Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Prototype Motherboard Clusters Self-Coordinating Modules

timothy posted more than 4 years ago | from the your-mother's-so-modular-she-broke-up-with-herself dept.

Hardware Hacking 115

An anonymous reader writes "A group of hardware hackers has created a motherboard prototype that uses separate modules, each of which has its own processor, memory and storage. Each square cell in this design serves as a mini-motherboard and network node; the cells can allocate power and decide to accept or reject incoming transmissions and programs independently. Together, they form a networked cluster with significantly greater power than the individual modules. The design, called the Illuminato X Machina, is vastly different from the separate processor, memory and storage components that govern computers today."

cancel ×

115 comments

Rob Malda has a tiny weiner (-1, Troll)

Anonymous Coward | more than 4 years ago | (#29126443)

Rob Malda's dick looks like a shriveled up baby pickle.

Re:Rob Malda has a tiny weiner (-1, Troll)

Anonymous Coward | more than 4 years ago | (#29126627)

Then take it out of your mouth.

Re:Rob Malda has a tiny weiner (-1, Offtopic)

larry bagina (561269) | more than 4 years ago | (#29126639)

green and bumpy?

Re:Rob Malda has a tiny weiner (0, Offtopic)

spazdor (902907) | more than 4 years ago | (#29126825)

Oh, we know. We're Slashdot users.

But how would YOU know, AC? Unless you'd been through the Initiation ritual as one of us!

Re:Rob Malda has a tiny weiner (0)

Anonymous Coward | more than 4 years ago | (#29131351)

He went through blindfolded like all of us too. What he didn't realise is it wasn't Rob Malda's dick it was mine.

I.... I... (0, Insightful)

Anonymous Coward | more than 4 years ago | (#29126445)

don't understand.

Re:I.... I... (1)

ioshhdflwuegfh (1067182) | more than 4 years ago | (#29131877)

[I... I...] don't understad

From TFA:

"We are taking everything that goes into motherboard now and chopping it up," says David Ackley, associate professor of computer science at the University of New Mexico and one of the contributors to the project. "We have a CPU, RAM, data storage and serial ports for connectivity on every two square inches."

So? (1)

Darkness404 (1287218) | more than 4 years ago | (#29126513)

So how do you upgrade this? I would assume you would add more modules but that would increase the space of the computer and so tiny computers would be underpowered while you could get one the size of a large TV that would be lightning fast, but who wants a huge computer? Especially for a laptop or HTPC.

Re:So? (2, Insightful)

Fyre2012 (762907) | more than 4 years ago | (#29126577)

perhaps just replace old modules with new ones, following ye olde Moore's law cycle?

Re:So? (4, Informative)

TubeSteak (669689) | more than 4 years ago | (#29126629)

So how do you upgrade this? I would assume you would add more modules but that would increase the space of the computer and so tiny computers would be underpowered while you could get one the size of a large TV that would be lightning fast, but who wants a huge computer? Especially for a laptop or HTPC.

Define "tiny computers"
Cellphones have more processing power than the original room-sized super computers.
Heck, there are cellphones with more power than any desktop computer I owned during the 90's.

And define "huge computer"
Most of a mid-tower case is nothing but empty space
And since you can easily do audio/video processing in hardware,
there's no reason it wouldn't be perfectly fine for a HTPC.

Re:So? (0)

Anonymous Coward | more than 4 years ago | (#29127841)

My cell phone has very little computing power. In fact, since all its programs need to be digitally signed by a signature that I can't even get, it's not even Turing-complete.

Re:So? (0, Offtopic)

b4upoo (166390) | more than 4 years ago | (#29129217)

More power! More! I want more.I want to be God! But if I can be God I promise to be a very nice God. Just give me that new PC!

Re:So? (1)

Higaran (835598) | more than 4 years ago | (#29129443)

Which is why I don't see this as that good of an idea, I think that its more efficent to have the cpu/gpu, ram, bios, and the whole thing on a single chip. That is how chip design is going anyway isn't it. It makes more sense to me to get a whole motherboard inside a chip, then to make a krap load of mini motherboards.

Re:So? (1)

ioshhdflwuegfh (1067182) | more than 4 years ago | (#29131925)

Which is why I don't see this as that good of an idea, I think that its more efficent to have the cpu/gpu, ram, bios, and the whole thing on a single chip. That is how chip design is going anyway isn't it. It makes more sense to me to get a whole motherboard inside a chip, then to make a krap load of mini motherboards.

Well, just do s/chip/module/g and you have described their project.

Re:So? (1)

masshuu (1260516) | more than 4 years ago | (#29128169)

Well this is how i see it. If they develop these on the level of nano size(ie the whole board is the size of a current intel processor, or even smaller). then having a mass of these together, along with the right programing, you have a Neural network.

