計(jì)算機(jī)專業(yè)外文資料翻譯----微機(jī)發(fā)展簡(jiǎn)史

1、<p>　　附 錄 外文文獻(xiàn)及翻譯</p><p>　　Progress in computers</p><p>　　The first stored program computers began to work around 1950. The one we built in Cambridge, the EDSAC was first used in the sum

2、mer of 1949.</p><p>　　These early experimental computers were built by people like myself with varying backgrounds. We all had extensive experience in electronic engineering and were confident that that expe

3、rience would stand us in good stead. This proved true, although we had some new things to learn. The most important of these was that transients must be treated correctly; what would cause a harmless flash on the screen

4、of a television set could lead to a serious error in a computer.</p><p>　　As far as computing circuits were concerned, we found ourselves with an embarrass de riches. For example, we could use vacuum tube di

5、odes for gates as we did in the EDSAC or pentodes with control signals on both grids, a system widely used elsewhere. This sort of choice persisted and the term famil logic came into use. Those who have worked in the com

6、puter field will remember TTL, ECL and CMOS. Of these, CMOS has now become dominant.</p><p>　　In those early years, the IEE was still dominated by power engineering and we had to fight a number of major batt

7、les in order to get radio engineering along with the rapidly developing subject of electronics. dubbed in the IEE light current electrical engineering. properly recognized as an activity in its own right. I remember that

8、 we had some difficulty in organizing a conference because the power engineers’ ways of doing things were not our ways. A minor source of irritation was that all IEE p</p><p>　　Consolidation in the 1960s <

9、;/p><p>　　By the late 50s or early 1960s, the heroic pioneering stage was over and the computer field was starting up in real earnest. The number of computers in the world had increased and they were much more

10、reliable than the very early ones . To those years we can ascribe the first steps in high level languages and the first operating systems. Experimental time-sharing was beginning, and ultimately computer graphics was to

11、come along.</p><p>　　Above all, transistors began to replace vacuum tubes. This change presented a formidable challenge to the engineers of the day. They had to forget what they knew about circuits and start

12、 again. It can only be said that they measured up superbly well to the challenge and that the change could not have gone more smoothly. </p><p>　　Soon it was found possible to put more than one transistor on

13、 the same bit of silicon, and this was the beginning of integrated circuits. As time went on, a sufficient level of integration was reached for one chip to accommodate enough transistors for a small number of gates or fl

14、ip flops. This led to a range of chips known as the 7400 series. The gates and flip flops were independent of one another and each had its own pins. They could be connected by off-chip wiring to make a computer or anyth&

15、lt;/p><p>　　These chips made a new kind of computer possible. It was called a minicomputer. It was something less that a mainframe, but still very powerful, and much more affordable. Instead of having one expen

16、sive mainframe for the whole organization, a business or a university was able to have a minicomputer for each major department.</p><p>　　Before long minicomputers began to spread and become more powerful. T

17、he world was hungry for computing power and it had been very frustrating for industry not to be able to supply it on the scale required and at a reasonable cost. Minicomputers transformed the situation.</p><p&

18、gt;　　The fall in the cost of computing did not start with the minicomputer; it had always been that way. This was what I meant when I referred in my abstract to inflation in the computer industry ‘going the other way’. A

19、s time goes on people get more for their money, not less. </p><p>　　Research in Computer Hardware. </p><p>　　The time that I am describing was a wonderful one for research in computer hardware.

