PS3 Linux Now Installable

Quinton writes "Around midnight Pacific time on the 17th, Sony updated their Open Platform website needed to install PPC Linux on the PS3. The FTP Site contains the CELL Linux ADDON CD image, which has the bootloader (kboot/otheros.bld) and instructions needed to install Fedora Core 5, PPC. A full install from DVD takes about two hours. Most all hardware is supported except for graphics accelerator support (framebuffer only, up to 1920x1200)."

Comments

neato

[undercanopy]

does it come beowulf ready?

nothing like a cluster of $10,000 nodes..

Re:neato

[Anonymous Coward]

does it come beowulf ready?

Well, that would leave nothing to the imagination.

PowerPC?

[Constantine XVI]

Did they say they were running standard PowerPC Linux on the PS3? In theory, what would stop us (besides Apple's legal dept.) putting the PowerPC Mac OSX on it?

Re:PowerPC?

[Anonymous Coward]

In theory, what would stop us (besides Apple's legal dept.) putting the PowerPC Mac OSX on it?

The same thing that prevented people from installing the PPC OS X on any other non-Apple PPC hardware. Namely, lack of support for the hardware itself. (Hint: just because the code is compiled to a specific processor doesn't mean that it automatically has hardware support for all of the other various chipset components--it just means it knows how to talk to the processor.)

Re:PowerPC?

[undercanopy]

I imagine you'd have a shot at porting darwin to it, but even before we talk about whatever kernel changes they had to make to run PPC linux on the Cell, you can bet that the drivers for basically everything else about the mahcine are non-existent in OSX.

However, my money is that even if the hardware drivers were there, they used a quite hacked-kernel to make it work on Cell... good luck getting apple to cross-compile for you.

Re:PowerPC?

[chasingporsches]

it'd be easier to just do Mac-on-linux instead

http://www.maconlinux.org/

Re:PowerPC?

[Anonymous Coward]

Short Answer: Binary format (it's cell, not PowerPC), bootloader and drivers.

Re:PowerPC?

[drinkypoo]

Short Answer: Binary format (it's cell, not PowerPC), bootloader and drivers.

Too bad you're wrong about that binary format. The Cell's PPE is a PowerPC; the SPEs are the cell execution units.

Well, you might be right, but just not because it's not PowerPC, because it is PowerPC; however, AFAIK it's a somewhat stripped PPC. It's certainly no G4, let alone G5.

Almost

[androvsky]

There's a hypervisor running between the kernel and the hardware, so I don't think it's going to be an easy task to hack the nvidia ppc macintosh drivers to run on this thing. I got the impression from the documentation that the accelerator was pretty much locked off, but even if it wasn't, we're pretty much stuck waiting for nvidia to cough up a binary driver blob. Unless someone wants to port opengl to the cell spus. It couldn't be nearly as fast as the nvidia chip, geforce3 territory at best, but it could support any kind of shaders you throw at it.

Re:Almost

[Anonymous Coward]

Sony won't boot a non-approved OS so don't hold out hope for a Linux that uses the RSX. Besides, you're not missing much. The RSX is a severely cut down nv40-based chip. As people are just now finding out, it has no scaler and no video acceleration (as in "PureVideo"). It is just a vertex shading pipeline and a very simplified pixel shading pipeline. Sony expected people to do all their pixel effects on the Cell, but that isn't working out too well which is why people are noticing fullscreen effects looking worse on PS3 versions of games like NFS:Carbon. Sigh. It's the PS2 all over again. Lots of raw processing power that is wasted because it is crippled by an underpowered, feature-poor rasterizer. It's like Sony couldn't create a balanced hardware design to save its life.

Re:Almost

[Wesley Felter]

Sony won't boot a non-approved OS so don't hold out hope for a Linux that uses the RSX.

The PS3 will boot any OS, but it runs under the hypervisor.

Re:Almost

[Daniel Phillips]

It is just a vertex shading pipeline and a very simplified pixel shading pipeline. Sony expected people to do all their pixel effects on the Cell, but that isn't working out too well which is why people are noticing fullscreen effects looking worse on PS3 versions of games like NFS:Carbon.

All you have noticed is that a highly optimized renderer isn't in service on day one, big surprise. As far as pixel shaders and vertex shaders go, you have got your FUD garbled. The RSX has on-board pixel shaders, and vertex shading is done by the Cells' SPE units. This approach pipelines well and looks perfectly elegant to me.

As I understand it, the Unreal engine is optimized for the Cell+RSX combo and Sony will sublicense it to any PS3 developer. I do not think we have seen a PS3 game yet that uses the Unreal engine, please correct me if I'm wrong.

Re:Almost

[EnglishTim]

It's a shame that th parent post got modded up, as it's almost completely incorrect.