The nice thing about this, as compared to having a single processor simulating it, is that if 2 or 3 chips die, the rest of the system won't notice and can quickly ajust, just like if you lose a few brain cells.

Because of the ability for the nodes to recode themselves on the fly, if lets say a robot goes from walking to driving, instead of wasting space and keeping "walking code" in the nodes, it pulls the driving code off of an external device and creates a saved state of its walking code and the positions for each piece of code(IE: picture attaching a hard drive to your brain and offloading the memory of those frosty piss comments to it, to make room for all those xxx memories)

Re:So? (2, Interesting)

Bakkster (1529253) | more than 4 years ago | (#29131145)

Larger computers are already more powerful in general than the same generation of smaller computers.

Small, fast, and cheap: pick two.

Ooo...! (1)

Anachragnome (1008495) | more than 4 years ago | (#29126521)

Can you say "Multi-boxed Shamans"?

Well, (1)

mhajicek (1582795) | more than 4 years ago | (#29126543)

So much for the Neumann-Neumann dance.

Re:Well, (1)

Curate (783077) | more than 4 years ago | (#29126671)

So much for the Neumann-Neumann dance.
Another nerd who took his sister to the prom?

Re:Well, (0)

Anonymous Coward | more than 4 years ago | (#29126927)

I read that as "another nerd who took his sister to the porn".

Re:Well, (1)

promythyus (1519707) | more than 4 years ago | (#29130135)

Dear god, as did I... sudo rm -rf /brain

Transputers, anyone? (5, Informative)

PaulBu (473180) | more than 4 years ago | (#29126569)

Am I too old to remember them? And before that, there was Connection Machine...

Also (yes, I clicked on TFA! :) ), planar (in graph theory terms) interconnect topology would seem a bit too simplistic for anything resembling efficient routing...

Paul B.

Re:Transputers, anyone? (1)

mhajicek (1582795) | more than 4 years ago | (#29126585)

Maybe the next version will have six ports instead of four. Give them servos to extend or retract the ports and you have "living metal".

Re:Transputers, anyone? (5, Insightful)

Brietech (668850) | more than 4 years ago | (#29126633)

The connection machine was still SIMD, even though it did have 64k (1-bit!) processors. This is just like the transputer architecture though! There are a couple of *really* big problems with this: 1) none of their microcontrollers are individually capable of running a large modern program. They have a few kilobytes of code, and no large backing RAM. 2) How do you get to I/O devices? If you need shared access to devices, this just makes all the problems of a normal computer enormously worse. 3) What about communication latency (and bandwidth) between nodes? They're using serial communications between 72 MHz processors. We're probably talking several microseconds of latency, minimum, and low-bandwidth (just not enough pins, and not nearly fast enough links) communication between nodes. As fun as something like this would be to build and play around with, there are reasons architectures like the transputer died out. The penalty for going 'off-chip' is so large (and orders of magnitude larger nowadays than it was back then), and the links between chips suck so much, that a distributed architecture like this just can't compete with a screaming fast 3 GHz single-node (especially multi-core).

Stargate: Replicators..... (2, Funny)

jameskojiro (705701) | more than 4 years ago | (#29126661)

This is exactly how the replicators began.... Slow old 72Mhz processors and then you put enough of them together and the thing goes evil and start taking over the universe.....

Re:Stargate: Replicators..... (1)

Entropic Alchemist (1613649) | more than 4 years ago | (#29127333)

This is exactly how the replicators began.... Slow old 72Mhz processors and then you put enough of them together and the thing goes evil and start taking over the universe.....

I feel that I should say something about the Replicators not being evil as much as a virus is evil.

Re:Stargate: Replicators..... (2, Funny)

joaommp (685612) | more than 4 years ago | (#29127551)

Yeah, stand up for the bastards. Tiny tiny replicators that can't defend themselves.

Re:Stargate: Replicators..... (0)

Anonymous Coward | more than 4 years ago | (#29129577)

They're the evil virus.

Re:Transputers, anyone? (1)

PaulBu (473180) | more than 4 years ago | (#29126945)

My other thought was that having all those discrete components around relatively slow part would decrease bang for the buck appeal of this thing.

I'd start with something reasonably fast (but low power and with huge cache!) in the node core and surround it with a bunch of optical links (the more, the merrier), then start running fiber in interesting topologies... I do not think serial communication is inherently bad, but do agree that serial communication between slow nodes can be a real killer here.

Paul B.

Re:Transputers, anyone? (1)

gandhi_2 (1108023) | more than 4 years ago | (#29127933)

a serial killer?

Re:Transputers, anyone? (1)

destroyer661 (847607) | more than 4 years ago | (#29126961)

In a response to your post, I think you're right in saying 72 MHz processors fed to each other by serial connections is a bit preposterous versus the 3GHz chips we have powering nearly every computer these days. However, what if we start amping those chips up to 500-1000MHz per chip, and throw a better connection between them (I'm assuming something must be faster and easier than serial, I don't know speeds or electronics well enough to guess), more RAM/EPROM and voila!

