Runtime Data Management on Non-Volatile Memory-based Heterogeneous Memory for Task-Parallel Programs
Runtime Data Management on Non-Volatile Memory-based Heterogeneous Memory for Task-Parallel Programs
复制标题
DOI：
10.1109/sc.2018.00034
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Kai Wu;J. Ren;Dong Li
中科院分区：
文献类型：
--
作者：
Kai Wu;J. Ren;Dong Li
非易失性存储器（NVM）提供了一种可扩展的解决方案，以取代DRAM作为主存储器。由于NVM相对于DRAM具有较高的延迟和较低的带宽，因此NVM经常与DRAM配对以构建异构主存系统（HMS）。决定基于NVM的HMS上的数据放置对于支持未来基于NVM的HPC至关重要。在本文中，我们研究了任务并行程序，并介绍了一个运行时系统，以解决基于NVM的HMS上的数据放置问题。利用任务并行程序的语义和执行模式，我们有效地表征任务的内存访问模式，减少数据移动开销。我们还引入了一个性能模型来预测HMS上具有各种数据放置的任务的性能。评估与一组HPC基准测试，我们表明，我们的运行时系统实现了更高的性能比传统的HMS不经意的运行时（平均提高24%）和两个国家的最先进的HMS感知的解决方案（平均分别提高16%和11%）。
Non-volatile memory (NVM) provides a scalable solution to replace DRAM as main memory. Because of relatively high latency and low bandwidth of NVM (comparing with DRAM), NVM often pairs with DRAM to build a heterogeneous main memory system (HMS). Deciding data placement on NVM-based HMS is critical to enable future NVM-based HPC. In this paper, we study task-parallel programs, and introduce a runtime system to address the data placement problem on NVM-based HMS. Leveraging semantics and execution mode of task-parallel programs, we efficiently characterize memory access patterns of tasks and reduce data movement overhead. We also introduce a performance model to predict performance for tasks with various data placements on HMS. Evaluating with a set of HPC benchmarks, we show that our runtime system achieves higher performance than a conventional HMS-oblivious runtime (24% improvement on average) and two state-of-the-art HMS-aware solutions (16% and 11% improvement on average, respectively).