World's Most Powerful x86 Supercomputer Boots Up in Germany

Nerval's Lobster writes "Europe's most powerful supercomputer — and the fourth most powerful in the world — has been officially inaugurated. The SuperMUC, ranked fourth in the June TOP500 supercomputing listing, contains 147,456 cores using Intel Xeon 2.7-GHz, 8-core E5-2680 chips. IBM, which built the supercomputer, stated in a recent press release that the supercomputer actually includes more than 155,000 processor cores. It is located at the Leibniz-Rechenzentrum (Leibniz Supercomputing Centre) in Garching, Germany, near Munich. According to the TOP500 list, the SuperMUC is the world's most powerful X86-based supercomputer. The Department of Energy's 'Sequoia' supercomputer at the Lawrence Livermore National Laboratory in Livermore, Calif., the world's [overall] most powerful, relies on 16-core, 1.6-GHz POWER BQC chips."

Comments

DID SOMEONE SAY BBQ?

[Rinikusu]

My fatass almost got excited for a second.. a supercomputer fueled by BBQ... :(

Re:DID SOMEONE SAY BBQ?

[Megahard]

No, it just runs hot enough to also work as a BBQ.

Re:I need that...

[Anonymous Coward]

Or check tpyos.

Re:I need that...

[Qubit]

...so I can first post mote quickly!

let's fix you're spelling frist, then work on the spead of you're posting.

power to x86

[SlashDev]

powerful and x86 are oxymorons. Try the i860 architecture now THAT's a processor, it's ancient I know.

Re:power to x86

[Joce640k]

I'm pretty sure they'll be running them in x64 mode, not x86.

I'm sure modern Intel CPUs with multiple instruction dispatch and SSE for math instead of x87 will give the i860 a run for its money.

But yeah ... some of those old chips were cool (even if they didn't have a proper divide or sqrt instruction :-)

Re:power to x86

[rgbrenner]

wow.. you're right. The i860 had 1 whole core and ran at up to 50mhz.

Imagine if they built this supercomputer out of those. Instead of 155,000, it would only need 8,370,000.

Now THAT's a super computer.

On a serious note, wikipedia says:

On paper, performance was impressive for a single-chip solution; however, real-world performance was anything but. One problem, perhaps unrecognized at the time, was that runtime code paths are difficult to predict, meaning that it becomes exceedingly difficult to order instructions properly at compile time.

Sounds like an earlier version of Itanium

Re:power to x86

[0123456]

I worked with i860s years ago. They weren't bad for graphics, but the guys who had to do general-purpose work on the i860 workstations hated them.

Except the one who was promoted to i860 from the Clipper machine. I don't know why he always got the worst jobs.

Re:power to x86

[cheesybagel]

Modern RISC processors are not that simple anymore. It used to be that they had no multiply or divide instruction but all modern RISC processors have those. It also used to be that their memory addressing was simpler but several modern RISC processors like POWER have complex memory addressing schemes. So boh.

Power BBQ Chips

[j. andrew rogers]

I need to find myself some of these Power BBQ Chips mentioned in the summary. Fast and tangy without the downside of Cheetoh fingers.

the real question

[slashmydots]

But the real question is, can it run bitcoin mining software? See, you thought I was going to say Linux or Crysis, didn't you? lol.

P.S. most miners are run on Linux btw ;-)

Re:the real question

[jpapon]

Most REAL miners use dynamite, pickaxes, shovels, and heavy machinery.

Re:I need that...

[damn_registrars]

...so I can first post mote quickly!

let's fix you're spelling frist, then work on the spead of you're posting.

You head two many correctly sppeled wurds you must be a bot.

Slashdot Grab Bag

[Roachie]

1) Does it run Linux?
2) I for one, would like to welcome our new register constrained overlord.
3) Can you imagine a Beowulf cluster of these?
4) In Soviet Russia supercomputer run YOU!
5) There is no God, I reject your fairytales.

Re:Slashdot Grab Bag

[damien_kane]

1) Does it run Linux?

Yes, SUSE

2) I for one, would like to welcome our new register constrained overlord.

Then you had better get started on its AI routines

3) Can you imagine a Beowulf cluster of these?

Why yes, yes I can (and it would be huge, power hungry, and require it be run at the bottom of the ocean for heat-dissipation)
BTW, from TFA this system is cooled "by dumping water directly on the microprocessors", after which the warmed water is used to heat the rest of the building in winter

4) In Soviet Russia supercomputer run YOU!

Only if you get around to finishing Point 2

5) There is no God, I reject your fairytales.

You mean you won't buy them any more?
Damnit, what am I going to do with this gross of tails I tore off of faeries last week? Not cool, man...

What about CE?

[Impy the Impiuos Imp]

> actually includes more than 155,000 processor cores

Scientists and engineers toyed with putting Windows 8 on it, but Windows 8 with 150,000-200,000 core support was over $73 trillion.

Re:What about CE?

[PRMan]

And Vista was still too slow on it...