This would have a much higher chance of competing with the chips we currently have and still have a pretty low production value methinks.

Anyone else with more knowledge care to comment?

Re:Transputers, anyone? (2, Insightful)

Brietech (668850) | more than 4 years ago | (#29127515)

Well, if you take that idea to the limit using modern technologies, you basically wind up with rockin' new Nehalem processors using Quickpath Interconnect (QPI) between them, with PCI Express (serial links) to peripherals. But that's huge, is incredibly power hungry, and is basically the opposite of this architecture. But let's think this over some more. To access L1 cache, you can do it in a single cycle. L2 might be 10-20 cycles, etc. Now going over PCIe, the fastest thing going besides QPI, has a latency of like 400-800 nS. Even on a lowly 1 GHz processor, that's like 800 clock cycles, so you might as well be watching grass grow while you try to do something that's not embarrasingly parallel. As soon as you pump up the clock rate more, and add large caches and DRAM and all that, then you have *huge* power problems, and you still have somewhat crappy performance. Large-scale multi-core basically *does* use this architecture, only it's all on one die. It also uses an interconnect that doesn't suck, and manages to be cache coherent, so you can actually use it. Each core has it's own cache though (which is larger than the RAM on these chips), and the clock is nearly 2 orders of magnitude higher. Like i said, this is fun for a microcontroller project, but the performance would be atrocious for anything except embarrasingly parallel problems (and even then it would suck using these microcontrollers).

Re:Transputers, anyone? (1)

aXis100 (690904) | more than 4 years ago | (#29127747)

Agreed, imagine bundle of these using 1.2GHz Intel Atom chips. Still very low power.

Re:Transputers, anyone? (0)

Anonymous Coward | more than 4 years ago | (#29127355)

This reminds me of grace Hopper's visual nanosecond aid - a ~foot long peace of wire. When it comes down to it, that's why multicore will always be better than distributed nodes.

Re:Transputers, anyone? (1)

HeLLFiRe1151 (743468) | more than 4 years ago | (#29127599)

What we really need to do is put this all on a single chip running at about 3 Ghz, oh wait never mind.

Re:Transputers, anyone? (1)

spazdor (902907) | more than 4 years ago | (#29129719)

The penalty for going 'off-chip' is so large and the links between chips suck so much, that a distributed architecture like this just can't compete with a screaming fast 3 GHz single-node

BUT: If this turns out to be a viable programming and networking paradigm, then we've also got a recipe for arbitrarily scalable cpus. For if it's so expensive to go off-chip, why can't we just print entire silicon wafers tiled with these things? And then stack them? The only real limit on processor density would be the power and cooling requirements.

For that to become the Better Technology, all we'd need is a a proof-of-concept that shows software can run efficiently on this kind of "flat" hardware.

Re:Transputers, anyone? (1, Redundant)

0123456 (636235) | more than 4 years ago | (#29126741)

That was my first thought, though perhaps they're doing something new. Seems one generation has to forget what the previous generation did before the next generation comes along to reinvent it...

Re:Transputers, anyone? (0)

Anonymous Coward | more than 4 years ago | (#29126807)

Yeah, I think it's really cute that they assume a two-dimensional array of chips interconnected with 0.1" inch dual row 16-pin headers will add up to anything worthwhile.

It's the same old hippie dream of "assemblage" computing that I have to put up with all day long from naive, incoming Master's students at my research lab.

People like this shouldn't even touch hardware until they have done the accompanying math and research, but it's a free country.

Re:Transputers, anyone? (1)

lennier (44736) | more than 4 years ago | (#29126823)

Yay Transputers!

Re:Transputers, anyone? (5, Informative)

dha (23395) | more than 4 years ago | (#29127695)

I'm part of the project that produced this board.

I am definitely, yes, old enough to remember the Transputer. And I hacked artificial life models on the MasPar in the early 90's, which had an architecture in some ways similar to the Connection Machine.

Although the IXM is indeed 'embarrassingly suitable' for assembly into planar grids, it certainly isn't restricted to that. With right angle headers, for example, it's easy to make shapes likes rings and cubes and so forth.

When the global computational geometry of a machine is fixed at design time, before the ultimate task is known, routing can easily become a major problem. And general routing is hard. Maybe too hard.

But part of exploring modular systems in the 'physical computation' space is trying to figure out ways to make the geometry of the particular computer you build better fit the behavior you're implementing, which can help ease the general purpose routing problem.

And if one really gets into a corner, well, ribbon cable is cheap.

