超級電腦沒有一個特別的定義,就像各人對不同射程的飛彈歸類不同般,但一般超級電腦指的是在速度上快PC數百倍至數萬倍的電腦. IBM之前推出的幾款號稱超級電腦的伺服器只不過是高階的伺服器電腦,跟本連超級電腦的邊都碰不上
現在世界上最快的電腦為日本的Earth Simulator,用途為模擬地球的各種變化,有如氣候,污染等
在此提供一個簡單的對照表
現在最高級的個人電腦
4 GHz Pentium 4(以特殊方法可以超頻到5.0GHz)
IBM超級電腦
4 * 3GHz XEON/OPTERON CPU (12 GHz)
Earth Simulator
5120 * 2 GHz NEC處理器 (10240GHz)

以上我們可以很清楚的看到真正的超級電腦與IBM的超級電腦的差別….

以超級電腦的運算能力,我們可以對複雜的物理現象(如空氣震波及超空泡化現象等),進行極度精確及快速的模擬,進而允許研發人員做出更有效率及更好的產品
不同電腦科技對研發能力影響我們可以在F-117對F/A-22及B-2上看出來
對雷達匿蹤的能力也是靠超級電腦運算出來的, 所以如果國內擁有可以對這些項目做出有效模擬的超級電腦,不只是軍事研發,對國內的精密產業也會有很大的幫助

AMS-01的那650個微電腦處理器上過發現者號太空梭測試其效能
雖號稱比美國速度快10倍
但因為其畢竟還是「微電腦處理器」的等級
只不過那是太空規格
CSIST能做的是太空規格的微處理器
AMS-02用的微處理器也是太空站上用的

小弟雖引述該則新聞，但已多次表明並不清楚CSIST在AMS中做出的那些微處理器的進一步資訊

CosmoHorizon 大在隔壁回應道CSIST如此便可製造出可當地球模擬器的超級電腦，此點因非巡弋飛彈議題故而建議另闢一欄以確定所謂「可當地球模擬器的超級電腦」的需求為何

小弟相信開欄大重點在討論「超級電腦」的規格與需求，AMS上的高速處理器應該只是這個超級電腦話題的引子吧？

量子電腦？破解ＲＳＡ演算法？
由於您所提供的連結進不去，請問
這裡所說的ＲＳＡ是否即公開密鑰的ＲＳＡ？
RSA是當今應用最廣的公開密鑰密碼系統演算法則
如果ＲＳＡ會被破，那全世界的資訊安全史恐怕要改寫了

RCI大,這裡的RSA就是公開密鑰的ＲＳＡ

Defense Advanced Research Projects Agency Technology Transition

這一份報告第31及87頁便有提到DARPAR對陸軍的技術移轉項目中的一項.....便是使用NN技術(這裡提到的只是小弟曾經STUDY到眾多NN應用其中的一項)

P.31
Once the advantages of a technology are demonstrated in a military systems environment, the technology is much more readily
accepted for enhancing systems performance via upgrades. Prime examples of this process are the insertions of artificial neural networks (ANN) technology into the Comanche helicopter for target recognition and GaAs digital electronics technology
into the digital signal processors (DSPs) to improve the resolution of the ISAR on the P-3 Orion....(以下略)

P.87
COMANCHE ANN-BASED ATR

Artificial neural networks (ANN) technology provides the Comanche with a man-in-the-loop aided target recognition system (ATR) that enables the Comanche to operate and be survivable on the battlefield within the threat engagement timelines.

The Army’s new reconnaissance helicopter, the Comanche, will deploy an artificial neural network (ANN)-based aided target recognition (ATR) system. In the first two comprehensive Army blind tests on Comanche forward looking infrared (FLIR) imagery, the ANN achieved factors of two to sixfold reduction in detection error, identification error, and false alarm rate over the competing template-matching algorithm. These results enable the Comanche performance specifications to be achieved, while the template matcher failed to meet those specifications....(以下略)

sasc31298
第8頁
...In support of undersea littoral warfare, DARPA has developed and tested an active acoustic system for enhanced detection, classification and targeting of submarines in the difficult littoral regions. The system uses an air-droppable sound-source that generates a sound wave; multiple listening sensors; and a torpedo linked via a fiber optic tether. The information from
multiple sensors is fused and processed using advanced signal processing algorithms and neural networks processing to allow a superior detection probability. Then, because of the datalink to the torpedo, the submarine track can be provided to the torpedo after launch, enhancing the probability that the torpedo will find the submarine and destroy it. Last year, we demonstrated the sound-source, multiple sensors and advanced processing at sea, with excellent results.

