Slashdot Mirror
Linux For Cell Processor Workstation
News for nerds writes "The Cell processor from Sony, Toshiba and IBM, has been known as the chip that powers the upcoming PlayStation 3 computer entertainment system, but except for that very little is known about how it's applied to a real use. This time, at LinuxTag 2005 from 22nd to 25rd June 2005, at Messe- und Kongresszentrum Karlsruhe, Germany, Arnd Bergmann of IBM will speak about the Cell Processor programming model under Linux, and the Linux kernel in the first Cell Processor-based workstation computer, which premieres at Linuxtag 2005."
but except for that very little is known about how it's applied to a real use.
And why are video games not considered to be "real use" ??
Can't wait!
Have to wonder about the timing of this story although it is almost certainly coincidental. If these are eventually marketed (and don't remain prototypes) they should make interesting development platforms.
It should be interesting what modifications, if any, IBM may have made in porting Linux to the cell, since my understanding is that it has many specialized sub-processors (cells). It should be at least as good as Linux for PPC though, no?
College Humor at it's best
What's the point of better architectures when Apple is moving to the brain-fucked x86 ISA? It's hard to be enthusiastic about computing when you know the beast just got a new lease on life.
/me pours himself another bitter one
the PS3 display at E3 was pretty disappointing...
What has impressed me about Linux is not so much that it has enabled some sort of "software revolution", but rather in how it has given chip/platform makers a specific, generic target OS that they can use freely to get something useful running on their hardware quickly.
It used to be the case that platform makers would have to either develop their own minimal operating system for testing purposes or work very closely with an OS maker to port their software to the new hardware platform. With Linux, this has been pushed into the anals of history. Now the Linux OS porting goes hand in hand with platform building, as evidenced by the almost immediate support for Linux at the time of hardware release.
I'm not so much interested in how the Cell board is going to revolutionize anything (it won't), but in how we have, in just the past few years, seen a dramatic increase in the number of hardware platforms being released. And not just in numbers, but also in variety. The number of different types of hardware platforms has risen dramatically. It's only limitation is the number of chip instruction sets supported by gcc and the imaginations of hardware manufacturers.
If you want to see how Microsoft's monopoly has hurt the computer industry, look no further than the current industry. Whereas hardware platforms were pretty standardized and boring, now, with Linux (and real competition to Microsoft's hegemony) the numbers of innovative platforms has increased dramatically. We need a Microsoft out there developing consumer-level applications and quality, user-friendly operating systems. However, we also need a real competitor like Linux to push the giant into innovating.
We are fast approaching an era where you'll be able to run any OS and any software you want on any architecture you want.
Too bad that at LinuxTag 2005 all you will get to see is a looped video on running "real time" on "similar hardware" simulating the great development advanced you will be able to achieve with the new cell processor.
Maybe the old man face and duck in water tech demos from the PS2 will also appear.. Did any PS2 game ever look as good as sonys techdemos?
EA David Gardner -"... but the consumers have proven that actually what they want is fun."
You could always try clicking this then
Cell info
In the end, It's all bovine dung you know
"Unlike existing SMP systems or multi-core chips, only the general purpose PowerPC core, is able to run a generic operating system, while the SPUs are specialized on running computational tasks. Porting Linux to run on Cells PowerPC core is a relatively easy task because of the similarities to existing platforms like IBM pSeries or Apple Power Macintosh, but does not give access to the enormous computing power of the SPUs.
Only the kernel is able to directly communicate with an SPU and therefore needs to abstract the hardware interface into system calls or device drivers. The most important functions of the user interface including loading a program binary into an SPU, transferring memory between an SPU program and a Linux user space application and synchronizing the execution. Other challenges are the integration of SPU program execution into existing tools like gdb or oprofile."
So I guess plenty of ex indrema developers are working on the ps3 then if it runs linux.
And if transmeta are working on the cell then it should be tailormade for linux.
Except that pages is really old...
In soviet russia cell processes YOU!
I can see it now: cell processors released, 5 years later Windows Cell Edition finally is finally released, and you'll have to get new drivers and 60% of your software won't run. does the cell have a 32 or 64 bit architecture?
I really hope that Cell will boost IBM since in the last few monthes they sold their Personal Computers department to Lenovo and have lost their partnership with Apple for PPC processors. I really think IBM has still a lot to give to the IT world and it would be a real waste to loose their know-how!
What's the point of better architectures when Apple is moving to the brain-fucked x86 ISA? It's hard to be enthusiastic about computing when you know the beast just got a new lease on life.
Perhaps you are in the wrong business or hobby. If inconsequential details like what CPU is sitting at the heart of Apple's proprietary design causes you emotional distress you really need to reconsider your life. Assuming of course that you are not in advertising and needed the faux x86/PPC conflict. If so please continue with your distress, otherwise, have you considered forestry?
http://data2.itc.nps.gov/digest/usajobs.cfm
The cell is amazing it will-
- optimize seamless communities
- generate vertical e-services
- everage synergistic convergence
and best of all
- engage e-business content
Perfect solution
Excuse me, I don't mean to impose, but I am the ocean
Awww, look at the liddle xbox fanboy trying to spread FUD!
Good boy, now roll over!
Wait till Billy Joe Bob ports his text editor!
