首页> 外文期刊>IEEE Transactions on Parallel and Distributed Systems >An Adaptive Algorithm Selection Framework for Reduction Parallelization
【24h】

An Adaptive Algorithm Selection Framework for Reduction Parallelization

机译:减少并行化的自适应算法选择框架

获取原文
获取原文并翻译 | 示例
           

摘要

Irregular and dynamic memory reference patterns can cause performance variations for low level algorithms in general and for parallel algorithms in particular. In this paper, we present an adaptive algorithm selection framework which can collect and interpret the characteristics of a particular instance of parallel reduction algorithms and select the best performing one from an existing library. The framework consists of the following components: 1) an offline systematic process for characterizing the input sensitivity of parallel reduction algorithms and a method for building corresponding predictive performance models, 2) an online input characterization and algorithm selection module, and 3) a small library of parallel reduction algorithms, which represent the algorithmic choices made available at runtime. We also present one possible integration of this framework in a restructuring compiler. We validate our design experimentally and show that our framework 1) selects the most appropriate algorithms in 85 percent of the cases studied, 2) overall, delivers 98 percent of the optimal performance, 3) adaptively selects the best algorithms for dynamic phases of a running program (resulting in performance improvements otherwise not possible), and 4) adapts to the underlying machine architectures (evaluated on IBM Regatta and HP V-Class systems).
机译:通常,不规则和动态内存引用模式可能会导致低级算法,尤其是并行算法的性能变化。在本文中,我们提出了一种自适应算法选择框架,该框架可以收集和解释并行约简算法的特定实例的特征,并从现有库中选择性能最佳的算法。该框架由以下组件组成:1)用于表征并行约简算法的输入灵敏度的离线系统过程以及用于建立相应的预测性能模型的方法; 2)在线输入表征和算法选择模块;以及3)小库并行约简算法,代表在运行时可用的算法选择。我们还介绍了此框架在重组编译器中的一种可能的集成。我们通过实验验证了我们的设计,并表明我们的框架1)在所研究案例的85%中选择了最合适的算法,2)总体而言,提供了98%的最佳性能,3)在运行的动态阶段自适应地选择了最佳算法程序(否则无法实现性能改进),并且4)适应基础计算机体系结构(在IBM Regatta和HP V-Class系统上进行了评估)。

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