Slashdot Mirror
DARPA Funds Development of New Type of Processor (eetimes.com)
The Defense Advanced Research Project Agency (DARPA) is funding a completely new kind of non-von-Neumann processor called a HIVE -- Hierarchical Identify Verify Exploit. According to EE Times, the funding is to the tune of $80 million over four-and-a-half years, and Intel and Qualcomm are participating in the project, along with a national laboratory, a university and defense contractor North Grumman. From the report: Pacific Northwest National Laboratory (Richland, Washington) and Georgia Tech are involved in creating software tools for the processor while Northrup Grumman will build a Baltimore center that uncovers and transfers the Defense Departments graph analytic needs for the what is being called the world's first graph analytic processor (GAP). Graph analytic processors do not exist today, but they theoretically differ from CPUs and GPUs in key ways. First of all, they are optimized for processing sparse graph primitives. Because the items they process are sparsely located in global memory, they also involve a new memory architecture that can access randomly placed memory locations at ultra-high speeds (up to terabytes per second). Together, the new arithmetic-processing-unit (APU) optimized for graph analytics plus the new memory architecture chips are specified by DARPA to use 1,000-times less power than using today's supercomputers. The participants, especially Intel and Qualcomm, will also have the rights to commercialize the processor and memory architectures they invent to create a HIVE. The graph analytics processor is needed, according to DARPA, for Big Data problems, which typically involve many-to-many rather than many-to-one or one-to-one relationships for which today's processors are optimized. A military example, according to DARPA, might be the the first digital missives of a cyberattack.
Computers are machines that help us think. If we can think better, we can do all the rest of those things you are talking about much, much easier. I would say more and better computing power is the only thing that is going to elevate us out of the purely biological drive to expand until collapse.
bend like the reed
cure cancer, mitigate climate change
To be honest, this processor design might have applications for both.
Imagine a Beowulf cluster!
Thats the worst backronym I have ever heard.
http://michaelsmith.id.au
Imagine a Beowulf cluster!
Is there such a thing any more? I recently had access to a lot of second-hand low-end machines and thought it'd be fun to set up a cluster, but I couldn't find the software - it had vanished into a haze of different distros.
Amen. DARPA should instead focus on things that matter; such as studies on gender inequality, and the apparent inability of the English language to express any notion that is not perceived as racist and misogynistic by the media. The government should instead spend time identifying the race gender and sexual identity and occupation of everyone alive and focus on how they have been marginalized by evil racist trump supporters who luv Russia and want to destroy mother earth. This is how we should conduct science in the future.
Always remember that you are right and everyone who disagrees has been brainwashed.
Cancer cures, global warming, Mars colonization. All those are pushing computer simulations to their max today. A better processor that could truely "multitask" would be a huge leap in toolset capability for any of those fields.
They use big data algorithms for medical research. See "folding@home". There's a lot of data out there that needs to be processed, and processing more medical / chemistry data means trying out more combos and quicker / better results. A customized processor that does a specific type of task far faster than traditional processors is a great investment.
BTW: "the new arithmetic-processing-unit (APU) optimized for graph analytics plus the new memory architecture chips are specified by DARPA to use 1,000-times less power than using today's supercomputers."
A supercomputer designed to scale better for big data processing, that uses 1000 times less power than current supercomputers. Thus, it has 1000 times less cooling needs. Currently we're effectively using networked PCs scale up to fill data centers for our processing needs. A system designed with big data in mind will knock the socks off the current set ups and lead to much more efficient and scalable big data processing for ALL industries and research needs.
And the reason it needs government funding is because then it's an open platform that anyone can use, instead of locked down with patent lawsuits for decades. This way, it gets built by the best of the best from multiple companies and it's openly publishable technology. The free market gave you Comcast and Verizon, it's DARPA that gave us the internet in the first place.
High performance computing is important to national defense. In fact, most computer technology was developed for weapons systems and national defense. Short term profit driven corporate group-think precludes taking the necessary risks to develop new computer architectures that are orders of magnitude faster and more efficient. It is government funded research that often makes important advances possible.
BTW, I have mod points but think you have a fair question.
Now if you are going to question why we need to spend so much on weapons, we'll that would be a fair question...
Greed is the root of all evil.
Generic chips that can be programmed in to anything you want in the field. It's a huge industry, they get used in everything from your car to your TV, but they have limitations that means they are never going to be a be-all, end-all.
There's a place for processors, FPGAs and ASICs, usually all combined.
DARPA is an acronym for Defense Advanced Research Projects Agency. They spend our money on defense and weapons research.
I'm not saying your other priorities are unimportant, but you shouldn't expect DARPA to fund non defense related research.
Greed is the root of all evil.