Yeah

[eightball01]

But does it run... oh wait... it does!

Re:Yeah

[MS-06FZ]

Heh, that's a good one. But here's one you may not have thought of: does it run Linux?

Re:Yeah

[Carlio]

I for one welcome our new Linux-running PS3 overlords.

Re:Yeah

[Jesterboy]

I guess we have to get something geekier now that Linux has become mainstream.

"Yeah, but does it run BSD?"; a new Slashdot meme is born!

Re:Yeah

[ipooptoomuch]

I predict that this will end up the same way as DVD+R and -R. All companies that support it WILL NOT give up because there has already been large amounts of money put into it and abandoning it would not be good for the companies. Even if it is at the detriment for all consumers (how would you like to buy both an HDDVD and BLURAY player?)

Re:Yeah

[Xymor]

Now you can play 20 year old games without paying nintendo a dime. http://www.youtube.com/watch?v=GIWwcGCI_nY&eurl

Cool

[Foofoobar]

This and the cell processor were the major reasons why I was looking forward to the PS3. Blu-ray and HD-dvd still have to fight it out and it doesn't look like it's going to end quickly

Re:Cool

[Anonymous Coward]

It ended when the PS3 sold 400,000 units in the past few days.

Re:cool

[bcmm]

PSP anyone?

How long before they accidentally break Linux in an "update" then?

(Just poking fun. I think it's cool, if it really works.)

Re:Cool

[Raenex]

[The Blu-ray vs HD-DVD battle] ended when the PS3 sold 400,000 units in the past few days.

Umm, there are 100s of millions of DVD players out there. Nobody doubts Sony will sell a few million PS3s. The big question is how fast and how much they will go beyond that.

There's a good chance that nobody wins the war, and players end up supporting both.

Most except...

[Odin_Tiger]

"Most all hardware is supported except for graphics accelerator support (framebuffer only, up to 1920x1200)."

So...everything but the thing that makes the machine be what it is? That's great. At least you can play nethack...

Re:Most except...

[thatguywhoiam]

So...everything but the thing that makes the machine be what it is? That's great. At least you can play nethack...

Its all about gameplay man, all about gameplay.

(Or wait.. its Friday. Do we like high resolution graphics again today on Slahdot? I forget.)

Re:Most except...

[Anonymous Coward]

I hate Sony but be fair ... you get the Cell to play with. 6 SIMD cores at 3.2GHz plus a dual-threaded PPC. Should make any geek's day.

That is, I assume they haven't locked off the SPUs too ... can anyone confirm?

Re:Most except...

[Anonymous Coward]

You have access to the SPUs. There's a filesystem interface for getting at their memory, dma state, mailboxes (spufs) and a higher level library on top of that (libspe).

-Q

Re:Most except...

[hr.wien]

The Cell PPE is a dual issue, dual threaded, in-order core, which means it ain't all that. A normal G4 would probably kill it. Yellow Dog Linux on the Cell only runs on the PPE (leveraging the other cores would take some heavy re-engineering of just about every piece of software in it), so I think it's safe to say the PS3 Linux experience won't be anything special either. Fun to play with, sure, but certainly no speed demon.

Re:Most except...

[Short Circuit]

Mod Parent Informative.

My interest in the PS3 just rose a couple notches up to "Maybe with my next Job" from "Like I'd ever have enough money."

Re:Most except...

[petermgreen]

i could be wrong but i belive sony's intention is that for gaming you would buy PS3 games and for other stuff you would use linux.

i suspect if they hadn't crippled the possibility of gaming under PS3 linux it would have severely pissed off the official game developers and those developers are the lifeblood of any console manufacturer (both from a financial point of view and the fact that your console will fail if it doesn't have a good selection of games availible for purchase)

Jeez

[TodMinuit]

First a reduce number of launch titles and now this. Sony really knows how to suck the fun out of a console.

chirp chirp

[anti-human 1]

I'm pretty sure that's the sound of no one caring... There are far more interesting things you could be doing with PPC hardware, like playing Aleph One. or EV Nova. Both of these can be done for a lot less than $5/600.

Re:chirp chirp

[RichardMarks]

Yeah, no one is clearly caring in these huge threads just a sampling of two console related sites:

http://www.neogaf.com/forum/showthread.php?t=12424 2

http://www.neogaf.com/forum/showthread.php?t=12943 7

http://www.beyond3d.com/forum/showthread.php?t=355 90

Re:chirp chirp

[Anonymous Coward]

Oh Dr Marks, you know as well as I do that Linux on PS3 is just a gimmick. With no GPU access, you're doing CPU rendering of the entire GUI ... using a PPC that doesn't have instruction reordering. Your customers can't do any interesting visualization stuff; people will have to write PS3-specific codec ports (I mean, port the things to the SPU architecture) to decode video on it; and isn't the audio on the GPU too, so no sound? A games/media machine with a version of Linux that can't do games or media. What a coup. Microsoft must be quaking in their boots.

