Slashdot Mirror
IBM Plans to Open the Cell Processor
morcheeba writes "According to an EETimes article, IBM is planning on releasing the full specifications and software libraries for the powerful processor that will be in the Playstation 3. The goal is to stimulate open-source development for other applications of the chip. The article doesn't mention if there will be some affordable development systems for all these programmers -- I'm hoping for a ps3 devkit." From the article: "IBM is eager to find other opportunities for Cell, but it's going to take a lot of software work...Going to the open-source community makes sense, because they could attract a lot of pretty smart programmers who could spin out software and applications for Cell."
is how does Sony feel about this?
I'll have it doing a lot more than just playing games in no time!
"Can there be a Klein bottle that is an efficient and effective beer pitcher?"
will it be able to run linux?
Holy crap! That's amazing. Now, is this "fully open" a la' "Shared Source" or "fully open" as in "you have the same docs we do?" And what's with the comment about hardware discounts?
-theGreater.I just realized this means both next-gen consoles and the GameCube all use IBM processors. Impressive. Now I hope they can hang on to the Mac market, and maybe both will benefit from advances in the other.
...f*ck yeah! Thanks IBM! :D
How is this different from every major processor's specification that is easily downloadable on the web. We're talking processors like Intel, PowerPC, etc.
When respoding to this message, please confirm you're not a script by typing the text shown in this image: [bvayigg/\/\<<<]
I guess if they encourage development outside of the Sony realm, they'd be fostering a 'Splinter Cell?'
Good thinking by IBM. Basically, get a lot of labor for free to make their chip popular. All that labor will surely make them more money as they sell the hardware and make money off the free labor.
IBM wants open source dev on cells like MS wants developers coding for Windows. It's an sales tool to convince manufacturers to source their parts.
Given that the only cell device is the PS3, and that sony would sooner slit their wrists than let users write their own code for it, we can only assume that IBM is hoping somebody else will pick up the cell for consumer devices.
From the article:
The trio is almost done with an application binary interface and language extensions for Cell. A system-level simulator is also nearly complete. Yet to come is a full-fledged Linux implementation for the CPU.
What other applications could Cell have besides the Playstation 3? What makes it special, and what applications is it best suited for?
This is just another indication that
IBM "gets" Open Source
IBM continues to be a major supporter of Open Source.
I still have to wonder about their intentions. Do Sony and IBM truly believe the Cell will be the replacement for Intel and AMD based chips?
Dollar Highway Financial News
Please correct me if I am wrong, but didn't IBM do the same thing with the x86 processors. If so would we be looking at the potential for another "IBM clone" situation thereby making cell the next x86 architecture?
Be careful when opening it, if you break it you have splinter cells all over the place.
Carbon based humanoid in training.
Unless mainstream systems start shipping, are we really going to see people using cell-based personal computers? If some affordable boards are developed then it would make sense to see alot of open source developed embedded solutions. After the demo of the cell processor some time ago decoding 17 video streams simultaneously, it should have some real potential for home/commercial media centers on embedded platforms.
Trackball users will be first against the wall.
The original IBM compatible standard (what we just call X86 nowadays) took off when Compaq reverse-engineered the BIOS and created the first "clone" of a "genuine" IBM PC. This undoubtedly resulted in explosive growth for Intel, who made the CPU. Now that IBM is manufacturing the chip (instead of Intel for the first IBM PC), it is absolutely in their best interest to make the Cell processor as mainstream as possible by opening up all of its specs.
Bill Clinton: Pimp we can believe in. - The Shirt!!!
Does anybody know anything about Java on these chips? I assume Linux will run, but how about a java runtime? Isn't that and example of where something like harmony would be useful just in case Sun didn't release a JRE for the cell?
... is when can I get a laptop with a cell processor?
GETPKG - Package Management for Slackware
... Linux on Playstation!
James P. Barrett
This could have a good plus side for many developers. One of the issues that I have been getting into lately is the open source appliance development. Previously I have been using xbox's and more recently the mac mini. One of the problems that I have had in developing software, tools and libaries is that I am often stuck with a lack of alternatives in hardware and performance. by having open plans for a high performance platform it will potentially give or open entirely new roads in development.
Got a question about UNIX ask it here : Unix/xBSD Forum
Good thinking, IBM. Now, let's get SML/NJ, Haskell, and O'Caml ported to these things.
"Why", you may wonder, but the answer is simple: Referential transparency or any kind of confinement of side-effects makes for easy parallelisation, which is what these Cell thingies are supposed to rock at.
This might be the one thing that will put FP back into the undergraduate curriculum.
-- Christoph
Sony must have given its approval for releasing this information. It could not happen without them.
If Sony did not know, and IBM made this move without their approval, I could see Sony NEVER buying from IBM again. That is too big a risk for IBM. Heck, most companies would think twice.