Oh wow, I don't know where to start.
1. Relevance: This comment has absolutely no relevance to the slashdot article.
2. Open-source software sucks compared to closed-source because it's not done by 'professionals'? Give me a break! Several open-source projects are funded by companies, organizations, and universities and are recognized world-wide.
3. You're saying you can't use those programs because of their silly names which you somehow derived as sexual euphemisms? What about windows cause it kinda sounds something like dildos LOL!
4. You're comparing programming to prostitution while discussing the lack of professionalism -- how very... professional!
WTG Apple! Steve throws a tantrum because he can't get his G5 Powerbook and instead of the insanely great stuff IBM is doing with Cell we get dumped into the garbage world of Intel x86. An architecture Intel themselves have been trying to dump for a decade.
Time to build a killer AMD64 Linux box...right after I take this now worthless G5 to the dumpster.
No one knows yet the Cell's true power on the desktop. If the SPUs can be harnessed or even parts of/entire OS's rewritten to utilise the chip properly Cell could wipe the floor with anything Intel could come up with. That it is, apparently not the priority of every developer to do that today is not the issue.
If Cell takes off, Apple have bought into an ancient bucket of junk (x86) designed, let's be honest, with one purpose in mind:
to run Windows XP.
Programmers are generally either overworked (hence no time to scratch your balls for you) or they are just assholes (go scratch your own fucking balls, loser). It's just that FOSS makes these personalities more public, but I can assure you that developers within closed source projects are assholes, too.
We were fast approaching that about 30 years ago. Then the personal computer "revolution" happened, and companies like Microsoft and Apple started from square one, making all the mistakes that their predecessors had been making, and then some: programming in low-level languages, extensive use of assembly, lack of hardware abstraction, etc.
Unfortunately, the so-called PC-pioneers like Gates, the Apple developers, and others, didn't have a clue what they were doing technically and were learning on the job; we all are still paying the price for it.
When people paid even a little bit of attention to prior work in operating systems (Amiga microkernel, Linux), the results were technically far superior.
OK, so it's not on the Cell architecture, but rather an FPGA-based softCPU, but certainly the problem of integrating asymmetric coprocessing engines into the Linux architecture has been thought about before.
Cool stuff nonetheless.
The IBM Cell workstations used for PS3 dev run a version of the Linux kernel to handle development I/O tasks: file transfers, communications with the PC host, starting/restarting programs etc. The game itself does not run in a Linux environment.
This is similar to the T10K PS2 devkits running Linux (on a separate X86 processor) to do similar purposes.
As with the PS2, the consumer PS3 console itself uses a custom bare-bones kernel; it is NOT Linux based, although I could certainly see Linux being ported to it, like Sony did with the PS2.
-- Samir Gupta, Ph. D. Head, New Technology Research Group, Nintendo Co. Ltd., Kyoto, Japan.
I don't think there is any question as to whether the Cell arch will take off.
It is actually a very straightforward arch and it is obvious what it is good at, video, sound, and a bunch of 3d/vector operation tasks. It utterly destroys anything Intel or AMD has or even plans on having in the future. Cell is going to be everywhere the 100+ million PS3 Sony will sell over the next five years, workstations, renderfarms, TVs, and boatload of other consumer electronic devices only Sony knows about right now.
Apple has blown it. Big time.
What I want to know is "Does this 'uber-multiprocessor ready' architecture have some kind of 'priority' flag that one uses on a thread?
More succinctly: how does it handle its passing of processing requests to other 'cells'?
Using some (tiny, tiny bits of) ASM, I started to wonder about this. I mean, dear GOD! How do you deal with it? Some form of modified call I would suppose, like:
call_avail mem_Address_Of_Function, MemAddress_To_Store_Result
And when the result comes in it fires some interupt. Maybe that would be specified in the ASM instruction?
Obviously the compiler would have to know when to use the 'external call allowed' ASM command, hence my mention of a priority flag (e.g. 'need this NOW!!!' vs 'hey.. whenever')
Anyone know and care to explain?
cheers,
The Cell architecture was developed with powerful and complex math applications in mind. How will existing Linux applications perform on it? It seems to me that the Cell's strengths are not integer math and general purpose computing, so in theory only floating-point intensive and vector applications can get a real kick out of it. There are not many well known applications with these characteristics.
That said, advances in parallelizing or vectorizing tasks within the kernel or popular applications are possible, but that's not a trivial task, so at first glance Cell's Linux benchmarks could look unimpressive or misleading, even though the architecture itself is revolutionary, at least in theory.
Here I hope IBM has done their homework and show something really impressive, yet realistic. I want to see things like Apache and GD serving hundreds of thousands of requests for dynamic content, or some real-time encoding/compositing of MPEG4 video for scalable delivery. I want to see Maya or Lightwave rendering a very complex scene. Rubber ducks may be fun to look at and -in all fairness- fit for a videogame-oriented crowd, but I want to see some kick-ass performance based on what it can potentially do to application development.
- Otaku no naka no otaku, otaking da!!!
That function name is way too long and descriptive. The acutal name would be something like addfunmemdestaddavsize().
And that would be followed by a series of non-sensical parameters which can be defaulted to NULL and everything still seems to work fine.