以下這個連結有15.8M下載前請自行考慮是否佔太大空間
Workshop on Computational Modeling and Simulation of Biological Systems (DARPA – DSO/MTO)
P.5及191

Transformation and Transition: DARPA’s Role in Fostering an Emerging Revolution in Military Affairs Volume 2 – Detailed Assessments
PP.138(V-8)
....
Automatic Target Recognition

Onboard computer and processing is an essential ingredient of any smart weapon. Advanced smart weapon systems typically rely heavily on automatic target recognition (ATR) software running in real time on high-speed processors. DARPA has consistently invested in ATR algorithms and processors for a variety of sensors, beginning in the 1970s with image understanding research. In 1983, the Director of DARPA approved a comprehensive ATR program for three sensor domains: passive thermal imaging, imaging laser radar, and millimeter wave range radar. This investment covered all aspects of ATR development, sensor phenomenology, and evaluation. The program emphasized metrics and standards to evaluate whether and to what degree ATR could provide a useful military capability in smart weapons and surveillance platforms. These programs produced standard data bases for the millimeter and infrared ATR communities to train and evaluate their algorithms. Many kinds of algorithms and processing schemes were supported to include template matching, neural networks, and model based vision concepts.
(以下略)

P.140(V-10)
....
Imaging Laser Radar

darpa_hasc_32504_final.pdf

其第3頁便提到了相關成果

DARPA’s sensor work is exemplified by the Standoff Precision Identification in Three Dimensions (SPI-3D) program to develop an airborne LIDAR sensor to provide positive target identification from standoff ranges via high resolution three-dimensional representations. SPI-3D will be cued by wide area surveillance sensors, such as synthetic aperture radar, which can determine the presence of possible targets but may be unable to confirm target type or identity. SPI-3D technology will close this gap, allowing commanders to positively identify targets as needed by our rules of engagement.

The Jigsaw program is developing a three-dimensional imaging laser radar capable of reliably identifying hidden targets through gaps in foliage and camouflage. The Jigsaw sensor will collect high-resolution, three-dimensional images from multiple viewpoints and combine them to form a composite three-dimensional image to enable the warfighter to see underneath the canopy and recognize targets, day or night. In field tests, we have successfully integrated, tested, and flown prototypes against targets hidden by various densities of foliage and types of camouflage. We are proceeding to ruggedize and miniaturize the Jigsaw sensor for the Army’s Future Combat Systems.

The National/Tactical Exploitation (NTEX) program uses imagery and data from both national reconnaissance systems and tactical assets to locate and identify enemy air defense units. During Operation Iraqi Freedom, NTEX supported our forces in Iraq by screening synthetic aperture radar imagery to look for enemy air defense emplacements.

另，以下連結中有DARPA在去(2003)年的3-D影像感測包括LADAR方面的各項計畫成果節要，請參考
http://www.darpa.mil/mto/3dimaging/summaries/index.ht

這是先用軟體作來測，接著開一顆ASIC來implementation，用不到超級電腦。

據該單位表示，五年內大部分車子裡面都會裝上這套系統.....

但是問題是,並非所有問題都適合分散式計算,所以運算速度的關鍵小弟以為是
設計人員對所解的問題的分析能力和分散式能力.
-------------------------------------------
但是人家美國現在都在玩量子計算了阿,連加拿大都有量子計算的國家級研究中心的設立
我們還在談super computer,唉...萬事老是慢了人家一步.
breaking unbreakable code, making unbreakable code...聽起來多炫阿,
一但這個軍事應用成功之後,老美又可把敵方整個電腦網路和軍事網路打穿了.