Will it be easier to make a mod chip if people know how the processor works? Or did Sony add their DRM elsewhere? Who knows. IBM is not releasing the blueprints for the Playstation 3, just the processor.
Sony is a big company that hires smart people. Maybe they figured out hiding the electronics will not prevent reverse engineering. Maybe the new PS3 has some technology that makes it difficult to mod.
Maybe this is like Microsofts WMV, it is unhackable, nobody can get it to play a stream if DRM v9 is enabled. Not one person on the planet. And it has been over a year now.
For the PS3, they don't need for their game machine to be unhackable forever, just until the PS4 comes out. :)
Rosco: "If brains were gunpowder, Enos couldn't blow his nose."
Makes sence to me, I've been iching to program some assembly hacks the second I first read about the CELLs PPE/SPE disign. I'd guess it'll take a lot of creativity to figure out ways of useing them to vectorize ordinary tasks, exactly the kind of challenge I'd love to play with, along with all those GNU Hurd people :o.
How long until somebody makes a Beowulf cluster of these?
BTW, whatever happened to Motorola. They were pretty big dogs about 10 years ago. Now they are just an after thought, they laid off over 10,000 people and are in a decline. They made good chips.
Rosco: "If brains were gunpowder, Enos couldn't blow his nose."
Luring in the real coders by offering those busy on writing codecs and multimedia and science stuff with a special offer PCI Express cards may help.
If we've got add-on card known to be capable of decoding ogg theora or dirac or playing complex animated VGG there might be a big linux market in the future. But nobody is going to buy this card without any useful software for it.
How would someone go about acquiring a CELL chip and other hardware required to run it? Sounds like a pretty big investment for the casual OS programmer.
Top 10 Reasons To Procrastinate
10.
Something this high-profile will help the business world see even more clearly the sheer, unadulterated power of Open Source.
I predict that the most innovative and enjoyable apps and games will come from developers who are working independently, on thier own, or in small groups, out of pure love of code. That is the way it has always been.
Technoli
Exactly what do the SPEs *do* in a timesharing OS such as Linux? Are the SPEs all parcelled out to processes on an individual basis, like normal processors would be? Are the SPEs attached to the same process as their corresponding normal-CPU PPC core, and the SPE's onboard memories just gets copied to main memory and then overwritten on every single context switch? Or what?
Irritable, left-wing and possibly humorous bumper stickers and t-shirts
Nice to see someone as important as IBM realising the importnace of open HARDWARE. I've found that until recently the concept has been overlooked or even derided. Even open software advocates didn't "get it" and said it could never work, becasue hardware is different--the argumant was that hardware isn't something individuals or small companies could influence becasue of the high cost of entry, and big companies needed to make money off licensing closed IP to fund development and production of new hardware.
This day and age, such an argument is complete BUNK. Hardware design is done on computers and chip specifications are more often than not specified in VHDL or Verilog--the "source code" of hardware if you will. Not only is design and simulation within the reach of even hobbyists, the end result is very similar to software in characteristics. While IBM is not completely opening things up to the point of showing the "source code" of the Cell processor, it is a great step to see all the specifications etc. without encumbrances.
Quite frankly I'm surprised the open source movement hasn't advocated open hardware much more vigourously. After experiences around NVidia and ATI and Intel you'd have to be a fool not to realise that open hardware isn't just an interesing idea, it is NEEDED for the success of open software.
Luring in the real coders by offering those busy on writing codecs and multimedia and science stuff with a special offer PCI Express card may help.
If we've got an add-on card known to be capable of decoding ogg theora or ogg dirac or playing complex animated SVG there might be a big linux market in the future. But nobody is going to buy this card without any useful software for it.
"We're not yet sure about the right licensing terms for the libraries. It can be hard to give stuff away for free," Kahle said...
Yeah? Since when?
This sig rocks the casbah.
Linux Insider is running a couple of editorials speculating about running Linux on the 'Cell'. The bold prediction? 'the Linux developer community will, virtually en masse, abandon the x86 in favor of the new machine.'
Why wouldn't Sony want IBM to do this. Since the platform specific game developer is going the way of the Dodo, how do you get an edge?
Perhaps by giving every anti-Microsoft fanatic video game freak an outlet? When licensed 3rd party support becomes even on both sides of the map, it will be consumer mods that make the difference to gamers. Can I mod chip it to play foreign games? Can I put vinyl kits on it? Can I use it to power my toaster?
Theoretically, one might be able to write some code that will allow you to play foreign games without having to void your warranty. How huge is that?
Also, Sony is going to need something extra to get people to buy it's system after a XBOX 360 Holiday season, and this may just be that.
Im not a lawyer and dont completely understand the GPL, but does this mean that since the processor specs and program libraries and the PS3 SDK will be GPL all the games the come out for the PS3 will have to be GPL? That would be cool.