20、The user of the 7400 series could work at the gate and flip-flop level and yet the overall level of integration was sufficient to give a degree of reliability far above that of discreet transistors. The researcher, in a

21、university or elsewhere, could build any digital device that a fertile imagination could conjure up. In the Computer Laboratory we built the Cambridge CAP, a full-scale minicomputer with fancy ca</p><p>　　Th

22、e 7400 series was still going strong in the mid 1970s and was used for the Cambridge Ring, a pioneering wide-band local area network. Publication of the design study for the Ring came just before the announcement of the

23、Ethernet. Until these two systems appeared, users had mostly been content with teletype-based local area networks. Rings need high reliability because, as the pulses go repeatedly round the ring, they must be continually

24、 amplified and regenerated. It was the high reliability pr</p><p>　　The RISC Movement and Its Aftermath </p><p>　　Early computers had simple instruction sets. As time went on designers of commer

25、cially available machines added additional features which they thought would improve performance. Few comparative measurements were done and on the whole the choice of features depended upon the designer’s intuition.<

26、/p><p>　　In 1980, the RISC movement that was to change all this broke on the world. The movement opened with a paper by Patterson and ditzy entitled The Case for the Reduced Instructions Set Computer.</p>

27、<p>　　Apart from leading to a striking acronym, this title conveys little of the insights into instruction set design which went with the RISC movement, in particular the way it facilitated pipelining, a system wh

28、ereby several instructions may be in different stages of execution within the processor at the same time. Pipelining was not new, but it was new for small computers </p><p>　　The RISC movement benefited grea

29、tly from methods which had recently become available for estimating the performance to be expected from a computer design without actually implementing it. I refer to the use of a powerful existing computer to simulate t

30、he new design. By the use of simulation, RISC advocates were able to predict with some confidence that a good RISC design would be able to out-perform the best conventional computers using the same circuit technology. Th

31、is prediction was ultimately</p><p>　　Simulation made rapid progress and soon came into universal use by computer designers. In consequence, computer design has become more of a science and less of an art. T

32、oday, designers expect to have a roomful of, computers available to do their simulations, not just one. They refer to such a roomful by the attractive name of computer farm. </p><p>　　The x86 Instruction Set

33、 </p><p>　　Little is now heard of pre-RISC instruction sets with one major exception, namely that of the Intel 8086 and its progeny, collectively referred to as x86. This has become the dominant instruction

34、set and the RISC instruction sets that originally had a considerable measure of success are having to put up a hard fight for survival.</p><p>　　This dominance of x86 disappoints people like myself who come

35、from the research wings. both academic and industrial. of the computer field. No doubt, business considerations have a lot to do with the survival of x86, but there are other reasons as well. However much we research ori

36、ented people would like to think otherwise. high level languages have not yet eliminated the use of machine code altogether. We need to keep reminding ourselves that there is much to be said for strict binary compatibi&l

37、t;/p><p>　　There is an interesting sting in the tail of this apparently easy triumph of the x86 instruction set. It proved impossible to match the steadily increasing speed of RISC processors by direct implemen

38、tation of the x86 instruction set as had been done in the past. Instead, designers took a leaf out of the RISC book; although it is not obvious, on the surface, a modern x86 processor chip contains hidden within it a RIS

39、C-style processor with its own internal RISC coding. The incoming x86 code is, af</p><p>　　The IA-64 instruction set. </p><p>　　Some time ago, Intel and Hewlett-Packard introduced the IA-64 inst

40、ruction set. This was primarily intended to meet a generally recognized need for a 64 bit address space. In this, it followed the lead of the designers of the MIPS R4000 and Alpha. However one would have thought that Int

41、el would have stressed compatibility with the x86; the puzzle is that they did the exact opposite. </p><p>　　Moreover, built into the design of IA-64 is a feature known as predication which makes it incompat

42、ible in a major way with all other instruction sets. In particular, it needs 6 extra bits with each instruction. This upsets the traditional balance between instruction word length and information content, and it changes

43、 significantly the brief of the compiler writer. </p><p>　　In spite of having an entirely new instruction set, Intel made the puzzling claim that chips based on IA-64 would be compatible with earlier x86 chi

44、ps. It was hard to see exactly what was meant.</p><p>　　Chips for the latest IA-64 processor, namely, the Itanium, appear to have special hardware for compatibility. Even so, x86 code runs very slowly.</p