As for your question, that's why they make the big bucks and you are posting on Slashdot. If you knew the answer, you'd be working for them.
RFID is amazing it will:
- optimize seamless communities
- generate vertical e-services
- leverage synergistic convergence
and best of all
- engage e-business content
Perfect solution!
In Korea only old people abuse memes.
Sounds like it belongs in an addon then. Not in a generic environment. Video, sound and 3D vector ops have very little in commen with, say, SQL queries.
0x86 chips have added silicon AFTER, not BEFORE Microsoft created all of their sound and video extensions. Unlike the implication of GP. And MMX was a response to the fact that 'omg! People use video and sound!'. Linux and anyone else is free to take advantage of the extra instructions, and is the case with Linux at least.
If Cell doesn't have special instructions for doing quaternion rotations then I don't give a crap how fast it is: an Intel/AMD/0x86 chip will walk all over it in video operations.
And even if Cell does... can that make it a great generic OS processor? Nope! Takes a lot more than that!
As in everything, time will tell. I certainly do hope that it is a revolution; I foresee living through very few GOOD revolutions during my lifetime. The more the merrier.
I don't think the reason we call them paedophiles is because 12 yearolds don't give very good hand jobs, is it?
My 3D Texturing Skinning work (under construction)
If inconsequential details like what CPU is sitting at the heart of Apple's proprietary design causes you emotional distress you really need to reconsider your life.
This is Slashdot, man. If we had a "life" to reconsider, we wouldn't be here.
I don't need a signature.
Those SPEs will be pretty useful for massaging and distilling large streams of data, which should make the cell great at tasks like video recognition and real-time market analysis. The cell may not be that revolutionary as parallelism has been touted in academia for a long time now, but the DSP like capabilities + parallelism will make the cell much more capable of responding quickly to complex sensory input than commodity hardware currently allows.
I picture the PS3 using a camera as a very flexible form of input to allow for more creative game design. Super-fast compression and decompression also come to mind, which could be useful for more complex and fluid internet play.
Recent articles have said the cell will have some hickups with physics and AI, because those tasks benefit from branch prediction, but this should be made up for by the fact that the cell will be able to recognize input at a far more human level than present technology affords.
If Steve isn't willing to give me registers by switching to x86, then this CPU could be sitting on my desktop in the future instead of my Macs.
All arguments about OS and usability aside, the next evolutionary step in computing needs the functionality in the Cell and not growing stacks due to the lack of CPU registers.
IMHO, of course.
my 2 cents
If the SPUs can be harnessed or even parts of/entire OS's rewritten to utilise the chip properly Cell could wipe the floor with anything Intel could come up with.
t ails.html?talkid=156
The SPUs are not for the OS, they are for high level libraries or apps. They are for highly specialized computationally intensive jobs. Maybe OpenGL could benefit but not the OS. FYI:
"Unlike existing SMP systems or multi-core chips, only the general purpose PowerPC core, is able to run a generic operating system, while the SPUs are specialized on running computational tasks. Porting Linux to run on Cells PowerPC core is a relatively easy task because of the similarities to existing platforms like IBM pSeries or Apple Power Macintosh, but does not give access to the enormous computing power of the SPUs. Only the kernel is able to directly communicate with an SPU and therefore needs to abstract the hardware interface into system calls or device drivers. The most important functions of the user interface including loading a program binary into an SPU, transferring memory between an SPU program and a Linux user space application and synchronizing the execution. Other challenges are the integration of SPU program execution into existing tools like gdb or oprofile."
http://www.linuxtag.org/typo3site/freecongress-de
Is this supposed Cell/Linux workstation something we actually know jack squat about it, or is it just IBM going "uh, we're gonna make one of these... someday"? Can we make any educated guesses based on what IBM usually does?
Specifically, is this, like, something that will be actually in the affordable range for people, or is this going to be like some kind of $6000 near-server tank?
Also, how many Cells is this likely to have? One? Two? Four? These SPEs are all well and good for computational stuff but the rest of the time it's nice not to be stuck with a single processor.
Irritable, left-wing and possibly humorous bumper stickers and t-shirts
You're high, or you haven't looked at cell.
If Cell takes off, Apple have bought into an ancient bucket of junk (x86) designed.
OMG, I bet Intel fanboi Steve Jobs never even considered Cell, and all the Intel loving drones in his engineering department(s) probably never even looked at. You should give him a call and save the day.
may it be possible that the game console makers pushed apple away from using powerpc's so their games can not be easily ported to a powerer mac?
How many stocks does microsoft own on apple?
LOL, it will happen as well, directly after a group of taxi drivers and drunk old guys who hang around bars all day form a government.
sounds good, very fast and so on, but I still love the z80a.
With all the continuing good news about the evolution of the PPC, including the Cell processor, I find it hard to believe that Apple has choosen now to move to Intel chips... and the developer workstations are only 32bit no less (I think they could have at least gone with AMD64).
The good news is that someone is at least taking advantage of the architecture and producing linux workstations based on the Cell... unfortunately i don't think tht will be enough for it to survive in the desktop/workstation market. I fear that unless Microsoft ends up releasing a new PPC version of Windows (which i consider unlikely at best), PPC is soon to be relegated to Servers, Gaming Stations and the embedded market only.
