Beta
×

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!

Parallel Processing For Cardiac Simulations Using an Xbox 360

Soulskill posted more than 4 years ago | from the just-watch-out-for-a-literal-red-ring-of-death dept.

Medicine 101

Foot-in-Mouth writes "Physorg has an article about a researcher, Dr. Simon Scarle at the University of Warwick's WMG Digital Laboratory, who needed to model some cardiological processes. Conventionally, he would requisition time on a university parallel-processing computer or use a network of PCs. However, Dr. Scarle's work history included gaming industry experience as a software engineer at a company associated with Microsoft Games Studio. His idea was that researchers could use Xbox 360s as an inexpensive parallel computing platform due to the console's hefty parallel processing-enabled GPU. He said, 'Although major reworking of any previous code framework is required, the Xbox 360 is a very easy platform to develop for and this cost can easily be outweighed by the benefits in gained computational power and speed, as well as the relative ease of visualization of the system.'"

cancel ×

101 comments

Sorry! There are no comments related to the filter you selected.

Why not the PS3? (1, Insightful)

yourexhalekiss (833943) | more than 4 years ago | (#29400677)

I thought everyone used the PS3 for this sort of off-the-shelf supercomputer thing.

Re:Why not the PS3? (4, Informative)

rlanctot (310750) | more than 4 years ago | (#29400731)

Because "Dr. Scarle's work history included gaming industry experience as a software engineer at a company associated with Microsoft Games Studio."

ie he's had experience in programming for the platform, was likely used to using Visual Studio with XNA and likely had all the tools he needed to program for the 360 already.

Re:Why not a PC (5, Informative)

adisakp (705706) | more than 4 years ago | (#29400821)

If you program C# Windows / Direct3D, programming, XNA for XBOX is easy to program for. You can actually start with XNA on the PC and most stuff will transfer over with minimal changes. You have access to the GPU and shader programming so GPGPU programming ideas can be ported as well.

The PS3 Linux is significantly more difficult to program for, has a different memory model (and programming architecture) for the SPU's, has very poor (compared to Visual Studio) debugging and programming IDE environment, etc. Not to mention that the latest version of the PS3 doesn't even support Linux. There is no GPU access so GPGPU algorithms available on the PC need to be manually ported to the PS3.

That said, if they actually did buy older PS3's, take the steep learning curve to SPU programming, port all of their code to a 100% custom platform with hard-to-use tools, and heavily optimize the SPU code, they would probably be running their algorithms significantly faster on PS3 SPU's than on the XBOX 360 GPU.

Re:Why not a PC (5, Insightful)

zaffir (546764) | more than 4 years ago | (#29401105)

Actually, the case could easily be made that programming a GPU that was NOT meant for general-purpose computing is quite a bit harder than the Cell, which WAS designed with more general-purpose computing in mind. You don't need to port everything required for GPGPU, you just use the libraries and tools developed by IBM for the Cell.

Re:Why not a PC (1)

badkarmadayaccount (1346167) | more than 4 years ago | (#29415855)

How much do they cost?

Re:Why not a PC (1)

interkin3tic (1469267) | more than 4 years ago | (#29401599)

That said, if they actually did buy older PS3's, take the steep learning curve to SPU programming, port all of their code to a 100% custom platform with hard-to-use tools, and heavily optimize the SPU code, they would probably be running their algorithms significantly faster on PS3 SPU's than on the XBOX 360 GPU.

I know next to nothing about parallel processing or either game console, but I have to ask couldn't they simply use more 360s and get the same speed, without having to spend time doing all of that?

Re:Why not a PC (1)

egr (932620) | more than 4 years ago | (#29404569)

Sure if the problem is embarrassingly parallel or not real-time, otherwise, latency for message transfer would probably kill it.

Re:Why not a PC (1)

TheRaven64 (641858) | more than 4 years ago | (#29404785)

Look up Amdahl's Law. Every 'parallel' problem is really a problem which has some parts that are independent and some parts that are not. Consider something simple, like sorting an array. You can combine two sorted arrays in O(n) time, just be iterating over the two of them and, at each step, taking the element from the head of one of the arrays, depending on which is smaller. You can, therefore, parallelise sorting by splitting an array in half, and sorting the two halves independently, then combining them[1]. You can take this further and sort each of the sub-arrays in the same way, so you have 4 concurrent bits, but the final combining step still can't be done in parallel. Eventually, you reach a point where it doesn't matter how many machines you use for the parallel bit, the serial bit is taking most of the time.

In the real world, there are other constraints, like the cost of distributing the data, the cost of spawning new parallel tasks, and so on. These all make the parallel part more expensive, so it eventually the benefits are outweighed by the cost.

It's quite rare to find a problem that you can split into completely isolated subproblems with no dependencies. These are known as 'embarrassingly parallel' problems. Things like SETI@Home fall into this category; each work unit can be processed independently without any knowledge of the others and the order in which they are processed doesn't matter. Finding an element in an array is a trivial example of this kind of problem; you can search subarrays in parallel and keep splitting the array until you are searching one-element subarrays in parallel. Even then, you have the cost of creating the threads or processes for the search, so this probably won't be the fastest case.