45、><p>　　Because of the above complications, implementation of IA-64 requires a larger chip than is required for more conventional instruction sets. This in turn implies a higher cost. Such at any rate, is the re

46、ceived wisdom, and, as a general principle, it was repeated as such by Gordon Moore when he visited Cambridge recently to open the Betty and Gordon Moore Library. I have, however, heard it said that the matter appears di

47、fferently from within Intel. This I do not understand. But I am very ready to</p><p>　　Shortage of Electrons </p><p>　　Although shortage of electrons has not so far appeared as an obvious limita

48、tion, in the long term it may become so. Perhaps this is where the exploitation of non-conventional CMOS will lead us. However, some interesting work has been done. notably by Huron Amend and his team working in the Cave

49、ndish Laboratory. on the direct development of structures in which a single electron more or less makes the difference between a zero and a one. However very little progress has been made towards practical</p><

50、;p><b>　　微機(jī)發(fā)展簡(jiǎn)史</b></p><p>　　第一臺(tái)存儲(chǔ)程序的計(jì)算開(kāi)始出現(xiàn)于1950前后，它就是1949年夏天在劍橋大學(xué)，我們創(chuàng)造的延遲存儲(chǔ)自動(dòng)電子計(jì)算機(jī)（EDSAC）。</p><p>　　最初實(shí)驗(yàn)用的計(jì)算機(jī)是由象我一樣有著廣博知識(shí)的人構(gòu)造的。我們?cè)陔娮庸こ谭矫娑加兄S富的經(jīng)驗(yàn)，并且我們深信這些經(jīng)驗(yàn)對(duì)我們大有裨益。后來(lái)，被證明是正確的，盡管我們也

51、要學(xué)習(xí)很多新東西。最重要的是瞬態(tài)一定要小心應(yīng)付，雖然它只會(huì)在電視機(jī)的熒幕上一起一個(gè)無(wú)害的閃光，但是在計(jì)算機(jī)上這將導(dǎo)致一系列的錯(cuò)誤。</p><p>　　在電路的設(shè)計(jì)過(guò)程中，我們經(jīng)常陷入兩難的境地。舉例來(lái)說(shuō)，我可以使用真空二級(jí)管做為門電路，就象在EDSAC中一樣，或者在兩個(gè)柵格之間用帶控制信號(hào)的五級(jí)管，這被廣泛用于其他系統(tǒng)設(shè)計(jì)，這類的選擇一直在持續(xù)著直到邏輯門電路開(kāi)始應(yīng)用。在計(jì)算機(jī)領(lǐng)域工作的人都應(yīng)該記得TTL，EC

52、L和CMOS，到目前為止，CMOS已經(jīng)占據(jù)了主導(dǎo)地位。</p><p>　　在最初的幾年，IEE（電子工程師協(xié)會(huì)）仍然由動(dòng)力工程占據(jù)主導(dǎo)地位。為了讓IEE 認(rèn)識(shí)到無(wú)線工程和快速發(fā)展的電子工程并行發(fā)展是它自己的一項(xiàng)權(quán)利，我們不得不面對(duì)一些障礙。由于動(dòng)力工程師們做事的方式與我們不同，我們也遇到了許多困難。讓人有些憤怒的是，所有的IEE出版的論文都被期望以冗長(zhǎng)的早期研究的陳述開(kāi)頭，無(wú)非是些在早期階段由于沒(méi)有太多經(jīng)驗(yàn)而遇

53、到的困難之類的陳述。</p><p><b>　　60年代的鞏固階段</b></p><p>　　60年代初，個(gè)人英雄時(shí)代結(jié)束了，計(jì)算機(jī)真正引起了重視。世界上的計(jì)算機(jī)數(shù)量已經(jīng)增加了許多，并且性能比以前更加可靠。這些我認(rèn)為歸因與高級(jí)語(yǔ)言的起步和第一個(gè)操作系統(tǒng)的誕生。分時(shí)系統(tǒng)開(kāi)始起步，并且計(jì)算機(jī)圖形學(xué)隨之而來(lái)。</p><p>　　綜上所述，晶體管

