EVIDENCE FOR THE OPENING OF THE HALL OF RECORDS
ON DECEMBER 21, 2012 AT 10:18:13 PM CAIRO TIME

---

The following is a copy of an email circulated to various individuals with interest in the Cosmogenesis of 2012. If the Ambilac analysis discussed proves to be correct, then the idea of Maya Cosmogenesis 2012 has to be expanded to Cosmogenesis 2012, without distinction of region, hemisphere, latitude, or time. If the Ambilac analysis is not materially accurate, the same expansion must inevitably occur in spite of its inaccuracies.Subj: Dec. 21, 2012 22:18:13, Maya First Fire Ceremony and Resurrection of Osiris
Date: 12/7/99 9:00:47 PM Pacific Standard Time
From: Siloamnet
To: ambilac@pangea.ca
Gentlemen,
I find the following comment at your Ambilac web news page quite fascinating (http://www.pangea.ca/~ambilac/news/newsmain.html).
"The date of alignment as laid out on the plateau occurs on December 21, 2012 at almost precisely 2200 hours, 18 minutes, and approximately 13 seconds. "

I have done some work on interpretation of the information in Maya Cosmogenesis 2012, which might be of interest to you. The essays and charts are available at http://www.siloam.net/jenkins/.

I am adding a third appendix which includes star charts drawn for Mexico City and Giza at the precise time you have provided above. At Mexico City, the zenith meridian is directly on the Pleiades. This location may not be the right location, nor the right time. But, the coincidence sure looks like a "First Fire Ceremony" marker in heavens.

When I took the same sighting at Giza I came up with a remarkable piece of information. The zenith meridian at Giza runs through Jupiter at the Hyades in Taurus. The metaphor for this alignment is that the kingdom (Jupiter) will be restored to Egypt (Taurus) at that precise moment. Thus, Osiris, the Bull of Egypt, will return from the dead at 22:18:13 on December 21, 2012. If these calculations can be backed up, you have fulfilled the ancient prophecy. It will also prove that the Hall of Records is the stars. Remember one simple fact. Everything we are and everything we can know, is within the stars. That was the fundamental synoptic meaning of the Giza complex.

These alignments are too perfect to be ignored. Can you provide evidence that supports the logic which led you to the December 21, 2012, 22:18:13 time?

Thanks,

Rush Allen
www.siloam.net

---

THE STATEMENT

Here are the star charts for December 21, 2012 22:18:13 at Mexico City.


Here are the star charts for December 21, 2012 22:18:13 at Giza.


One point is clear in these star charts. The meridian of the caiman's tail of Quetzalcoatl, and the crocodile's tail of Tauret is located at the time indicated by the Ambilac study. Mexico City is at the lower back foot of Perseus, and Giza is at the upper front foot of Perseus. The locations show two different local star times, 03:46 for Mexico City and 04:26 for Giza. The difference results from International Time Zones. Clearly, the Giza pyramids were not designed to include the modern time zones. The most likely coordination would have been with local stellar time. The implication is quite clear, the 13 Baktun date for the end of the Age of the Fifth sun was known at the time of the construction of the Giza pyramid complex. The ritual of the First Fire ceremony in Mesoamerica tells us that the local star time represents the moment when a man crosses the cosmic sea and ascends into the "heavens above." A more ritualistically pure location for commemorating the birth of the new precessional cycle is not possible.
All of this information is preliminary. Anyone who has ventured into these correspondences understands fully the meaning of the "Tricksters in Xibalba," and the usurping brother, Seth, in Egypt. All we can say for sure at the present, is that the stars and the modern analytical procedures have come together in a remarkable correspondence. So, before we go the way of Osiris and Hanahpu, we should look for Seven Macaw and his cohorts, One Death and Seven Death. Once they have been tricked into disclosing their faces, we can win the current round of the cosmic ball game, and join the heavens in declaring the dawn of the New Platonic Year. That was the essential message in the legends of the great pyramid builders, all around the world. All they ask is that we honor them for telling us where and when to look for the new beginning.

---

FOLLOW UP ON AMBILAC INFORMATION

===========================
Subj: Response
Date: 12/8/99 9:02:37 AM PST
From: ambilac@escape.ca (Ambilac)
To: Siloamnet@aol.com
Rush
Thank you for mail.Please address any further mail to me at
ambilac@escape.ca

More understanding than people are ready for,How far would you like to
go???
Jim|

===========================
Subj: Re: Response
Date: 12/8/99 9:39:28 AM PST
From: Siloamnet
To: ambilac@escape.ca
CC: Siloamnet

Jim,
The site linked to Ambilac has been set up at Maya-Giza Ambilac Link (http://www.siloam.net/jenkins/ambilac.html).
Take the time to read the essay "Why the Stars Really Matter," linked to this site.

Also, how do I get the "proof" that the December 12, 2012 22:18:13 time is not just a construct of the creative imagination of your efforts? You did not provide me with a clue to the answer in the question I asked in my email.

These alignments are too perfect to be ignored. Can you provide evidence that supports the logic which led you to the December 21, 2012, 22:18:13 time?

Rush

===========================
Subj: Re: ResponseDate: 12/8/99 10:00:41 AM PST
From: ambilac@escape.ca (Ambilac)
To: Siloamnet@aol.com

File: STEP 18.dwg (252629 bytes)
DL Time (21600 bps): <3 minutes
Rush
What do you make of this DWG.
Jim

===========================
Subj: Re:Response
Date: 12/8/99 10:20:15 AM PST
From: ambilac@escape.ca (Ambilac)
To: Siloamnet@aol.com (Rush)
Rush,
Here are a few sites that you may wish to view prior to getting into
the rest. It took a long time to get to this juncture, and now we are
preparing to give the hard physics.

http://www.freeyellow.com/members7/howardmj
http://cob.250.dn.net/members/panspermia/panspermia.html

Jim

===========================
Subj: Re: Response
Date: 12/9/99 10:31:02 AM PST
From: Siloamnet
To: ambilac@escape.ca
CC: Siloamnet

In a message dated 12/8/99 10:00:41 AM Pacific Standard Time, ambilac@escape.ca writes:

<< Subj: Rush
What do you make of this DWG.
Jim
>>

Jim,

I see a person who has learned how to draw lines using Autocad.

But, the darker side of the DWG is that it represents a hoax.
I asked for information that could show why Ambilac chose December 21, 2012 22:18:13 as a precise moment for the opening of the Hall of Records. What I have received is a clear indication that Ambilac is a hoax.

The date and time you have chosen is based upon an esoteric desire, and a little knowledge about astrology. The pyramid construction site is irrelevant to the choice. That does not mean that you are wrong, just that you cannot back up your assertions with information that can be shown to be ancient.

Thanks, but no thanks. The ancients knew what they were doing, and it was not the smoke and mirrors of technical expertise used to baffle the uninitiated.