[1] This is a parallel mergesort, which is one of the simplest concurrent sorting algorithms. It's not the best, so don't implement it in real code, but it's a good exercise for people starting parallel programming.

Cost of Creators Club (1)

tepples (727027) | more than 4 years ago | (#29407181)

I have to ask couldn't they simply use more 360s and get the same speed, without having to spend time doing all of that?

Each Xbox 360 costs $299, plus $99 per console per year for "Creators Club", a certificate to run self-signed .NET assemblies. So the fewer consoles you buy, the less you have to pay Microsoft to rent a soft-mod. (Incidentally, Apple copied this model for the iPhone developer program.) The fat PS3 was $399, and the owner had the ability to boot into Other OS permanently.

Re:Cost of Creators Club (0)

Anonymous Coward | more than 4 years ago | (#29407309)

I object to your use of the term 'soft-mod'.

Then what is a soft-mod? (1)

tepples (727027) | more than 4 years ago | (#29412391)

I object to your use of the term 'soft-mod'.

As I understand it, a soft-mod is a piece of data installed on a video game console that allows it to execute a program not explicitly approved by the console maker. XNA Creators Club fits this definition, or how did I misdefine soft-mod?

"take the steep learning curve to SPU programming" (2, Interesting)

Anonymous Coward | more than 4 years ago | (#29401625)

Give me a break. So long as your program doesn't need more than 256k of memory per thread you can port it by typing little more than "CC=gcc-spu make". There is a nice helper library that wraps your main() and passes I/O to and from the SPU. I got about 40kloc of audio processing code running on the SPU in a grand total of 30 minutes, which included downloading the SDK (and reading the docs while it downloaded and installed). It required zero code changes. Getting good performance requires vectorizing the code with intrinsics which is exactly like coding for x86's SSE2 but easier because the SPU vector engine is a lot more complete. If you need to work with more memory you need to do some manual memory management, but it's nowhere near as invasive as the shuffling you need to do to move data on and off a video card. CELL is quite simply FAR easier than GPGPU.

tl;dr version: GPGPU is complex and specialized enough that you have to write for it, CELL is so simple that you can get regular CPU code running on it with few to no changes.

Boggle (-1, Flamebait)

Anonymous Coward | more than 4 years ago | (#29402223)

OMG!!! Some little PC/Xbox fanboy is babbling about how anything out his sad little range of experience is 'hard teh develop'.

What an idiot.

Re:Why not a PC (1)

moon3 (1530265) | more than 4 years ago | (#29404005)

SPUs are not suitable for everything. CPU side of the Xbox 360 has 6 hardware threads on 3 general purpose cores, while PS3 has only one general purpose core.
If you doesn't need SPUs the PS3 turns to be very poor contender agains 3 very fast HT cores of the Xbox. Larger shared CPU/GPU memory architecture also helps the Xbox.

Re:Why not the PS3? (2, Insightful)

Anonymous Coward | more than 4 years ago | (#29400733)

If he was planning on tailoring the computations for a GPU, the Xbox is the best choice as it has more features for generic data manipulation and more computational power. As mentioned in the summary, ease of development was actually the primary motivator. PS3 fails hands down in this arena.

Re:Why not the PS3? (4, Interesting)

mkaushik (1431203) | more than 4 years ago | (#29400787)

He should've used something like CUDA instead, for long term gains. This would have shown far better performance than the Xbox's GPU (which is quite dated now), and easy scalability as better GPUs keep coming to the market. His familiarity with Xbox programming might have enabled him to come up to speed with CUDA quickly.

Re:Why not the PS3? (0)

Anonymous Coward | more than 4 years ago | (#29400993)

Tell me when you find CUDA for 199.

Re:Why not the PS3? (2, Interesting)

Spatial (1235392) | more than 4 years ago | (#29401181)

Almost all of the cards that support it are less than 200 dollars, namely the 8x00, 9x00 and GTX series. Only four or five of them cost more than that, mainly multi-GPU cards.

Re:Why not the PS3? (1)

NewbieProgrammerMan (558327) | more than 4 years ago | (#29401459)

Yep, I've got two 9800 GT's in my machine and use them for CUDA. It looks like you can get them now for less than $100 [google.com] .

Re:Why not the PS3? (1)

HazMat 79 (1481233) | more than 4 years ago | (#29402409)

But then you still need the rest of the computer, where as you get the whole platform for $199 with the Xbox. That would only be cheaper if he had did not already have the PC hardware laying around. Maybe just taking a stab in the dark here.

Re:Why not the PS3? (3, Interesting)

Svartalf (2997) | more than 4 years ago | (#29402941)

Perhaps. Depends on how many nodes he had to set up.