But anyways kudos to IBM, by doing this they have just expanded their market by 10 fold and I'm sure it will work out for them. Hopefully if this works out, other processor companies, and all software companies will switch to OSS.
Good job IBM!
Well, if it has a power save mode, is it a Sleeper Cell?
500GB of disk, 5TB of transfer, $5.95/mo
Now if someone can just tell me:
1) When will the chip be available?
2) How much power will it disipate?
3) How much will it cost?
Then maybe I can design a product around it. Until then, it's vaporware for all practical intents and purposes.
I've abandoned my search for truth; now I'm just looking for some useful delusions.
It seems to me that this is a first step by IBM to try and move the Cell more into the foreground of computing i.e. to start transitioning computers over to start using Cell instead of x86. Going to the open source community with this project is the only feasible way to do this anymore, really. As much as big companies might like to, they will not be able to put in near the amount of effort or creativity that open source can provide.
As well, I think that moving to Cell would be a very positive step for the computer industry as a whole, helping it to get out of a rut that it seems to have fallen into. The benefits are enormous, the least of which is that if Cell starts becoming standard, average computing power of a desktop will skyrocket, allowing for brand new, highly computing intensive applications to be developed.
This has the sound of the next Slashdot Fortune Cookie in the making -- or should I say in the baking?
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
the cheaper it will be to produce for the long haul. I would think Sony would be in favor of that.
Except for ending slavery, the Nazis, communism, & securing American independence, war has never solved anything.
This setup looks a lot like the inverse of IBM's greatest strategic loss: the PC. That time, IBM had the brand, and sold hardware to a maverick niche market of PC hobbyists. They viewed software, including the OS, as a necessary sidelight, and let Microsoft judo them out of their control of the market revolution they created. IBM later lost $20B as their market failure came home to roost, and never recovered the leadership they squandered.
This time, IBM is the necessary part in the Playstation, which is in the hands of this generation's maverick niche market: gamers. Their Cell processors give them Microsoft's opportunity: base the market in the demanding niche, and market their product outside of it, leveraging their market feedback and brand into the larger market, including supplying competitors to the original platform. IBM is flipping the script: selling hardware means opening the software promotes their sales, inverting Microsoft's formula of taking software proprietary to capture more of the market defined by the hardware.
It all looks great on paper. Especially the greater scalability and persistence of open software, compared to Microsoft's centralized, proprietary approach. Time will tell if IBM can manage the opportunity, competing against Microsoft, as well as Microsoft did in the 1980s - and better than Microsoft will in the 2000s.
--
make install -not war
They're opening up the specs and associated software. Why TF does the processor need associated software, that's something I don't really understand.
Linux? Sure. The "PPE" portion of the Cell is a POWER64, which Linux already runs on. The "SPE" engines are effectively going to need their own kind of OS to manage them, but you could start with a mostly-user-space API and move it into the Linux kernel after people have figured out what that OS should really look like. This is all new stuff.
Looking at the CELL architecture overview, though, the Cell doesn't look to me like a desktop replacement. It looks like a video card replacement. Think about it: the biggest piece of closed-source, proprietary hardware in your PC right now is your video card, with its sekrit interfaces and binary-only drivers. We're already starting to see a movement towards more general-purpose use of that hardware with things like nVidia's Cg toolkit. The CELL is the logical next step in that direction. You'll have a video card that runs Linux (or, ideally, a video card that acts as just another (heterogeneous) processor in your system).
Couldn't a Cell-based processor be the basis for a completely open graphics chipset? How would it compare with the latest and greatest from NVidia or ATI?
Does this mean we're finally one step closer to playing video games on a mac?
Cell is a multipurpose system. It's main claim to fame is a low-level logic that allows it to farm tasks out to other Cells it connects to dynamically. One Cell is pretty potent and will likely be able to handle the needs of a typical HDTV so IBM hopes every TV, TiVo, and stereo system has a Cell.
. ars . ars
The cell system workload sharing system is apparently accessible through the general bus so it can theoretically farm tasks out to any Cell on the same network. So if you've got a WiFi network between your PS4, HDTV, TiVo, Stereo, and cell-powered PDA your video games (or PDA) could take advantage of those other devices' unused clock cycles.
Here's some A to RTF.
http://arstechnica.com/articles/paedia/cpu/cell-1
http://arstechnica.com/articles/paedia/cpu/cell-2
I've been on slashdot so long I'm starting to get out of touch with the cool stuff if it ain't on slashdot.
Who cares? Just stick that mofo in my P-P-P-Powerbook.
Don't mod me, bro'!!!!
"Each Cell contains 8 APUs. An APU is a self contained vector processor which acts independently from the others. They contain 128 X 128 bit registers, there are also 4 floating point units capable of 32 GigaFlops and 4 Integer units capable of 32 GOPS (Billions of Operations per Second). The APUs also include a small 128 Kilobyte local memory instead of a cache, there is also no virtual memory system used at runtime.
