在日前舉行的《Hot Chips》大會(huì)上，發(fā)表專題演說(shuō)的業(yè)界專家指出，預(yù)告“IC中可容納的晶體管數(shù)每隔18-24個(gè)月就會(huì)增加1倍，從而使性能也提升1倍”的“摩爾定律”(Moore's Law)即將在2020年約7nm節(jié)點(diǎn)時(shí)走到盡頭。 隨著微影技術(shù)進(jìn)展停滯不前以及制程技術(shù)逐漸面臨限極限，業(yè)界的種種預(yù)測(cè)也越來(lái)越多。雖然業(yè)界有許多人都預(yù)期摩爾定律即將終結(jié)，但很少有人能夠提出深入且具說(shuō)服力的解釋。 “對(duì)于時(shí)程的規(guī)劃，我認(rèn)為2020年將會(huì)是足以說(shuō)摩爾定律已死的時(shí)間點(diǎn)，”致力于尋找后續(xù)新技術(shù)的美國(guó)國(guó)防部先進(jìn)研究計(jì)劃署(DARPA)微系統(tǒng)技術(shù)辦公室總 監(jiān)Robert Colwell指出，“你或許會(huì)說(shuō)是2022年，但無(wú)論是發(fā)生在7nm或5nm節(jié)點(diǎn)時(shí)，它都是個(gè)大問(wèn)題?！盧obert Colwell曾經(jīng)是英特爾 Pentium 處理器設(shè)計(jì)團(tuán)隊(duì)的工程師之一。 他指出，過(guò)去三十年來(lái)，摩爾定律持續(xù)呈指數(shù)級(jí)成長(zhǎng)，速度從1MHz提升到5GHz，增加了大約3,500倍。相形之下，同一時(shí)期內(nèi)的智能架構(gòu)所能實(shí)現(xiàn)的最大進(jìn)展不過(guò)增加了50倍。 指數(shù)級(jí)成長(zhǎng)的終結(jié)通常由于本身無(wú)法持續(xù)自然地進(jìn)展。Colwell說(shuō)，遺憾的是，這樣的機(jī)會(huì)并不多見(jiàn)。 “我并不指望未來(lái)30年還能在電子產(chǎn)業(yè)看到另一個(gè)3,500倍的速度提升，或許只有50倍吧！”遺憾的是，Colwell指出，“我認(rèn)為這個(gè)領(lǐng)域并沒(méi)有多余的錢可挹注于每年僅增加10%的一點(diǎn)好處?！? 對(duì)于許多人還盲目地相信會(huì)找到另一個(gè)指數(shù)級(jí)成長(zhǎng)曲線以取代摩爾定律，Colwell也對(duì)其潑了一盆冷水，“我們或許能進(jìn)行一大堆的調(diào)整，但卻無(wú)法解決指數(shù)級(jí)的損失?！? DARPA列出多達(dá)30種可能取代摩爾定律主流 CMOS 技術(shù)的替代方案。Colwell說(shuō)：“我個(gè)人認(rèn)為其中有兩、三種具前景的方案，但卻都不被看好?！? DARPA的微系統(tǒng)部門就有兩項(xiàng)資金充份的計(jì)劃，其一是以Upside程序探索近似運(yùn)算，另一個(gè)則是探索旋轉(zhuǎn)扭矩振蕩器的影響，以解決部份方案在較低功耗時(shí)遭遇的問(wèn)題。 Colwell還列出可改善芯片后CMOS技術(shù)的其它方式，包括3D堆棧、新架構(gòu)與應(yīng)用程序、新的開(kāi)關(guān)技術(shù)、更好的人機(jī)接口，以及只是一般的創(chuàng)意行銷等。 Colwell提出了幾種具體情況，例如以千百個(gè)原子的層級(jí)打造組件。此外，“還有許多人機(jī)接口等，能找到更佳互動(dòng)方式的人就能取得成功?！? 隨著摩爾定律逐漸接近尾聲，他表示，“最后將由經(jīng)濟(jì)因素決定摩爾定律的終止，而不是實(shí)體定律，所以看緊你的荷包吧！” 也就是說(shuō)，推動(dòng)芯片持續(xù)向前進(jìn)展的新機(jī)會(huì)將會(huì)出現(xiàn)，因此，工程師們必須“隨時(shí)改變?cè)O(shè)計(jì)思維，但同時(shí)也計(jì)劃未來(lái)，因?yàn)橐磺幸巡粫?huì)太遙遠(yuǎn)了，”他說(shuō)。 本文授權(quán)編譯自EE Times，版權(quán)所有，謝絕轉(zhuǎn)載 編譯：Susan Hong 參考英文原文：Moore's Law Dead by 2022, Expert Says，by Rick Merritt

相關(guān)閱讀：
• 20nm的價(jià)值：持續(xù)創(chuàng)新價(jià)值
• 先進(jìn)工藝需求遞增，晶圓代工產(chǎn)值兩位數(shù)成長(zhǎng)
• 制程技術(shù)向7nm大躍進(jìn)，3D IC硬著頭皮也要上QxMesmc

{pagination} Moore's Law Dead by 2022, Expert Says Rick Merritt PALO ALTO, Calif. — Moore's Law -- the ability to pack twice as many transistors on the same sliver of silicon every two years -- will come to an end as soon as 2020 at the 7nm node, said a keynoter at the Hot Chips conference here. While many have predicted the end of Moore's Law, few have done it so passionately or convincingly. The predictions are increasing as lithography advances stall and process technology approaches atomic limits. "For planning horizons, I pick 2020 as the earliest date we could call it dead," said Robert Colwell, who seeks follow-on technologies as director of the microsystems group at the Defense Advanced Research Projects Agency. "You could talk me into 2022, but whether it will come at 7 or 5nm, it's a big deal," said the engineer who once managed a Pentium-class processor design at Intel. Moore's Law was a rare exponential growth factor that over 30 years brought speed boosts from 1 MHz to 5 GHz, a 3,500-fold increase. By contrast, the best advances in clever architectures delivered about 50x increases over the same period, he said. Exponentials always come to an end by the very nature of their unsustainably heady growth. Unfortunately, such rides are rare, Colwell said. "I don't expect to see another 3,500x increase in electronics -- maybe 50x in the next 30 years," he said. Unfortunately, "I don't think the world's going to give us a lot of extra money for 10 percent [annual] benefit increases," he told an audience of processor designers. Colwell poured cold water on blind faith that engineers will find another exponential growth curve to replace Moore's Law. "We will make a bunch of incremental tweaks, but you can't fix the loss of an exponential," he said. DARPA tracks a list of as many as 30 possible alternatives to the CMOS technology that has been the workhorse of Moore's Law. "My personal take is there are two or three promising ones and they are not very promising," he said. DARPA's microsystems group has "a fair amount of money chasing" two programs. One is exploring approximate computing in a program called Upside; another is exploring the effects of spin-torque oscillators to settle on partial solutions at relatively low power. Colwell ticked off a list of other routes to improving chips post-CMOS, including 3D stacking, new architectures and apps, new switching technologies, better human interfaces, and just plain creative marketing. "You laugh, but you will see this," he said, citing Intel's dolls of fab workers. Colwell called out a few specifics, such as work building devices at the level of a hundred to a thousand atoms. In addition, "there's a lot of work in brain-machine interfacing -- people who figure out better interfaces will win," he said. As the end approaches, "when Moore's Law stops it will be economics that stops it, not physics, so keep your eye on the money," he said. That said, new opportunities will emerge to nudge chips forward, so engineers need to "keep designing our heads off, but at the same time plan for the future because it's not that far off," he said.