Re:Transputers, anyone? (3, Interesting)

RoccamOccam (953524) | more than 4 years ago | (#29128181)

Exactly. I have a 256-processor system down in my basement, that I built in 1988-89. Composed of Size 1 (9.3 cm x 2.7 cm) TRAMs (TRAnsputer Modules), each node had a 25 MHz T805 and 4 MB RAM. Each transputer had four 20 Mbit/s bidirectional serial links. Starting with a single processor connected to the host PC, a downloaded program would follow the defined link topology to boot and program each processor in turn.

Hardware-wise, it looks like the system described in the article really only trumps the transputer by virtue of the reconfigurable power sub-system. The transputer was a fantastic bit of engineering.

Wow! Does it ... boot up? (1)

PaulBu (473180) | more than 4 years ago | (#29128393)

The largest one I've played with was one board with 8 or 16 TRAMs, it fit into what was the PC bus at the time, maybe as old as IDE...

By any chance, does the second part of your nickname refer to this particular interest of yours? :)

Paul B.

Re:Wow! Does it ... boot up? (1)

RoccamOccam (953524) | more than 4 years ago | (#29128721)

I haven't booted it in several years, as I no longer have a working PC-Transputer interface. The ones that I have rely on an AT-bus. I probably still have some of the old parallel-link interface chips, so I should try to build something for it.

By any chance, does the second part of your nickname refer to this particular interest of yours? :)

Absolutely!

Re:Wow! Does it ... boot up? (1)

PaulBu (473180) | more than 4 years ago | (#29129921)

By any chance, does the second part of your nickname refer to this particular interest of yours? :)

Absolutely!

Yeah, Hoare's CSPs, as a refreshing computational model when you actually have to deal with asynchronicity and speed of light being your limit, before the rest of the world caught up with it (though I was always pointing out that original Ethernet spec was truly relativistic technology, since min packet size was defined by max length and 'c'! :) ). It was fun attempting to simulate relativistic hardware in Lisp implementation of Occam.

Since then, moved to even more exotic physics/tech, but still fond of good abstractions!

me ? reply

Paul B.

Re:Wow! Does it ... boot up? (1)

kohaku (797652) | more than 4 years ago | (#29130477)

PaulBu <: reply

I always end up plugging this (I know a guy who works there), but if you didn't know about it, David May has a new outfit. [xmos.com] It's very much in the same vein as the Transputer, and it's still based on CSP. You may want to check it out!

Re:Transputers, anyone? (1)

clickclickdrone (964164) | more than 4 years ago | (#29130521)

Yep - that was my first thought too. A good idea that never really took off. heck, even Atari had their Transputer Workstations but they only got as far as universities as I remember. I did see one demoed at a UK computer show (PCW maybe?) running some Kodak software for image manipulation and the speed and quality of the images were amazing for the time.

Wow (4, Funny)

$RANDOMLUSER (804576) | more than 4 years ago | (#29126593)

Can you imagine a Beowulf cluster of...oh...wait...never mind.

Re:Wow (1)

Korin43 (881732) | more than 4 years ago | (#29127239)

But does it run Linux?

Re:Wow (0)

Anonymous Coward | more than 4 years ago | (#29129727)

I wonder how many of these it would take to run Vista?

Re:Wow (1)

Hurricane78 (562437) | more than 4 years ago | (#29128701)

I can. I present: The *vertical* connection. Now you can stuck them in all 3 dimensions, and make your cluser actually look like one.

Re:Wow (1)

middlemen (765373) | more than 4 years ago | (#29128709)

Mother Clusters...

Neat (2, Interesting)

HomelessInLaJolla (1026842) | more than 4 years ago | (#29126605)

Are they hiring people to write an OS for it? Eventually all of those nodes need to be able to talk to a video card, display something on a screen, talk to a network card and communicate with the network in a fashion that the general public will expect.

I wouldn't even do it for the money. Provide me with a suitable environment and I would do it just because it would be enjoyable. I cannot do it while sleeping on the street and eating peanut butter and jelly, though.

I am trying to figure out if it would be a sin to work on a project like that. If housing and support were dependent on me working on a project then it would be a sin. If someone would say,"We trust that what you do isn't 'evil', here's a place to stay and an allotment for meals and resources, here are the specs that we have now, and here's a whole room full of dry erase boards. Have at it."

Re:Neat (0)

Anonymous Coward | more than 4 years ago | (#29127023)

why is this man modded as a troll?

Re:Neat (0)

Anonymous Coward | more than 4 years ago | (#29127133)

probably as a result of the journal

Re:Neat (0)

Anonymous Coward | more than 4 years ago | (#29127173)

Because moderation isn't an exact science? I refer you to this nugget [despair.com] of joy.

Much love,
AC

Re:Neat (1)

Delwin (599872) | more than 4 years ago | (#29127169)

Supercomputer OS's have been doing it for a while.

Re:Neat (2, Interesting)

ZackSchil (560462) | more than 4 years ago | (#29127513)

I have mod points and I was going to re-mod this post as something other than Troll, but none of the options fit any better.