Independent processing The APUs are not coprocessors, they are complete independent processors in their own right. The PU sets them up with a software Cell and then "kicks" them into action. Once running the APU executes the apulet in the software Cell until it is complete or it is told to stop. The PU sets up the APUs using Remote Procedure calls, these are not sent sent directly to the APUs but rather sent via the DMAC which also performs any memory reads or writes required."
A bit complicated to understand, but you get the picture.
IMHO, aside from graphics rendering and video, stream processing, and DSP etc, I think it's got serious security potential because of the independence of these vector processors. I would expect it to be very usefull for secure processing. Let's face it - it's a bloody complicated platform!!! IT's gonna be good for security. The API for it alone would put many crackers off...
More here: http://www.blachford.info/computer/Cells/Cell3.htm l
I'll have it doing a lot more than just playing games in no time!
My first thought when reading this was, could this replace the Motorola 68XXX I used in college? It's more powerful, has multiple cores, but what it needs is accessories like a D/A A/D, serial port and several other things. If they could turn it into a microprocessor, it could really take off at the college level. And since they keep talking about having these in all sorts of embeded devices, that makes a lot of business sense too.
Fly me to the moon Let me sing among those stars Let me see what spring is like On jupiter and mars
IBM ditched their PC business days before they announced the CELL chip was shipping and given the fact that IBM claims the CELL can multiple OSes simultaneously and has 10 or so cores my guess is all you would need to do would be to write virtualizing software for the CELL and then run anything you want on top of that.
Because the CELLs got so much horsepower the user wouldn't notice a performance hit at all!
The CELL if it proves as capable a some claim could very well be an INTEL and more importantly a WINTEL killer.
I think APPLE isn't talking to INTEL about their chips but they are instead talking to IBM about the CELL.
Computing is about to change, in a huge way. IBM's backing of Linux isn't for no good reason. Cell is the reason. IBM is going to take it all back. Watch and wait, it will be incredible.
Now wait, this is business as usual. Pick just about any processor (ARM,
PowerPC, x86, MIPS, you name it) and you can download detailed specs, both for
the programming model and the hardware details. Honestly, I can't think of a
CPU that this hasn't been true for. Maybe with the general closedness
of GPUs people are forgetting this.
People have already been clustering PS2's so clustering is an obvious place that PS3 would be immediately useful. It would be especially useful if it could be booted off a livecd that would allow automatic scaling of the cluster like openmosix, but that ability is not likely without a mod chip, which would make clustering impossible through stock hardware. Unless, of course, somebody legally got ahold of a PS3 dev kit and... well, the possibilities run wild. At any rate, clustering would be a perfect use for PS3's.
How can this be modded insightful? Somebody clearly didn't get the joke...
will it run OS/2?
How would someone go about acquiring a Cell chip and other hardware required to run it, with a fully documented bootloader?
This is offtopic but the idea that Apple and Intel may join forces (I feel) is linked to the IBM's processors being in all of the next generation game systems. I don't think Apple went to Intel, I think it is the other way around Intel went to Apple. The result could be "some" very affordable Apple systems being built around Intel running OS X ... to take it even further perhaps an "open" architecture could then be released upon the market?
Wonder when the roumors about a new Amiga running on a Cell processor gets out? :)
#1 Assuming they're going with the classic console business plan, Sony isn't making any money by selling PS3's, they're making money by licensing and selling games. Opening the hardware is a good first step towards modding the PS3 and of course Sony doesn't want that.
#2 It's not going to be an Xbox killer if IBM opens up the architecture for the Chip that's running in the Xbox 360. I see a lot of talk about Sony in this thread, but the Xbox 360 also runs the Cell CPU so all speculation could be equally switched from Sony to Microsoft. IBM isn't opening anything that's console specific here. That would be like assuming you'd be able to tweak out your Honda because it has a certain brand of tires while ignoring the fact that the same brand of tires are on Toyota's too.
The original story on the PS3 like a year or two ago was running Linux. Can't find it now. Looked like a server box.
I wonder if China is going to rip IBM off and make a clone of the Cell processor -- DragonCell or something. How could IBM even think of stopping China?
I've got my own project on there, in a bid to develop a totally parallel OO-based processor, but not had much time to work on that recently.
Those interested in Open Hardware should visit this and similar sites, to see what is happening out there, whether or not they believe the idea could work in practice. Why? Because it is an excellent source of ideas, and ideas are what keep all the IT markets moving.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
That's what Sony thought - but they found it's just not as good as a regular video card is. That's why the PS3 has an nvidia chip instead of a second Cell, as they originally planned.
Which is of course quite funny because Sony opted to use a dedicated GPU instead of the Cell for rendering the graphics.
Justice is the sheep getting arrested while an impartial judge declares the vote void.
That might clue people into the fact that the Phantom Game Console runs Duke Nukem Forever on AmigaOS.