Of course people will still figure out how to hack it without Sony's support, but it'll probably require a mod-chip. Can you sue people for making mod-chips that merely unlock the GPU under Linux? I suspect not.

But

[Kuku_monroe]

Does it run hurd?

cool

[treak007]

Its really cool that Sony is recognizing that people want to have a full OS on their gaming console, unlike M$ who locked their console down to prevent people from doing just that. This also allows people to justify spending more money for the ps3, as it can be used as a computer/gaming console.

This is encouraging news.

[LogicHoleFlaw]

Honestly, this is pretty cool. I'd love to get a PS3 to play around with the Cell processor. This is really a new thing - far from discouraging homebrew hacking on their system, Sony is making it possible to install a full-blown Linux system on *launch day*. The hardware in the system is all standard stuff so everything should Just Work. I imagine that the community will have the custom graphics processor up and running in no time. If I understand correctly, the seven Cell cores are already supported by Linux due to IBM's desire to have the Cell architecture be used in more than just PS3s. It's just the custom graphics chipset which needs to have drivers written.

I can understand why Sony hasn't written such drivers - it looks like they've architected the system to be easy to install alternative OSes, but they haven't gone out of their way to write code for a particular 3rd party OS vendor. I look forward to seeing where this all goes.

Re:This is encouraging news.

[crossmr]

Why do people like the cell processor? Its only here to make games shiny, but crappy:
http://crystaltips.typepad.com/wonderland/2005/03/ burn_the_house_.html

Re:This is encouraging news.

[drinkypoo]

This is really a new thing - far from discouraging homebrew hacking on their system, Sony is making it possible to install a full-blown Linux system on *launch day*.

Rumors of the PS2 Linux kit circulated before the PS2 release and I think they may have even been confirmed before launch day. It took a while for the kit to come out, but come out it did - and it had the same flaw THIS kit does, which is to say a lack of graphics support.

In other words, this is not really a credible attempt to deliver Linux on PS3 to the masses. The only people who will find this useful are people who want to dump data to the cell for processing. It will be great for clusters, but only when each system needs little memory as they only have 256MB and due to the system's architecture it may be exceptionally arduous to add more without breaking compatibility.

Re:This is encouraging news.

[SScorpio]

Would you care to reference somewhere that states you can't access the graphics with PS2 Linux? It seemed to run OpenGL just fine to me. By default you didn't have direct access to the graphics hardware, but you weren't forced to just use a frame buffer like you currently are with the PS3; however, I'm sure Nvidia with fix that.

Re:This is encouraging news.

[TerranFury]

>Why do people like the cell processor?

It's not about the games. It's more important than that: The Cell points in the direction in which we can expect all computing to move. The Cell has a lot of hype which should be taken with your-daily-recommended-value-of-sodium-chloride, but I think it's true that it represents a legitimate effort by a company to put R&D into a new architecture designed around multiple cores. That matters.

Up front: A gaming machine might be the wrong application for the Cell. A lot of the buzz surrounding the Cell actually has to do with using the processors for scientific computation: The supercomputing market. I'm sure IBM et al didn't design the Cell with that in mind, since it's only a 32-bit chip (and serious scientific computation tends to require more precision than that), but I've heard rumors of a new 64-bit Cell (if IBM didn't scrap that project when they gutted their PowerPC/microprocessor teams of late).

But the Cell represents an important direction in processor design because, frankly, it looks like we can't make the chips much faster: We're already switching logic at microwave frequencies! It used to be that we could keep making transistors smaller and smaller and they'd get faster and faster -- but now, scaling is bottoming out: oxide thicknesses are 4 atoms! Since we can't push the transistors much more (I'm not counting on finFETs to save the day), we need to start paying attention to the architecture. I'm glad that someone is doing something a little innovative.

And you know: Maybe it's ok for games too. It was always my fantasy to do realtime raytracing. How about radiosity or photon mapping at interactive framerates? Those algorithms parallelize pretty well! ;-)

Re:This is encouraging news.

[drinkypoo]

Sorry, it's the DVD drive you couldn't use at all. You can use the graphics hardware in a crippled fashion using OpenGL as you say. So far the PS3 has neither, although perhaps you can use the optical drive, certainly I haven't read anywhere that you can't.

Re:This is encouraging news.