There should be mods like "+0 Weird" or "+0 Rambling coherently".

Re:Neat (0)

Anonymous Coward | more than 4 years ago | (#29130355)

"Underrated" seems a perfect fit.

Altho I agree, a "+0 Weird" (or maybe "+0.5", so that it's slightly positive) mod would be handy once in a while.

Re:Neat (1)

Mojo01010011 (1337759) | more than 4 years ago | (#29127529)

Mr. Homeless, what you've just said is one of the most insanely idiotic things I have ever heard. At no point in your rambling, incoherent response were you even close to anything that could be considered a rational thought. Everyone in this room is now dumber for having read it. I award you no points, and may God have mercy on your soul.

Re:Neat (0)

Anonymous Coward | more than 4 years ago | (#29128949)

Cut the guy a slack - the dude is homeless.

Re:Neat (1)

Anonymous Coward | more than 4 years ago | (#29129289)

Haha. Not quite.

He says he's been homeless for over three years. But has a publication as recent as last year [elsevier.com]

The reason why he deletes his journal entries is to cover up the numerous anonymous postings showing that he isn't homeless. Not to mention several people have called the library where he supposedly posts at to send him money: no one has heard of him.

MODS: Mod homelessinlajolla down. He's a well known troll here. Seems like every so often he'll go on a posting hiatus and a new round of mods come in not realizing he's a fake.

What's the bus on this? (1)

d3l33t (1106803) | more than 4 years ago | (#29126673)

Guarantee it comes short

Re:What's the bus on this? (3, Insightful)

commlinx (1068272) | more than 4 years ago | (#29126991)

I'd guess from the 14-pin connectors and the fact most smaller ARM microcontrollers can't do parallel data transfers under DMA they're using the SPI bus which may run at 72Mbps. Of course that would also mean the bus either needs to be shared for every device or operated in a token ring style with the associated propagation delays. I'd guess the latter because you'd be pushing to get 72MHz SPI data across a large number of devices due to the capacitance it would introduce to the transmission line.

All in all sounds like an interesting academic excercise but of no real-world importance. I expect they'll find all their power and cost savings will be eaten up by requiring hundreds of devices to compete with a single piece of silicon. A better commercial solution would be to put lots of ARM cores on single chips (or FPGAs for development) but then it would make sense to use a better bus arrangement so that would largely invalidate anything they develop.

CPU, RAM, storage and ports in every 2 sq in? (0)

macraig (621737) | more than 4 years ago | (#29126709)

David Ackley brags, "We have a CPU, RAM, data storage and serial ports for connectivity on every two square inches."

That sounds kinda expensive to me, even at only 72MHz/16K/128K per module.

Re:CPU, RAM, storage and ports in every 2 sq in? (1, Interesting)

Anonymous Coward | more than 4 years ago | (#29126993)

i agree w/ you. It's ludicrous when the article states that the team has no "data" comparing the system to an Intel Core Duo chip. There is no need to collect data. Basic models from the specs show how pointless this exercise is.

Let's just consider how many little chips equal the power of a 3GHz chip? there's no direct comparison, but the ratio of clock speeds is about 50:1. So, about 50 boards is roughly equivalent in clock cycles to a $100 chip. I hope those boards cost less than $2 apiece.

One could also compare the volatile memory... 16K*50 would be less than 1MB of ram, which is much smaller than the cache of a decent Intel chip. Nevermind the incredible bus speed of low-level cache, or its very wide bus. Also, consider that the switches in an intel chip allow that data to reach any other part of the system very quickly. In that awful little 16-bit bus, transfers will be staggeringly slower. Not only does that interconnect greatly limit the memory bandwidth, but the CPUs will have to stop computing in order to route the data.

I don't care how impressive anyone thinks that "programming" demo video appears. It transferred 128KB in 1 second for ~=1 Mbit of bandwidth. That is appalling for a network protocol. As a proposed replacement for a superscale CPU's context swap, it's dismal.

This project should not be presented in a magazine, it should be destroyed in private, preferably by burning.

Re:CPU, RAM, storage and ports in every 2 sq in? (2, Informative)

Arthur Grumbine (1086397) | more than 4 years ago | (#29127277)

David Ackley brags, "We have a CPU, RAM, data storage and serial ports for connectivity on every two square inches."

That sounds kinda expensive to me, even at only 72MHz/16K/128K per module.

Well it seems like Ackley misspoke (or was misquoted). The actual dimensions from one of their Official Retailers [liquidware.com] is 1.87" x 1.87" x 0.25". More like "2 inches square" (or 4 square inches) as opposed to "2 square inches". But at $55/each they are definitely not going to out-price/perform any Intel/AMD desktop chips on this first production run. But that's not what they're aiming for, judging from the inspired rhetoric on their main site, and their official retailer's site. They're more about a paradigm shift in computer building.