Let's do a bit of "napkin math" on this:

I believe there's 48 unified shader cores in the 360's GPU. That's a nice amount.

There's 112 shader cores in the 9800GT. With the SLI setup, that's 224 of them at your disposal to do GPGPU thread processing with.

Now...done right (meaning not going overboard on the CPU, etc...), you can field a machine for about $600 or so that has an inexpensive SLI board, case, memory, etc. If you're doing a cluster node, you wouldn't need a disk, etc. so you could shave a bit more than you'd think off the price past the first machine bought.

$200 versus $600. The price is compelling. But, unfortunately, you're talking about a machine that's nearly 5 times more powerful (Possibly more, I'm not doing apples-to-apples comparisons on the shader cores...) at this sort of task with the PC- for only about 3 times the cost. To gain the same performance level, you would have to field 5 360's per each PC compute node. If you only need the power of two or three of the 360 nodes, then it makes some sense to do it with that, especially if you're familiar with the environment (the gent we're talking about in the threads here was that...).The power consumption will be comparable across the board, so that's not so much a consideration.

Where it really hits the wall is with the cluster fabric itself. Using PS3's and 360's is "cool" but it's actually not overly practical past about 10 or so machines for most performance computing applications because of the limitation of the cluster interconnect you have at your disposal. With those machines you will be limited to 1Gb Ethernet which limits your interconnect performance to about 750Mbits per node. When you go to match the performance of the PC box, you will find that you can do it, but it'll take 5 or so 360's to do it because of the overhead, lower performing hardware, and all. You'll have difficulty matching a cluster of the same numbers of PC's- and we won't get into using Myrinet, Infiniband, or iWarp channel adapters for 10Gb interconnects on the PC's which will make it be basically a huge SMP machine for all intents and purposes until you scale it to about 32 or so machines.

I think the assessment that it's familiarity and "cool" factor that drove this decision- not price or actual usefulness.

Re:Why not the PS3? (1)

tepples (727027) | more than 4 years ago | (#29407209)

In addition to what Svartalf said:

you get the whole platform for $199 with the Xbox.

But you don't get the soft-mod. That's an extra $99 per console per year.

Re:Why not the PS3? (1)

nobodyman (90587) | more than 4 years ago | (#29402395)

True, but I suppose the GP should have been more clear: $200 will buy you a CUDA card. Then you'll need power, cpu, networking, input, and RAM.

Re:Why not the PS3? (1)

JJJK (1029630) | more than 4 years ago | (#29401811)

Or use OpenCL and choose any GPU vendor that supports it (ATI and nVidia already do - in beta)

I must admit that CUDA is pretty easy, you'll understand the basics and make a simple application in less than one day. I have some experience with programmable shaders and I know how GPGPU works, but that's a lot more complicated than using CUDA. I'm not sure what kinds of features the xbox provides, but I doubt it's easier than that. And OpenCL is almost the same concept, it's just using a compilation method more similar to what shader programmers are used to.

Re:Why not the PS3? (1)

badkarmadayaccount (1346167) | more than 4 years ago | (#29416673)

With these guys' products [cyclone.com] you'll need exactly one machine.

Re:Why not the PS3? (2, Informative)

LucidLion (1145739) | more than 4 years ago | (#29403453)

This type of simulation can be and is being done using CUDA. In fact a talk is being given at the upcoming nVidia technology conference on this very subject. nVidia's website won't let me create a direct link, but if you click here [wingateweb.com] and then Session Catalog > Session ID 1036, you can read the abstract.

Re:Why not the PS3? (3, Interesting)

TeethWhitener (1625259) | more than 4 years ago | (#29400789)

Well, since the introduction of CUDA by Nvidia, using GPUs for accelerated physical simulations has started to catch on. I've heard of people using PS3 and XBox occasionally, but usually for this sort of work, they'll take a half-dozen or so GeForce cards and use CUDA to parallelize the code. I'm not too familiar with all the ins and outs myself, but as a part of the chemistry community, I get to see a lot of neat applications of the stuff.

Re:Why not the PS3? (-1, Flamebait)

Anonymous Coward | more than 4 years ago | (#29400843)

Because he isn't a pretentious piece of shit like the sub-human cock-gobblers that infest this website.

You fucking pretentious nerds make me sick.

If your really going to act that way why don't you just put on a black turtle neck while you suck Steve Jobs AIDS infected dick.

Just get it over with already.

Re:Why not the PS3? (-1, Troll)

Anonymous Coward | more than 4 years ago | (#29400895)

Why not the PS3? How else would he be able to astroturf for Microsoft? Seriously - this does not impress anyone on slashdot. And I bet soulskill put it on the front page just to be able to make his "literal ring of death" joke.. :)

Because it's an advetorial, perhaps? (5, Insightful)

david_craig (892495) | more than 4 years ago | (#29401211)

Because it's really a publicity stunt from Microsoft trying to get the Xbox360 in the forefront of peoples minds in the lead up to Christmas.