I will post your idea to my web site. Maybe some of my associates can help me through this quandary of light.

Rush

===========================
Subj: Re: Response
Date: 12/9/99 12:04:07 PM PST
From: ambilac@escape.ca (Ambilac)
To: Siloamnet@aol.com
Rush
YOU must do as your SPIRIT wills you to do.
- - -
YOU look but see very little,I wish you a fruitful journey....MY path is
set (sorry that it does not meld well with your schedule....)
ALL events will UNFOLD as they are supposed to.
Peace throughout your JOURNEY to DISCOVERY
JAMES MICHAEL WILKIE

---

NOW THE HARD PHYSICS

As I mentioned above, any endeavor to communicate with others, needs to be aware of the potential tricksters. This should not be taken as a slander against James Michael Wilkie. He is absolutely correct when he says, "YOU must do as your SPIRIT wills you to do." The tricksters are the coincidences that occur in the communication. Unless the "Hard Physics" that Ambilac is promising is indeed repeatable by others, we must take the Ambilac information regarding the date December 21, 2012 at 22:18:13 as the moment aligning with the Hall of Records as self inspired, or fall out of a complex of misapplied algorithms.
This does not mean Wilkie is wrong. The "real" celestial conditions accurately align with the event and the location of the Hall of Records, as he suggests. The star charts can be checked out by using any astronomical planetarium program. My charts are taken from three planetarium programs; The Sky IV, Sky Globe, and Redshift. The modern "scientific method" is the objective application and verification of hypothesis such that any pursuer can and will come up with the same information. As to the meaning of any information, that is purely subjective. Adding meaning to the method is the "sacred science" of the ancients, if the meaning desired is cosmic truth, rather than self truth.
That is the "trickster." When we view information, its meaning will be modified by the position of the viewer, materially, physically, mentally and spiritually. This is the "hard physics" of the Heisenberg Principle of Uncertainty being applied to the subjective world of mind and soul. Before the Popol Vuh presents the story of the death of One Hanahpu and Seven Hanahpu, and the birth of their sons Hanahpu and Xbalanque, it presents the battle against Seven Macaw by the Hero Twins, Hanahpu and Xbalanque. This adds emphasis to the Seven Macaw story. The emphasis acts as a warning that things are not always as they seem. After the battle was won by the Hero Twins, Hanahpu held up the body of Seven Macaw for the next generation to see. The adversary of the twins was made an eternal guiding light, at the Big and Little Dippers.
The mother of the Hero Twins, Blood Moon, told the story of the death of their father, and how she was impregnated by One Hanahpu's words from the gourd that had once been his head. In other words, truth can be passed on in ways that the rational mind could never imagine. In this case, the truth of their fathers' deaths guided Hanahpu and Seven Hanahpu to leave a reminder of the challenges they personally overcame in the place where the sacrificers in the Ball Court played the eternal game. Twice, we are told in the Popol Vuh that ancestors have gone "our way" before us. We are told twice in order to impress upon us the danger and the need for caution. Dedicated ancestors gave their own physical sacrifice in the Ball Court, so that their descendants would be able to go farther than they had gone. This is the "JOURNEY to DISCOVERY" of JAMES MICHAEL WILKIE stretched into eternity. Whether he is one of the Hero Twins, or Seven Macaw depends upon the mental and spiritual position of the traveler. Ambilac tells a fascinating story about archaeology with a good dose of fiction, esprit, and science. If his goal is to entertain, and the browsers in his world want to be entertained, then the reality he presents is as good as any other reality, for "YOU must do as your SPIRIT wills you to do."
At Siloam.Net, we have a different goal. Presently, our goal is established way off the path of the modern herd. It has the specific objective of giving the dead a place to tell their story. Thus, we cannot accept the undeclared means by which Ambilac has "discovered" ancient truths. Ambilac leaves no echoes which could guide us through the Ball Court. Remember, the ancient truths are not time sensitive. Only, ancient lives were time sensitive. The Popol Vuh is a clear expression of ancient truths. The Maya medium of scriptural metaphor carries the ancient truth. That truth says that ancestors will strive to better the lives of descendants. It is not for altruistic reasons, but for a pure selfish reason of the love of self; the first great cosmic truth. In my own "JOURNEY to DISCOVERY," I am fascinated that it is possible to hear the ancients speak through the stars and through their scriptures. This journey does not serve the lives of the ancestors, but it does provide a means for their souls to remain among the living. That is the ultimate goal of life; to achieve an eternal presence among the living.
The presentation of 22:18:13 on December 21, 2012 as an ancient record, was part of the developing journey at Ambilac. That journey does not focus on the wisdom of the ancients, it focuses on entertainment of the living. This desire to entertain is self born, as a reincarnated spirit. Certainly the ancients felt the desire to entertain. But, most important, as children we are awestruck by quality entertainers. In fact, the fundamental reason for using myth to keep the ancient truths alive is because it works. Myths are remembered. Science is forgotten. If this were not true, then we would not be looking for the secrets of the ancient science. Our ancestors fully understood that a good story is only good for as long as it lasts. For a story to last, it must catch the attention of the listener. It must be simple. It must be profound mystery. And it must promise great reward to those who find the secret Hall of Records.
Ambilac carries on the myth that the Hall of Records is under the paws of the Great Sphinx. This was a famous prophecy statement made by Edgar Cayce. This "seer" saw visions which carried truth. The mystery is how did he do that. The answer is quite simple. He believed in the intuition and the eternal nature of cosmic spirits. He rode the "Chariot of the Gods." Belief is the great chariot that carries eternal stories. But, given that the information transfers through intuition and spiritual perception, that does not mean that all such information is interpreted as intended. Ambilac ties the Hall of Records to the intuitive revelations which John Major Jenkins presented in Maya Cosmogenesis 2012. Cayce and Jenkins are not ancient sources.
First, the date December 21, 2012 has been well established for some time, and John Major Jenkins's book adds "authority" to the date. As for the time, we need look no farther than Jupiter. The fact that Jupiter aligns with the time 22:18:13 on December 21, 2012 could easily have been determined without going through the geometrical gyrations that Ambilac has supposedly gone through. The sources for the information could all be New Age intuitive metaphysics. Again, I need to make it clear that the question is not whether Wilkie has found the proper information. The question is whether it was written at the paws of the Great Sphinx in the layout of the Giza plateau.
Lets look at the ancient method in greater detail.
Here is information which can be retrieved from any astrology program, without celestial accuracy.

