Japan Planning Exascale Computer For 2020 38
Nerval's Lobster writes "Japan has thrown its hat into the ring for exascale computing, reported the country's newspapers. The goal: achieve one exaFLOPS of performance by 2020. Japan's finance ministry has agreed to begin work next fiscal year on a supercomputer with a performance capability 100 times that of the K computer, a 10-petaFLOPS computer that debuted as the most powerful supercomputer in the world in 2011. The midterm report for the new supercomputer was concluded Thursday, the Asahi Shimbun business daily reported. The Japan Times was slightly more conservative, reporting that the Education, Culture, Sports, Science and Technology Ministry will seek funding to design the new machine in its fiscal 2014 budget request — implying that the project has not necessarily been approved. The science ministry is hoping to keep the cost of the new supercomputer below the ¥110 billion mark ($1.08 billion) that was required to develop the K computer, the paper reported. (Slashdot couldn't find any evidence that the project had been approved on the ministry Webpage, although the K computer was mentioned several times in a discussion of public-private partnerships.)"
Re: (Score:2)
you mean like the complex being built by the NSA in the Utah desert. good luck finding stats on that if you do look forward to a visit by the black helicopters and SUV's.
priorities... (Score:5, Interesting)
we could build several of these for the price of a single B2 bomber.
wish we would spend our money on something like this instead.
Re: (Score:1)
Re: (Score:2)
Yeah but the B2 won't be obsolete by the time it's built. :P
That didn't stop the F-22 project, did it?
Re: priorities... (Score:1)
Re: priorities... (Score:4, Interesting)
Re: (Score:2)
The Defense Industry has sent men to the moon in the 60s, built the internet, GPS, and super computers.
These companies don't only work for the Defense Department and they don't only build bombers.
Re: (Score:1)
The "defense industry" and "DARPA" are not necessarily the same. Alas, enjoy your corporatism...
Re: (Score:2)
damn, you're right. and think of how far we could push the state of the art of nuclear weapons design with those machines.
Brain (Score:1)
Re: (Score:2)
The top systems today are approximately at the same capacity as a human brain.
Brain neurons perform an operation that's similar to a dot product [wikipedia.org]. Their operation can be simulated by a weight for each dendrite that's multiplied by that dendrite's input.
In rough order of magnitude, a human brain has a hundred billion neurons, or 1e11 in standard computer language notation. Each neuron has an average of one thousand inputs, 1e3, and performs a hundred operations per second. That is 1e11 * 1e3 * 1e2 = 1e16 flop
Re: (Score:1)
About damn time (Score:3, Funny)
Re: (Score:2)
Bitcoin (Score:1)
Meanwhile, the Bitcoin network has already broken the equivalent of the exaFLOP barrier. Of course you can't coordinate this computing power in the same way, but it's interesting to note.
1996 teraflop 2006 petaflop on Linpack (Score:3)
Electricity bill (Score:3)
The main challenge of exascale computing is energy efficiency. It's going to cost 100 million dollars per year in electricity alone.
...and MTBF. (Score:2)
Re: (Score:2)
What good would a exa-scale supercomputer be, if you couldn not run a full-system job on it for even one hour?
It would be one hour more worth than current Japanese Fifth Generation Computer Systems.
If they build robots, might as well... (Score:1)
What are they going to use it for? (Score:2)
Are there enough heavy-computing tasks that will keep this computer occupied? Is there a shortage of computing power currently?