The article reads like most of the marketing cover I see from Microsoft (and for that matter most other software companies).

Organisation X needed to do Y but the competing product was too expensive (in price/effort/time). Our product does Y at a fraction of the price/time/effort of our competitor.

The people at Orgaisation X are smart people who know all about Y and are very happy with our product.

Re:Because it's an advetorial, perhaps? (0, Offtopic)

Silas is back (765580) | more than 4 years ago | (#29401315)

+1 Insightful

Microsoft Really Needs To Try Harder (0)

Anonymous Coward | more than 4 years ago | (#29402267)

You would think that with Microsoft's billions they could hire PR/marketing people with a bit more subtlety.

With the relaunch of the search engine, it was painful to read the drones sitting around in some marketing company's office posting "I'm a long time Google user and I decided to give Bing a try and by golly! I'm switching".

You would think the last thing Microsoft wants the public to associate the worst console hardware in history with cardiology.

Way to go Microsoft, you product that's only claim to fame(or infamy) is The Red Ring of Death is being associated with the organ that is the number one cause of Death in people from heart disease or failure.

 

Re:Because it's an advetorial, perhaps? (4, Interesting)

innerweb (721995) | more than 4 years ago | (#29402809)

Only problem I have with the X-Box is how crappy the hardware has been so far. Rings of death, circle of death, failed rom drives, failed hard drives ...

Why on Earth would you want to rely on such a poorly constructed piece of hardware to do real work? Every component has failures, but when so many of my childrens' friends are on their 3rd or fourth in a few years, there is a real issue. And, no, they are not abusive to their equipment. The same kids have Wii,s PCs, PS3s, GameCubes and more without all the issues they have with X-Box 360s.

InnerWeb

Re:Because it's an advetorial, perhaps? (1)

AHuxley (892839) | more than 4 years ago | (#29404043)

6.40 Processes Should Be Enough For Anyone :)

Re:Because it's an advetorial, perhaps? (1)

Rewind (138843) | more than 4 years ago | (#29407493)

Actually the latest version of the 360 is (at least from what I have seen) less likely to fail than the PS3. However the stigma of the notoriously unreliable early versions will stick around for some time to come.

It is a real issue and it does seem odd to pick the least reliable system for this, but Microsoft does replace them for free, and at least on the gaming front, reliability has never been a huge deal. People want to ramble on about how it will impact console wars, but the PS2 was easily the most failure prone of the last generation and it was also the best selling. *shrug* People want the software. If the PS2/360 has their games they will put up with failures. I would say the same holds true here. History of MS dev = MS platform for this.

Re:Because it's an advetorial, perhaps? (0)

Anonymous Coward | more than 4 years ago | (#29410865)

I think the best the about the xbox 360 is the butthurt rage it sends fags into, lulzy.

Re:Because it's an advetorial, perhaps? (3, Insightful)

kestasjk (933987) | more than 4 years ago | (#29403253)

Do cardiovascular research scientists buy much of their research equipment for Christmas?

Re:Because it's an advetorial, perhaps? (0)

Anonymous Coward | more than 4 years ago | (#29403427)

Do cardiovascular research scientists buy much of their research equipment for Christmas?

For marketing purposes irrelevant.

Re:Because it's an advetorial, perhaps? (0)

Anonymous Coward | more than 4 years ago | (#29403835)

No, but their children do.

Re:Because it's an advetorial, perhaps? (1)

Trogre (513942) | more than 4 years ago | (#29408027)

With R&D budget cuts across the board, Santa is pretty much their last remaining equipment source.

Re:Because it's an advetorial, perhaps? (2, Interesting)

julesh (229690) | more than 4 years ago | (#29403703)

Because it's really a publicity stunt from Microsoft trying to get the Xbox360 in the forefront of peoples minds in the lead up to Christmas.

The article reads like most of the marketing cover I see from Microsoft (and for that matter most other software companies).

I've worked with WMG people before, and they aren't the kind of organisation that takes a payoff like that. And they certainly aren't a typical MS shop, either. My guess is simply that the guy was more familiar with Xbox as a platform than he was with PS3... I doubt there's much more to it than that.

Re:Because it's an advetorial, perhaps? (0)

Anonymous Coward | more than 4 years ago | (#29403853)

The "more to it" would be /. throwing up every other slightly pro-MS story they get. I wouldn't be surprised if a lot more people think this is astroturfing than there are people who have any slight interest in this story.

Re:Because it's an advetorial, perhaps? (1)

AHuxley (892839) | more than 4 years ago | (#29404031)

Published in Elsevier :)
MS is learning from the pharmaceutical companies :)

Re:Because it's an advetorial, perhaps? (0)

Anonymous Coward | more than 4 years ago | (#29404987)

Many game companies won't employ people over 35 as programmers, so such people either set up their own companies or move into academia. So it could be one for him to show that he is still working on console systems. The researcher had previous experience of programming the X-Box, so it boosts his chances of getting a paper published if he uses a hardware platform that no-one else has used.