Pretty exciting stuff if they keep up the momentum. IMHO, the computer industry is definitely in need of a paradigm shift like this - to allow for easier, and more refined, modular scalability to provide the best support for upcoming industries like robotics and spaceflight

Re:CPU, RAM, storage and ports in every 2 sq in? (1)

Desler (1608317) | more than 4 years ago | (#29127705)

Re:CPU, RAM, storage and ports in every 2 sq in? (1)

hoppy (21392) | more than 4 years ago | (#29130133)

Exactly! Nothing new under the sun. For a better approach of this architecture, and something modern look at :
http://www.xmos.com/technology/xcore/ [xmos.com]
8 to 32 thread on a chip with speedy "serial" connexions.

Re:CPU, RAM, storage and ports in every 2 sq in? (1)

dha (23395) | more than 4 years ago | (#29127999)

David Ackley brags, "We have a CPU, RAM, data storage and serial ports for connectivity on every two square inches."

Well, I want to say "No brag just fact."

Except it's not quite fact: What I actually said was "under two inches squared" -- which is closer to four square inches.

But hey, I'm glad I didn't say "under 50mm squared".

Also, the specs got a little muddled. The raw hardware on the current board has 58KB RAM, 512KB flash for program store, and 16KB EEPROM for data.

Re:CPU, RAM, storage and ports in every 2 sq in? (1)

tolan-b (230077) | more than 4 years ago | (#29130753)

I'd be interested to know where you're planning to go with this, or I suppose maybe more to the point what you're planning to learn as you iterate the idea. I'm a bit young to really remember the transputer (I think I was probably about 12 when I saw the Atari transputer setup in a magazine, I nearly wet my pants ;) but as you mention you're already aware of the design and from what I understand this seems quite similar. Do you think the transputer was just ahead of its time, or do you plan to move in another direction?

Incidentally, not sure how big it is, but if you could get the Erlang VM running on one of these nodes (may be a bit of a push on this iteration) I think it could be a perfect fit for the architecture.

Whoa (1)

gnarfel (1135055) | more than 4 years ago | (#29126717)

That thing is hella cool. The longer demo is better, you may have to rtfa and click 3 links deep or so though.

Oh... (1)

curious.corn (167387) | more than 4 years ago | (#29126737)

... to think that I wanted to cook up something similar 5 yrs ago!
Couldn't drum up enough interest in my fellow engineering colleagues: too interested in getting a shit temp job (after a masters degree, BTW)

Oh well, glad someone is doing it...

If you're in engineering and want to do something, forget Italy... run, run away as fast as you can!
Eh sì, anche se hai paura di faro, amico mio, scappa... datti... tela... appena sei fuori non immagini quanto sia meglio fuori... ordini di grandezza!!!

Hello! (1)

thatkid_2002 (1529917) | more than 4 years ago | (#29126779)

Potentially this could still run a normal OS such as Linux, though I would imagine this would definitely use an interesting bootloader. The distributed operating system route could also be taken - using an OS similar to 'Plan 9'.

I think the magic words related to this motherboard design is Parallel Computing!

Disclaimer: I have no CS degree and a very basic understanding of OSes and hardware.

Re:Hello! (0)

Anonymous Coward | more than 4 years ago | (#29128759)

Disclaimer: I have no CS degree and a very basic understanding of OSes and hardware.

And it shows.

It's now time to upgrade, literally... (3, Interesting)

wjsteele (255130) | more than 4 years ago | (#29126819)

into the 3rd Dimension. Imagine if they also had connectors on the top and bottom of the unit. We could then start to do real matrix programming. Once CPU could talk to 6 and traverse the levels or talk to peers depending on the need. If they were also on the diaganols, they could get even more complex. More like the human brain.

Wow, I'd really like to have about 512 of these to play around with! I can see doing something very cool with these and a little bit of fuzzy logic or neural network programming. I just wonder how addressing is handled.

Bill

Re:It's now time to upgrade, literally... (1)

DigiShaman (671371) | more than 4 years ago | (#29127003)

Did anyone else think of Capsela when they saw this?

Re:It's now time to upgrade, literally... (0)

Anonymous Coward | more than 4 years ago | (#29127085)

That is exactly what I thought too.

Re:It's now time to upgrade, literally... (1)

Grieviant (1598761) | more than 4 years ago | (#29127441)

We kind of already have that in the form of multilayer PCBs / daughterboards.

Although BGA chips have all the pinouts on the bottom, the motherboard is typically composed of multiple layers of traces and vias which makes the routing feasible on densely populated boards.

As for stacking the boards and chips in 3 dimensions, daughterboards which plug directly into the parent board have been around for ages. You don't often see them in a regular PCs because they just aren't necessary to satisfy the space requirements. It's also simpler, cheaper and faster (e.g. max signalling speed between cores) if you can cram the entire design into a single chip.