Re:Europe suddenly got bigger...

[rgbrenner]

You might want to read the article again. It says it is Europe's fastest supercomputer AND the worlds fastest x86 supercomputer.

It's #4 on the top500, and the other 3 are not x86 (POWER BQC for #1 and #2, and SPARC VIIIfx for #3).

I can hear the chants ...

[jxander]

We're number four!!
We're number four!!
We're number four!!

Re:I can hear the chants ...

[Kjella]

Looks like Hollywood has got prior art.

That Clock Speed Sucks

[barlevg]

I really hate how the focus these days is on more cores, not faster cores.

Not every task is trivially parallelizable, and even with those that are, the speedup you get from running on N cores is always going to be less than Nx.

I'd be much more impressed by a supercomputer running, say, 1/4 as many 4.0 GHz+ processors.

Also: if what you're going for is massively parallelizable tasks, x86 is so last century--GPGPUs are where it's at.

Re:That Clock Speed Sucks

[AReilly]

Limiting factor these days is how much power you can get in and out of the box. They will have optimized for that. And these processors probably do have GPUs on them.

Re:That Clock Speed Sucks

[slew]

I think we're going to be stuck in the same ghz range until we're past silicon.

That's what I remember being told, anyway...

Even when we get past "silicon", there are some fundamental issues that will likely constrain clock-speeds things until we solve them.

First, the design of small low power devices (e.g, switching transistors) is currently problematic. Minimum sized geometries tend to "leak" more power, and potential subsitutes for silicon that are faster also tend to have leakier transistors (like graphene). We can make the devices bigger to minimize this, but then they switch slower, and there is more distance to traverse between devices. This is problematic in that the perf per watt tradeoff isn't great if you are doubling the watts to get 50% more perf (as an example), sometimes it doesn't make sense to go so fast.

Second, we are reaching manufacturability limits. Today, one of the biggest problems with silicon is parametric yield loss. This is basically device-to-device variation of circuit parameters due to manufacturing variation. This requires quite a bit of over-engineering of margin which reduces the ability to use any of the intrinsic speed advances. We are now using nearly every trick in the book to get small devices that lay down stuff where you can count the dimensions of some features in atoms on your fingers and toes, so parametric yield loss due to + or - one atom dimension average change causing a 5-10% variation isn't likely to go way very soon.

Third, re-syncronization uncertainty is now a big problem and getting worse. If a re-synchronizer circuit (say one that harmonizes two sides of an asynchronous fifo across 2 clock domains running at the same nominal frequency) is designed so that it would only fail 1-in-a-million times, you could have a reasonable failure-rate by cascading a few of them. If you are running 10 or 100 times faster, that's not a scalable strategy. Nowdays, even the jitter from a phase-locked and delay-locked loops or from two slightly mismatched clock-trees on different parts of a chip can be several clock periods long so what used to be a fairly simple syncrhonization problem now would likely be 10-100 times harder if it was 10-100 times faster (jitter isn't improving as fast as the potential clock rate).

Of course if we stop using electrons in lattices for computational circuits (e.g., use photons in crystals), and developed new structured circuit realization technologies that allowed reducing some of the engineering margins required to yield devices, some of these limitations might be solved in different ways, but those types of advances are probably quite far off... I'm willing to wager, that we will start to leverage alternate computation technologies (e.g., like ubiquitous parallel operation, or even quantum) before we get there, so maybe going so fast won't seem as critical as it does today...

Re:Someone had to say it...

[cephus440]

I'm glad they didn't use Cyrix CPUs.

Re:Q: Why are we still on x86 and 64bit and not 12

[Jaywu]

The 16, 32, 64, 128-bit computing refers to the standard register size for integers and pointers in a processor. Specifically, a 32-bit computer can generally access 2^32 locations of memory, which is 4GB. A "true" 64-bit processor would be able to address 2^64 (18 quintrillian) bytes of memory. However, x86-64 only use 40 bytes for addressing, which will handle 1 TB of RAM. Additionally, doubling the data size makes every operation take significantly longer, so clock speeds have to suffer. Since very few applications actually need 64-bit or higher math functions, its more efficient to implement higher order stuff in software, and have a faster executing processor.

Re:Q: Why are we still on x86 and 64bit and not 12

[six]

Don't mix up addressing and computing.

The whole internet would fit in a 64 bit address space, there is really absolutely no need at all for more than 64 bit for addresses in CPUs, that's why x86_64 and other 64 bit archs are here to stay, and you'll probably never see "128 bit" processors at all.

On the other side, today's x86_64 CPUs are capable of 128 bit (SSE) and 256 bit (AVX) computing. The width of the compute units is also bound to increase for some time, with Intel already planning to go 1024 bit in the not-so-far future.

Re:what's it going to run?

[KingMotley]

Greece's deficit.

Well?

[StripedCow]

World's Most Powerful x86 Supercomputer Boots Up in Germany

So, how fast does it boot?