Plus Sony has made the decision not to allow researchers to use their hardware for research. Which is rather retrograde because having students learn about the hardware of the console by writing research demos is one way of getting suitable trained programmers.

Sounds like a DMCA violation... (1, Interesting)

Anonymous Coward | more than 4 years ago | (#29401321)

Better send him to jail.

Re:Why not the PS3? (-1, Offtopic)

dimeglio (456244) | more than 4 years ago | (#29401607)

PS/3 fan here. That is such a WASTE of such a fucking awesome machine. Saving lives is such a trivial objective when a PS/3 can bring instead WORLD PEACE! Nice to see a 360 that's actually working. Too bad they had to have it serviced over 9000 times already.

Re:Why not the PS3? (0)

Anonymous Coward | more than 4 years ago | (#29404099)

Looks like we got XBOX fanboys rading this thread.

Re:Why not the PS3? (0)

Anonymous Coward | more than 4 years ago | (#29401795)

Why not a PC for that matter, the Xbox 360 is just an ATi Radeon GPU, and an outdated one for that matter, I can't imagine this being any more robust than developing a platform for a regular PC.

Re:Why not the PS3? (1)

AHuxley (892839) | more than 4 years ago | (#29404073)

Does using a beige PC for parallel-processing come with a "pharmaceutical gift"?
A positive parallel-processing MS 360 story might get your stocking filled.
Philanthropy MS PR style.

Re:Why not the PS3? (1)

Hal_Porter (817932) | more than 4 years ago | (#29405459)

Does using a beige PC for parallel-processing come with a "pharmaceutical gift"?

Most PC users have to pay for their pharmaceuticals as far as I can see.

Re:Why not the PS3? (3, Informative)

drinkypoo (153816) | more than 4 years ago | (#29404847)

Sony just canned the PS3 Linux install option. :)

I doubt he's using JUST the GPU. The 3x3.2GHz PowerPC processors in the Xbox 360 are pretty compelling. The PS3 MIGHT have more raw power but you're not actually even allowed to use its GPU unless you have first-string developer status. Scientific computing on the PS3 focuses on the Cell, and it seems like there's an awful lot of unuseful hardware wrapped around it.

Hmm... (0, Offtopic)

TheBilgeRat (1629569) | more than 4 years ago | (#29400715)

Will you have to be an XboxLive Gold member to get this service?

Panties STINK!!!! (-1, Troll)

Anonymous Coward | more than 4 years ago | (#29400877)

Panties Stink!
They really, really stink!
Sometimes they're red, sometimes they're green,
Sometimes they're white or black or pink
Sometimes they're satin, sometimes they're lace
Sometimes they're cotton and soak up stains
But at the end of the day, it really makes you think
Wooooooo-wheeeee! Panties stink!

Sometimes they're on the bathroom floor
Your girlfriend- what a whore!
Sometimes they're warm and wet and raw
From beneath the skirt of your mother-in-law
Brownish stains from daily wear
A gusset full of pubic hair
Just make sure your nose is ready
For the tang of a sweat-soaked wedgie
In your hand a pair of drawers
With a funky feminine discharge
Give your nose a rest, fix yourself a drink
cause wooooooo-wheeeeeee! panties stink!

Was there a risk assessment? (1)

burnin1965 (535071) | more than 4 years ago | (#29400717)

Using the XBox 360 as a parallel computing platform when "major reworking of any previous code framework is required" seems like a huge risk when considering the XBox 360 reliability problems [wikipedia.org] .

Perhaps the newer systems have better reliability, I only hope for their sake they did their homework before buying the boxes.

Re:Was there a risk assessment? (2, Informative)

Timesprout (579035) | more than 4 years ago | (#29400933)

I am guessing that using the XBox as a parallel programming platform is pretty easy on your game disks.

Re:Was there a risk assessment? (1)

Spatial (1235392) | more than 4 years ago | (#29401171)

Read more than the first line of the index. There are problems with practically every aspect of the hardware, including GPU failure.

How would this work in practice? (3, Interesting)

grumbel (592662) | more than 4 years ago | (#29400773)

How would this work? Does Microsoft sell licenses for such purposes? Would they need to buy special development boxes instead of cheap of the self hardware? Has the Xbox360 been hacked enough to make this practical?

And most important of all: Why use a Xbox360 GPU in the first place? Aren't there PC GPUs that could run circles around what is in the Xbox360? Wouldn't a PS3 be better suited duo to being an open platform (well, at least as long as the old models are still available)?

Re:How would this work in practice? (0)

Anonymous Coward | more than 4 years ago | (#29400807)

> Aren't there PC GPUs that could run circles around what is in the Xbox360?
As others have cited, familiarity.

> Wouldn't a PS3 be better suited duo to being an open platform (well, at least as long as the old models are still available)?
If the plan was to use the GPU for processing, neither Xbox360 or PS3 wins due to being an open platform. AFAIK, Sony has been very careful about not allowing full-featured access to the GPU.