Wow... someone missed the point a tad. Violent liberalists eh? Liberalists sure, but violent, thats a bit harsh and not something that you could really aim at most nerds/geeks on /. what are we going to do attack Bush with a pocket calculator?
Oh, and dude... "open-saucers"? Check your misguided and vaguely insulting comments before posting them, for someone with a supposed PhD in moecular biology I would expect better.
I've not even got started on the implication that people who use open source software are also paedophiles. Where did that come from?
The main PowerPC processor has been, as I understand it, stripped down a bit (wonder why Steve's mad?) to allow the clock rate to be kicked up over 3GHz. Come to think of it, maybe the whole reason G5s haven't done 3GHz is the complexities Steve insisted on. (Stumbling in the dark, here.)
I think the fact that Apple have switched to x86 at this point could very well mean that they've seen the Cell, and it's no where near as good as it's supposed to be.
Maybe Apple would like to use a nice IBM chip :-)
When you had some new hardware, you bought a (relatively cheap) Unix source license, and had something running fast
Linux is better though, because the GPL encourage hardware vendors to share their modifications.
With Unix all you had access to was the original source, and the ports done by non-commercial/academic groups (source as UCB). Not other vendors code.
I have news for you,... we programmers have been letting the hardware designers have FAR too much fun for far too long! It wasn't until my recent retirement from more than 35 years of computer programming (I've had many different titles) that I've had the time to learn the Verilog hardware design language - and it's GREAT FUN!!! :-) Verilog is very liberating because it removes the boring sequential execution of most CPU's and provides a clean slate with which to design any sort of little tiny electronics machine (that's how I think of VLSI design) that my heart desires. There is a GPLed version of SystemC (a higher level hardware design language than Verilog) on SourceForge that I've been meaning to take a look at, but first I'm creating a 640 bit-wide(!!!) factoring machine in Verilog which I hope to fit into one of the Lattice or Altera FPGA parts.
Really, I highly encourage programmers or anyone interested to learn and use Verilog or some other high level hardware design language. Verilog is similar in many ways to the C language, so if you're familiar with C then you already know most of Verilog's operators, precedence rules, etc. The only thing that takes a little getting used to is Verilog's inherently parallel nature. That is both its strength and the source of most Verilog design errors (at least for me). Also, Verilog is even more bit-picky than C but I sort of actually prefer the extra control that languages like C and Verilog give me over the hardware versus languages that try to insulate me from it.
9/11 Eyewitnesses to Explosive WTC Demolition 1 of 2
The Cell also is simple, but in a way that that inflates the gflop rating at the cost of programmer time.
By comparison the modern x86 is a dream to program for, just note how two fairly radically different cpu's (Athlon64 and the P4) handle the same code very nicely without any big performance issues. Compare this to the Cell, where all the explicitness will make sure that any binary you write for the Cell today will run like crap on the next version.
The point here is that Apple could absolutely not have switched to the Cell, it is inconvenient now and hopeless to upgrade without having to rewrite a ton of assembler and recompile everything for the new explicit requirements.
The Cell is the thing for number crunching and pro applications where they are willing to spend the time optimizing for every single CPU, but for normal developers it is a step back.
I was talking to a friend about this new Cell processor they were going to have in the PS3, that was supposed to have all these nifty new capabilities, and he was looking at me like I'd grown another head. I asked him why he was looking at me so oddly, and he said, "Dude, Celerons are not that good."
Stasis is death. Embrace change.
In case you don't remember, the point of RISC was to put optimization on the compiler so it wouldn't require massive on-the-fly speculative bibbledy-bop with millions of extra transistors and hideous pipelines like we have nowadays. This was done by providing, essentially, a compiler-accessible cache in the form of lots of registers, and by having an instruction set that was amenable to automated optimization.
In theory, you don't need any GP registers at all, you could just have memory-memory ops and rely on the cache. This is impractical due to the size of memory addresses eating up your bandwidth (incidentally, this is a problem with RISC architectures, eating bandwidth and clogging the cache, but that's another story). As an alternative, you can simply expose the cache as one big honking register file using somewhat smaller addresses, and let your fancy-pants optimizing compiler do its best.
The real problem seems to be that compilers have just not been able to keep up with the last 20 years of theory. Witness the Itanium--in theory it should have been the ultimate, but they didn't seem to be able to get things optimized for it (other problems, too). Then what happens are curmudgeons complain about the extra work of optimization and insist on setting us back to early 80s architecture rather than writing a decent compiler.
Moral of the story: write a decent compiler and stop trying to glorify crappy ISAs that suit your antiquated and inefficient coding habits.
Possibly.
The other theory goes like this:
Jobs always wanted Mac OS X on Intel and that was always the plan, hence 5 years of OS X running secretly on Intel boxes.
Dear TurboBling,
:)
You seem to have a lot of drive and enthusiasm, which is obviously not finding a productive outlet, have you thought about getting some part-time work in IT? Perhaps try doing some volunteer work!
Maybe you've not yet graduated and are going through that 'difficult' stage. Girls don't seem to like you, the sporty kids bully you. We've all been there, it'll pass. The simple fact that is girls mature faster than boys.
In a few years, you'll look back on these days and laugh!
Anyway, take care.
AC.