I have an interesting sugestion for IBM:
IBM should release a version of the Cell on a PCI or faster BUS card, or even some sort of crazy processer adapter thingy that one can buy so that Open source programers/users or other interested parties can start using the Cell right away.
The [3D rendering/complex math/video encoding] crowd would love a $200 card that they could just plug in to speed up their rendering buy a factor of 10x.
"Going to the open-source community makes sense, because they could attract a lot of pretty smart programmers"
hahaha, do you really believe all the smart programmers give a shit about open source or working for free?
We're all out to generate money and make a living, not be a slob like linus or esr.
They can do a lot more than allow Cell processor development. PS3 is a closed system on purpose. They design their software to be region-specific. This isn't going to change that. They could change the region codes simply by eliminating them, as they did on the early PS2's (by accident). What you suggest isn't the rationale for this move. The rational is home servers and selling more Cells, to help cover development costs.
#1 - I partially agree. The reason Sony and other game companies try to keep games localized is so that they may target the games content for the region. If I order a game from Japan, it's not localized, but did go through the SEOJ process. The license has already been paid, the game was made, printed, and packaged. So their business model would still be intact.
#2 - While it's true that the XBOX does use the same processor as the PS3, there is a cultural difference between your typical Open Source guy and general tech guy. An open source guy is most likely driven to purchase anything NOT Microsoft (PS3), if the tool can do what they need it to do. This person is also more likely to develop applications that have some use, not just "Hello World." Not knocking Windows programmers, but your average 15 year old kid who can mod his XBOX is only going to try and write a virus in MHO.
XBox 360 uses a PPC chip, NOT a Cell chip. The chip in the 360 is more akin to a chip found in a Power Mac than the Cell chip found in a PS3.
So IBM fires 10k employees in Europe, opens their specs, and uses the OSS community to bolster the success of their new cell architecture. Yep, sounds like a new business model to me.
If IBM partnered with Ubuntu to develop a full-fledged linux desktop / media pc machine using the cell processor, desktop linux could finally reach maturity.
Or Dragonball Z?
(1) Port GCC to it, optionally another much more optimized compiler that is compatible with gcc.
(2) Give it to taiwanese motherboard makers to make microatx mobos on the cheap. Aim for $40 for lower speed ones and $100 for full speed Cells.
(3) Put out all the specs of the Cell and any possible firmware sources online, and put them under the BSD license.
(4) Provide licenses to other devleopers to make cheaper versions of the Cell.
(5) Watch Linux and NetBSD grow on it. Watch cisco use it on their high-throughput routers and other manufacturers use it. Watch the app base grow.
(6) Profit!
Alternatively sit on it and let it rot like Palm is doing with BeOS.
"Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
Hmmm... perhaps this and the ever recurring "Apple is going Intel" are related. Probably just my natural paranoia.
NO IT DOESN'T! It uses a bog-standard PPC chip, not a Cell.
TWW
"Encyclopedia" is to "Wikipedia" what "Library" is to "Some people at a bus stop"
The only area I could ever see Apple and Intel working together, would be a PDA type device, something that would benefit from a XScale.
? entry_id=1111006
OSX needs a PowerPC, an Intel version would break all software compatibility and require new development. Something that Apple would not do, not even for a low-cost option. This is why Apple's Mini uses a G4. If Apple wanted to commit suicie, they would siwtch to a X86 processor.
All of Apple's products are invested too heavily into Altivec, something that is not available with Intel's chips. This SIMD was co-developed by IBM, Motorola, and Apple. It's why Macs have such a huge performance advantage over PCs when it comes to things like encoding video. It's even used to assist in OSX's GUI acceleration along side the GPU. Even iTunes uses it.
Besides, Intel's desktop/workstation chips are not RISC, nor do the majority of their chips support 64-bit VM addressing, a feature that is available for the PowerPC, and is supported by Tiger. The only Intel option is an Itanium 2, an expensive pokey processor, that has been trumped by all other 64-bit options, including the G5 of course.
http://wiredblogs.tripod.com/cultofmac/index.blog
I can't help but wonder if this is directly related to IBM's decision to sell their PC business to Lenovo. IBM has watched counless Linux geeks mod the XBox and install their OS of choice. If it were to take off like wildfire, this kind of modding would be potentially dangerous to the traditional OEM PC market, because it would mean that cheap (like $199) machines that can be made to run a powerful OS and do things like MythTV and the like could subvert the normal PC market. Sure, the market for modded Xboxen is small, and confined to hobbyists, but if the architecture were open and you didn't have to mod it, a lot more people would do it.
Of course if you aren't an OEM, this looks much less terrifying. In fact, it starts looking more and more like an opportunity. So a company like IBM can sell its money-losing OEM business and get into the game system market with no worries about what happens to x86 if the new consoles start to hurt the PC.
