首页> 外文会议>International Conference on Computing and Information Technologies Exploring Emerging Technologies, Oct 12, 2001, Montclair State University, NJ, USA >INVESTIGATION OF A LOW-COST HIGH-PERFORMANCE SHARED-MEMORY MULTIPROCESSOR SYSTEM FOR REAL-TIME APPLICATIONS
【24h】

INVESTIGATION OF A LOW-COST HIGH-PERFORMANCE SHARED-MEMORY MULTIPROCESSOR SYSTEM FOR REAL-TIME APPLICATIONS

机译:用于实时应用的低成本高性能共享存储器多处理器系统的研究

获取原文
获取原文并翻译 | 示例

摘要

The proposed architecture can effectively support up to 64 modern digital signal processors (DSPs) in contrast to a smaller number of DSPs supported by existing bus-interconnected systems. This significant enhancement is achieved by introducing two small programmable fast memories (Twins) between the processor and the shared bus interconnect. While one memory is transferring data from/to the shared memory, the other is supplying the core processor with data. The elimination of the traditional direct linkage of the shared-bus and processor data bus makes feasible the utilization of a wider shared bus i.e., the shared bus width becomes independent of the data bus width of the processors. Simulation results show that the fast prefetching memories and the wider shared bus provide additional bus bandwidth to the system, which eliminates large memory latencies; such memory latencies constitute the major drawback for the performance of shared-memory multiprocessors with standard memory modules.
机译:与现有的总线互连系统支持的DSP数量较少相比,所提出的体系结构可以有效支持多达64个现代数字信号处理器(DSP)。通过在处理器和共享总线互连之间引入两个小型可编程快速存储器(Twin),可以实现这一显着增强。当一个内存从共享内存传输数据到共享内存时,另一个则向核心处理器提供数据。消除共享总线和处理器数据总线的传统直接链接使得可行的是,可以使用更宽的共享总线,即,共享总线宽度变得独立于处理器的数据总线宽度。仿真结果表明,快速的预取存储器和更宽的共享总线为系统提供了额外的总线带宽,从而消除了大的存储延迟。这样的内存延迟构成了具有标准内存模块的共享内存多处理器性能的主要缺点。

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