Re:How would this work in practice? (0)

Anonymous Coward | more than 4 years ago | (#29401009)

How would this work? Does Microsoft sell licenses for such purposes? Would they need to buy special development boxes instead of cheap of the self hardware? Has the Xbox360 been hacked enough to make this practical?
>It's called XNA. Code in C# on Windows and then deploy it on the 360. Easy. Look it up.

Wouldn't a PS3 be better suited duo to being an open platform (well, at least as long as the old models are still available)?
>PS3s are notoriously difficult to program for with that stupid memory model and architecture.

Re:How would this work in practice? (1)

zippthorne (748122) | more than 4 years ago | (#29401017)

Well, TFA says he had experience specifically programming for the 360 already, so he didn't need to learn another GPU.

Also.. You're missing the possibility of mass production. Imagine including a "free" xbox360 to run your wondrous cardiac software as a turn-key system. It'd be much easier to get some mass-produced consoles in a bulk order with some minor cosmetic changes to send out to doctors as a complete "single-purpose supercomputer" (within the bounds of the cardiac simulation he was working on) than to try to do the same thing by picking all your own components and put it together yourself.

I'm not sure if that actually benefits anyone, but it's not hard to imagine that something like it could benefit a lot of people.

Re:How would this work in practice? (1)

pantherace (165052) | more than 4 years ago | (#29401425)

The GPU in the Xbox 360 is roughly equivilent to maybe the HD 2900 from ATI. The system has 512MB Main RAM (a 10MB frame buffer for the GPU) and the memory is accessed through the GPU. The Xbox, has roughly a 7800 in it. It was added quite late, after Cell wasn't panning out quite as well as they wanted, so they went to Nvidia and asked what they could do, so it's closer to a desktop version than the one in the Xbox. Open platform... both are exceedingly closed. The person probably should have gone with a PC, but it's 'cool' to do things on consoles, even when they aren't all that efficient, or reliable. A new laptop with a decent graphics card would probably do about as well as an Xbox, were it able to run this person's code. A new desktop card should blow it away.

Re:How would this work in practice? (0)

Anonymous Coward | more than 4 years ago | (#29401685)

Just a note: the XBox 360's GPU is in no way equivalent to a Radeon HD 2900. The 360 GPU is a pre-R600 GPU and lacks a number of features found on the 2900; it also performs quite a bit worse, I believe.

Re:How would this work in practice? (1, Interesting)

Anonymous Coward | more than 4 years ago | (#29402813)

It is important to note that the CPUs and GPU share the RAM, though, so shuffling off a dataset to be crunched by a shader is a free operation.

Re:How would this work in practice? (1)

faragon (789704) | more than 4 years ago | (#29403989)

Wouldn't a PS3 be better suited duo to being an open platform (well, at least as long as the old models are still available)?

Being new PS3 models not able to run Linux [slashdot.org] , my guess is that Microsoft will push that side in order to attract geeks.

Hole closed Re:How would this work in practice? (1)

mrmeval (662166) | more than 4 years ago | (#29405155)

Microsoft just patched it shut.

What if something goes wrong? (2, Funny)

RobDollar (1137885) | more than 4 years ago | (#29400783)

It would perhaps give a new meaning to the red rings of death.

Re:What if something goes wrong? (1)

badkarmadayaccount (1346167) | more than 4 years ago | (#29416815)

Microsoft: Giving new meanings to "------- of Death" memes since the beginning.

Would CUDA be cheaper? (0)

Anonymous Coward | more than 4 years ago | (#29400801)

Would offloading to Xbox GPUs be cheaper than multi-GPU PCs doing the same thing? I totally get that he went with the 360 hardware having previous experience using it, I'm just curious how the actual hardware pricepoint works out... Suppose it comes down to exactly what is in the 360.

What about in 5 years? (2, Insightful)

i.r.id10t (595143) | more than 4 years ago | (#29400837)

What about in 5 years, or some other point in the future? The advantage of programming for say, x86, etc. is that the hardware will be out there and available for some time, and it will keep getting more clock cycles, etc. However, how long will the X Box be on the market? Will researchers be hunting pawn shops and garage sales in 5 years to replace broken hardware units?

Re:What about in 5 years? (1)

Savior_on_a_Stick (971781) | more than 4 years ago | (#29402229)

Possibly.

I met a guy in a dark alley behind a strip club to buy a couple of non-lobotomized Linksys routers, since no one carried the good ones locally and I needed them immediately.

Re:What about in 5 years? (1)

badkarmadayaccount (1346167) | more than 4 years ago | (#29416847)

Seriously?

Re:What about in 5 years? (1)

julesh (229690) | more than 4 years ago | (#29403733)

The advantage of programming for say, x86, etc. is that the hardware will be out there and available for some time, and it will keep getting more clock cycles, etc. However, how long will the X Box be on the market? Will researchers be hunting pawn shops and garage sales in 5 years to replace broken hardware units?

