• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Proceedings of the ACM computing frontiers conference >GA-GPU: Extending a Library-based Global Address Space Programming Model for Scalable Heterogeneous Computing Systems
【24h】

GA-GPU: Extending a Library-based Global Address Space Programming Model for Scalable Heterogeneous Computing Systems

机译：GA-GPU：扩展可扩展异构计算系统的基于库的全局地址空间编程模型

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Scalable heterogeneous computing (SHC) architectures are emerging as a response to new requirements for low cost. power efficiency, and high performance. For example, numerous contemporary HPC systems are using commodity Graphical Processing Units (GPU) to supplement traditional inulticore processors. Yet scientists continue to face challenges in utilizing SHC systems. First and foremost, they are forced to combine a number of programming models arid then delicately optimize the data movement among these multiple programming systems on each architecture. In this paper, we investigate a programming model for SMC systems that attempts to unify data access to the aggregate? memory available in GPUs in the system. In particular, we extend the popular and easy to use Global Address Space (GAS) programming model to SHC' systems. We explore multiple implementation options, and demonstrate our solution iu the context of Global Arrays, a library based CIAS model. We evaluated these options in the context of kernels and NWOhem, a scalable chemistry application . Our results reveal that GA-GPU can offer considerable benefit to users in terms of programmability, and both our empirical results and performance model provide; encouraging performance benefits for future systems that offer a tightly integrated memory system.
机译：可扩展的异构计算（SHC）架构作为对低成本新要求的回应而出现。功率效率和高性能。例如，许多当代的高性能计算系统都在使用商用图形处理单元（GPU）来补充传统的针刺处理器。然而，科学家在使用SHC系统方面仍面临挑战。首先，最重要的是，他们被迫结合多种编程模型，然后在每种体系结构上精细地优化这些多个编程系统之间的数据移动。在本文中，我们研究了SMC系统的编程模型，该模型试图统一对聚合的数据访问？系统中GPU中可用的内存。特别是，我们将流行且易于使用的全局地址空间（GAS）编程模型扩展到SHC's系统。我们探索了多种实现方案，并在基于库的CIAS模型Global Arrays的背景下展示了我们的解决方案。我们在内核和可扩展化学应用程序NWOhem的上下文中评估了这些选项。我们的结果表明，GA-GPU在可编程性方面可以为用户带来可观的收益，而我们的经验结果和性能模型都可以提供；对于提供紧密集成的内存系统的未来系统，可带来令人鼓舞的性能优势。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号