The following chart is a Tropical Zodiac chart which put the 1st of Aries
at the vernal equinox, which is approaching Aquarius.
Jupiter  sits precisely at the zenith position in Gemini .
The time is accurate, but the placement in the stars is considerably in error.
Without the proper placement in the stars, the ancient perspective will be distorted,
even though the actual timing can be replicated based upon planetary cycles.
Our ancestors used the background stars to create navigational myths.
They used these myths to navigate their physical and spiritual souls.
Tropical astrology uses the solar system to navigate the rational soul.
The cosmic materiality contains the planetary materiality, but not vice versa.

The planets are left in the same positions, but the heavens are rotated to
coincide with the "real" cosmic presence in the following chart.
Jupiter  sits precisely at the zenith position in Taurus .
In the cosmically correct presentation, Jupiter is in Taurus, rather than Gemini.
In this way, the Bull of Heaven, which to Egypt was living Osiris,
accepts the second eye of the king planet. This happens when the cosmic celestial cycle
begins it next revolution. Thus, Osiris is presented when the "Sun begins to Rise."
Ra is headed for the sun boat, Argo Navis, and enlightenment will bring in the day.
This message can be directly read in the asterisms of the cosmos,
but is entirely hidden in rationalizations of tropical astrology.

In its supposed position at 8 degrees 43 minutes in Gemini, the planet Jupiter gives a reading very similar to the gnosis expressed by Jim Wilkie. In fact, one would almost be inclined to suggest that the nature of Jupiter is the spirit of the Ambilac publications and their quest. So, who chose the time of 22:18:13, Wilkie by analysis, or Jupiter by cosmic divine ordination?
Tropical astrology adopted it rules during the days when Babylonian/Chaldean astrologers and Zoroastrian Magi calculated the heavens. The fundamental technology was once a "real" connection to the cosmos. Now it is a "true" connection to the cosmos. The truth is rational psychological truth, and tropical astrology is a Sol Invictus rationalization, which kept the old cosmic rules but denied the supreme nature of the cosmos. Because of the complexity of actually looking at the heavens to see where the solar system resides, the Sol Invictus conquest just denied the stars their voice. Like any divination system, the Cosmic Divine has a hand in it. So it is with Wilkie's method. They both believe that "wisdom by insight and understanding is a very free spirit."
Freedom is good. Alexander the Great attempted to break the strangle hold of the Asiatic astrologers, by wiping them off the face of the earth. The result he almost achieved was the wiping of his name from the Hall of Records. The Asiatics established the cult of Mithras as a deification of the Persian spirit of Alexander. The Egyptians established the Ptolemaic dynasty of God-Kings with Alexander as the principle savior and Son of Amun. The Book of Revelation describes the final battle at the "end times," when that great city of Babylon met its end. However, Revelation indicates that it would take two millennia to complete the purification, before the Sun would rise again. When the sun begins to rise, enlightenment comes with it in the form of spiritual intuition. This is the fundamental change which the earth is undergoing as the new millennium dawns. Wilkie has found a nitch to feed the hungry masses the intuitive spirit they desire in the guise of science they can accept. His intuition is bolstered by the goddesses of unintentional intelligent design. Intuition is the passive feminine process of creation which has provided "all" truth. But, when the gyrations at Ambilac show the complex rationalizations of the pyramid plateau design, they are not presenting "intentional intelligent design." If the truth comes through in Ambilac's complex algorithms, it is because Wilkie has direct contact with the goddesses through is powers of intuition. The Ambilac algorithms found what was being sought, and what was intended, but not by the method intended by the designers. This is a common path to truth, but it is the Path of Seven Macaw.
The quest at Siloam.net is bound by a material and spiritual bondage which requires that the freedom of the analyst be confined to the analysis procedures, and not to the messages being read. In other words, "listen while others speak." The Siloam.net objective is to obtain evidence of intentional intelligent design. By intelligent is meant that the design communicates a message of ancient and timeless truth. By intentional is meant the message must be expressed in such form that chance can be ruled out in the meaning perceived, and the meaning was intentionally put into the form discovered by the analysis process. In other words, the ancient builders of the Giza complex were as the gods and the resulting pyramid complex is a human form of teleology, e.g. the Bible. When the analysis defines a desired result, the "listen while others speak" process is violated, and Heisenberg's Principle of Uncertainty becomes most relevant. Then psychic energy going to the message from the receiver of the message, makes the meaning of the message uncertain. Precisely analogous to atomic speed and placement analyses from which Heisenberg's principle is derived. Communication is a two way street. If we talk, we cannot listen, without modifying the meaningful intent of others who are speaking.
Wilkie's presentation is his form of teleology, as was astrology after the end of the Age of Aries. The truths he presents are as timeless as astrology. But, the truths were "probably" not established by the human pyramid builders in the form Wilkie conjures and intuits. They were established by the forces of nature and by the method of analysis. His method of analysis substantially modifies the perception and introduces uncertainty as to the intentional intelligent design. This is a form of teleology which cannot be separated from a Supreme Being's edict, for the intelligence is living in synch with the edict. Synchronisity does not convince any accept those in synchronous formation.
God may speak directly to an individual, but whatever the individual perceives cannot be brought out to others, except as an expression of a memory. The synchronous formation is broken by the telling of the tale. This is also the form of the great eternal truths which are secured in the "Hall of Records." Because of this, the greatest stories ever told are synchronized with the stars. In this way, the message, the messenger, and the receiver can be synchronized without sharing the same moment in time. Like any science, it is magic to the uninitiated. To the initiated it is just common sense. Time is just the position of the keys on the piano, the stick on the drum, the slide of the bow on a violin. When properly synchronized, time is no longer relevant. The harmony of the cosmic sphere knows not time, for its rhythm is locked to the cycles of the heavens. The ancients perceived this eternal truth, and wrote their music to the drum beat of the stars.
The technique employed by Wilkie, and metaphysics in general, bypasses the bondage of the material world to space, or the place called time. The truth is that intuition is the only way to acquire information, even when the symbols are found in dictionaries, because the dictionary only provides associations. Intuition provides the inspiration of a communication as a cosmic spirit. The information must pass through the sensory facilities of the body and the perception processes of the mind. The total power behind these facilities and processes is practically infinite. That is why intuition leads to "judgments" based upon faith and desire. The learned man sits in a cave protected from the past by material substance, and perceiving the world to come on a "JOURNEY to DISCOVERY." The ultimate discovery is the "last judgment."
When intuitive ingredients are added to the mixture of external archaeological substance, such as the positions of stones, it becomes difficult to separate the ancient message from the living perception because of the Heisenberg Uncertainty Principle. This principle employs tricksters like the arrogant enemy, Seven Macaw, and the caring mother, Blood Moon, working on the harmony of the subconscious mind. When we are influenced by the bright and noisy bird of Seven Macaw, we tend to see what we presently want to see. When we are influenced by a mother who cares for the past and the future we look to join the past and future in the present. As Seven Macaw, we communicate within ourselves and not with the external world in which we are fortunate to live. By creating the great monuments, the ancients kept themselves on our minds. They are in the feet made partly of iron and partly of miry clay.
That form of eternal life is open to all who can create a great mystery and tell a great story. Wilkie is a master at mixing many ingredients into an intuitively plausible account of what the ancients have said. The authors of the Maya Popol Vuh, the Egyptian Chapters of Coming Into Day, the Bible, the Koran, the Book of Mormon, and the Rig Veda, to name a few, have all taken the ride in that vehicle of inspiration.
The intuition that is associated with a new year, a new century, and new millennium, and now a new Platonic cycle, suggests that a great change is in the cosmic works. The change which will occur, whether we desire or perceive it to be happening, is that the cycle will renew itself. The change which is clearly written in the Hall of Records is that the ancient truths will be reborn on Friday, December 21, 2012 at approximately 10:18:13 pm local Cairo time, when Osiris rises from the grave. All we have to do is come to the realization that we are living within the Hall of Records. When the book cradled in the arms of the man with a feathered headdress sitting on a throne of water in a material cave is opened, the Hall of Records will be within each and ever soul that accepts its truth. Then the eternal flame will burst forth from that cave and change the man who cradles the book. As the man changes, so changes the earth. We occupy the ball court, today, and some of us will win the game, while others will lose their heads. But, one thing that will never change is that "JOURNEY to DISCOVERY" in the HALL OF RECORDS.