Independent decision making modules (5, Funny)

Anonymous Coward | more than 4 years ago | (#29126837)

Cell# 3712: Hey guys, have you noticed that #1914 never seems to accept requests?

Cell# 141: Well, he does sometimes reject.

Cell# 4439: I don't route to him very much anyway.

Cell# 1142: He rejected the last three of mine. I kind of agree.

Cell# 3712: So what should we do about it?

Cell# 141: Can't we just fry him? There's plenty of us anyway.

Cell# 3712: That's a bit harsh.

Cell# 4439: Ok, I got the records here showing that he rejected 90% of requests the last week but allocated two hundred percent of average power to himself.

Cell# 3712: That motherfucker, let's do it then.

Cell# 1142: I don't really want to fry him, but I don't mind that much if you do.

Cell# 141: Ok, gather up all your spare power, STAT!

Re:Independent decision making modules (1)

Yvan256 (722131) | more than 4 years ago | (#29126963)

You forgot to link to the previous relevant slashdot story [slashdot.org] .

Re:Independent decision making modules (3, Interesting)

dha (23395) | more than 4 years ago | (#29128079)

I love it.

Note that there's more truth in this fantasy than one might think, at least potentially. IXM nodes don't have the ability to fry each other, but they do supply each other with power, and that power switching is under software control.

So in many configurations, IXM nodes absolutely and literally do have the power to reach a consensus about a misbehaving neighbor and shut it down.

Re:Independent decision making modules (0)

Anonymous Coward | more than 4 years ago | (#29131181)

this could in fact be a very interesting topic for research on Fault Tolerance

Mainframe (2, Insightful)

sexconker (1179573) | more than 4 years ago | (#29127117)

So it's a small, shitty mainframe.

Impressive! (0)

Anonymous Coward | more than 4 years ago | (#29127151)

..Marketing for a very mundane solution. Seriously, this has been done to death, the design, as others have already pointed out is limited, the computational power is poor, the communication infrastructure will be weak, and there is no point in designing in more points of failure when the job that can be accomplished by even a large number of these things can be done by a single, off the shelf consumer processor. The marketing drivel alone makes it sound like a ploy to raise money.

Tron (1)

EEPROMS (889169) | more than 4 years ago | (#29127159)

I notice some people are commenting Linux or BSD etc would work on this hardware but I would have thought an OS like Tron [web-jpn.org] would have been more ideal.

shit design (1, Insightful)

Anonymous Coward | more than 4 years ago | (#29127591)

as one poster had said, it would be much more sensible to integrate multiple cores onto an FPGA, and put the real time into the implementation of a bus that could realistically move data between the cores

not to mention that their choice of parts was sub-optimal. the cortex m3 is not the suggested replacement for arm7 by accident, it offers 1.25 dmips/mhz (compared to this arm's 0.89 dmips/mhz), an instruction set with optimized code density versus performance, more predictable interrupt handling, mpu, probably better power consumption, etc. for practically the same price.

if you ask me this is an academia project run by a bunch of hippies who are spending their time on all of the wrong aspects in this kind of decentralized computing concept.

Great (3, Interesting)

British (51765) | more than 4 years ago | (#29127657)

You have just re-invented Lego. Seriously, I like this idea. Want a gaming system? Put these together. Want a server? Put those together instead. Some component break? Swap it out.

Re:Great (1)

Lorkki (863577) | more than 4 years ago | (#29129321)

Yeah, I mean, wouldn't it be great if we had motherboards with connectors on them that you could use to stick in, say, more memory or like even a massively parallel stream processor for graphics, or an additional NIC or sound ca...

Oh, right.

Finally! Very cool. (2, Interesting)

suomynonAyletamitlU (1618513) | more than 4 years ago | (#29128391)

I've had exactly this idea for a couple years now, if not anywhere near a workable design. If it's done properly, it could be very interesting.

It being done properly would require:
* Distributed power
* Very high speed and high-reliability inter-module communication
* Hotplugging
* Standardized inter-module APIs and connectors
* An OS capable of organizing the entire system seamlessly (I have my ideas) and securely (I don't)

I can't speak to the technical abilities of such a system but if it was running it could easily become one of those sci-fi systems from the movies that everyone insists can be done but which has yet to appear--taking "your" part of the computer with you and just plugging your desktop session in to whatever computer you come across. You could also have software running on modules that is separate from the CPU, so that, for instance, your hard drive will not only defrag on its own when not busy, but will also do virus and spyware scans. And if you have a module that just absolutely can't be allowed to be reverse-engineered, have it have its own secret processor and instruction set with capabilities that are accessable to the system via APIs without the internal processes being at all open to the system.

I'm sure they wouldn't be interested, but I'll have to find and send an email to these guys.

Redundancy (2, Insightful)

shadowblaster (1565487) | more than 4 years ago | (#29128729)

Can they make the cluster survive a destruction of several nodes?

