首页> 外文OA文献 >Temperature-Insensitive Analog Vector-by-Matrix Multiplier Based on 55 nm NOR Flash Memory Cells
【2h】

Temperature-Insensitive Analog Vector-by-Matrix Multiplier Based on 55 nm NOR Flash Memory Cells

机译:基于55的温度不敏感模拟矢量矩阵乘法器   nm NOR闪存单元

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

We have fabricated and successfully tested an analog vector-by-matrixmultiplier, based on redesigned 10x12 arrays of 55 nm commercial NOR flashmemory cells. The modified arrays enable high-precision individual analogtuning of each cell, with sub-1% accuracy, while keeping the highly optimizedcells, with their long-term state retention, intact. The array has an area of0.33 um^2 per cell, and is at least one order of magnitude more dense than thereported prior implementations of nonvolatile analog memories. The demonstratedvector-by-vector multiplier, using gate coupling to additional periphery cells,has ~2% precision, limited by the aggregate effect of cell noise, retention,mismatch, process variations, tuning precision, and capacitive crosstalk. Adifferential version of the multiplier has allowed us to demonstrate sub-3%temperature drift of the output signal in the range between 25C and 85C.
机译:我们已经基于55 nm商业NOR闪存单元的重新设计的10x12阵列,制造并成功地测试了一个模拟的矩阵乘数乘数。修改后的阵列可对每个单元进行高精度的单个模拟调谐,精度不到1%,同时保持高度优化的单元及其长期状态保持不变。该阵列每单元具有0.33μm2的面积,并且比所报告的非易失性模拟存储器的先前实现方式密度高至少一个数量级。使用门极耦合到其他外围单元的已证明的逐矢量乘数具有〜2%的精度,受单元噪声,保留,失配,工艺变化,调谐精度和电容串扰的综合影响所限制。乘法器的差分形式使我们能够证明输出信号在25C至85C之间的范围内低于3%的温度漂移。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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