[crossmr]

It might be okay in games where artificial intelligence isn't attempted at all. Multiplayer games with no bots or enemies, or parlour games. For any game that should make use of artificial intelligence though its not good, and those are the games people want. People want first person shooters with AI so real you think its a human, or real time strategy games where the computer controlled opponents have more than a couple set build structures and attack patterns. The use of the cell processor in a mainstream gaming device is a bit of a kick in the ass for all of that. That means any games which get developed for the PS3 then ported to say the PC likely won't be improved and the AI will be old and tired. In the article they mention that the Xbox 360 was planning to use the cell processor (I never actually heard if that happened or not) but if 2 mainstream units are using it, it only compounds the problem created for gamers by this processor.

It also furthers the argument that consoles are "dumbing down" games. Publishers aren't known for their willingness to toss money at a PC port to really make it shine. That is unlikely to change. Many games are seemingly made for multiple environments and that means the lowest common denominator will get served to all. A brilliant game designer is going to take advantage of the new multi-core environment of the PC (as it becomes more prevalent) and create a ridiculously amazing game. Problem with that? Big business. Many publishers will not want to throw away the investment they've made in the console market. If you suddenly had games on the PC absolutely blowing away the latest console games doing something that consoles couldn't even do, you've got a problem. Since we know EA intentionally gimped NHL 2k7 on the PC vs the 360 version, we know they wouldn't have a problem keeping their PC games gimped for Microsoft (I suspect there are some back door deals going on there that arranged that).

Sounds like fud, but we already have precedent for publishers behaving that way. The cell processor might be interesting for strictly business applications but it has no place in a gaming environment.

Re:This is encouraging news.

[Anonymous Coward]

PS3 Linux has access to the HDD and optical drive through hypervisor calls. The HDD access restricts Linux's view of the drive to its partition only. The optical drive access "restricts certain commands", by which I assume they mean "enforces content protection and prevents you from reading gamedata"

-Q

Re:This is encouraging news.

[Morphine007]

your comment was interesting... pray tell, how is it that a system custom-built for parallel processing is *bad* for ai? I'm an ai researcher and I'm dying to get my hands on one of these things cuz they'd be perfect for MAS/MRS research... hell, you could have 6 of those processors running the ai code for the 6 bots you're playing against... so please, tell me, how is it bad?

Re:This is encouraging news.

[grimsweep]

Think about it. You've got an average of 6 processors to play with. Part of what makes AI for gaming so crappy right now is that it must all be stream-lined for a real-time system that shares processing time with graphics, sound, physics, etc. Look at the PC. What allowed us to create more realistic environments? The graphics accelerator (basically an additional processor).

It may not happen right away, but dedicating a processor or two to artificial intelligence will undoubtedly lead to gameplay that only multi-core PCs could match without sacrificing a consistent frame-rate.

Re:This is encouraging news.

[SScorpio]

There will likely be new drivers for the HDD that will allow you to view the whole thing. That was developed for the original PS2 Linux. As for the DVD-ROM lock down, that was due to how the PS2 authenticated disks to be readable. Using a modchip this made any disk look like an original enabled full usage of the disk drive. An external USB optical drive was also an option.

Re:This is encouraging news.

[Anonymous Coward]

You could also access the video hardware directly, you just needed the appropriate driver (not supplied by Sony, but that someone else was able to write it just shows that the environment wasn't as limited as you make it out to be.)

Re:This is encouraging news.

[SnowZero]

Yeah I don't know what he's talking about. I would love to have a Cell for our RoboCup robots. Computer vision algorithms will map quite nicely onto SPUs, and will allow many techniques to run at video frame rates which are currently out of the question. As far as game-ai type stuff, path planning could use denser meshes for more realistic motion, and there is even enough CPU to do some local kinematic planning as well (imagine AIs that don't drive wheeled vehicles into walls constantly). The small local memories might become an issue without some form of paging though. There should be enough CPU for better line-of-sight evaluations, allowing more stealthy AIs that consider more points they could position themselves at. Finally, there should be enough CPU for just about any coordination method you'd like to use for teams, allowing better breakup of subtasks for the AIs on a team.

Now, whether or not game developers will use the extra CPU for such things is another question altogether...

Re:This is encouraging news.

[Morphine007]

CMU Dragons? Dude, can I talk to you or one of your guys about design? I've seen the videos of you guys in Germany this year and they're insane. There's no Canadian presence in the small league atm (to my knowledge) and I'm trying to get funding to get a team in there... I'm hoping to present a PIPE variant in Hotlanta in July, but other than some simulation-league stuff that I'm hoping to put together for souzhou the year after, my university doesn't have anything :-(

Re:This is encouraging news.