There's distributions out there like ROCKS for rolling out the software side of clusters quickly.
On the minus side, they will create Skynet or something more insidious, with slimy humans in charge.
On the plus side, isn't this how you would make hardware ideal for a raytracer? Fixated on memory, a big heap of global memory (can't really dice the memory locality too much, rays have to go all over in the whole scene) with huge bandwiths flying everywhere, and you just want do zillions of intersections.
The "Graph Acceleration Processor" could operate on e.g. a sparse octree, to give a simple example?
I would like if someone more knowledgeable can give some thought or insight.
In the 90s we still thought we would have a flying car, but that may take the second place to real-time raytraced games! That's what we will play in the future. After the Nintendo that's as powerful as a Silicon Graphics..
An application-specific integrated circuit, or ASIC. Not a new type of CPU.
OK, I'm not making any judgments whatsoever about this new architecture, but...ANY radical change in our "accepted" mode of thinking cannot help but be a GoodThing(TM) - ultimately - IMO. $.02
This reminds me of the Content Addressable File Store that ICL developed some 50 years ago. OK: different implementation, but today a huge amount of RAM is affordable whereas CAFS needed to search for the data on disk.
Neural networks don't work for generic tasks. Try to sort a bank's records with a neural network, or try to use them to display a UI description.
And the reason it needs government funding is because then it's an open platform that anyone can use, instead of locked down with patent lawsuits for decades. This way, it gets built by the best of the best from multiple companies and it's openly publishable technology. The free market gave you Comcast and Verizon, it's DARPA that gave us the internet in the first place.
If only. Typically as part of the deal, DARPA contractors (like Intel and Qualcomm) are allowed to patent (and own the patents) used to commercialize the technology. That may or may not mean an open commercial platform, but it certainly doesn't mean they won't get to own patents on key parts of the technology to potentially keep competitors at a disadvantage.
I'm not saying your other priorities are unimportant
I think that the parent AC is actually implying that these other priorities are less important or, at least, heavily misused and systematically brought out of context. By using a more Slashdot-friendly reply: WHOOOSH!!
:)
DISCLAIMER: I am plainly sharing some properly-understanding help. I have no relationship whatsoever with this other AC and am not implying that I (dis)agree with anything of what is expressly or implicitly said in any of the previous posts.
DISCLAIMER TO THE DISCLAIMER: logically, I have some opinion about all this, but my point is that it is completely irrelevant here as far as my contribution is only meant to address what I think that is a real-intention-misinterpretation problem.
DISCLAIMER TO THE DISCLAIMER TO THE DISCLAIMER: I am not implying that people concerned about certain issues are usually misinterpretation-prone and require lots of unnecessary-for-any-properly-understanding-individual clarifications.
etc.
Custom Solvers 2.0 = Alvaro Carballo Garcia = varocarbas.
Wow, you aren't even trying to hide your ignorance.
Anons need not reply. Questions end with a question mark.
DARPA is an acronym for Defense Advanced Research Projects Agency. They spend our money on defense and weapons research.
And as a bonus, it sounds very close to DERPY.
Ezekiel 23:20
DARPA money funded the invention of the Internet. I'd argue that the Internet certainly helps the efforts of curing cancer, mitigating climate change, and colonizing Mars. Computers that do critical tasks 1000 time more efficiently would be a fundamental breakthrough that could help all these efforts and many more.
Greed is the root of all evil.
Please explain how a neural network would sort bank records. Or how to implement Excel using a neural network. Or ...
I'm appaled at all the "what's the use of this?" posts. When the principles behind lasers were discovered, they were regarded a physical curiosity with no real practical consequences. It's almost the definition of fundamental research that you can't immediately see the applications - else it's applied research. And DARPA's very mission is to fund research that currently borders on science fiction but one time may have practical consequences. They also played a big role in the development of what would eventually become the internet. With this HIVE project (horrible acronym BTW), they're even being quite conservative, as one can easily see a host of potential applications that are quite relevant to society.
"What's the use of this" is exactly the wrong question to ask when it comes to funding science/tech. Yeah, it's something populist politicians like to wave around, but in reality, fundamental research pays for itself as a driving force for future economic growth. There will be failed projects that get nowhere and are never heard of again (except in arguments to cut funding), but the success stories easily make up for them. To again cite a very conservative example that is a bit in the gray zone between "fundamental" and "applied": think of Xerox putting a bunch of smart people together at PARC and giving them an allowance to fool around with.
One could even argue that the generous funding with few questions asked that existed in a "distant" past has helped the US to be at the forefront of tech for decades.
Forget implementing Excel, you could run the damn original by creating an x86 processor in a neural network. You do realize that brains are neural networks, right?
