，我们提出了一种基于MPC框架的MPI实现，称为MPC-MPI，可以减少总体内存占用。我们在基准测试和实际应用程序中获得了高达47%的内存增益。
Message-Passing Interface (MPI) has become a standard for parallel applications in high-performance computing. Within a single cluster node, MPI implementations benefit from the shared memory to speed-up intra-node communications while the underlying network protocol is exploited to communicate between nodes. However, it requires the allocation of additional buffers leading to a memory-consumption overhead. This may become an issue on future clusters with reduced memory amount per core. In this article, we propose an MPI implementation built upon the MPC framework called MPC-MPI reducing the overall memory footprint. We obtained up to 47% of memory gain on benchmarks and a real-world application.