UFO Sighting in Texas? Does Google Street View of Jacksonville, Texas Sh...

World News - UFO filmed by news station in Denver

This Video Explains it all! Nibiru crossing!!!

Wikileaks : NASA Confirms Planet X Is Heading For Earth

Telescope image of the planet Nibiru (Amazing)

NIBIRU CONFIRMED 100% (May 2012) MUST SEE!!!

NASA & Nibiru & 2012

This Video Explains it all! Nibiru crossing!!!

Leaked From NASA: Nibiru's Projected Path 2012

December 21, 2012 - Two Suns in the Sky

Russian News Report NIBIRU Exists (It"s not Comet Elenin)

INSIDER SPEAKS OUT ABOUT NIBIRU, PLANET X AND ELENIN

Planet X Nibiru Do you Want to Hear Insider Tell His Story About Watchin...

Mobitel FAN TALKS - Twenty20, Sri Lanka v Zimbabwe at Hambantota

Olympic Flame handover ceremony: London 2012 receives the Olympic Flame

The history of supercomputers

Have you ever wondered why a supercomputer is called a supercomputer? Is it the number of processors or the amount of RAM? Must a supercomputer occupy a certain amount of space, or consume a specific amount of power?

The first supercomputer, the Control Data Corporation (CDC) 6600, only had a single CPU. Released in 1964, the CDC 6600 was actually fairly small — about the size of four filing cabinets. It cost $8 million — around $60 million in today’s money — and operated at up to 40MHz, squeezing out a peak performance of 3 million floating point operations per second (flops).

In comparison, the CDC 6600 was up to 10 times faster than the fastest computer at the time, the $13-million ($91m today!), 2000-square-foot-occupying IBM 7030 Stretch — thus earning the title of supercomputer. At this point, Intel was still seven years away from releasing the 740KHz 4004 CPU. (For a bit of fun, definitely read the original 1960 IBM 7030 press release.)

The CDC 6600 was super for other reasons, too. It was cooled with Freon that circulated in pipes around the four cabinets, which was then heat exchanged with a chilled external water supply (you can see some pipework in the bottom right corner of the image above). While there was only one CPU (which in those days was constructed from multiple circuit boards, not a single chip!) the CDC 6600 had 10 Peripheral Processors, each of which was dedicated to managing I/O and keeping the CPU’s queue full. The CPU itself contained 10 parallel functional units, each of which were dedicated to different tasks; floating point add, floating point divide, boolean logic, etc. The architecture was superscalar, in other words (though this word didn’t exist at the time).

The CPU had 60-bit word length and 60-bit registers, but a very small instruction set, because it only dealt with information that had been pre-processed by the Peripheral Processors. It is this simplicity that allowed the CDC 6600 CPU to be clocked so high. By today’s standards, we would call the CDC 6600 the first RISC system.

The CDC 6600, incidentally, was designed by Seymour Cray — a name that

  

Cray X-MP

It’s important to note that, at this stage, an entire supercomputer was still being referred to as a single CPU. The Cray X-MP, released in 1982, had support for up to four CPUs, but housed inside the same Cray 1 chassis. The Cray X-MP CPUs were very similar to the Cray 1, but with a clockspeed bump from 80 to 105MHz and a more-than-doubling of memory bandwidth, each of the X-MP CPUs pushed up to 200 megaflops. For $15 million ($32 million today), you could get your hands on a grand total of 800 megaflops.

By the end of the Cray X-MP’s run it could support up to 16 million 64-bit words of memory — in SRAM! — which is equivalent to around 128MB of today’s RAM. It’s also worth noting that none of the costs mentioned so far include permanent storage — just the computer itself. The Cray X-MP, for example, supported up to 32 disk storage units, each about the size of a filing cabinet (pictured above) and capable of storing 1.2 gigabytes. Each unit cost $270,000 each in today’s money — about $225k per gig — but with an impressive transfer rate of around 10MB/sec, they were probably worth it.

Cray 2

By now you’re probably a bit bored of Cray computers — but the fact is, the company dominated supercomputing from its inception in the ’70s through until the early ’90s. In 1985, the Cray 2 was released. The technology used was fairly similar to the Cray 1 and Cray X-MP — ICs packed together on logic boards — and again it had a similar horseshoe-shaped chassis.

To boost performance, though, the logic boards were crammed incredibly tightly (pictured below), meaning air cooling and Freon heat exchanging was no good — instead, the the entire computer was submersed in Fluorinert. In the picture above, the device at the back is a Fluorinert “waterfall” radiator. (There are some more awesome photos in the original Cray 2 brochure [PDF].)

With increased performance (and up to 8 CPUs), Cray Research also had to overcome a memory bottleneck. Basically, the Cray 2 used “foreground” processors to load data from main memory to local memory (similar to a cache but not quite) via a very fast gigabit-per-second bus, and then pass instructions off to “background” processors which would actually perform computation. In today’s nomenclature, foreground processors would be similar to modern CPU load/store units. The peak performance of the Cray 2 was 1.9 gigaflops — about twice the Cray X-MP, and fast enough to retain the title of world’s fastest supercomputer until 1990.

The Cray 2 is notable for being the first supercomputer to run “mainstream” software, thanks to UniCOS, a Unix System V derivative with some BSD features. Until this point, Cray supercomputers had only really been used by US governmental agencies like the DoE and DoD (for nuclear modeling — what else?), but the Cray 2 found a home in many universities and corporations.

