Yasmin K. Abdelmagid, Renad T. Nawar, Mennatullah K. Rabie, Ahmed S. Tulan, Ahmed H. Hassan, Andoleet Saleh, H. Mostafa
{"title":"Investigation of DW Spintronic Memristor performance in 2T1M Neuromorphic Synapse","authors":"Yasmin K. Abdelmagid, Renad T. Nawar, Mennatullah K. Rabie, Ahmed S. Tulan, Ahmed H. Hassan, Andoleet Saleh, H. Mostafa","doi":"10.1109/NILES50944.2020.9257896","DOIUrl":null,"url":null,"abstract":"Memristor, the two-terminal memory-resistance device discovered by Chua in 1971, is a promising solution for future processing problems. Its CMOS integration compatibility and large resistance in small size, makes it very successful candidate for large-scale systems like Neural Networks. In last decade, memristors were used in many Neuromorphic Synapses for its advantage of combining processing (dot-product) and memory in same device. There are different materials that can be used to fabricate memristors. In this paper, a comparison between spintronic and TiO2-resistive memristor in two-transistors-one memristor synapse, is introduced. The work was done on Cadence Virtuoso with using Verilog-A for memristor modeling. The comparison reveals that the synaptic implementation with a spintronic memristor is more efficient when high speed is needed. However, the resistive memristor is more adequate due to its lower power dissipation.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NILES50944.2020.9257896","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Memristor, the two-terminal memory-resistance device discovered by Chua in 1971, is a promising solution for future processing problems. Its CMOS integration compatibility and large resistance in small size, makes it very successful candidate for large-scale systems like Neural Networks. In last decade, memristors were used in many Neuromorphic Synapses for its advantage of combining processing (dot-product) and memory in same device. There are different materials that can be used to fabricate memristors. In this paper, a comparison between spintronic and TiO2-resistive memristor in two-transistors-one memristor synapse, is introduced. The work was done on Cadence Virtuoso with using Verilog-A for memristor modeling. The comparison reveals that the synaptic implementation with a spintronic memristor is more efficient when high speed is needed. However, the resistive memristor is more adequate due to its lower power dissipation.