XNA/Managed DirectX, the development environment he would have been using for this project, is somewhat hardware independent. The same software could be run on a PC, for instance, although a PC capable of running it would be more expensive than the xbox.

isn't this somewhat boring? (2, Informative)

Trepidity (597) | more than 4 years ago | (#29400867)

Apologies for the rhetorical question, but obviously GPGPU for scientific simulations isn't new. We've had a [slashdot.org] whole [slashdot.org] lot [slashdot.org] on [slashdot.org] that [slashdot.org] already [slashdot.org] . The only possible new thing could be using the Xbox360 for it. But as far as I can tell (confirmed by all the comments I've seen so far), there isn't even anything interesting about that--- this guy just used the Xbox360 because he was already familiar with the programming environment, not because it has any particular advantages over CUDA on a PC.

Re:isn't this somewhat boring? (1, Interesting)

Anonymous Coward | more than 4 years ago | (#29401159)

The GPU computing is nothing new.

However, the paper on the-
"Implications of the Turing completeness of reaction-diffusion models"
is fascinating.

It's about spatially diffused chemical reactions, which is basically cell chemistry and thus life.
If this process can be regarded as being Turing complete then we have to regard a cell membrane, or even a simple mix of chemicals as being able to compute. And to be able to compute anything.

Turing's original reaction-diffusion model of morphogenesis concentrated on animal skin patterns, but these guys have taken a whole new approach.

Re:isn't this somewhat boring? (1)

speedtux (1307149) | more than 4 years ago | (#29401553)

If this process can be regarded as being Turing complete then we have to regard a cell membrane, or even a simple mix of chemicals as being able to compute. And to be able to compute anything.

That's nothing new either; of course, you can compute with fairly simple systems of coupled chemical reactions.

Re:isn't this somewhat boring? (2, Insightful)

olsmeister (1488789) | more than 4 years ago | (#29401773)

If this process can be regarded as being Turing complete then we have to regard a cell membrane, or even a simple mix of chemicals as being able to compute. And to be able to compute anything.

I can compute anything, given enough time. Part of my computational process may even involve designing a computer to speed the process and giving it specific instructions on what to do, and then waiting for a result.

Re:isn't this somewhat boring? (0)

Anonymous Coward | more than 4 years ago | (#29401801)

Of course, this has been done already. Turns out, the answer is 42.

Re:isn't this somewhat boring? (2, Interesting)

namgge (777284) | more than 4 years ago | (#29403625)

I can compute anything, given enough time.

Then have a go at a tiling problem [cs4fn.org] and let us know when you've finished.

Namgge

Comments from TFA (2)

earlymon (1116185) | more than 4 years ago | (#29400945)

I've found that - for me - most comments (when available) on most linked articles are of low quality (I'm not referring to /. comments, but the ones at any given article site itself). However, the ones addressing TFA at the physorg site are pretty cogent and informative, IMO.

Red Circle Of Death (-1)

Anonymous Coward | more than 4 years ago | (#29400955)

Home they don't get the Red Circle Of Death in the middle of a surgery.

achievement unlocked (4, Funny)

santax (1541065) | more than 4 years ago | (#29401027)

Found cure for cancer. Patented it.

WoW (1)

ae1294 (1547521) | more than 4 years ago | (#29401039)

Think of what a Beowulf Cluster.. O wait, nevermind.

I wonder if the Microsoft Audit team will show up and slap a fine for violating the EULA or something...

Re:WoW (1)

Korbeau (913903) | more than 4 years ago | (#29401775)

I wonder if the Microsoft Audit team will show up and slap a fine for violating the EULA or something...

I think these Xboxes have probably been provided free by the Microsoft Marketing team and that's one of the reason it's such "cost-effective" :)

From the summary:

Although major reworking of any previous code framework is required

Let's conservatively say that that alone require a programmer underpaid 30'000$ for a whole year (or two for 15'000 for six month, etc.) With that money you can buy 30 PCs that outweigh the Xbox in every performance aspects (or 39 considering that 30 Xbox would have cost 9000 to start with anyway).

I cannot see how this cannot be some kind of PR stunt from a former Microsoft related game dev.

The PS3 beowulf cluster cell-processing hype made a lot more sense, even more so when the PS3 was just hitting the shelves and thus was more or less on par with what desktop computer performances offered at the time.

Heh... (0)

Anonymous Coward | more than 4 years ago | (#29401065)

First thing that sprang to mind: Shelf after shelf of RROD's

Not really news... (1)

HalAtWork (926717) | more than 4 years ago | (#29401127)

So some guy somewhere said: "Yeah, it's possible." But even if someone started planning such a thing, why would they use 4 year old technology?

why use consoles just because they have GPU (1)

wjh31 (1372867) | more than 4 years ago | (#29401207)

so does any PC you like, and withe NVideas line of GPGPU cards, and their CUDA development kit its perfectly do-able with much more parallel processing power. Especially once you consider packages like accelereyes with matlab that make it easy.