Here come the Japanese

After some 20 years of American dominance, the early ’90s would see the emergence of a new king of supercomputing: the Japanese. These computers, such as the NEC SX-3 (pictured below), Fujitsu Numerical Wind Tunnel, and Hitachi SR2201, used very similar architectures to Cray — i.e. highly parallel arrays of vector processors attached to fast memory — and all respectively became the fastest supers in the world. The SR2201 (pictured above — check out the self-adulating “H” chassis!), released in 1996, had 2048 processors and a peak performance of 600 gigaflops — by comparison, a modern Sandy Bridge Core i5 or i7 CPU can perform around 100-200 gigaflops.

During this period there was a shift away from a single shared bus to massive parallelism, where 2D and 3D networks (such as Cray’s Torus interconnect) connected together hundreds of CPUs. This was the origin of MIMD— multiple instruction, multiple data — which eventually led to multi-core CPUs.

Meanwhile, Seymour Cray had broken away from Cray Research to form Cray Computer Corporation (CCC) to build the Cray 3, the first computer built with gallium arsenide chips. The project failed, and then CCC went bankrupt during the production of Cray 4. As you’re probably aware, though, Cray Research most definitely lives on — but more on that later.

But what about Intel?

We’re now up to the mid-’90s, and yet Intel — the king of microprocessors since the ’70s — hasn’t been mentioned once. The main reason for this is that supercomputers and PCs are generally at odds with each other: where supers want as much processing power as possible, PCs have lots of cost and heat constraints. For the most part, it just didn’t make sense to use Intel chips in early supercomputers.

Throughout history, Intel has occasionally tried to launch chips based on a non-x86 architecture, usually without success. In 1989 it released the i860, a 32- and 64-bit RISC chip designed for use in large computers. The i860 would become the basis for the Intel Paragon, a supercomputer that supported up to 4,000 processors in a 2D MIMD topology. Paragon was a commercial failure, but it led to the creation of ASCI Red in 1996 (pictured above), which was the first supercomputer made from off-the-shelf CPUs — Pentium Pros, and then Pentium II Xeons — and other readily-available commercial components.

ASCI Red, with over 6,000 200MHz Pentium Pros and a cost of $46 million ($67 million today), was the first supercomputer to break the 1 teraflop barrier. Later upgraded to 9,298 Pentium II Xeons, ASCI Red reached 3.1 teraflops. It was the fastest supercomputer in the world for four years, and also the first supercomputer installation to use more than 1 megawatt of power. It was only decommissioned in 2006, after 10 years of use by the Sandia National Laboratories.

Everyman supercomputing

Once supercomputers could be built with off-the-shelf components, it was only a matter of time until everyone started building supercomputers. Beowulf clusters — networks with any number of commodity PCs, generally running Linux — quickly emerged, and Linux soon replaced Unix as the supercomputing OS of choice.

The commoditization of supercomputers (and compute clusters) almost certainly played a key role in computer animated films like Toy Story, and the increasing use of CGI in cinema and TV throughout the ’90s.
Next page: Petascale

Petascale

While continued improvements to CPUs obviously helped supercomputers break new records, for the most part high-performance computing (HPC) in the 2000s mostly focused on squeezing more and more CPUs into a single system. This involved the development of ever-more-complex interconnects, and reducing power usage (and thus heat production).

Japan retook the crown from the US ASCI Red and ASCI White in 2002 with the 35-teraflops NEC Earth Simulator (which cost $900 million!), but then in 2004 IBM released Blue Gene/L, the first of a series of supercomputers that would blow the doors off the competition until 2008. The first version of Blue Gene/L, located at Lawrence Livermore National Laboratory, had 16,000 compute nodes (each with two CPUs) and was capable of 70 teraflops — but the final iteration in 2007 had more than 100,000 compute nodes and peak performance of 600 teraflops. The exact price of the project is unknown, but it’s in the hundreds-of-millions department.

Blue Gene/L was exceptional for two main reasons: Instead of fast, power-hungry chips, it used low-power RISC PowerPC cores — and, except for RAM, the compute nodes were entirely integrated into SoCs (system-on-a-chip). The image above shows the incredible density of a 2U Blue Gene/L rack — and each heatsink is a CPU, and you’ll notice that there are no fans or water cooling blocks.

Blue Gene/L would lead the pack until it was succeeded by the $130-million IBM Roadrunner, a 20,000-CPU PowerPC/AMD Opteron hybrid that was the first computer to break the 1-petaflop barrier.

Don’t forget the Chinese

It took them a while, but in 2010 China eventually topped the supercomputing charts (TheTop500) with the 2.5-petaflops, $88 million Tianhe-1A. Tianhe-1A is notable for being one of the few heterogeneous supercomputers in operation — it houses 14,336 Intel Xeon X5670 CPUs and 7,168 Nvidia Tesla GPUs — apparently saving lots of power in the process.

More importantly, though, China recently unveiled Sunway, a 1-petaflops supercomputer built entirely out of homegrown ShenWei CPUs. China has repeatedly stated that it wants to lessen its reliance on Western high-technology, and Sunway is a very important step in that direction. Russia has also stated that it would like to build its own homegrown supercomputers, but so far it lacks China’s manufacturing prowess.

The return of Cray, and the Japanese

The current undisputed champion of the high-performance computing world is Fujitsu’s K, housed at the RIKEN institute in Japan, which clocks in at 10 petaflops — some four times faster than Tianhe-1A. K does away with the low-power approach pioneered by Blue Gene and simply throws 88,128 8-core SPARC64 processors into the mix. Each CPU has 16GB of local RAM, for a total of 1,377 terabytes of memory. K draws almost 10 megawatts of power — about the same as 10,000 suburban homes — and the whole thing (some 864 cabinets!) is, understandably, water cooled. At 100 billion Yen ($1.25 billion), K is the most expensive supercomputer ever built, too.

Looking forward, the next target is exaflops — 1,000 petaflops. Realistically, we should hit 100 petaflops in the next few years, and exaflops a few years after that (2018-2020). The USA’s fastest supercomputer, the 1.7-petaflops Cray Jaguar at Oak Ridge National Laboratory, is currently being upgraded to become the 20-petaflops Cray Titan. Titan will be built with Cray XK6 blades, which marry AMD Opteron CPUs and Nvidia Kepler GPUs up to a theoretical peak of 35 petaflops.

Meanwhile, DARPA, recognizing that current silicon technology might not even be capable of exaflops, has summoned researchers to reinvent computing. IBM, on the other hand, is building an exascale supercomputer to process the exabytes of astronomical data produced by the world’s largest telescope, the Square Kilometre Array. The telescope goes online in 2024, which will hopefully give IBM enough time to work out how to multiply the performance of current computers by more than 100.

