This is not the actual machine. It is for illustration only 🙂
Software Applications Insight
February 01, 08
Calculate this – up close to the UK’s newest supercomputer
Few understand or have ever seen a supercomputer. But they do more than play chess these days.
By John E. Dunn, Techworld
They call it HECToR and it’s the latest and greatest of the UK’s supercomputers, a breed of machines that have evolved from their distant ancestors in the mainframe world of 1960’s cleanrooms to become one of the most important phenomena of modern computing.
Installed in a non-descript building in a wooded facility south of Edinburgh, it is run as open-access computing serviced by the Edinburgh Parallel Computing Centre (EPPC), a wing of the University of Edinburgh. Made up of a series of wardrobe-like Cray XT4 towers that sit beside one another in rows, HECToR (or High-End Computing Terascale Resource, to use its longer and less cuddly name), its creators will try to convince visitors that it is as beautiful as its £113 million ($220 million) project price tag would imply.
Come face to face with it for the first time, and what that hits you first is not its looks but its noise – a loud, steady boom of rushing air – the consequence of the beast’s immense thirst for cooling. Then you are swamped by the warm, dry air. It is imposing in an alien sort of way, like a massive fist that is no longer attached to a real body, but which continues to flex. Around it stand a small team of technicians in labcoats, who fuss over it like gardeners tending to a morbid rose.
Beyond the eerie charisma of a calculating furnace, there’s remarkably little to say about HECToR as a physical object. It’s a bunch of cabinets packed with nests of 2.8GHz AMD Opteron microprocessors (11,328 in total), strung together with fancy interconnects at the rear of each tower, and cooled like crazy to stop the whole thing melting.
Scheduled to be replaced in two years, its matter-of-fact design hints comically at its obsolescence. One day they’ll unplug HECToR’s cabinets, wheel them out of the room, and replace with something that looks exactly the same but which has around four times as much processing power. Then they’ll repeat this exercise at roughly two-year intervals from now until the ability to resolve the world through digital muscle hits some kind of law of diminishing returns. Will that happen one day? Nobody can say.
It’s HECToR’s vital figures that make its case persuasive. Four times the rating of its predecessor, it can manage up to 63 billion calculations per second, equivalent its makers say, to every human being on earth doing 10,000 calculations each, over the same second. According to the respected supercomputing league table run by Top500.org, this makes it the 17th most powerful such system on earth, impressive if you consider that a number ahead of it on the list are systems run by the US military and not as open to the civilian scientific community as is HECToR.
Then there’s the electricity bill for all this, a staggering £8.2 million ($16.4 million) a year to keep it lit up, roughly a quarter of which is just the cooling.
Here is the full story.
63 billion?!
64 billion thanks to all for this website blog!
It’s over 9000!!!????
Hi, talking about powerfull computers i remembers a little calculation i did some years ago about the game of chess.
Imagine you have the most powerfull computer possible…now how do you know which is the fastes computer possible ever in the universe?
Lets say its a computer with a CPU the size of the universe (imagine all the universe occupied by atoms size by size with no space in between them), in which each atom computes a chess move in the time the light takes to travel the lenght of an atom (i imagined this because this is as fast as the information could get out of the atom).
Now i would like to know how long do you think this “computer” would take to make the first move in a chess game if it had to be absolutly certain that that move lead to victory (assuming that is possible with the white pieces) ?
I really did make these calculations and will give the answer later.
Wrong picture!
It shows an IBM BlueGene while the text babbles something about a Cray XT4.
But they do more than play chess these days
They don’t play chess at all, they can’t. How to efficiently implement a chess engine on a distributed memory computer is still an issue of ongoing research.
Note that that is probably a british billion (10^12) which is 1000 times larger than a U.S. Billion (10^9).
Brad Hoehne
Well, answering my own question..:), about 100 times the age of the Universe…!!!
There may be some way to simplify the calculations and no be necessary to compute every possible move, but anyway i think we can be sure there will NEVER be anything (human, computer, biological ou artificial) that can play perfect chess..which is quite good news and to me adds to the mistery of the game.
(Just a note, to say if this is so with such a simple thing as chess we may very well forget ever beeing able to predict the weather or the behaviour of any real complex system…)
To all of the computer comments in here, Good try.
A new breed of computers are comng that will revolutionize not only chess by mankind as a whole.
Quantum Computers.
Google it.
Get educated.
Learn.
I’m not quite sure why this story appears in this blog, especially when it has the wrong picture heading it.
Yes: “63 million” = 63.10^12 … my laptop does 3.10^9 so we’re talking about 21k of those.
There is more than one successful chess engine based on such a ‘distributed memory’ machine, and HYDRA is not the first.
Hydra isn’t a true chess computer.
It uses FPGA’s (Field Programmable Gate Arrays” integrated chips to do statistical walks and then pruning of the many paths or “ply” that involve potential chess moves. Each FPGA has been tailored to do only chess calculations with a “hardwired” program running on the chip.
A supercomputer would use the power of high-end CPU’s, that are very different from FPGA’s, and the ability to share large amounts of data.
An FPGA will have better performance because all communication takes place on the chip and memory bus.
As networks, CPU’s, and memory get faster; FPGA’s may meet their match in Supercomputers.