半導體運算已經發展到一個非常高原的狀態了，哪一個國家可以搶先取得量子運算的關鍵技術，就可以主導未來的數位運算，在這種情況下當然卯起來研發量子運算
就跟PW與GE兩家發動機大廠現在卯起來玩PDE一樣，一個是未來數位運算的門票，一個是未來發動機的門票
今天如果反重力理論可以被證實，你看會有多少國家卯起來衝反重力機構實用化，曲速科技也一樣啦

現年六十歲的陳世卿是在台灣出生的美國公民，一九八○年代為科技先鋒克雷公司服務時，公認是全美最頂尖的超級電腦設計師。後來，他移居中國大陸，率領一支研究團隊，企圖締造世界最快的電腦運算速度紀錄。

中共當局正運用超級電腦，助其加快從低成本造業轉型躋身全球經濟強國的速度。中共領導階層知道，要在全球科技及各種先進產品設計領域位居樞紐地位，高速運算能力絕對不可或缺。

「現在，中國人已開始注意；他們正迎頭趕上，而且他們學得很快，」陳世卿說。他目前大部分時間都在中國大陸和加州聖荷西兩地奔波，因為他太太凱特和四個孩子都住在加州。

長久以來，美國軍事情報專家對中共可能利用超級電腦提升軍備研發能力始終非常關切。許多科技和經濟專家說，光有超級電腦運算能力，並不代表就足以構成核武威脅。相對的，他們反而更關切中共在具經濟與科學效益的領域快速迎頭趕上美國。

陳世卿會在大陸設立公司，實在是始料未及。他有最新的點子，苦於無法在美國找到創投資金，剛好中國大陸有機會建立一家在他看來發展前景遠比在美國還要好的新公司。陳世卿認為，網路泡沫化已使投資氣候受到戕害。

陳世卿雖然不是大陸人，但是他的決定卻和來多在外國出生，以為可以在美國充分發揮所學的研究人員一樣。許多學有專精的人才正不斷回流到中國大陸、印度和其他開發中國家，在那裡創業或加入先進的科技公司。

今年五月，陳世卿加入星盈科技（深圳）有限公司。他這項決定反映出一個事實，亦即中國大陸的高效能電算市場發展速度，已舉世無匹。中國大陸雖然還不是超級電算的主要國家，但是，美國電算專家指出，這種情況已在改變。

星盈科技最近在北京一家生物醫學研究所展示陳世卿最新的超級電腦原型。他說，這部機器每秒可以做一兆個運算。

這種超級運算能力現在正是世界經濟的核心要角，充分明美國數十年來處心積慮企圖控制先進資訊處理科技流動的努力有待商榷。

專家說，像中國大陸、印度、俄羅斯等國公司，要迎頭趕上美、日等先進工業國家水平，只是遲早的問題。

在世界各處高速電腦晶片唾手可得的情況下，造超級電腦的技術已轉移到可以將數以百計或千計晶片聯結起來的軟體開發上面。陳世卿就是世界公認這方面技術的權威。

一九七五年，卅一歲的陳世卿從台灣前往美國，進入研究所攻讀電腦學。離開克雷研究中心後，陳世卿在ＩＢＭ助下，於一九八七年九月創設自己的超級電算系統公司。後來他擔任思群電腦系統公司首席科技工程師，這家公司後來被ＩＢＭ購。

美國超級電腦專家說，二○○二年，日本開發出世界最快的超級電腦「地球模擬器」，各國政府科技專家咸感震驚，陳世卿到中國大陸，會有類似的效應。

【2004/11/03 聯合報】【編譯蔡繼光／綜合舊金山二日電】

=== Original Articel from New York Times

Have Supercomputer, Will Travel
By JOHN MARKOFF
Published: November 1, 2004

SAN FRANCISCO, Oct. 25 - Add Steve Chen to the growing list of Americas high-technology exports.

Mr. Chen, a Taiwanese-born American citizen who was considered one of the nations most brilliant supercomputer designers while working in this country for the technology pioneer Seymour Cray in the 1980s, has moved to China - where he is leading an effort to claim the world computing speed record.

Supercomputing is being seized upon by the Chinese government to help speed the nations transition from low-cost manufacturing to becoming a more powerful force in the world economy. Chinas leaders know that high-speed computing is essential to global leadership in scientific fields and advanced design of a variety of sophisticated products.

Right now the Chinese have started to pay attention; they are catching up and they learn fast, said Mr. Chen, 60, who is splitting his time between China and San Jose, Calif., where his wife, Kate, and their four children live.

Military intelligence experts in this country have long been concerned that supercomputing capabilities may aid Chinas weapons development. But many technologists and economists say that blazing computing speeds alone do not represent a particularly new nuclear weapons threat. Instead, they are more concerned that the Chinese may catch up more quickly with the United States in areas that have economic and scientific, rather than military, ramifications.

