{"title":"摩尔定律是违宪的","authors":"W. Rhines","doi":"10.1109/ICVD.2005.121","DOIUrl":null,"url":null,"abstract":"Moore's law is the empirical observation that component density and performance of integrated circuits - approximately doubles every eighteen months. It is not a 'law' in the sense that basic principals of physics and thermodynamics constitute the rules of nature. But there is a 'law' that serves as the basis for Moore's law; it is the general principle that governs learning curves, i.e. that efficiencies improve a fixed percentage with increases in the total accumulated volume of production, when analyzed on a logarithmic scale. Analyzing current trends in integrated circuit technology reveals the potential left to achieve performance, reliability and cost improvements via the traditional means of shrinking design rules and increasing die and wafer size. It also suggests where nontraditional innovation is likely to have its greatest impact. This talk explores these projections for future technology and suggest where the discontinuities are most likely to occur.","PeriodicalId":382435,"journal":{"name":"VLSI design (Print)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2005-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Moore's Law is Unconstitutional\",\"authors\":\"W. Rhines\",\"doi\":\"10.1109/ICVD.2005.121\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Moore's law is the empirical observation that component density and performance of integrated circuits - approximately doubles every eighteen months. It is not a 'law' in the sense that basic principals of physics and thermodynamics constitute the rules of nature. But there is a 'law' that serves as the basis for Moore's law; it is the general principle that governs learning curves, i.e. that efficiencies improve a fixed percentage with increases in the total accumulated volume of production, when analyzed on a logarithmic scale. Analyzing current trends in integrated circuit technology reveals the potential left to achieve performance, reliability and cost improvements via the traditional means of shrinking design rules and increasing die and wafer size. It also suggests where nontraditional innovation is likely to have its greatest impact. This talk explores these projections for future technology and suggest where the discontinuities are most likely to occur.\",\"PeriodicalId\":382435,\"journal\":{\"name\":\"VLSI design (Print)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2005-01-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"VLSI design (Print)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICVD.2005.121\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"VLSI design (Print)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICVD.2005.121","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Moore's law is the empirical observation that component density and performance of integrated circuits - approximately doubles every eighteen months. It is not a 'law' in the sense that basic principals of physics and thermodynamics constitute the rules of nature. But there is a 'law' that serves as the basis for Moore's law; it is the general principle that governs learning curves, i.e. that efficiencies improve a fixed percentage with increases in the total accumulated volume of production, when analyzed on a logarithmic scale. Analyzing current trends in integrated circuit technology reveals the potential left to achieve performance, reliability and cost improvements via the traditional means of shrinking design rules and increasing die and wafer size. It also suggests where nontraditional innovation is likely to have its greatest impact. This talk explores these projections for future technology and suggest where the discontinuities are most likely to occur.