54、開(kāi)始代替正空管。這個(gè)變化對(duì)當(dāng)時(shí)的工程師們是個(gè)不可回避的挑戰(zhàn)。他們必須忘記他們熟悉的電路重新開(kāi)始。只能說(shuō)他們鼓起勇氣接受了挑戰(zhàn)，盡管這個(gè)轉(zhuǎn)變并不會(huì)一帆風(fēng)順。</p><p>　　小規(guī)模集成電路和小型機(jī)</p><p>　　很快，在一個(gè)硅片上可以放不止一個(gè)晶體管，由此集成電路誕生了。隨著時(shí)間的推移，一個(gè)片子能夠容納的最大數(shù)量的晶體管或稍微少些的邏輯門和翻轉(zhuǎn)門集成度達(dá)到了一個(gè)最大限度。由現(xiàn)了我們

55、所知道7400系列微機(jī)。每個(gè)門電路或翻轉(zhuǎn)電路是相互獨(dú)立的并且有自己的引腳。他們可通過(guò)導(dǎo)線連接在一起，作成一個(gè)計(jì)算機(jī)或其他的東西?，F(xiàn)了我們所知道7400系列微機(jī)。每個(gè)門電路或翻轉(zhuǎn)電路是相互獨(dú)立的并且有自己的引腳。他們可通過(guò)導(dǎo)線連接在一起，作成一個(gè)計(jì)算機(jī)或其他的東西。</p><p>　　這些芯片為制造一種新的計(jì)算機(jī)提供了可能。它被稱為小型機(jī)。他比大型機(jī)稍遜，但功能強(qiáng)大，并且更能讓人負(fù)擔(dān)的起。一個(gè)商業(yè)部門或大學(xué)有能力

56、擁有一臺(tái)小型機(jī)而不是得到一臺(tái)大型組織所需昂貴的大型機(jī)。</p><p>　　隨著微機(jī)的開(kāi)始流行并且功能的完善，世界急切獲得它的計(jì)算能力但總是由于工業(yè)上不能規(guī)模供應(yīng)和它可觀的價(jià)格而受到挫折。微機(jī)的出現(xiàn)解決了這個(gè)局面。</p><p>　　計(jì)算消耗的下降并非起源與微機(jī)，它本來(lái)就應(yīng)該是那個(gè)樣子。這就是我在概要中提到的“通貨膨脹”在計(jì)算機(jī)工業(yè)中走上了歧途之說(shuō)。隨著時(shí)間的推移，人們比他們付出的金錢得

57、到的更多。</p><p><b>　　硬件的研究</b></p><p>　　我所描述的時(shí)代對(duì)于從事計(jì)算機(jī)硬件研究的人們是令人驚奇的時(shí)代。7400系列的用戶能夠工作在邏輯門和開(kāi)關(guān)級(jí)別并且芯片的集成度可靠性比單獨(dú)晶體管高很多。大學(xué)或各地的研究者，可以充分發(fā)揮他們的想象力構(gòu)造任何微機(jī)可以連接的數(shù)字設(shè)備。在劍橋大學(xué)實(shí)驗(yàn)室力，我們構(gòu)造了CAP，一個(gè)有令人驚奇邏輯能力的微機(jī)。

58、</p><p>　　7400在70年代中期還不斷發(fā)展壯大，并且被寬帶局域網(wǎng)的先驅(qū)組織Cambridge Ring所采用。令牌環(huán)設(shè)計(jì)研究的發(fā)表先于以太網(wǎng)。在這兩種系統(tǒng)出現(xiàn)之前，人們大多滿足于基于電報(bào)交換機(jī)的本地局域網(wǎng)。</p><p>　　令牌環(huán)網(wǎng)需要高可靠性，由于脈沖在令牌環(huán)中傳遞，他們必須不斷的被放大并且再生。是7400的高可靠性給了我們勇氣，使得我們著手Cambridge Ring.