[crossmr]

The issue is the type of processing, not the amount of processors. If you read the link I provided in my original comment you'll see what is said about the cell processor. Its an in-order processing model and this makes writing good AI more difficult. The amount of sequels and other things we've seen show that the gaming industry isn't really interested in hard work. So even if good AI is theoretically possible on that type of processor we likely won't see it. I don't pretend to understand all the nitty gritty of it, but I also don't believe Chris Hecker pulled that information out of his ass just to create FUD. I think an ideal system would not only have multiple cores, but different types of cores. He did say that Cell cores were good for making things shiny and handling physics. So you may see multicore systems that has 2 cell cores and 2 of the current cores which do out of order processing.

Re:This is encouraging news.

[Morphine007]

Even with the inefficiencies of having an in-order processor doing ai calculations, I still think that the fact that you can have a processor completely dedicated is what will make the difference. I'm not entirely sure what game makers typically use for their opponent ai, but on the cutting edge of ai research in general, all of the algorithms I've looked at can benefit from having multiple processors (especially any type of algorithm which uses a population of candidates who all have to try out the task before they determine which is best, like Genetic Algorithms/Programming). There's also a lot of brute force calculations (like positional location, line of sight determination for ai algorithm inputs, etc...) which are usually tackled in a "quick and dirty" manner because of horsepower constraints... these constraints would all but disappear with some extra cells onto which you can offload these calculations... I think I've got my prof convinced to buy a couple after the Christmas rush and, like I said before, I'm pretty psyched to get them (and not just because it'll give me something to do in the lab when I'm feeling brainfscked...)

Re:This is encouraging news.

[crossmr]

We can talk about what might be theoretically possible, but we have practical experience to tell us that that won't happen. Inefficient is the key here. The impression I got from what was said in the article wasn't that dedicating a core just to the AI would solve the problem. It seems like it will be fundamentally more difficult to write the AI in the first place. We know that publishers don't typically want to make difficult games. I was perhaps harsh in saying the cell processor has no place, but its place is limited in scope. As the sole processor in a gaming system, I think its going to result in a negative effect on the quality of games.

Re:This is encouraging news.

[Morphine007]

funny... I write my ai code in C... game developers usually use whatever they're coding their games in... I still don't see how poor handling of branch prediction* (or no handling of it at all) is going to have any effect on whether or not a coder can code in an ai using a language that completely and utterly abstracts that low level crap away? There's a difference between not being able to easily code something, and not having your code run in quite the optimized way that it used to. The former simply isn't true from anything I've seen (hell... even ASSEMBLER abstracts that extremely low level shit away...) and the latter is a matter that's up for debate; having your code run a bit slower than normal is somewhat bad, but having it be able to run on a dedicated processor and hence much faster than normal more than makes up for it.

So I'm still calling bullshit on this one so far, but only because no one has given any details... if you know them, please show 'em...

* - it should be noted that branch prediction is just an OPTIMIZATION technique at the hardware level... code in whatever language you want, it'll still run fine, the processor just won't have already prefetched the instruction and associated memory blocks... if this is all the FUD boils down to, then it's massively busted since my (and anyone elses) ai code will still run perfectly fine on it....

Re:This is encouraging news.

[crossmr]

As I said, I don't pretend to understand the nitty gritty, but if he says its bad, and knowing what I've seen from big publishers, I don't see it coming to a good conclusion.

I'm not sure how approachable he is, and he's currently working on Spore, but you could try getting in contact with him if you're interested in more details on why he feels this way:
http://www.d6.com/users/checker/
He's left an e-mail address on that page.

Re:This is encouraging news.

[Morphine007]

he really only talks about the gameplay code... code that throws a lot of exceptions... ai code is generally a lot smoother. I mean, stuff like neural nets and genetic algorithms would be absolutely fine on these things... but anything coded like an expert system would potentially suffer from performance issues. He says that that kind of code will run 1/3 to 1/10th it's "normal" speed on an out-of-order processor. But this code is normally vying for processor time in between context switches... and who really cares about ai anyway right? as long as the game looks pretty... well... now the same code can run 1/3 slower, but 100% of the time on a cell.... I seriously think that the ai in games could get a helluva lot better as a result of cells.

Re:This is encouraging news.

[doug363]

By "exceptions" he means exceptional (i.e. special) cases. There's tons of that stuff in AI and gameplay code. Games generally don't use neural nets or GAs or fuzzy logic or anything... it's all expert systems, min-max, pathfinding with heuristics, etc. The most important thing for game AI is not that it actually learns well (or at all), it's that it doesn't do blatantly stupid things. Game AI code tries to detect all the special cases so this doesn't happen. You can't guarantee that stupidity won't happen with learning algorithms.