Oh wow, I don't know where to start.
There's only one thing worse than repetitive, uncreative, irrelevant trolls.
It's the fucktards that reply to them on a point-by-point basis as if it does anything other than justifying the trolling.
Next time you feel the need to reply to such a lame, obvious troll, try sucking your own cock instead. It's an endeavor that will doubtless keep you occupied for days and be far less distasteful to onlookers.
I doubt this is the result of a 5 year plan simply because Jobs loves Intel. That's just pure insanity.
The other possibility is that Apple have got seriously pissed off watching IBM spew out the 3-core G5 for the XBox 360, the Cell for the PS3, and leaving them with an aging 2.7GHz CPU.
I mean, optimizing Maya or Lightwaves raytracing/radiosity engines to make use of the Cell is NOT a trivial task.
seriously..
who knows.
We know for a fact that IBM will be making cells for PS3 developers.
In that case they would be specialized machines to be made in low numbers. They would be VERY expensive if they get offered at all to the general public.
Then it's also interesting if you remember that Apple is saying they will pretty much abandon IBM for their desktop setups within a year or two. So that leaves Linux as IBM's last hope at anything closely resembeling PPC-based desktops or workstations.
There is also some interesting details for PS3. For instance the use of USB ports on the back.. perfect for mice and keyboards. The fact that they had a public-offered PS2 Linux dev kit.
Even if they don't offer Linux for the wallmart crowd (for HDTV-based browsing and desktop stuff) if they help out the Linux devs just in a small way you'd expect a Linux version for PS3 in a short order.
So you have a possible range of:
1. no linux cell workstations aviable.
or any and possible all combination of the following:
2. Linux Cell desktop for 200-600 dollars in the form of a PS3 running one cell.
3. Linux Cell workstations running multiple cells from 2K to 10k
4. rare Linux cell workstation for PS3 development for probably above 9k for a slow version.
5. hacked up versions of cell based blade servers.
You confuse "Real Use" with "Real Work". You can "use" a lot of stuff, without it counting as "work".
E.g., you get some real use out of your bed at home, but I wouldn't say sleeping there counts as "work". (Or if it does, where can I sign up to get paid for it?) And screwing doesn't really count as work for most people either.
E.g., you get some real use out of your TV, but most people don't get paid to watch TV, nor consider it "work".
Same here. Playing a game _is_ "real use" of a computer. It might not be "work", but "use" it is.
A polar bear is a cartesian bear after a coordinate transform.
Right and using OpenGL for desktop rendering of items? We are already using the GPU'S for just such a purpose.
now imagine this.
One or two Cell's pushing regular data through.
one cell rendering your desktop,
three Cell's rendering three full screen movies on three diffrernt monitors
That is what the Cell's can do. Notice how i didn't say HD movies. I am not sure about those, but it should be able to encode on the fly HD.
they don't sound anything alike.
i've never heard anyone call a celeron anything other than 'celeron' or 'celery'
SearchIRC - Now with live chat directory!
Maybe OpenGL could benefit but not the OS.
So what do you think WGF in Longhorn would be called then? Part of the OS or "high level libraries or apps"?
"I've got more toys than Teruhisa Kitahara."
Oh... and it will contain some bizarre GPL contortion that will create gigabytes of acrimonious discussion here on Slashdot.
I come to this conclusion by blending the old PS2 content creation workstation with IBM's higher end workstations and mixing in a few of the various participants recent behaviors. In short it will be a device that a lot of here would like to have but none of us will have enough use for it to justify the staggeringly high price, thereby insuring that a relatively interesting device only reaches a production volume of a few thousand.
Nothing in the world is more dangerous than sincere ignorance and conscientious stupidity.
I agree HDLs (be it Verilog or VHDL) are much fun to use. And developer boards are becoming more affordable as well. (You can get a dev board with an FPGA and a bunch of ports for a few hundred bucks.)
The drawback is that most of the high-end tools (Modelsim and synthesisers) are extremely expensive. But there are often free tools that work allright, I know Xilinx supply these for free.
The way I see it, phasing out PC industry and introducing Cell was all very carefully crafted and rolled out just like it should, slowly but with increasing momentum over a period of several months to years.
No surprises anywhere, and they're definately not in trouble. Cell is going to be the huge wave of the future, implicated by the upcoming blade server design. It most definately is not a coincidence that things have gone this way.
Perhaps Apple thought that introducing Cell based workstations would cut too much into their own niche. It'd be too much competition with Wintel PC, Apple, Linux PC and IBM Cell (Linux?) all on market.
Will this lead to Wintel-Apple vs Linuxes polarization? Only time will tell. However IBM has been more than wise embracing Linux.
Man, News for Nerds seriously needs to work on his comma usage. I do not actively try to pick on punctuations whenever I read but the bad comma usage in this post by News for Nerds was seriously irritating hehe.
I have been thinking for a while that it would be fun to get into hardware design, but I really don't know where to start. Could you point me in the direction of good resources to read (online and offline) and what kind of kit I'd need to buy to start?
I am TheRaven on Soylent News
Agreed. Just because it has a lot of text doesn't mean that it's not a troll.