Maybe they weren't thinking "Let's get rid of this money-losing PC business." Maybe they were thinking "Let's kill x86 by building a cheaper PC market on another architecture, staring with a console, but expanding into other appliances. We'll open it up so that people get interested, Linux will be running on it in no time, new Linksys and Netgear routers will use it, and then on to other appliances we haven't even imagined yet. It'll find its way into PCs, and PCs will suddenly be as cheap as a console. Come to think of it, before we do any of this, let's schedule a meeting with Lenovo ... suckers."
It's like deja vu all over again from 12 years ago.
This time it's got even less likelyhood of succeeeding.
Anyone remember OS/2 for PowerPC and the 615?
Wake me when I can buy it at fry's.
This will definitely help adoption of the new processor. No doubt a linux kernel built for it will show up in good time. Plus I'm sure someone will build an x86 emulator for it to soften the move. Way to go IBM.
x86 has benefited a lot from being open, and has help train numerous programmers their trade.
im sure opening the cell will really offer an advantage for ibm.
What else is out there anyway? The main contenders are PPC and Intel. Both Intel and AMD produce x86/64 chips only. Sure everyone also produces arm/strongarm chips, but theyre still weak, the fastest strongarm from Intel is used on higher end PDAs.
Whats left is MIPS, Ultrasparc, PA-RISC, Alpha and special purpose FPGA chips.
MIPS is dead. SGI was producing servers on Itanium which also died.
Ultrasparc is dying in favor of x64. Sun guards its IP jealously. Low throughput but high floating and thread performance.
PA-RISC gives the best bang for the MHz. Good float, everything else runs too hot for now. Old old architecture.
Alpha was killed by HP. They'll try to sell you Itanium or PARISC before they sell you an Alpha. Development on it has completely stopped since 21264c. And I mean COMPLETELY.
FPGA chips are less efficient, and better use an ARM than an fpga chip.
So the two champions are PPC (and its derivative, Cell) and x86/x64.
Architecturally, PPC, and a 64-bit-only x64 are efficient. But IBM has been trying to push PPC in the market, working hard on a grand plan to take the market dominance away from x86. Look at all their offerings for Linux on PPC. They're prepping up this combination against wintel... and any usage of PPC means profits for them and Motorola, mostly to IBM in the higher end.
The choice is rather easy. If you will not use an IBM chip for a higher-end game console, what will you choose?
"Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
Seeing how console devkits are traditionally priced in the low to medium five-figure amounts, I don't think an affordable PS3 devkit is anything I'd hold my breath for.
Going to the open-source community makes sense, because....
they will work for nothing!
Open the specs for Cell! now I can build my own Red Ribbon Army! with the best Android they ever built!
Well Android 18 was something else, but I digress, Cell incoperates android 18 to power up, so now I need soneone to open the specs on android 18!.
PS: don't let Gohan near my perfect android!
god damn it i hate slicing onion!
No, for real. I'm very happy about this. That's just what i dreamed last night!
Oh, wait, IBM stole my intellectual property.. Gimme a sec.
It would be very interesting to see if anyone could design a new brand of PC around this core chip and how that would work out...?
Would make it more accessable to the average joe to play with.
---- Booth was a patriot ----
Can the APU run a kind of hypervisor and coordinate Linux running on the SPUs?
I keep reading the APU is a rather dumb PowerPC and all the heavy lifting is done within SPUspace.
http://www.dieblinkenlights.com
...Cell yes!
It's unlikely that people would abandon the PC architecture for Cell. They would have to make cheap machines that were much more powerful than the others in order to overcome the x86 inertia. In particular x86 are commodity parts with multiple suppliers, they advance quickly, and proprietary drivers are slow to move off(nvidia, ati, broadcom, etc), proprietary applications are a nuisance to get on unusual platforms (java, WINE, flash, etc). The platform would have to be much more amazing for these problems to be overcome.
Michael
Sorry, I didn't check my references properly.
I am preparing to commit seppuku right now.
Not video. Well, maybe. I view the Cell more as a multimedia processor for real-time processing of audio and video. I can envision playing a flight simulator or first-person shooter with streaming video and audio.
The Garda'll be after you, killing yerself's illegal, you know.
TWW
"Encyclopedia" is to "Wikipedia" what "Library" is to "Some people at a bus stop"
You're right. I was mistaken in thinking that the Xbox 360 uses a Cell.
Obviously you're too stupid too realize just how funny what you wrote is.