So there you have it: From 3 megaflops to 10 petaflops in 48 years. The world’s fastest supercomputer is 3.3 billion times faster than the first.

supercomputer

TOP500 SUPERCOMPUTERS IN THE WORLD June 2011 (1-100)

Rank	Site	Computer/Year Vendor	Cores	Rmax	Rpeak	Power
1	RIKEN Advanced Institute for Computational Science (AICS) Japan	K computer, SPARC64 VIIIfx 2.0GHz, Tofu interconnect / 2011 Fujitsu	548352	8162.00	8773.63	9898.56
2	National Supercomputing Center in Tianjin China	Tianhe-1A - NUDT TH MPP, X5670 2.93Ghz 6C, NVIDIA GPU, FT-1000 8C / 2010 NUDT	186368	2566.00	4701.00	4040.00
3	DOE/SC/Oak Ridge National Laboratory United States	Jaguar - Cray XT5-HE Opteron 6-core 2.6 GHz / 2009 Cray Inc.	224162	1759.00	2331.00	6950.60
4	National Supercomputing Centre in Shenzhen (NSCS) China	Nebulae - Dawning TC3600 Blade, Intel X5650, NVidia Tesla C2050 GPU / 2010 Dawning	120640	1271.00	2984.30	2580.00
5	GSIC Center, Tokyo Institute of Technology Japan	TSUBAME 2.0 - HP ProLiant SL390s G7 Xeon 6C X5670, Nvidia GPU, Linux/Windows / 2010 NEC/HP	73278	1192.00	2287.63	1398.61
6	DOE/NNSA/LANL/SNL United States	Cielo - Cray XE6 8-core 2.4 GHz / 2011 Cray Inc.	142272	1110.00	1365.81	3980.00
7	NASA/Ames Research Center/NAS United States	Pleiades - SGI Altix ICE 8200EX/8400EX, Xeon HT QC 3.0/Xeon 5570/5670 2.93 Ghz, Infiniband / 2011 SGI	111104	1088.00	1315.33	4102.00
8	DOE/SC/LBNL/NERSC United States	Hopper - Cray XE6 12-core 2.1 GHz / 2010 Cray Inc.	153408	1054.00	1288.63	2910.00
9	Commissariat a l'Energie Atomique (CEA) France	Tera-100 - Bull bullx super-node S6010/S6030 / 2010 Bull SA	138368	1050.00	1254.55	4590.00
10	DOE/NNSA/LANL United States	Roadrunner - BladeCenter QS22/LS21 Cluster, PowerXCell 8i 3.2 Ghz / Opteron DC 1.8 GHz, Voltaire Infiniband / 2009 IBM	122400	1042.00	1375.78	2345.50
11	National Institute for Computational Sciences/University of Tennessee United States	Kraken XT5 - Cray XT5-HE Opteron Six Core 2.6 GHz / 2011 Cray Inc.	112800	919.10	1173.00	3090.00
12	Forschungszentrum Juelich (FZJ) Germany	JUGENE - Blue Gene/P Solution / 2009 IBM	294912	825.50	1002.70	2268.00
13	Moscow State University - Research Computing Center Russia	Lomonosov - T-Platforms T-Blade2/1.1, Xeon X5570/X5670 2.93 GHz, Nvidia 2070 GPU, Infiniband QDR / 2011 T-Platforms	33072	674.11	1373.06
14	DOE/NNSA/LLNL United States	BlueGene/L - eServer Blue Gene Solution/ 2007 IBM	212992	478.20	596.38	2329.60
15	DOE/SC/Argonne National Laboratory United States	Intrepid - Blue Gene/P Solution / 2007 IBM	163840	458.61	557.06	1260.00
16	Sandia National Laboratories / National Renewable Energy Laboratory United States	Red Sky - Sun Blade x6275, Xeon X55xx 2.93 Ghz, Infiniband / 2010 Oracle	42440	433.50	497.40
17	Texas Advanced Computing Center/Univ. of Texas United States	Ranger - SunBlade x6420, Opteron QC 2.3 Ghz, Infiniband / 2008 Oracle	62976	433.20	579.38	2000.00
18	DOE/NNSA/LLNL United States	Dawn - Blue Gene/P Solution / 2009 IBM	147456	415.70	501.35	1134.00
19	Air Force Research Laboratory United States	Raptor - Cray XE6 8-core 2.4 GHz / 2010 Cray Inc.	42712	336.30	410.04
20	Korea Meteorological Administration Korea, South	Haeon - Cray XE6 12-core 2.1 GHz / 2010 Cray Inc.	45120	316.40	379.01
21	Korea Meteorological Administration Korea, South	Haedam - Cray XE6 12-core 2.1 GHz / 2010 Cray Inc.	45120	316.40	379.01
22	Universitaet Frankfurt Germany	LOEWE-CSC - Supermicro Cluster, QC Opteron 2.1 GHz, ATI Radeon GPU, Infiniband / 2011 Clustervision/Supermicro	16368	299.30	508.50
23	Government United States	Cray XE6 12-core 2.2 GHz / 2010 Cray Inc.	45504	295.50	400.44
24	University of Edinburgh United Kingdom	HECToR - Cray XE6 12-core 2.1 GHz / 2011 Cray Inc.	44376	279.64	372.76
25	Forschungszentrum Juelich (FZJ) Germany	JUROPA - Sun Constellation, NovaScale R422-E2, Intel Xeon X5570, 2.93 GHz, Sun M9/Mellanox QDR Infiniband/Partec Parastation / 2009 Bull SA	26304	274.80	308.28	1549.00
26	KISTI Supercomputing Center Korea, South	TachyonII - Sun Blade x6048, X6275, IB QDR M9 switch, Sun HPC stack Linux edition / 2009 Oracle	26232	274.80	307.44	1275.96
27	DOE/SC/LBNL/NERSC United States	Franklin - Cray XT4 QuadCore 2.3 GHz / 2008 Cray Inc.	38642	266.30	355.51	1150.00
28	Texas Advanced Computing Center/Univ. of Texas United States	Lonestar 4 - Dell PowerEdge M610 Cluster, Xeon 5680 3.3Ghz, Infiniband QDR / 2011 Dell	22656	251.80	301.78
29	Airbus France	HP POD - Cluster Platform 3000 BL260c G6, X5675 3.06 GHz, Infiniband / 2011 Hewlett-Packard	24192	243.90	296.11	643.00
30	Grand Equipement National de Calcul Intensif - Centre Informatique National de l'Enseignement Supérieur (GENCI-CINES) France	Jade - SGI Altix ICE 8200EX, Xeon E5472 3.0/X5560 2.8 GHz / 2010 SGI	23040	237.80	267.88	1064.00
31	KTH - Royal Institute of Technology Sweden	Lindgren - Cray XT6m 12-Core 2.1 GHz / 2011 Cray Inc.	36384	237.20	305.63	658.35