59、項(xiàng)目。</p><p>　　精簡(jiǎn)指令計(jì)算機(jī)的誕生</p><p>　　早期的計(jì)算機(jī)有簡(jiǎn)單的指令集，隨著時(shí)間的推移，商業(yè)用微機(jī)的設(shè)計(jì)者增加了另外的他們認(rèn)為可以微機(jī)性能的特性。很少的測(cè)試方法被建立，總的來(lái)說(shuō)特性的選取很大程度上依賴于設(shè)計(jì)者的直覺(jué)。1980年，RISC運(yùn)動(dòng)改變了微機(jī)世界。該運(yùn)動(dòng)是由Patterson 和 Ditzel發(fā)表了一篇命名為精簡(jiǎn)指令計(jì)算機(jī)的情況論文而引起的。</p&

60、gt;<p>　　除了RISC這個(gè)引人注目縮略詞外，這個(gè)標(biāo)題傳達(dá)了一些指令集合設(shè)計(jì)的見(jiàn)解，隨之引發(fā)了RISC運(yùn)動(dòng)。從某種意義上說(shuō)，它推動(dòng)了線程的發(fā)展，在處理器中，同一時(shí)間有幾個(gè)指令在不同的執(zhí)行階段稱為線程。線程不是個(gè)新概念，但是它對(duì)微機(jī)來(lái)說(shuō)是從未有過(guò)的。</p><p>　　RISC受益于一個(gè)最近的可用的方法的誕生，該方法使估計(jì)計(jì)算機(jī)性能成為可能而不去真正實(shí)現(xiàn)該微機(jī)的設(shè)計(jì)。我的意思是說(shuō)利用目前存在的

61、功能強(qiáng)大的計(jì)算機(jī)去模擬新的設(shè)計(jì)。通過(guò)模擬該設(shè)計(jì)，RISC的提倡者能夠有信心的預(yù)言，一臺(tái)使用和傳統(tǒng)計(jì)算機(jī)相同電路的RISC計(jì)算機(jī)可以和傳統(tǒng)的最好的計(jì)算機(jī)有同樣的性能。</p><p>　　模擬仿真加快了開(kāi)發(fā)進(jìn)度并且被計(jì)算機(jī)設(shè)計(jì)者廣泛采用。隨后，計(jì)算機(jī)設(shè)計(jì)者變的多些可理性少了一些藝術(shù)性。今天，設(shè)計(jì)者們希望有滿屋可用計(jì)算機(jī)做他們的仿真，而不只是一臺(tái)。</p><p><b>　　x86

62、指令集</b></p><p>　　除非出現(xiàn)很大意外，要不很少聽(tīng)到有計(jì)算機(jī)使用早期的RISC指令集了。INTEL 8086及其后裔都與x86密切相關(guān)。x86構(gòu)架已經(jīng)占據(jù)了計(jì)算機(jī)核心指令集的主導(dǎo)地位。被認(rèn)為是相當(dāng)成功的RISC指令集現(xiàn)在的生存空間越來(lái)越小了。</p><p>　　對(duì)于我們這些從事計(jì)算機(jī)學(xué)術(shù)研究的人，x86的統(tǒng)治地位讓我們感到失望。毫無(wú)疑問(wèn)，商業(yè)上對(duì)于x86的生存會(huì)

63、有更多的考慮，但是這里還有很多原因，盡管我們多么希望人們考慮其他的方面。高級(jí)語(yǔ)言并沒(méi)有完全消除對(duì)機(jī)器原始編碼的的使用。我們?nèi)孕枰粩嗵嵝盐覀冏约海何覀儜?yīng)該嚴(yán)格的與先前的應(yīng)用在機(jī)器層面上保持兼容。然而，情況也許有所不同，如果Intel的主要目的是為是生產(chǎn)一個(gè)好的RISC芯片。有一個(gè)已經(jīng)取得了更大的成功，我所說(shuō)的i860（不是i960，它們有一些不同）。從許多方面來(lái)說(shuō)，i860是個(gè)卓越的芯片，但是它的軟件借口不適合在工作站上應(yīng)用。對(duì)于x86