Graphics Chip will never work

[keithpreston]

It's nice that Sony will let us run Linux, but I highly doubt the graphic chip will ever work on Linux. It's simple, without a graphic chips it impossible to use Linux to play pirated games. That's generally the biggest opposition to opening up a platform is piracy issues. That's why the Xbox 360 is locked down unlike any other machine.

Re:Graphics Chip will never work

[LWATCDR]

It's simple, without a graphic chips it impossible to use Linux to play pirated games.

With out the graphics chip it is impossible to run any good games in Linux.

If Sony opened up the graphics chip then people could create games without Sony's okay.

On a bright note it opens up the critter to emulators :)
MAME PS/3 anyone?
When it calms down and the price drops I might get one.

Re:Graphics Chip will never work

[adam31]

It's nice that Sony will let us run Linux, but I highly doubt the graphic chip will ever work on Linux

A lot of people highly doubted that Sony was serious about this Linux thing, and here it is on launch day. It's likely that Sony hasn't had time to write graphics chip drivers yet since they've been busy with... other things. For console devs they probably just provided bare-metal access and moved on.

From the looks of it, Sony built support for non-game OS from the very beginning, and most of the work to bring the OS to Cell was by third parties. However, Sony will definitely not let third parties do stuff like gfx drivers, so we'll have to wait til it bubbles to the top of somebody's priority list. I think it will happen though.

Regardless, this is a seriously cool development. Think of something as simple as a 7-node compile farm. Depending on how this progresses, there may be a lot more value in that $600 than anyone was expecting.

Re:Graphics Chip will never work

[Anonymous Coward]

"With out the graphics chip it is impossible to run any good games in Linux."

Not entirely true... it could still run good, commercial-quality* OSS stuff like frozen bubble, stepmania and wesnoth, as well as those emulators. Of course, those games also run fine on any junk PC you can pick up from the sidewalk....

*OK, perhaps commercial-quality for GBA, but they're still good enough to be in software stores.

Re:Graphics Chip will never work

[SanityInAnarchy]

It's simple, without a graphic chips it impossible to use Linux to play pirated games.

It would be impossible anyway. The only advantage you'd have is using that Linux to try to bootstrap a pirated game, but since they were obviously lying about the PS3 including Linux on the hard drive when it ships, no PS3 game is going to be written to run under Linux -- they'll all be running on the bare metal.

Re:Graphics Chip will never work

[Anonymous Coward]

I suspect the reason Sony haven't provided the driver
is that they can't: nvidia obviously supply the OpenGL ES
driver for the ps3. I doubt their contract with sony compels
them to provide a ps3 linux binary.

Fedora, not Yellow Dog?

[bunbuntheminilop]

I thought Yellow Dog was supplying linux for the ps3. Whats going on?

Re:Fedora, not Yellow Dog?

[brunascle]

they are. Yellow Dog seems to be the only distro branding it as "linux for the PS3" but it sounds like you can use pretty much any PowerPC version.

amazing

[Anonymous Coward]

all this relevant text, and the only thing i find myself focusing on is this inexplicable

[ Experimental threading: One Two Three Four ]

Re:amazing

[Anonymous Coward]

Yeah, it must be pretty experimental... I keep pressing the different links but nothing happens, can anyone explain what is it suppose to do?

Re:amazing

[Anonymous Coward]

If you have to ask, you don't deserve to know.

PS3... Linux... Sony...

[Anonymous Coward]

PlayStation 3....

Linux... Good!
Sony... Bad!

but but... which is greater...?
*head explodes*

How long for MythTV, MAME etc.?

[DrXym]

Install Linux, install Myth, plugin a Haupage WinTV USB device - the PS3 becomes a PVR, plays DiVX etc. Or install MAME, UAE, Virtual Boy, SheepShaver, QEMU, Bochs and you have a pretty decent console / arcade gaming rig. Might even be able to play those SNES / N64 titles before they turn up on the Wii...

Re:How long for MythTV, MAME etc.?

[bcmm]

That's actually a really good idea. This is already designed to fit under the TV while including a DVD drive, be silent, use TV-out, etc. MythTV on it would rule.

Re:How long for MythTV, MAME etc.?

[ClamIAm]

Unfortunately, there's no driver for the graphics card. If one never surfaces, just hope and pray that you can somehow wrangle those SPEs into doing all that video decoding.

Re:How long for MythTV, MAME etc.?

[DrXym]

I have no idea what the refresh rate & characteristics are the display buffer, but it should possible to offload codecs, zip/bzip2 compression and even parts of Mesa (shaders, transformations, etc.) onto the SPEs. The net result would be a system which while not stellar should be able to put out reasonable 3D and video performance.

I expect a whole cottage industry will spring up to add functionality to the various libs that does just that.