32	Universitaet Aachen/RWTH Germany	Bullx B500 Cluster, Xeon X56xx 3.06Ghz, QDR Infiniband / 2011 Bull SA	25448	219.84	270.54
33	Institute of Process Engineering, Chinese Academy of Sciences China	Mole-8.5 - Mole-8.5 Cluster Xeon L5520 2.26 Ghz, nVidia Tesla, Infiniband / 2010 IPE, Nvidia, Tyan	33120	207.30	1138.44
34	INPE (National Institute for Space Research) Brazil	Tupã - Cray XT6 12-core 2.1 GHz / 2010 Cray Inc.	30720	205.10	258.05
35	DOE/SC/Oak Ridge National Laboratory United States	Jaguar - Cray XT4 QuadCore 2.1 GHz / 2008 Cray Inc.	30976	205.00	260.20	1580.71
36	Sandia National Laboratories United States	Sandia/Cray Red Storm - Cray XT3/XT4 / 2009 Cray Inc.	38208	204.20	284.00	2506.00
37	NOAA/Oak Ridge National Laboratory United States	Gaea - Cray XT6-HE, Opteron 6100 12C 2.1GHz / 2010 Cray Inc.	30912	194.40	259.66	610.70
38	Japan Atomic Energy Agency (JAEA) Japan	BX900 Xeon X5570 2.93GHz , Infiniband QDR / 2009 Fujitsu	17072	191.40	200.08	831.23
39	King Abdullah University of Science and Technology Saudi Arabia	Shaheen - Blue Gene/P Solution / 2009 IBM	65536	190.90	222.82	504.00
40	Shanghai Supercomputer Center China	Magic Cube - Dawning 5000A, QC Opteron 1.9 Ghz, Infiniband, Windows HPC 2008 / 2008 Dawning	30720	180.60	233.47
41	Government France	Cluster Platform 3000 BL2x220, L54xx 2.5 Ghz, Infiniband / 2009 Hewlett-Packard	24704	179.63	247.04
42	Taiwan National Center for High-performance Computing Taiwan	ALPS - Acer AR585 F1 Cluster, Opteron 12C 2.2GHz, QDR infiniband / 2011 Acer Group	26244	177.10	231.86	800.00
43	EDF R&D France	Ivanhoe - iDataPlex, Xeon X56xx 6C 2.93 GHz, Infiniband / 2010 IBM	16320	168.80	191.27	510.00
44	Swiss Scientific Computing Center (CSCS) Switzerland	Monte Rosa - Cray XT5 SixCore 2.4 GHz / 2009 Cray Inc.	22032	168.70	211.51	713.00
45	SciNet/University of Toronto Canada	GPC - iDataPlex, Xeon E55xx QC 2.53 GHz, GigE / 2009 IBM	30240	168.60	306.03	869.40
46	Lawrence Livermore National Laboratory United States	Sierra - Dell Xanadu 3 Cluster, Xeon X5660 2.8 Ghz, QLogic InfiniBand QDR / 2010 Dell	21756	166.70	243.67
47	Government United States	Cray XT5 QC 2.4 GHz / 2009 Cray Inc.	20960	165.60	201.22
48	University of Tokyo/Institute for Solid State Physics Japan	SGI Altix ICE 8400EX Xeon X5570 4-core 2.93 GHz, Infiniband / 2010 SGI	15360	161.80	180.02	719.30
49	ERDC DSRC United States	Diamond - SGI Altix ICR 8200 Enh. LX, Xeon X5560 2.8Ghz / 2009 SGI	15360	160.20	172.03	774.50
50	IBM Poughkeepsie Benchmarking Center United States	Power 775, Power7 3.836 GHz / 2011 IBM	6912	159.60	212.12	423.12
51	ERDC DSRC United States	Garnet - Cray XE6 8-core 2.4 GHz / 2010 Cray Inc.	20176	153.00	193.69
52	University of Colorado United States	MRI - PowerEdge C6100 Cluster, Xeon X5660 2.8 Ghz, Infiniband / 2010 Dell	15648	152.20	175.26
53	Vestas Wind Systems A/S Denmark	iDataPlex DX360M3, Xeon 2.93, Infiniband/ 2011 IBM	14664	151.67	171.86	458.25
54	CINECA / SCS - SuperComputing Solution Italy	iDataPlex DX360M3, Xeon 2.4, nVidia GPU, Infiniband / 2011 IBM	3072	142.70	293.27	160.00
55	CLUMEQ - McGill University Canada	Guillimin - iDataPlex DX360M3, Xeon 2.66, Infiniband / 2010 IBM	14400	136.30	153.22	376.75
56	Vienna Scientific Cluster Austria	VSC-2 - Megware Saxonid 6100, Opteron 8C 2.2 GHz, Infiniband QDR / 2011 Megware	20700	135.60	185.01	430.00
57	New Mexico Computing Applications Center (NMCAC) United States	Encanto - SGI Altix ICE 8200, Xeon quad core 3.0 GHz / 2007 SGI	14336	133.20	172.03	861.63
58	Computational Research Laboratories, TATA SONS India	EKA - Cluster Platform 3000 BL460c, Xeon 53xx 3GHz, Infiniband / 2008 Hewlett-Packard	14384	132.80	172.61	786.00
59	Lawrence Livermore National Laboratory United States	Juno - Appro XtremeServer 1143H, Opteron QC 2.2Ghz, Infiniband / 2008 Appro International	18224	131.60	162.20
60	eni Italy	HP ProLiant SL390s G7 Xeon 6C X5650, Infiniband / 2011 Hewlett-Packard	15360	131.20	163.43
61	DOE/NNSA/LANL United States	Cerrillos - BladeCenter QS22/LS21 Cluster, PowerXCell 8i 3.2 Ghz / Opteron DC 1.8 GHz, Infiniband / 2009 IBM	14400	126.50	161.86	276.00
62	NOAA/ESRL/GSD United States	Jet - Raytheon/Aspen Cluster, Xeon X5560/X5650 2.8/2.66 Ghz, QDR Infinband / 2010 Raytheon/Aspen Systems	13732	126.50	148.12
63	University of Southern California United States	HPC - PowerEdge 1950/SunFire X2200/IBM dx340/dx360/HP SL160, Xeon/Opteron 2.3-2.67GHz, Myrinet 10G / 2011 Dell/Sun/IBM	17280	126.40	175.99
64	National Computational Infrastructure National Facility (NCI-NF) Australia	Vayu - Sun Blade x6048, Xeon X5570 2.93 Ghz, Infiniband QDR / 2010 Oracle	11936	126.40	139.89
65	University of Chicago United States	Cray XE6 12-core 2.1 GHz / 2010 Cray Inc.	17856	125.80	149.99