64、取得勝利的最后有一件有意思的事情。直接應(yīng)用先前x86的實(shí)現(xiàn)方式對(duì)于滿足RISC處理器的持續(xù)增長(zhǎng)的速度要求，是不可能的。因此，設(shè)計(jì)者們沒(méi)有完全實(shí)現(xiàn)RISC指令集，盡管這不是很明顯。表面上，一片現(xiàn)代的x86芯片包含了隱藏實(shí)現(xiàn)的部分，好象和實(shí)現(xiàn)RISC指令集的芯片一樣。當(dāng)致命的異常發(fā)生時(shí)，x86引入的代碼是，經(jīng)過(guò)適當(dāng)?shù)拇鄹暮螅晦D(zhuǎn)化為它的內(nèi)部代碼并且被RISC芯片處理。</p><p>　　對(duì)于以上RISC運(yùn)動(dòng)的總結(jié)，

65、我非常信賴最新版本的哈里斯和培生出版社的有關(guān)計(jì)算機(jī)設(shè)計(jì)的書籍。請(qǐng)參考特殊計(jì)算機(jī)體系構(gòu)造，第三版，2003，P146，151-4，157-8</p><p><b>　　IA-64指令集</b></p><p>　　很久以前，Intel 和 Hewlett-Packard引進(jìn)了IA-64指令集。這最初主要是為了滿足通常的64位地址空間問(wèn)題。在這種情況下，隨后出現(xiàn)了MIP

66、S R4000和Alpha。然而，人們普遍認(rèn)為Intel應(yīng)該與x86構(gòu)架保持兼容，可令人疑惑的是恰恰相反。</p><p>　　進(jìn)一步說(shuō)，IA-64的設(shè)計(jì)與其他所有的指令集在主要實(shí)現(xiàn)方式上有所不同。特別的，每條指令它需要附加的6位。這打亂了傳統(tǒng)的在指令字長(zhǎng)和信息內(nèi)容的平衡，并且它改變了編譯器作者的原先的大綱。</p><p>　　盡管IA-64是個(gè)全新的指令集，但I(xiàn)ntel發(fā)表了一個(gè)令人困

67、惑的聲明：基于IA-64的芯片將與早期的x86芯片保持兼容。很難弄懂它所指的是什么。</p><p>　　最新的稱為Itaninu IA-64處理器顯然需要特殊的兼容性的硬件，盡管如此，x86編碼運(yùn)行的相當(dāng)慢。</p><p>　　由于以上的復(fù)雜因素，IA-64的實(shí)現(xiàn)需要更大的體積相對(duì)與傳統(tǒng)的指令集，這暗示著更大的消耗。因此，在任何情況下，作為常識(shí)和一般性的標(biāo)準(zhǔn)，Gordon Moore在

68、訪問(wèn)劍橋最近開(kāi)放的Betty and Gordon Moore 圖書館時(shí)所反復(fù)強(qiáng)調(diào)。在聽(tīng)到他說(shuō)問(wèn)題出現(xiàn)在Intel內(nèi)部也許有所不同，我很不理解。但是我已經(jīng)作好了準(zhǔn)備，去接受這樣的事實(shí)，我已經(jīng)完全不了解半導(dǎo)體經(jīng)濟(jì)學(xué)了。</p><p><b>　　電子的不足</b></p><p>　　盡管目前為止，電子每表現(xiàn)出明顯的不足，然而從長(zhǎng)遠(yuǎn)看來(lái)，它最終會(huì)不能滿足要求。也許這是