Mr. Chens decision to set up shop in China was driven in part by an unexpected twist: the opportunity to build a new company looked more promising to him there than in the United States, where he was unable to secure financing from American venture capitalists for his latest ideas. Mr. Chen concluded that the fallout from the collapse of the Internet bubble had poisoned the investment climate.

I saw the crazy stuff going on, he said recently in a telephone interview from Shenzhen, near Hong Kong. A lot of people got hurt.

While Mr. Chen is not a native of mainland China, his decision has parallels to an increasingly common odyssey by foreign-born researchers, who once would have found the greatest openings to use their skills in the United States. As the spread of capitalism creates opportunities elsewhere, many such talented people are returning to China, India and other developing countries to create or join advanced technology firms.

In May, Mr. Chen joined Galactic Computing Shenzhen, which is backed by investment money from a Hong Kong company that supported an earlier Chen venture and with further backing from a group of Chinese universities. His move reflects the fact that the market for high-performance computing is growing more rapidly in China than elsewhere in the world.

The Chinese are not yet a major force in supercomputing, but according to American computing experts, that is changing rapidly.

Today there are 14 Chinese supercomputers among the top 500, ranking the country fourth in the world, equal to Germany and behind only the United States, Japan and Britain. In June, a supercomputer assembled at the Shanghai Supercomputer Center using more than 2,500 chips designed and manufactured by Advanced Micro Devices of Sunnyvale, Calif., became the worlds 10th-fastest computer.

In terms of momentum they are the most rapidly ascending country in the world, said David Keyes, a professor of applied mathematics at Columbia University, who visited China last month to participate in a conference on high-performance computing.

Galactic recently demonstrated a prototype of Mr. Chens newest supercomputer at a biomedical research institute in Beijing. The machine, he said, is capable of one trillion calculations a second, a performance level that would place it among the top half of the worlds 500 fastest computers.

Such computing now occupies a central role throughout the global economy, providing stark proof that decades-long American attempts to control the flow of advanced information-processing technologies are largely moot. It is only a matter of time, experts say, before companies in places like China, India and Russia essentially match the capabilities of the American and Japanese leaders.

When they really get noticed, said Horst D. Simon, director of the computation center at the Lawrence Berkeley National Laboratory in California, will be when a country like Malaysia or Australia decides to buy a supercomputer from a Chinese company like Mr. Chens rather than from I.B.M.

Now that computer chips openly available anywhere in the world have reached such high speeds, the expertise needed to build supercomputers has shifted to the software needed to hook hundreds or thousands of processors together. Mr. Chen has long been recognized as one of the worlds pioneers in that specialty.

Have Supercomputer, Will Travel

Published: November 1, 2004

Natalie Behring for The New York Times
Steve Chen in Beijing last month. His move to China mirrors that countrys push to develop supercomputers, which can have both civilian and military applications.

(Page 2 of 2)

He arrived in the United States from Taiwan in 1975, at age 31, to pursue graduate studies in computer science. During the 1980s, Mr. Chen was widely considered one the leading computer designers in the United States.

As a computer architect at Cray Research from 1979 to 1987, he gained a reputation for machines that were both elegant and blindingly fast. He also became known as a visionary who frequently needed assistance in finishing overambitious projects.

Hes very charismatic, said David J. Kuck, a computer scientist and Intel researcher, who was Mr. Chens professor in a Ph.D. program at the University of Illinois at Urbana-Champaign in the 1970s. His English wasnt the greatest, but everyone understood what he wanted to do.

As a graduate student, Mr. Chen designed one of the first software programs known as a parallel compiler, which was useful in restructuring programs so they could run on computers with multiple processors. That pioneering work became the basis for much of todays commercial parallel computing software.

At Cray Research, Mr. Chen had an intense rivalry with Mr. Cray, who was leading a team that pursued a competing design. Ultimately, Crays chief executive, John Rollwagen, canceled one of Mr. Chens computer projects. Soon afterward, in September 1987, Mr. Chen established his own supercomputing company, Supercomputing Systems, with backing from International Business Machines.

That effort led to a partially completed prototype, but the company failed commercially in 1992 when I.B.M. canceled funding. Because the Cold War was ending, military funding for high-performance computing slowed dramatically. Later, Mr. Chen became the chief technology officer of Sequent Computer Systems, which was later acquired by I.B.M.

