T. Soliman, F. Müller, T. Kirchner, T. Hoffmann, H. Ganem, E. Karimov, T. Ali, M. Lederer, C. Sudarshan, T. Kämpfe, A. Guntoro, N. Wehn
{"title":"基于超低功耗柔性精确场效应晶体管的内存模拟计算","authors":"T. Soliman, F. Müller, T. Kirchner, T. Hoffmann, H. Ganem, E. Karimov, T. Ali, M. Lederer, C. Sudarshan, T. Kämpfe, A. Guntoro, N. Wehn","doi":"10.1109/IEDM13553.2020.9372124","DOIUrl":null,"url":null,"abstract":"This paper presents an efficient crossbar design and implementation intended for analog compute-in-memory (ACiM) acceleration of artificial neural networks based on ferroelectric FET (FeFET) technology. The novel mixed signal blocks presented in this work reduce the device-to-device variation and are optimized for low area, low power and high throughput. In addition, we illustrate the operation and programmability of the crossbar that adopts bit decomposition techniques for MAC operation. Our crossbar based ACiM accelerator achieves a record peak performance of 13714 TOPS/W.","PeriodicalId":415186,"journal":{"name":"2020 IEEE International Electron Devices Meeting (IEDM)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"39","resultStr":"{\"title\":\"Ultra-Low Power Flexible Precision FeFET Based Analog In-Memory Computing\",\"authors\":\"T. Soliman, F. Müller, T. Kirchner, T. Hoffmann, H. Ganem, E. Karimov, T. Ali, M. Lederer, C. Sudarshan, T. Kämpfe, A. Guntoro, N. Wehn\",\"doi\":\"10.1109/IEDM13553.2020.9372124\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents an efficient crossbar design and implementation intended for analog compute-in-memory (ACiM) acceleration of artificial neural networks based on ferroelectric FET (FeFET) technology. The novel mixed signal blocks presented in this work reduce the device-to-device variation and are optimized for low area, low power and high throughput. In addition, we illustrate the operation and programmability of the crossbar that adopts bit decomposition techniques for MAC operation. Our crossbar based ACiM accelerator achieves a record peak performance of 13714 TOPS/W.\",\"PeriodicalId\":415186,\"journal\":{\"name\":\"2020 IEEE International Electron Devices Meeting (IEDM)\",\"volume\":\"46 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-12-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"39\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE International Electron Devices Meeting (IEDM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IEDM13553.2020.9372124\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Electron Devices Meeting (IEDM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IEDM13553.2020.9372124","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Ultra-Low Power Flexible Precision FeFET Based Analog In-Memory Computing
This paper presents an efficient crossbar design and implementation intended for analog compute-in-memory (ACiM) acceleration of artificial neural networks based on ferroelectric FET (FeFET) technology. The novel mixed signal blocks presented in this work reduce the device-to-device variation and are optimized for low area, low power and high throughput. In addition, we illustrate the operation and programmability of the crossbar that adopts bit decomposition techniques for MAC operation. Our crossbar based ACiM accelerator achieves a record peak performance of 13714 TOPS/W.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