IBM has a huge amount of Cell resources online

[RichardMarks]

To get a glimpse of what you have to look forward to when you install Linux on your PS3:

http://www-128.ibm.com/developerworks/power/cell/d ocs_documentation.html

Best option is getting the $499 20gig model and buying a 100+ gig drive to upgrade the machine. The PS3 will partition the disk for you right from a menu and then you just follow the instructions they give you for the distro of your choice. People who just got their machines this morning already have things going and are posting pictures and results.

There is a full set of all the normal Linux dev tools that you get with any distro but there also is the Cell devkit - which you can get right now to check out although you won't be able to run anything of course.

Cell programming is incredibly cool...

Re:IBM has a huge amount of Cell resources online

[a16]

Hi,

Any chance of any links to these pictures and results, I for one would be interested.

Re:IBM has a huge amount of Cell resources online

[jgeorger]

Why can't you run anything with the IBM Cell devkit?

This thing has obvious potential for HPC.

Re:IBM has a huge amount of Cell resources online

[Anonymous Coward]

I think they were referring to the fact that you can download the kit on your computer right now but won't be able to run any Cell executables until you have a PS3 or other Cell based system to run them on.

Although that isn't entirely true since there is a Cell emulator I believe somewhere that you can run on your home computer. But that is targeted at people who were preparing to do Cell programming back before the hardware was available.

Re:IBM has a huge amount of Cell resources online

[dch24]

I am one of the people who worked with the Cell emulator when it first came out.
If I recall correctly (it's been a year) they still only have an x86 emulator, not a PPC emulator. However, it's a full-featured environment and very useful. Of course, it's only designed to work with Fedora, which is where I was involved--I successfully ported it to several other linux distros, but there wasn't a lot of demand for the patch I had, so I've moved on to other things.

Re:IBM has a huge amount of Cell resources online

[r_jensen11]

Unless you're concerned about things like wireless networking or being able to use SD, CF and Memory Stick cards.

But OpenGL ES and Collada will (hopefully)

[Anonymous Coward]

Graphics Chip will never work

You're forgetting one rather important little point: Kutaragi (and also one other top Sony guy whose name I forget) both said that they want to encourage amateur games development on the console, and to foster a culture of community development for it.

That doesn't mean that the graphics chips will be programmable directly of course, but it does mean that the graphics subsystem will be made available at least through an API. Since the PS3 uses OpenGL ES and Collada, it's easy to see how this could be achieved without too much effort.

Unless of course Kutaragi et al were simply lying in the name of generating buzz.

Ok so it runs linux...

[jonwil]

But does it run NetBSD?
If not, hopefully someone can port it.
If BSD can run on a toaster, surely it can run on the "most powerfull games machine ever created" (or so says sony PR)

Re:Ok so it runs linux...

[soccerisgod]

I know nothing about BSD tbh, but it can't be that difficult. You got all the code you need, so basically an experienced BSD hacker should be able to add support within BSD in a rather short time.

Gentoo

[gentoofu]

I wonder how long it would take to install Gentoo and the stuff on it...

ps2

[minus_273]

let me guess this is going to be as great as the ps2 linux kit. remember that thing?

Re:ps2

[CronoCloud]

Of course I remember the PS2 Linux kit, I have one.

This is different, it requires no additional hardware, is free, and is available at launch.

Re:ps2

[DrXym]

The PS2 Linux kit was perfectly okay, it was just by the time you added the cost of the hd, network adapter, keyboard, mouse and OS onto cost of the PS2 you were left with something that wasn't good for much and certainly far less capable than a PC.

The PS3 doesn't require you buy anything extra, or even use a specially "blessed" version of Linux. Just plug in any USB mouse and keyboard, burn any Linux for PS3 onto CD and install. I expect that Fedora, Ubuntu, YDL and specialist Myth / Mame Linuces will appear in due course. Pick your poison.

Re:ps2

[Anonymous Coward]

let me guess this is going to be as great as the ps2 linux kit.

They're not giving us access to the video hardware like they did on ps2 linux.

So it depends on why you want to put linux on ps3-- if you want "yet another linux box", you win.

If you want any kind of "homebrew experience", you lose. Now granted, on ps2 linux you really only had access to the graphics hardware, the mips manual, and the VU's and such (with no access to sound or the IOP.) But graphics is where it's really at with homebrew.

It's a shame, really.

Re:ps2

[Anonymous Coward]

Maybe they did it quick so it has a chance to persuade the EU that the PS3 is in fact a computer not a games machine, so they can get a tax break (they failed with the PS2 linux IIRC). Now they have months before the EU launch to try to persuade the tax-collectors to give them a break.

yellow dog linux

[operato]

didn't yellowdoglinux say they'd be supporting ps3?