This is exciting stuff. The PS3 is *supposed* to go at 2 teraflops, but without a useful OS you can't really link up PS3s together to work in tandem. If you can run Linux on the PS3 however, you suddenly have a large library of apps to run, and I'm sure theres a couple that take advantage/distribute work amogst a system with many linked processors. Which all adds up to the ability to make a 100teraflop supercomputer for around $20,000. (I believe the fastest supercomputer today runs at around 30-40 teraflops). Not bad if you ask me...
And the Xbox display was running on what exactly?
Why is our desire for BET4R GRAFX driving the largest processing innovation in a while that actually reaches the masses?
I'd buy a Tivo with a Cell CPU. Maybe even a Cell based GPU graphics card. But never a general purpose computer based on a Cell CPU.
The Cell is very good at things like video decoding. It's not that great at everything else. Why the hype about this chip?
The other advantage is low power laptop chips and a roadmap to ramp up the (already good) performance of them.
The other possibility is that Apple have got seriously pissed off watching IBM spew out the 3-core G5 for the XBox 360, the Cell for the PS3, and leaving them with an aging 2.7GHz CPU.
Yep, you got it. Apple had no choice. They were going to lose the laptop market completely. In fact they will already be a good deal behind when the first Powerbooks with intel roll out.
But, I had always expected that if Apple had stayed with IBM for chips that they would get OS X onto the cell processor, and that would have rocked. But, I like Linux too, so I'll be fine with Linux being the first os to get to cell. I think it will be revolutionary. I also hope Microsoft has a lot of problems getting Windows ported to cell processors, but their foray into the PowerPC for the 360 might actually just be part of their plan to get there.
- the crypto api module and related stuff like the crypt target in the MD device mapper and the cryptoloop filesystem driver
- software RAID
- CRC-32 routines
- oprofile, which would need to be updated to support system profiling on SPUs.
So, yeah, there is definitely some areas of the kernel that need to or should support SPUs.My blog
Yeah yeah, don't feed the trolls -- I know.
So, you are saying that
- Micro$oft is a "world leader" (probably you meant "market leader" or some such but the mistake is a telling one)
- M$ servers are more secure than open-source ones
- Liberal political views impairs programming
- Open-source developers are sex-crazed (hence the "kinky" program names) and probably paedophile
I'd hate to be you, dude, for it seems that YOU are the one with the problem of being simultaneously arch-conservative and sexually preoccupied. Not too mention you seem to derive a false sense of security from people telling you "it's secure" in much the same way you probably believe Bush really cares about your "security".
Oh and "violent liberalists"? Like someone posted before, you think we're going to assault Bush with a pocket-calculator? Bill Gates had better fear my 19" titanium abacus though.
If it's bad enough to reply to trolls, doesn't it mean that it's worse to reply to replies of trolls?
In that case, wtf are you doing replying?
Exactly. Nice switch, leave Apple with rotting decomposing shitty old x86 while M$ rightly move Longhorn onto much sweeter Cell hardware.
Well done Jobs, nice way to kill off Apple once and for all.
we've got some LPARs here, which are these fancy boxes where processors, memory, network cards, hard drives...you name it...can all be swapped all around on running systems. It really neat, but entirely impractical for several reasons.
Anyway, to do this swapping around you need AIX5.2 or...yes...Linux. Cool, eh?
Anyway, to the point: I wonder when we'll see cell units one can just plug into each other for expandable "on the fly" machines? Ie, you have your cell stack, I walk over with mine and we attach them...but not on a network interface, but actually on a system bus level. If your laptop is using up too many watts, just unplug a few cells...and the docking station could have a cell or two as well, to handle various things. With processors that are designed with a different purpose than the do-everything "central" processing units we're used to, its hard for a lowly unix admin like me to predict.
I dunno. It can be really fun to imagine what the future might bring.
Perhaps apple could pick up using CELL chips for the new MACs, instead of ruining them by shoving a ix86 in them...
---- Booth was a patriot ----
Not to mention that it'll come with an addon chip implementing 100% reliable DWIM and will have Duke Nukem Forever preinstalled.
USE HOT GRITS WITH STATUE OF NATALIE PORTMAN (NAKED AND PETRIFIED)
As you can expect from a CPU coming from Sony it contains DRM (Digital Rights Management, or as you might prefer to call it Digital Restriction Management (that is what it really is)).
Thanks for elucidating some possible reasons why Apple decided to go x86 instead of the Cell (which ostensibly uses the same instruction set). Actually, since I thought it used the same (or similar) instruction set, I don't understand why they would have had to "rewrite a ton of assembler" except to take advantage of the vector portion, but elaborate if you wish.
;)
Now all I need to know is why they decided Intel instead of AMD, and I'll decide this was a sane decision on the Steve's part.
I've been looking at getting this kit, or waiting for this kit to become available. There are plenty of Verilog tutorials out on the web. Not sure of any good sites for teaching digital design... you might want to try MIT's OpenCourseWare for 6.111.
Actually linux hackers are mostly neo-conservative... try reading the jargon file some time, buddy!
Apple deal was barely break even for IBM. Consoles have a bigger audience and you only need to design and produce 1 chip.
Have you ever been to a turkish prison?
You should consider switching to 6502. They are both faster chips as well as ones that can support more than 64K and can more easily be found. (used in Commodore 64 and 128 respectively)
I agree how this processor is unsuitable for a Mac.