Retard...
upon reading the actual article, it seems pretty clear that right now the only place you'll find the cell is inside a ps3, "The IBM Corp. fellow who led the design team said his company currently has no plans to make Cell-based chips for its own systems or for the merchant market." at least thats what i get from the article.. and they arent making it for the market... so why does it matter whether its open or not, why / how am i going to develeop anything for the cell processor if i dont have a system thats using it? and if the market isnt going to be using it? i dunno it seems to me like a lot of the open source development going on in the open source community is being done on peoples own machines, part of the reason it happens if you ask me, people right things which will be of use to them and release them to share with others etc.. so if the only way to get a "cell" is to get one custom built and designed for you, who gives a crap if its "open" if someone builds you a custom processor and wont give you the details of how it works why in the world would you buy it? and if no one else has it without getting it custom built again, why would i want to write anything on it? i must be missing something
"Jazz isn't dead, it just smells funny" ~Frank Zappa
EdelFactor
It's up to the programmer to determine how SPE's will be used.. They can appear as individual cores, or just a single cpu.
In a normal OS like Linux the OS would not see the Cells as individual proccessor core.
The OS will see the entire Cell, powerPC core and SPE's, as 2 cpus. (It will see 2 cpus instead of just one because the Cell will support IBM's version of 'hyperthreading', which pre-dates Intel's by a few years, btw)
So to Linux it will appear to be just a semi-normal PowerPC core with Altivec AND a additional 128 registers extra.
The SPEs will be used like extra instructions like MMX, or Altivec, or 3DNow! or anything like that... However instead of just being multi-media specific it will be a able to run floating point calculations very fast.
Also keep in mind that the SPE's are not _just_ floating point, they can calculate other data types like integers and double integers and such.. it's just floating point is what they are best at.
So then it's up to the compiler to produce optimized code to use the extra registers that the Cell provides over a normal PPC + Altivec cpu like the Power970.
It's similar how you can optimize code on a x86 to use MMX multimedia instructions.
So you won't see HUGE performance increases over normal PowerPC and x86 cores. In fact most code will run quite a bit slower since the PPC/Altivec stuff in the Cell is very stripped down... HOWEVER the important stuff such as 3d graphics, sound, multimedia etc will have considurable increase in performance.
Also this is very nice for low-power setups.. since each SPE can be individually turned off you not only have MHZ scaling possible, but also can reduce the number of cores you have to power to conserve electricity, which is why Toshiba likes it.
You probably won't see it very much in workstations or desktops unless Linux takes off in a big way, or OS X is ported to it (don't hold your breath). What it would be good in is very low power setups like handhelds, phones, miniture laptops, whatever.
It would be GREAT though if Sony released a 'developement' package for Linux for PS3 like they did with PS2.
I would kick the Mac Mini's ass. It would be the perfect multimedia linux PC for your living room.
You obviously don't know much about virtual machines. :)
Or else you forgot about the JIT. You did forget about the JIT, didn't you? You know, the run-time compiler that generates machine code for your Java methods after you execute them a few times?
I don't think Sun has a JIT for PPC (they have one for x86 and probably Sparc).
Ooooh. Touched a nerve, there, didn't ya? Don't forget the multiple desktops!
"A language that doesn't affect the way you think about programming, is not worth knowing" - Alan Perlis
I B M, F*** Yeah!
Savin the world from the mutha F***in day Yeah!
I B M, F*** Yeah!
Intel, M$ your day is through
The Cell is what you're answerin' to
I B M, F*** Yeah!
So lick my dongle and suck on my RAM
I B M, F*** Yeah!
Now I want an Cell-powered ATX (and/or miniATX) motherboard. C'mon IBM, that would be sweet.
And of course if it ever happens, I hope they'll be cheap enough to justify buying one for non-serious uses. Seriously, PowerPC ATX motherboards (ie. Pegasos) are way too expensive.
#2 Wrong. The 360 uses a 3 core PowerPC. The cell is very different. That's why 300 posters before you failed to bring that point up.
"A language that doesn't affect the way you think about programming, is not worth knowing" - Alan Perlis
If you don't mind, I think I've read about functional programming 15+ years ago in Dr. Dobbs (I'll have to look it up in my archives).
Refresh my memory please. How does
sum [1....10]
translate into better performance over OOP or procedural languages using CELLs or even multi-proccessor systems? You still have to increment the result by one don't you? Or does the processor increment all the cells by one and then return the final result?
How does the compiler translate different data types? For instance, (monthday being an integer):
sum [monthday1....monthday30] / 0.019
Is there a decent Primer for functional compilers/programming available?
Just curious,
thanks for the info.
Enjoy,
It's just the normal noises in here.
Yes, Intel and AMD publish info on their processors--this is exacly why they are successful. There have been proprietary processors in the past as well. They are not common knowledge because they were big flops. The IBM PC model 5150 that spawned the architecture we use today was NOT the first PC that IBM made--that honour goes to the IBM model 5100. Why was it a complete flop? Well, IBM did NOT release detailed specs for the processor of the 5100, or any of the hardware for that matter. They kept the instruction set and everything secret! Non-IBMers could only program it in high-level languages!
