...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computer architecture news >SlackSim: A Platform for Parallel Simulations of CMPs on CMPs
【24h】

SlackSim: A Platform for Parallel Simulations of CMPs on CMPs

机译：SlackSim：在CMP上并行模拟CMP的平台

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

The fast simulation of chip multiprocessors (CMPs) presents a critical challenge to the architecture research community as both industry and academia shift their research focus to multi-core design. Parallel simulation is a technique to accelerate microarchitecture simulation of CMPs by exploiting the inherent parallelism of CMPs. In this paper, we explore the simulation paradigm of simulating each core of a target CMP in one thread and then spreading the threads across the hardware thread contexts of a host CMP. We implement several parallel simulation schemes using POSIX Threads (Pthreads). We start with cycle-by-cycle simulation and then relax the synchronization condition in various schemes, which we call slack simulations.rnIn slack simulations, the Pthreads simulating different simulated cores do not synchronize after each simulated cycle, but rather they are given some slack. The slack is the difference in cycle between the simulated times of any two target cores. Small slacks, such as a few cycles, greatly improve the efficiency of parallel CMP simulations, with no or negligible simulation error. We have developed a simulation framework called SlackSim to experiment with various slack simulation schemes. Unlike previous attempts to parallelize multiprocessor simulations on distributed memory machines, SlackSim takes advantage of the efficient sharing of data in the host CMP architecture.rnWe demonstrate the efficiency and accuracy of some well-known slack simulation schemes and of some new ones on SlackSim running on a state-of-the-art CMP platform.
机译：随着行业和学术界将其研究重点转移到多核设计上，芯片多处理器（CMP）的快速仿真对架构研究界提出了严峻的挑战。并行仿真是一种通过利用CMP固有的并行性来加速CMP的微体系结构仿真的技术。在本文中，我们探讨了在一个线程中模拟目标CMP的每个核心，然后将线程分布在主机CMP的硬件线程上下文中的仿真范例。我们使用POSIX线程（Pthread）实现了几种并行仿真方案。我们从逐周期仿真开始，然后在各种方案中放松同步条件，我们将它们称为“松弛仿真”。在松弛仿真中，模拟不同模拟内核的Pthread在每个模拟周期后都不会同步，而是给它们一些松弛。松弛是任意两个目标核心的模拟时间之间的周期差异。较小的松弛（例如几个周期）极大地提高了并行CMP仿真的效率，而没有或几乎没有仿真误差。我们已经开发了一个名为SlackSim的仿真框架，以试验各种slack仿真方案。与之前尝试并行化分布式内存机器上的多处理器仿真的尝试不同，SlackSim利用主机CMP架构中数据的有效共享。rn我们演示了一些著名的slack仿真方案以及运行在SlackSim上的一些新方案的效率和准确性。最新的CMP平台。

著录项

  • 来源
    《Computer architecture news》 |2009年第2期|20-29|共10页
  • 作者

    Jianwei Chen; Murali Annavaram; Michel Dubois;

  • 作者单位

    Department of Electrical Engineering - Systems University of Southern California, Los Angeles, CA 90089-2562, U.S.;

    Department of Electrical Engineering - Systems University of Southern California, Los Angeles, CA 90089-2562, U.S.;

    Department of Electrical Engineering - Systems University of Southern California, Los Angeles, CA 90089-2562, U.S.;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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