Similar work using PS (1)

halukakin (1636389) | more than 4 years ago | (#29401303)

Last year I attended a presentation by Dr. Middelkoop. He showed us a demo on distributed computing using PS3s. http://www.ise.ufl.edu/middelkoop/ [ufl.edu] His work was focused on optimization.

Re:Similar work using PS (0)

Anonymous Coward | more than 4 years ago | (#29403993)

Not anymore: $ony has dumped Linux support for new consoles. So the cheap supercomputer times is long gone. "Thank you" Sony :-S

Wouldn't it have been better... (1)

blind biker (1066130) | more than 4 years ago | (#29401481)

...if they chose a platform that is more [osnn.net] reliable [quartertothree.com] than an Xbox 360. [wikipedia.org]

That's right bitches, 54.2% failure rate. [n4g.com]

Re:Wouldn't it have been better... (1)

js3 (319268) | more than 4 years ago | (#29403705)

...if they chose a platform that is more [osnn.net] reliable [quartertothree.com] than an Xbox 360. [wikipedia.org]

That's right bitches, 54.2% failure rate. [n4g.com]

that would mean and all of my xbox360 buddies must be in the other percentile... say for silent majority? I can pull %s out of my ass too but it won't be pretty.

not cost effective (1)

speedtux (1307149) | more than 4 years ago | (#29401521)

You're getting more bang for the buck with a desktop PC and standard graphics cards.

RROD (-1, Redundant)

dandart (1274360) | more than 4 years ago | (#29401705)

So, does the red ring of death mean the guy dies?

Local knowledge (1)

julesh (229690) | more than 4 years ago | (#29403769)

I find this story interesting, perhaps for a different reason to why it was posted here. I walk past the WMG Digital Lab on my way to the bank whenever I go, and I'm quite impressed that they've managed to do the research, get a paper published and get it talked about here within a couple of months of the building work on the lab being completed...

Oh the medical conditions. (0)

Anonymous Coward | more than 4 years ago | (#29403783)

Power and speed, yes. Accuracy, well, that wasn't a requirement before, was it? It merely had to look good. I don't know if I'd settle for medical imaging that merely looks good but fudges over the nasty bits that show the doctor just why it hurts. And because the calculations are too complex and too many to check by hand, we'll have to rely on automated checking too. Suppose, assuming they do check, thanks, they use the same hardware for that? Whoops.

Geowulf? (1)

cheros (223479) | more than 4 years ago | (#29403987)

You cannot possibly come up with a more transparent ploy to get game consoles for the whole department. I bet the next stage is "simulation at home"..

In all seriousness, there appears to be call for what I would call Geowulf clusters (a Beowulf cluster of graphics processors)..

Graphics card? (1)

Hurricane78 (562437) | more than 4 years ago | (#29404287)

Just add a recent graphics card into your system. With CUDA, it’s all already prepared for you.

Re:Graphics card? (1)

drinkypoo (153816) | more than 4 years ago | (#29404891)

Yes, that graphics card costs more than an Xbox 360 and might also draw more power than the whole system! Stupid objections make for stupid arguments, suggesting stupid people.

The ATI GPU in the Xbox 360 provides numerous important enhancements, primarily that shaders don't have to hit main memory. All you need for some portability is a shader language. There are numerous obvious advantages to just using the incredibly cheap and powerful Xbox 360. If only Microsoft didn't have every reason to try (in vain) to fight Linux, they might have offered us a Linux option, and I would have bought an Elite by now. (I wouldn't buy a used console, perhaps that is what the RROD is all about, killing the used market.) In particular the unified memory in the 360 makes it more appealing than the PS3, because it allows you to use it flexibly. The PS3's main memory is horribly anemic and prevents it from being a desktop replacement. It ends up more like a thin client with a fancy compute engine in it, which is retarded.

How many (1)

rbanffy (584143) | more than 4 years ago | (#29404883)

Given that:

- Microsoft subsidizes every XBox 360 system and makes an investment for every unit sold
- Microsoft only recoups that investment with game and accessory sales
- A supercomputer built on Xbox 360 nodes would not need any games or accessories

We can try to answer:
- How many nodes would a supercomputer need to completely suck the life out of Microsoft once and for all?
- How much that machine would be able to do?

Even if it is not make it to the top 500, just killing Microsoft is a worthy goal.

Planned obsolescence? (1)

lskovlund (469142) | more than 4 years ago | (#29405303)

And how long will it take before they need to redo their software all over again because Microsoft abandons the platform?

And this, Sony (1)

Trogre (513942) | more than 4 years ago | (#29407975)

... is what you'll be missing out on. All because you ostensibly couldn't pay someone to write a hypervisor driver for your new SKU. You would have been better off releasing the specs and having the community do it for you.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

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>