首页> 外文会议>International conference on computer design >Fast boolean logic mapped on memristor crossbar
【24h】

Fast boolean logic mapped on memristor crossbar

机译:快速布尔逻辑映射在Memristor CrossBar上

获取原文
获取外文期刊封面目录资料

摘要

As the CMOS technology is gradually scaling down to inherent physical device limits, significant challenges emerge related to scalability, leakage, reliability, etc. Alternative technologies are under research for next-generation VLSI circuits. Memristor is one of the promising candidates due to its scalability, practically zero leakage, non-volatility, etc. This paper proposes a novel design methodology for logic circuits targeting memristor crossbars. This methodology allows the optimization of the design of logic function, and their automatic mapping on the memristor crossbar. More important, this methodology supports the execution of Boolean logic functions within constant number of steps independent of its functionality. To illustrate the potential of the proposed methodology, multi-bit adders and multipliers are explored; their incurred delay, area and energy costs are analyzed. The comparison of our approach with state-of-the-art Boolean logic circuits for memristor crossbar architecture shows significant improvement in both delay (4 to 500 x) and energy consumption (1.22 to 3.71 x). The area overhead may decrease (down to 44%) or increase (up to 17%) depending on the circuit's functionality and logic optimization level.
机译:随着CMOS技术逐渐降低到固有的物理设备限制,出现了与可扩展性,泄漏,可靠性等有关的重大挑战。替代技术正在研究下一代VLSI电路。由于其可扩展性,实际零泄漏,非波动性等,忆故读物是有希望的候选人之一。本文提出了一种针对映射映射器横梁的逻辑电路设计方法。该方法允许优化逻辑函数的设计,以及它们在Memitristor Crossbar上的自动映射。更重要的是,该方法支持在与其功能无关的恒定步骤内执行布尔逻辑函数。为了说明所提出的方法的潜力,探讨了多位加法器和乘法器;分析了他们的延迟,区域和能源成本。我们对Memristor CrossBar架构的最先进的布尔逻辑电路的方法的比较显示延迟(4到500 x)和能量消耗(1.22至3.71 x)的显着改进。根据电路的功能和逻辑优化级别,区域开销可能会降低(低至44%)或增加(高达17%)。

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