Mr. Chens decision to try his luck in China as an entrepreneur stands in contrast to an earlier example of technology transfer from the United States to China. During the 1950s Tsien Hsue-shen, a leading aerospace designer with a Ph.D. from the California Institute of Technology, was deported from the United States as a presumed security threat during the Communist witch hunts of the McCarthy era. After returning to China, he became the father of the countrys intercontinental missile program.

During the Clinton administration, Washington attempted to control the flow of high-performance computers to China because of fears they could be used to design nuclear weapons. That policy, with modifications, has continued. Indeed, just this month, State Department officials renewed calls for maintaining the arms sales embargo against China, which extends to restrictions on the fastest computers.

But with the new type of supercomputer - which blends thousands of freely available off-the-shelf microprocessors connected via high-speed fiber-optic cables that can stretch for hundreds of miles - restrictions on the sale of so-called dual-use computers that have both military and civilian applications no longer stand in the way of developing systems able to compete with the fastest machines made by American and Japanese companies.

American supercomputer experts said that Mr. Chens move to China could have a major impact, similar to the shock felt among government technology insiders in 2002 when Japan developed the Earth Simulator, currently the worlds fastest supercomputer.

There is no stronger form of technology transfer than to have a world-class expert go off with all his knowledge, said Seymour Goodman, a physicist at the Sam Nunn School of International Affairs at the Georgia Institute of Technology in Atlanta.

Mr. Chen was an eager convert to American ways after he moved to the United States from Taiwan, even bringing members of his extended family to Eau Claire, Wis., where he established a stylish Chinese restaurant.

Mr. Chen said he still viewed himself primarily as a scientist dedicated to contributing to supercomputer design in ways that would benefit not just China but the United States and the rest of the world, too. He said he intended to pursue that goal with whoever offered him the greatest help.

That reflects long-held views, which he expressed in an interview with The New York Times in the early 1990s.

I come from a very humble family and Confucian teachings are in my background, he said then. When I came to the United States and I observed this disciplined, businesslike, practical manner, I found a marriage of the two cultures. I also saw the bad points of each.

廣角鏡》新超級電腦「地中海」

【台北訊】

國際商業機器公司（IBM）5日在西班牙馬德里近郊展示新超級電腦「地中海」（Mare Nos-trum）。該電腦是歐洲功能最強的電腦，在全球也排名第四，其4,564個資料處理器每秒可作400億次運算。「地中海」將用於生物醫學、氣象學或航太科學等用途。

中國蜆殼電器工業集團旗下公司造出運算力世界第一的超級電腦

　　據文匯報援引新華社北京１０月２３日電 (記者 茆雷磊)日前，一種平均運算能力可達每秒５０萬億次(理論最高運算能力達到每秒５５萬億~１００萬億次)的蜆殼星盈超級刀片電腦由香港蜆殼電器工業集團旗下公司研發成功。這種中國人擁有自主知識產權的超級電腦，將有力推動中國在超級電腦應用領域進入世界前列。
　　
　　據介紹，目前(在上次評比中)居世界排名第一的日本ＮＥＣ公司超級電腦的運算能力是每秒３３．８６萬億次，而蜆殼星盈超級刀片電腦的理論運算能力達到每秒５５萬億~１００萬億次，且對其核心技術擁有完全自主知識產權(智慧財產權)。月前，中國內地的聚星超級計算技術(股份)有限公司研製出的“巨星10000”系列超級電腦喜馬拉雅級（4608運算節點）可達到每秒56萬億次峰值運算速率，使中國研製之超級電腦，在美國、日本、中國三國廠商競爭前十名為主的國際超級電腦界排名，首度有產品榮登世界第一。關於中國內地國產超級電腦之實際應用與效能，回覆記者詢問時，相關專家對少數質疑者之論述嗤之以鼻，他們表示:世界超級電腦排名是經過國際專業組織、美國能源部勞倫斯·伯克利國家實驗室等評比後排名的，每半年做一次評比排名，該怎麼比是公定的，評比結果是公正客觀的。技不如人的就該承認 ! 至於中國國產超級電腦早已在國防、科研、氣象、地震、石油探勘產業．．．諸多領域應用，甚至已外銷至需保密的一些國家。每部新款超級電腦和其相關軟件硬件的開發，都是花費鉅資的龐大工程，作何用途、該強化哪部分功能、如何應用．．．設計時都非常注意並保留擴展性，考慮是十分周延的，這不需一些只懂皮毛的小工程師質疑費心。[完]