【24h】

Network Of Cores For Large Systems

机译:大型系统的核心网络

获取原文

摘要

A comparison between SoC with shared bus medium and NoC using Transaction Level Modeling (TLM) is presented. The router of the NoC is implemented using SystemC. Different traffic patterns and loads are used to evaluate the implementation. Detailed performance evaluation using different metrics such as throughput, latency, number of hops and power consumption is provided. It is shown that the throughput of NoC is higher in addition to its scalability as number of cores in large systems increases. The rate of throughput increase in NoC is higher than the rate of increase of power consumption as compared to SoC as system size increases. SoC could not satisfy the continuous demands of large systems while NoC is highly scalable.
机译:提出了使用事务级别建模(TLM)在具有共享总线介质的SoC和NoC之间进行的比较。 NoC的路由器是使用SystemC实现的。使用不同的流量模式和负载来评估实现。提供了使用不同指标(例如吞吐量,延迟,跳数和功耗)的详细性能评估。结果表明,随着大型系统中内核数量的增加,NoC的吞吐量和可扩展性都更高。随着系统尺寸的增加,与SoC相比,NoC吞吐量的增加速率要高于功耗的增加速率。当NoC具有高度可扩展性时,SoC无法满足大型系统的持续需求。

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