FYI open SOFTWARE isn't very new either--in the early days where computing was a more purely scientific/academic endeavour coders tended to share their code with relatively few restrictions. When computers became popular and commercial software got proprietary--the GNU movement was actually reactionary in a sense--a desire to return to the early days of true sharing and collaberation.
There appears to be an analogue situation happening with PC hardware. In the 70s there was little effort put into protecting designs--Intel and AMD are just following that legacy with their CPUs. The Homebrew club members proudly showed off their clever designs. Computers even came with schematic drawings (even pre assembled ones)! By the 80s hardware vendors started going down the proprietary path (encrypted Atari7800 cartriges, The Macintosh, IBM's MCA bus, etc) until we have absurdities like ATI and NVidia GPUs, "soft" modems and wireless chipsets and so on that you cannot make work without proprietary information.
Open ANYTHING isn't new...it's just the relisation that success of an idea is ultimately limited or impossible in an environment that is too closed.
Oh, and you might not want to talk about FPGAs becasue they're "uncompetitive"--that is not the point--I personally HAVE obtained HDL code and configured an FPGA and "RAN" that code for far less than $1000. Could a pre-fabbed ASIC be obtained cheaper? absolutely...probably for one tenth the cost and far less trouble...but it is unmodifiable. I can take a RISC CPU core and other bits and pieces and make my own customised design for next to nothing...almost as easily as making custom software apps. The arguments about TCO of MS vs GNU are continually shot down for software--the same can be said about hardware...there are far more important benefits to open-ness than just the cost factor once you've achieved a certain critical barrier-to-entry.
"This is a million times worse than the old Pentium 3 CPU-IDs."
Piracy payback is a bitch.
AFAIK Sony tried very hard to declare the Playstation 2 as a computer in the EU so that they did not face the Tax For Toys. In this light, it makes very much sense for Sony as well as for IBM to open the Cell for as many developers as possible.
BTW, this announcement nicely agrees with the predictions from the first articles on Slashdot about the Cell, namely that it is posed to take over the world.
-----
a signature is what declares the argument types of a function
The SPE's will only be much use if you're doing number crunching, since the SPE's are vector units (floating point processors). So I'm thinking the PowerPC core will be the only part that'd get much use running Linux.
Having said that, there's been talk about support for multiple OS's at the same time...
"This is your life, and it's ending one minute at a time."
Obviously A Mac Fanatic? or Apple Heathen??
Might Apple Apple consider migrating Mac to the Cell architecture? Cell's phenomenal media processing capabilities seem to fit Apple's niche market well, while the Cell core is still PPC. Is the core general purpose enough to run a desktop or server OS like OS X? Their relationship with IBM, their current use of IBM's PPC architecture, this news or IBM's opening of the Cell, plus the media processing advantage that Cell would give the Mac platform, all seem to suggest this is something Apple should seriously consider.
Flying is easy, just throw yourself at the ground and miss. -Douglas Adams
In general it doesn't seem obvious how you'd use an SPU in a traditional manner, however it seems like SPUs might offer a great opportunity with regard to X11. All in all it's not too big a leap from how I imagine SPUs will be used in the PS3.
An SPU implemenntation would have direct access to the video hardware, would mean no need to context switch on the main CPU, and would be able to leverage lots of FPU/ALU power for accelerating complex compositing operations and SVG.
There it is! IBM knows there's exactly zero chance of MS supporting the PowerPC line - they've committed to the 64-bit offerings from AMD and Intel. Linux support the PowerPC quite well, so pushing people to use Linux is not only good advice for the customer, it's good advice for IBM. They get to sell you something they made entirely again - the whole widget.
Selling people a Windows box nets them the support money, and that's it. With PPC Linux, they get the income for manufacruting the hardware and perhaps the software running on it.
As you said, too, moving to another supplier is difficult, as Freescale (Motorola) has shown little ability or interest to make high-performance CPUs.
± 29 dB
Once IBM releases the full specs of the Cell chip, it would be a lot easier to manufacture mod chips for the PS3, instead of trying to reverse engineer it, allowing people to use copy DVD's/Blue ray disks.
Even so, the Linux community might prefer it over a non-documented graphics chip that only works with closed source drivers.
Assuming there will be something like a Cell workstation, its Linux graphics drivers might do their calculations in the SPEs and use a cheap framebuffer card.
C - the footgun of programming languages
"Opening Processor" should mean releasing sources VHDL/Verilog/Whatever for that stupid processor, not just giving away it's datasheet.
It's just a cheap promotion for this crappy chip.
BTW, it still bothers me -- isn't The Super Cell a very very weak and cheap ASIC'ed deign made on Xilinx Virtex4 FPGA? Because it seems very the same - PowerPC controls hardware processing conveyors. So it's just an unflexible, hardware-locked, serial-number and DRM-featuring parody for FPGA based computer.
And while we're at it, use one or more SPEs to run OpenGL as well ... after all, it's a streamed state machine, exactly the right sort of candidate for implementation on SPEs.