首页> 外文会议>2013 International Symposium on System on Chip >System interconnect extensions for fully transparent demand paging in low-cost MMU-less embedded systems
【24h】

System interconnect extensions for fully transparent demand paging in low-cost MMU-less embedded systems

机译:系统互连扩展,可在低成本,无MMU的嵌入式系统中实现完全透明的需求分页

获取原文
获取原文并翻译 | 示例

摘要

MMU-less embedded systems are the state of the art solution for deeply embedded computing environments. Thanks to the rapid evolution of such devices, nowadays applications that run on top of them are evolving from simple control tasks to more complex applications that involve an Operating System (OS). At the same time, cost budget remains unchanged in spite of the growing performance requirements. For this reason, traditional code loading and execution techniques like full code shadowing or execute-in-place may lead to a performance bottleneck. Even demand paging strategies lack consensus due to the customization and the complexity of the software infrastructure dealing with the memory management. The objective of this work is to implement a transparent hardware-based demand paging strategy for code loading and execution, targeting MMU-less embedded systems. This approach consists of making the system interconnect aware of the memory map, without burdening on the legacy OS code, application code and on the compilation framework. This approach materializes lower boot-up latency and shorter application execution time with respect to traditional loading and executing schemes.
机译:不含MMU的嵌入式系统是用于深度嵌入式计算环境的最新解决方案。由于此类设备的快速发展,如今,运行在这些设备之上的应用程序已从简单的控制任务演变为涉及操作系统(OS)的更复杂的应用程序。同时,尽管性能要求不断提高,但预算预算仍保持不变。因此,传统的代码加载和执行技术(例如完整的代码阴影或就地执行)可能会导致性能瓶颈。由于定制和处理内存管理的软件基础结构的复杂性,甚至需求分页策略也缺乏共识。这项工作的目标是针对无MMU的嵌入式系统实现一种透明的基于硬件的需求分页策略,以进行代码加载和执行。这种方法包括使系统互连知道内存映射,而不会给遗留的OS代码,应用程序代码和编译框架造成负担。与传统的加载和执行方案相比,此方法可实现更低的启动延迟和更短的应用程序执行时间。

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