S. Moazeni, Sen Lin, M. Wade, L. Alloatti, Rajeev J Ram, M. Popović, V. Stojanović
{"title":"29.3基于45nm SOI CMOS环形谐振光DAC的40Gb/s PAM-4发射机","authors":"S. Moazeni, Sen Lin, M. Wade, L. Alloatti, Rajeev J Ram, M. Popović, V. Stojanović","doi":"10.1109/ISSCC.2017.7870473","DOIUrl":null,"url":null,"abstract":"Silicon photonics is a rapidly maturing technology, promising to realize low-cost and energy-efficient optical links for rack-to-rack, within-rack datacenter applications, and supercomputer interconnects. Recently, the possibility of implementing ultra-power-efficient silicon photonic links using an unmodified state-of-the-art 45nm SOI CMOS process has been demonstrated [1]. This approach enabled the fabrication of millions of transistors and hundreds of photonic devices in the same chip to improve processor-memory link bandwidth, and opened a path to solving this traditional computation bottleneck.","PeriodicalId":269679,"journal":{"name":"2017 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"29.3 A 40Gb/s PAM-4 transmitter based on a ring-resonator optical DAC in 45nm SOI CMOS\",\"authors\":\"S. Moazeni, Sen Lin, M. Wade, L. Alloatti, Rajeev J Ram, M. Popović, V. Stojanović\",\"doi\":\"10.1109/ISSCC.2017.7870473\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Silicon photonics is a rapidly maturing technology, promising to realize low-cost and energy-efficient optical links for rack-to-rack, within-rack datacenter applications, and supercomputer interconnects. Recently, the possibility of implementing ultra-power-efficient silicon photonic links using an unmodified state-of-the-art 45nm SOI CMOS process has been demonstrated [1]. This approach enabled the fabrication of millions of transistors and hundreds of photonic devices in the same chip to improve processor-memory link bandwidth, and opened a path to solving this traditional computation bottleneck.\",\"PeriodicalId\":269679,\"journal\":{\"name\":\"2017 IEEE International Solid-State Circuits Conference (ISSCC)\",\"volume\":\"32 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 IEEE International Solid-State Circuits Conference (ISSCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISSCC.2017.7870473\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE International Solid-State Circuits Conference (ISSCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISSCC.2017.7870473","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11
摘要
硅光子学是一项迅速成熟的技术,有望实现低成本和节能的光链路,用于机架到机架、机架内数据中心应用和超级计算机互连。最近,已经证明了使用未经修改的最先进的45nm SOI CMOS工艺实现超节能硅光子链路的可能性[1]。这种方法使得在同一芯片上制造数百万个晶体管和数百个光子器件,从而提高了处理器-存储器链路带宽,为解决这一传统的计算瓶颈开辟了一条道路。
29.3 A 40Gb/s PAM-4 transmitter based on a ring-resonator optical DAC in 45nm SOI CMOS
Silicon photonics is a rapidly maturing technology, promising to realize low-cost and energy-efficient optical links for rack-to-rack, within-rack datacenter applications, and supercomputer interconnects. Recently, the possibility of implementing ultra-power-efficient silicon photonic links using an unmodified state-of-the-art 45nm SOI CMOS process has been demonstrated [1]. This approach enabled the fabrication of millions of transistors and hundreds of photonic devices in the same chip to improve processor-memory link bandwidth, and opened a path to solving this traditional computation bottleneck.