Anons need not reply. Questions end with a question mark.
You do realize that our brains are really, really imperfect: forgetful and illogical?
Is this your way of admitting that you know jack shit about neural networks?
Anons need not reply. Questions end with a question mark.
Take a look at neo4j.com. When you organize graph-like data as a graph instead of the typical set of relational tables, you can vastly speed up certain kinds of queries, and thinking about the solution becomes much clearer.
This is generic technology with uses far outside military applications. My own needs are for event correlation, and finding the cause in amongst a lot of data telling you the effects of a systems outage.
Marry graph databases to a CPU that is specially tailored for this kind of work and you get a powerhouse.
Cloud providers such as AWS can then bring in these machines, virtualization them, and in a cost effective manner rent them out to everyday developers.
So what can YOU do with it?
Why would you compare to a general-purpose computer? This will be a special-purpose computer, the relevant comparison is to the performance of other architectures in the same problem domain.
In a similar vein, the operating system itself doesn't necessarily need to leverage the new architecture particularly well, except for the performance-critical subsystems such as memory management - and even that might be handled primarily by the client software. Heck, initially it might not even use an operating system at all - after all they're a convenience, not a necessity, though at least a thin "shim" layer seems likely. In fact, the thinner the better probably, as it's almost certainly going to take many years/decades to work out how to leverage the hardware as effectively as possible, and an operating system tends to obscure hardware realities.
It will likely be expensive though. Maybe that has something to do with the fact that they're planning for $100 million for the hardware design and $7M-$14M for the software?
And while it may well need massively overhauled compilers to effectively leverage, I suspect it won't need major changes in the rest of the tool chain. *Maybe* in the assembler, certainly not in a hex editor. After all it's not like any of those tools need to run on the new architecture - cross-platform compiling is pretty standard with novel architectures.
--- Most topics have many sides worth arguing, allow me to take one opposite you.
You think we should add an additional layer of abstraction and computation that slows things down and eats up more energy to arrive back at the exact same spot we already were (running x86 code)?
Why would you want to do that?
I never said you would, I said you could. Know the difference.
Anons need not reply. Questions end with a question mark.
This kind of weird name is given to pie-eyed future technology projects so that when the dust settles no-one really knows precisely what didn't pan out.
Because odds are, they're going to have to fund this again—with an inkling of clue & a vaguely comprehensible name—before this twinkle finally deposits a nugget, third time lucky.
Uhhhh, that was your response to how to sort bank records, that you "could" implement x86 on a neural network, which leads to a couple questions:
1 - If you only said "could" knowing that it's not really a good solution, why post it all?
2 - Given that you seem to agree that is not a good solution (e.g. not efficient), what is your answer to the poster that asked you about how you would sort bank records? (the implied full question of course is "how would you do it efficiently with NN compared to current computing methods?")
No, they're not. A brain is a neural network as much as a tree (plant) is a tree (data structure)
I say that with a bit of rhetorical fun, but neural networks aren't actually made from neurons. They don't get drunk and have sex (in no particular order). They don't have a chemical nature and unknown features not the computer "neurons" have DNA.
Back when I was in university for engineering, I had a professor tell us that there was nothing better than Von Neumann architecture so don't bother looking for it. One has to wonder what else university professors are wrong about.
I don't know how you think about our brains, but implementing an x86 in them is not a great idea. That's much better done in silicon, where the components are reliable, small and fast. The fastest signal in our CNS travels at about 20m/s.
There's a 0 missing, but you get my drift.
1 - If you only said "could" knowing that it's not really a good solution, why post it all?
To make a point about the flexibility of NNs, duh.
2 - Given that you seem to agree that is not a good solution (e.g. not efficient), what is your answer to the poster that asked you about how you would sort bank records?
Processors designed for NN chips will be faster and scale to new heights. Also, sorting bank records is actually something trained NNs would kick ass at.
Anons need not reply. Questions end with a question mark.
I don't know how you think about our brains, but implementing an x86 in them is not a great idea.
you're a step behind this fellow.
Anons need not reply. Questions end with a question mark.
There is no such thing as "1000-times less". One times less power would be zero. (If a processor used 1 Watt, then this would use a 1000 times less, as in -999 Watts?) And one thousandth of the original is NOT the same as a thousand times less.
You can have a thousand times more, but you can't have a thousand times less!
---
> To make a point about the flexibility of NNs, duh.
You don't seem to get that for a neural network there is no difference between memory and processing.
> sorting bank records is actually something trained NNs would kick ass at.
I really would like a demonstration of that. Input: a few million bank records. Output: the same bank records, ordered according to some criterion like SSN, bank account or credit.
But you're a troll, aren't you?