But an in-order core is okay in a console, because all the memory latencies and pipeline latencies are fixed for the 5 year run of the console. If you get your compiler to get it right, it'll run like a top.
The in-order becomes a problem (as you alude to) when you try to make follow-on chips and machines that have different characteristics. This wouldn't happen in a console.
I remember how MIPS didn't have memory latency interlocks (in fact, it is was in their name!) in the R2000. But they quickly found out they had to add them in the R3000, when they sped up clock speeds and the latencies which had been staticly compiled into their code were not sufficient anymore.
http://lkml.org/lkml/2005/8/20/95
How many times do people have to be told? It's the built in DRM that Hollywood, I mean Apple wants in their designs. With a chip like the Pentium D in place, and it's associated hardwired DRM, Apple will eventually announce that you'll be able to download movies via iTMS. Hollywood wanted this to prevent pirating of movies. And now that Steve has it, and this slightly successful thing called the iTunes store, wait til you see what he's going to do in a years time. Apple wants 70% of the profits from Blockbuster, Hollywood Video and the like. This isn't about hardware, it's about movies and where Apple wants to be five years from now.
Tell me, what do you think the GPU on a nice new ATI or NVidia video card is? It's a parallel CPU designed to do a specific task extremely well and extremely quickly at the cost of programmer time. There is simply no reason, other than fear of change, why the concepts behind modern 3D GPU performance cannot be extended to more general purpose applications. As the high level programmer APIs to the Cell evolve, the programmer time required to take advantage of this technology will reduce.
Ignorant simpletons probably had the same argument as you when the concept of threads were introduced. "They're too hard to use" the PHBs screamed. Well guess what? Programmers are actually quite smart people, and when you give them a wicked new toy like the Cell, they will figure it out.
There's very nice cheap FPGA kits available at http://www.easyfpga.com/. They also have pointers to some online resources, and the kits include code samples. If you're interested in discussing more about hardware design and FPGA, feel free to contact me. (Note: I have absolutely no relation to easyfpga at all, just been looking at buying a kit for some time now)
Wow, that Spartan 3E kit looks mighty impressive, and at an amazing price to boot. I think I'll be holding out for that one before buying an FPGA board. Thanks for the link.
You're lowballing by an order of magnitude or two. The Cell (one cell) has been demoed decoding 48 MPEG-2 stream simutainously using 6 of the 7 or 8 available SPUs. (7 in PS3, but could be 8 in other uses)
"A language that doesn't affect the way you think about programming, is not worth knowing" - Alan Perlis
Apple has blown it. Big time.
Well, maybe. I certainly think going x86 is a huge mistake for them....unless they're planning on licensing out OSX, which has its own issues. But more importantly, these guys have blown it lots of times before. Seems like they always keep coming back. I'll bet if Cell does make a really big splash Apple will run on those procs as well in a short while. The biggest news for me yesterday was that they consider OSX "cross-platform" from a design perpective. They can juggle chips all they want now, same as Linux.
Given a choice between free speech and free beer, most people will take the beer.
The reply to the troll wasn't a troll, it was an idiot.
I'd even take it a step further; by going cross-platform with the OS, and abstracting the binary compatibility issue away with XCode and Rosetta, they are now no longer beholden to any chipmaker. Intel is probably giving them a sweet deal (they are a pretty high-volume seller, after all), but should that deteriorate, they can always go over to AMD. Or back to IBM for power/cell chips. And in fact, they can do all at once....if they decide they want to have pentium-M in the laptops, cell in the desktops, and opterons in the servers, no problem.
That's so far the only way I can view Apple's move yesterday that makes any sense to me. This is more than just another archetecture move...it's a move above archetectures.
Given a choice between free speech and free beer, most people will take the beer.
So there.
Perfect for mice, keyboards, and more.
"A language that doesn't affect the way you think about programming, is not worth knowing" - Alan Perlis
Why do you think the OS cannot benefit from the SPU? What about encryption? What about RAID and filesystem level API? And networking code (imagine the whole networking code of the kernel running on one SPU, filesystem on another SPU, and X with KDE on yet another.
I didnt think the SPU was specialized. They're general chips that are used as specialized chips in the PS3.
"Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
I really do hope you are right about this. If Apple does things right, they can co-exist on multiple architectures.
I hope so too....I feel my stock will perform a lot better this way than if they are just going over to x86 ;-)
Given a choice between free speech and free beer, most people will take the beer.
CAn'T CompreHend SARcaSm?
Possibly. The other theory goes like this: Jobs always wanted Mac OS X on Intel and that was always the plan, hence 5 years of OS X running secretly on Intel boxes.
Well that is a theory, albeit a poor one. Here is a more realistic one: As a business contingency, as a way to ensure that code remained portable, and as a way to improve QA and debugging Apple maintained an internal x86 build of Mac OS X. Much as Microsoft keeps building Windows internally on non-x86. This is simply good software development.
Wrong. If Apple wanted DRM they could have simply implemented it on the motherboard. I suspect you have it wrong with respect to Intel as well, new DRM is probably implemented via a PCI chipset or some other motherboard component, not the CPU itself. The CPU's involvement is probably only a serial number of some sort, if that. The motherboard could have the serial number, Apple used to do this.