Re:yellow dog linux

[gentoofu]

I think that's what Quinton meant. Yellow Dog Linux is derived from Fedora Core 5 for PPC architecture.

Re:yellow dog linux

[Provocateur]

They already do.
 

Re:yellow dog linux

[Anonymous Coward]

Who's saying they don't?

Awesome

[jrshabadoo]

This is awesome! If I ever do get a PS3, this will be THE reason.

j

Java?

[CaptainPinko]

Can anyone run Java on it? This would be a great opportunity to showcase the 'run-anywhere' aspect of it. Once the source is released (AFAIK it's only been announced not released) I'm sure that the community could come up with some wicked optimizations even if it is just dedicating one core to garbage collection and another for analyizing for runtime optimizations.

Re:Java?

[Wesley Felter]

The existing IBM PPC/Linux VM should run fine. Getting Java to use SPUs sounds insanely hard, though.

No need to install The Gimp ...

[Purity Of Essence]

Most all hardware is supported except for graphics accelerator support (framebuffer only, up to 1920x1200)

... it comes gimped right out of the box.

Compute Cluster?

[bill_mcgonigle]

It still sounds good for a target for a massive compute cluster, ala BigMac. If the algorithm is sufficiently simple and easily parallelized the lack of branch prediction and out of order execution might not be too bad, especially at a FLOP-per-$ or FLOP-per-square-foot or FLOP-per-Watt*$ basis. My uneducated guess is that this would work out OK using gcc 4 (with SSA trees) on things like BlueGene does or even just computing Rainbow tables. Without myrinet or inifiniband you'd need a good ram cache and more CPU than I/O.

Anybody doing this for a day job care to comment/shred my guesses?

Re:Compute Cluster?

[Anthony]

As a side issue, what was BigMac used for?

Re:Compute Cluster?

[bill_mcgonigle]

As a side issue, what was BigMac used for?

I'm not sure what it's used for primarily, but I found this list.

USB reader

[SuperKendall]

You can get an external WiFi adapter or simply hook into the gigabit Ethernet included on all PS3's (and if you were running Linux, wouldn't that be more desirable anyway?)

As for the CF/SD issue, just buy an external USB reader (or use the one you have already)- it mounts mass storage you know. Sheesh!

How about amiga OS 4

[p.gogarty]

Linux on PS3 cool, but we knew it was comming. Nice to see sony release it so early though.

What I am really waiting for is Amiga OS4

As Hyperion state in feature 12 of their 20 features of OS4
"It would be eminently suitable for - and relatively trivial to port to - the STI Cell processor used in the Playstation 3"

Please Hyperion, it's going to be a lot cheaper for Amiga enthusiasts that shelling out for A1 based systems

Maybe a widespread plea from slashdotters would convince them hint hint

No GPU Access, eh?

[triso]

...Most all hardware is supported except for graphics accelerator support (framebuffer only, up to 1920x1200).

So what GPU is in the PS3? Is it a Nvidia or an ATI product? How many days will it take to get a driver for it?

Re:No GPU Access, eh?

[Anonymous Coward]

So what GPU is in the PS3? Is it a Nvidia or an ATI product?

You can't be serious?

Re:No GPU Access, eh?

[triso]

So what GPU is in the PS3? Is it a Nvidia or an ATI product?

You can't be serious?

Aha! http://news.teamxbox.com/xbox/9132/PlayStation-3-G PU-More-Powerful-than-GeForce-7800/ says it is a Nvidia RSX, whatever that is.

Great opportunity for linux

[Zekolas]

This could be a HUGE opportunity for linux. I mean all PS3 will have the same hardware, some one could create a fast lean stripped down distro specifically complied for the PS3 hardware. It wouldn't be hard to make a distro that "Just worked" as you know exactly what hardware everyone will have. The user will not have to install any drivers or install linux to find out their network card is unsupported. Think Millions of people will have this linux compatable computer sitting in their living room. Create a specialized live cd/dvd for it, with some multi-media apps and kids will install linux so they can have a home media center, After millions of kids install linux that "just works" on their PS3 they will want to install linux on their computer, or at least not view linux as that weird "Other Operating system".

Very good Webpage

[onlineshop]

A very interesting site, I think. The Idea of Technometry was new for me but worth to be read and thought abot it (although I'm not a native english-speaker and have some difficulties whith this language) mfg Dirk Karl Maßat My Webpages http://www.einemillioneurohomepage.de/ http://www.einemillioneurohomepage.net/ http://www.einemillioneurohomepage.info/ http://www.einemillioneurohomepage.org/ http://www.einemillioneurohomepage.ch/ http://www.einemillioneurohomepage.com/

abuse of moderation

[drinkypoo]

This is one of several obviously non-troll comments I have posted that has been marked as a troll.