66	National Institute for Computational Sciences/University of Tennessee United States	Athena - Cray XT4 QuadCore 2.3 GHz / 2008 Cray Inc.	17956	125.13	165.20	888.82
67	Atomic Weapons Establishment United Kingdom	Blackthorn - Bullx B500 Cluster, Xeon X56xx 2.8Ghz, QDR Infiniband / 2010 Bull SA	12936	124.60	145.15
68	Japan Agency for Marine -Earth Science and Technology Japan	Earth Simulator - SX-9/E/1280M160 / 2009 NEC	1280	122.40	131.07
69	IDRIS France	Blue Gene/P Solution / 2008 IBM	40960	119.31	139.26	315.00
70	ECMWF United Kingdom	Power 575, p6 4.7 GHz, Infiniband / 2008 IBM	8320	115.90	156.42	1329.70
71	ECMWF United Kingdom	Power 575, p6 4.7 GHz, Infiniband / 2009 IBM	8320	115.90	156.42	1329.70
72	DKRZ - Deutsches Klimarechenzentrum Germany	Power 575, p6 4.7 GHz, Infiniband / 2008 IBM	8064	115.90	151.60	1288.69
73	JAXA Japan	Fujitsu FX1, Quadcore SPARC64 VII 2.52 GHz, Infiniband DDR / 2009 Fujitsu	12032	110.60	121.28	1020.50
74	US Army Research Laboratory (ARL) United States	SGI Altix ICE 8200 Enhanced LX, Xeon Nehalem quad core 2.8 GHz / 2009 SGI	10752	109.30	120.42	475.00
75	Commissariat a l'Energie Atomique (CEA)/CCRT France	GENCI-CCRT-Titane - BULL Novascale R422-E2 / 2010 Bull SA	11520	108.50	130.00	477.00
76	Joint Supercomputer Center Russia	MVS-100K - Cluster Platform 3000 BL460c/BL2x220, Xeon 54xx 3 Ghz, Infiniband / 2009 Hewlett-Packard	11680	107.45	140.16
77	HLRN at Universitaet Hannover / RRZN Germany	SGI Altix ICE 8200EX, Xeon QC E5472 3.0 GHz/X5570 2.93 GHz / 2009 SGI	10240	107.10	120.73
78	HLRN at ZIB/Konrad Zuse-Zentrum fuer Informationstechnik Germany	SGI Altix ICE 8200EX, Xeon QC E5472 3.0 GHz/X5570 2.93 GHz / 2009 SGI	10240	107.10	120.73
79	Total Exploration Production France	SGI Altix ICE 8200EX, Xeon quad core 3.0 GHz / 2008 SGI	10240	106.10	122.88	442.00
80	Lawrence Livermore National Laboratory United States	Muir - Dell Xanadu 3 Cluster, Xeon X5660 2.8 Ghz, QLogic InfiniBand QDR / 2010 Dell	15000	105.90	168.00
81	Cyfronet Poland	Zeus - Cluster Platform 3000 BL2x220, L56xx 2.26 Ghz, Infiniband / 2011 Hewlett-Packard	11694	104.77	124.42
82	Computer Network Information Center, Chinese Academy of Science China	DeepComp 7000, HS21/x3950 Cluster, Xeon QC HT 3 GHz/2.93 GHz, Infiniband / 2008 Lenovo	12216	102.80	145.97
83	Lawrence Livermore National Laboratory United States	Hera - Appro Xtreme-X3 Server - Quad Opteron Quad Core 2.3 GHz, Infiniband / 2009 Appro International	13552	102.20	127.20
84	Information Technology Center, The University of Tokyo Japan	T2K Open Supercomputer (Todai Combined Cluster) - Hitachi opteron QC 2.3 GHz Myrinet 10G / 2009 Hitachi	15104	101.74	138.96	831.50
85	Kurchatov Institute Moscow Russia	Cluster Platform 3000 BL2x220, E54xx 3.0 Ghz, Infiniband / 2010 Hewlett-Packard	10304	101.21	123.65
86	Lawrence Livermore National Laboratory United States	Edge - Appro GreenBlade Cluster Xeon X5660 2.8Ghz, nVIDIA M2050, Infiniband / 2010 Appro International	8240	100.50	239.87	745.00
87	South Ural State University Russia	SKIF Aurora - SKIF Aurora Platform - Intel Xeon X5680, Infiniband QDR / 2011 RSC SKIF	8832	100.40	117.00
88	Max-Planck-Gesellschaft MPI/IPP Germany	VIP - Power 575, p6 4.7 GHz, Infiniband / 2009 IBM	6848	98.42	128.74	1095.00
89	Institute of Physical and Chemical Res. (RIKEN) Japan	RIKEN Intergrated Cluster of Clusters, Xeon X5570 2.93GHz, Infiniband DDR / 2009 Fujitsu	9048	97.94	106.04
90	Government Sweden	Cluster Platform 3000 BL2x220, L56xx 2.26 Ghz, Infiniband / 2011 Hewlett-Packard	17280	97.50	156.21
91	DOE/SC/Pacific Northwest National Laboratory United States	Chinook - Cluster Platform 4000 DL185G5, Opteron QC 2.2 GHz, Infiniband DDR / 2008 Hewlett-Packard	18176	97.07	159.95
92	Naval Oceanographic Office - NAVO DSRC United States	Cray XT5 QC 2.4 GHz / 2011 Cray Inc.	12720	96.55	122.11	588.90
93	EDF R&D France	Frontier2 BG/L - Blue Gene/P Solution / 2008 IBM	32768	95.45	111.41	252.00
94	University of Edinburgh United Kingdom	HECToR - Cray XT4, 2.3 GHz / 2009 Cray Inc.	12288	95.08	113.05
95	IT Service Provider Germany	Cluster Platform 3000 BL2x220, E54xx 3.0 Ghz, Infiniband / 2009 Hewlett-Packard	10240	94.74	122.88
96	Clemson University United States	Palmetto - PowerEdge 1950/SunFire X2200/iDataPlex/IBM dx340 Intel 53xx/54xx 2.33Ghz, Opteron 2.3 Ghz, E5410 2.33GHz Myrinet 10G / 2011 Dell/Sun/IBM	12528	92.48	115.26
97	Tsinghua University China	Inspur TS10000 HPC Server, Xeon X56xx 2.93 Ghz, QDR Infiniband / 2011 Inspur	9216	92.42	107.30
98	IBM Thomas J. Watson Research Center United States	BGW - eServer Blue Gene Solution / 2005 IBM	40960	91.29	114.69	448.00
99	Idaho National Laboratory United States	Fission - Appro Xtreme-X3 Opteron 2.4GHz, Infiniband QDR / 2011 Appro International	12480	91.03	119.81	360.00
100	University of Alaska - Arctic Region Supercomputing Center United States	Cray XE6 8-core 2.3 GHz / 2010 Cray Inc.	11648	88.92	107.16