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.
Can anyone explain how this research and development benefits anyone at all? This is a waste of money that could go toward studying how to cure cancer, mitigate climate change, colonize Mars, or so many other things that are far more worthwhile than this. We don't need this new professor and taxpayer funds shouldn't go toward this. I know I'll be modded down to -1 for asking this important question, and I'll be in the receiving end of ad hominem logical fallacies. However, those are simply evidence that I'm right and my statements can't be refuted. Can anyone justify the value of this research and development? I am very confident that the answer is no.
...Gen. 'Buck' Turgidson
Thats the worst backronym I have ever heard.
http://michaelsmith.id.au
> Graph analytic processor (GAP)...
Well I think this could be the solution to massive social surveillance, imagine you can solve a huge graph of targets and they relationships.
“Just because you're paranoid doesn't mean they aren't after you.”
they're gone Mac 3Hat they think is and has instead
The problem we have currently is that we are focused on creating specific types of circuits. What we should be doing is working on dirt-cheap generic circuits that can reconfigure into anything you want aka neural network chips. The advantage of these is that you can have flaws in the fabrication process and make up for it by just making a shitload of identical neurons. You could even make up for having a low speed system by having an ungodly number of neurons in a single machine. This opens the door to using low fabrication resolution to build monstrously deep silicon chips with thousands of layers.
The future is massive amounts of generic circuitry.
Anons need not reply. Questions end with a question mark.
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.
Why exactly shouldn't this be available for anyone in the US to commercialize? Intel certainly doesn't need more IP fodder to further their monopoly abuses. If anything, their right to hold IP at all should have been voided long ago.
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.
From TFA:
"The four-and-a-half-year DARPA program will spend the first year with Intel and Qualcomm designing rival architectures, while Georgia Tech and PNNL design rival software tools. After the first year, one hardware design and one software design will be chosen. DARPA will provide the company with the winning hardware design with $50 million in funding, on the condition that the company kick in $50 million of its own. DARPA will also provide $7 million to the organization that provides the winning software design.
Meanwhile, Northrup will be given $11 million in non-matching funds to set up the Baltimore center to survey all of the Defense Department needs in graph analytics and make sure that the hardware and software builders meet those needs."
This is fairly common for DARPA - have an initial bake off phase with then pick a winner to go further. Developing new technologies is risky and expensive and I'd be willing to bet that if there are any cost overruns, the government isn't throwing in any more money. The hardware vendors probably see this as important technology to develop for the future no matter what and they're happy to get a bit of cost offset from the government with what are likely to be very few IP restrictions and a pretty modest 16 node (on a single board) deliverable.
Northrup makes out pretty well, too, for what seems to be a vaguely defined survey and needs oversight role.
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.
Oh BeauHD, are you sure it's not Northrop Grumman? Neither North Grumman nor Northrup Grumman seem to be real corporations...
I doubt it's possible unless they have a *very* large number of threads they cycle between so a mem issue is fulfilled when the issuing thread finally gets its turn again.
Even that doesn't make much sense. Memory access seems to be the core of most bottlenecks, am I supposed to believe it's gone now.
I'd like to be proven wrong.
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.
A 1000x rate is fake because it is not doing a comparison to another general purpose machine.
How do they think of how to build an inexistent "operating system" for this specific processor? Same question for inexistent compiler, assembler, linker, debugger, profiler, hex-editor, ...
I think that they will use "64-bit CP/M" because it's the most simple. And cross-compilers also.
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?
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.
Everyone knows that.
He's an American, therefore....
That is not very much for these companies. The product will not be a big seller, a small fab less player could probably do better.
This smells like an academic exercise that will lead to nothing.
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.
These chips would be perfect to analyse many to many relationships of its citizens in real time. Every gathering will be checked for threat analysis.
Might not want to invite your non-white non-christian friend to your next wedding... we saw how they deal with weddings in that leaked drone footage....