On-chip hardware in support of security system for intellectual property protection.
Each Cell is given a GUID, a global identifier.
Some will no doubt be turned off by the fact that DRM is built into the Cell hardware.
on-chip hardware DRM support
It also has built-in on-chip digital rights management (DRM)
It seems that details on this DRM system are still secret, but I would wager strong odds that is it exactly compliant with the Trusted Computing Group specification. Exactly compliant with the Intel La Grande DRM system, exactly compliant with the AMD Presidio DRM system, exactly compliant with the Transmeta Security eXtensions DRM system.
One DRM to rule them all, One DRM to find them,
One DRM to bring them all and in the darkness bind them.
One Trusted Computing system to bind a network of software running on different CPUs.
-
- - You can't take something off the Internet! That's like trying to take pee out of a swimming pool.
The value of Apple stock is due to iPod not Mac. There is a euphoria surrounding iPod. Unfortunately when, not if, a major competitor such as Sony puts together a viable competitor the stock may come crashing down. That said, stock price has little to do with Apple being an excellent company with excellent products.
> If these are eventually marketed (and don't remain prototypes) they should make interesting development platforms.
Indeed. With all the on-chip DRM, don't whine about on-chip DRM because they're "interesting development platforms".
Thats interesting isnt it? I thought GPL didnt allow it.
By law the coin slot should be broken.
"Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
actually i was going to bring it up since everyone seems to be mum on the issue...
and lets not forget, that the main cpu is a piece of garbage by modern standards. so that it wouldn't make sense to use it in a general purpose computer.
and vectorized code only covers a small handful of apps that could benefit from the cell.
but thanks for the good post and nice links.
DRM baby, here we come.
i just loooooooove handcuffs.
not to mention, i definitely hate being in control of my own hardware and software. what an outmoded way of thinking.
sony: i wish you all the luck in squashing dvd decrypter and similar projects. please, bless us once again with your cuddly DRM schemes.
2 teraflops of DRM power!! who can resist that?
same goes to your cute and friendly allies, nintendo and MS.
Science : Proprietary , Knowledge : Open Source
I can't wait to see what Pong will look like on this baby!
Wouldn't plan9 be the best candidate for the cell processor?
If all these devices are connected with high bandwidth the unix developers that moved to develop plan9 may find this architecture ideal.
"I disapprove of what you say, but I will defend to the death your right to say it." - Voltaire
about Apple's announced move to Intel architecture?
(1) yet another round of binary incompatabilities.
(2) switching endians.
(3) switching from the 64-bit G5 to the half-assed 32-bit plus 64-bit addressing of the x86-64.
(4) yet another competitor in the commodity x86 PC market (which will confuse many users when Apple's new hardware still isn't price competative)
(5) Apple's wholehearted embrace of Intel's DRM strategy, as represented by Intel's new processor and chipset.
Apple taking on Intel as a senior partner makes about as much sense as Sun taking on MSFT as a
partner -- there is far more to risk than to gain. DEC, SGI, and HP all placed a heavy trust and reliance
upon Intel's processor "roadmaps", which have borne much bitter fruit.
Apple is essentially tossing in the towel by adopting Intel 's processor. Only by fully embracing Intel's DRM can they be assured of not having their hardware/software solution trumped by some alternative OS. Loyal Apple users will have a difficult time going from no DRM to crippling DRM. Without that DRM to enforce Apple's "standards", there will be no way to differentiate Apple's pricy hardware from the commodity PC hardware that's already out there in the marketplace.
I find it difficult to believe that Apple having bragging rights to a 3.0 GigaHertz 32-bit laptop crippled by
Intel DRM is worth more than having dual 64-bit desktops and servers and supercomputer clusters.
The CEO of IBM has stated his intention to change IBM from a technology company to an "on demand" company (whatever that means). IBM doesn't want to be in the computer business anymore. IBM wants to do accounting and consulting.
IBM believes there are companies waiting in line to wholesale turn over their internal operations. IBM believes that it knows best how to run a company and wants to teach the world to sing.
Wake up people... IBM is on the wrong path. Current IBM management doesn't care about Linux or computer technology. This story, and others like it, is the fleeting breaths of the IBM technical community.
You'll need to look elsewhere for your savior.
The point is that "better architecture" needs compiler technology that doesn't exist yet - and probably won't for at least a decade - to be really be better and not just on paper!
And who the fuck cares about the fucking ISA, nobody is writing hand assembler for x86, face it, the chips are here, they are fast as hell, and they WORK.
x86 is the right choice at the moment, Apple can and does move again if Cell or any of it's descendants ever becomes realistic alternative instead of vaporware buzzword bullshit.
Many of the comments on this article leave the distinct impression that the writers have not bothered to learn anything about the beast on their own, and are either reading between the lines of the original press release, or blindly accepting whatever they find in one or more response threads. For those who care about getting their facts at least a little straight, there's a link in the "Related Links" slashbox that points at a number of IBM articles on various aspects of the hardware architecture of Cell: http://www.research.ibm.com/cell/ . With a little more digging on Google, you can find the following presentation slides shown by some Sony engineers: http://www.research.scea.com/research/html/CellGDC 05/index.html/ which includes a presentation on programming models for the Cell SPEs.