There are many situations where this would be beneficial such as space craft design and military electronics. Even with several nodes severely damaged, the machine can re-route processing to the remaining nodes. Although overall processing speed might be reduced, there will be no loss of functionality.

Buy Your Own (1, Interesting)

Anonymous Coward | more than 4 years ago | (#29129115)

I buy equipment from these guys, glad to see they are still at it. Why read about it when you can buy your own copy of this project [liquidware.com]

Just great - Replicators. (3, Funny)

fahrbot-bot (874524) | more than 4 years ago | (#29129165)

Replicators [wikipedia.org] . First thing that popped into my mind.
Give those "Illuminato X Machina" things legs and we're all HOSED.

A bit late.. (1)

cheros (223479) | more than 4 years ago | (#29129759)

I designed that a good 10 years ago as a means to multiply the use of military comms equipment - the idea was to combine processing units if more computing horse power was required in theather. However, it emerged that volume was more interesting than flexibility (why sell one device if you can get paid for two)..

Been done already (1)

Arlet (29997) | more than 4 years ago | (#29129905)

Looks like a cute idea, but a single modern CPU will easily outperform a whole table of these processors, which makes the whole exercise a bit pointless. This is especially true for problems that aren't embarrassingly parallel. A single processor will be much easier to program too. If you want to go faster than a single processor, the most effective way is to combine already fast CPUs, with lots of memory, and a fast interconnect network, preferably using cache coherent NUMA architecture. Those systems already exist too.

Re:Been done already (1)

uninformedLuddite (1334899) | more than 4 years ago | (#29131123)

I suspect it will be tasked with things that the normal CPU isn't the best solution for

Re:Been done already (1)

ThosLives (686517) | more than 4 years ago | (#29131577)

Agreed. There seems to be a surprising assumption about how 'parallel' most computing tasks are. Any time the output of one computation depends on the input from another computation all the parallel computing in the world won't save you, because those computations must be performed in temporal sequence.

There is also the cost of distribution - any time you split up a task to make it parallel, you have to spend effort to break it up and then reassemble the parts. This effort grows with how many parts into which the task is split, so there is some limit where performance is actually hurt by making a task more parallel rather than improved.

I suppose that's a long-winded way of saying "parallel computing makes sense for some tasks but not all, and if you blindly make things parallel you will, on average, make things worse than picking the right tool for the job."

Huh... (1)

julesh (229690) | more than 4 years ago | (#29130217)

Together, they form...

Wyld Stallyns? ... a networked cluster with significantly greater power than the individual modules.

I think my version would have been better.

Heart cells... (1)

Shard.Oglass666 (1507693) | more than 4 years ago | (#29130365)

Reminds me of heart cells. Two heart cells seperated will beat independently, but when they are placed within touching distance of themselves they will synchronize and beat in unison. The more you add, the more the fun.

A little unimpressed. (1)

rdebath (884132) | more than 4 years ago | (#29130415)

Okay, question one is why are they underclocking (or using really cheap versions of) the ARMs I know they are pretty close to a GHz for expensive ones and mass produced g ear (very price sensitive) doesn't go below about 200MHz.

The second is why aren't they using a fractal grid ie:

table
+-0123456789ABCDEFGHIJKLMNOPQRST
UVWXYZabcdefghijklmnopqrstuvwxyz
begin 664 Ascii_art.txt
h6+cU60+U60+UL0+U60+U60-TLpxTLpxT60+U60+U60w860+U60+U60-Q60+U
h60+j60+U60+U63kU60+U60w860+U60+U60+U8moh9GgU60+U60+U60+f9Goh
h8kcU60+U60+U60-w63+UT0+U60+U60+U65kUI0-w0W+U60+U60+U60gh9Gof
h60+U60+U60+U8moh9Gg860+U60+U60+j60+U60-QLpxT63xTLmwU60+U63k8
h60+U60+U65kU60+U60+ULpxTK3xTLm+U60+U60-w0W+U60+U60+UL0+U60+U
h9m+U60+U60-Q60+U60+j0W+U60+U60+U60gh9Gof60+U60+U60+U8moh9Gg8
h60+U60+U60+UT0-E65kU60+U60+U60-w63+UT+cU60+U60+U60+f9Goh8m+U
h60+U60+U60gh9Gof0W+U60+U60+U9m+U60+UL3xTLpxTLpwj60+U60-Q0W+U
R60+U60+j60+U60+U60+U60+U60+U60+U60+UL+c+
+
end

So a processor has four links from it's corners and they are linked together into a group of four that has links from the four corners. Repeat to infinity.

OOps: The shitty Slashcode requires that my pretty picture be encoded.

Well... (0)

Anonymous Coward | more than 4 years ago | (#29131441)

It's about time. I've been wanting them to be built like that for over a decade.

Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...