Slashdot Mirror
How Sony's Development of the Cell Processor Benefited Microsoft
The Wall Street Journal is running an article about a recently released book entitled "The Race for a New Game Machine" which details Sony's development of the Cell processor, written by two of the engineers who worked on it. They also discuss how Sony's efforts to create a next-gen system backfired by directly helping Microsoft, one of their main competitors. Quoting:
"Sony, Toshiba and IBM committed themselves to spending $400 million over five years to design the Cell, not counting the millions of dollars it would take to build two production facilities for making the chip itself. IBM provided the bulk of the manpower, with the design team headquartered at its Austin, Texas, offices. ... But a funny thing happened along the way: A new 'partner' entered the picture. In late 2002, Microsoft approached IBM about making the chip for Microsoft's rival game console, the (as yet unnamed) Xbox 360. In 2003, IBM's Adam Bennett showed Microsoft specs for the still-in-development Cell core. Microsoft was interested and contracted with IBM for their own chip, to be built around the core that IBM was still building with Sony. All three of the original partners had agreed that IBM would eventually sell the Cell to other clients. But it does not seem to have occurred to Sony that IBM would sell key parts of the Cell before it was complete and to Sony's primary videogame-console competitor. The result was that Sony's R&D money was spent creating a component for Microsoft to use against it."
Pray I do not alter it further.
Help stamp out iliturcy.
I didn't mean to kill the thread with the second comment, but yeah, is there something else that needs be said to this?
Help stamp out iliturcy.
What parts of the processor did IBM pass on to Microsoft? The XBox 360 processor Xenon is basically a three core hyperthreaded PowerPC. The Playstation 3 has a single PowerPC core (not hyperthreaded) and 7 (or 8) simpler SPU processors.
the cell is not "made from scratch". It's based on powerpc. Minus the branch prediction and some other goodies, and with additional cores specialised for numerics called "SPEs". Without the SPEs it's a piece of junk. And the xbox360's processor doesn't have the SPEs.
This article is full of shit.
Big deal if M$ got their hands on a crap, slow design based on the G5 powerpc, and they made it able to execute 2 threads per core and put 3 cores on a die. It has NOTHING LIKE the gigaflops of the cell.
I'm not a games console programmer, but I understood that the 'core' of the Cell and the chip used in the XBox 360 are both derivatives of the standard PowerPC chip. This smells like a couple of trolls being mischievous. IBM can do what they like with PowerPC, and that includes selling it to both Micrsoft for the XBox 360 and to Nintendo to power the Wii.
Sony's payback comes when Playstation3 programmers learn to fully utilize the Cell architecture.
in so many levels.
Can't believe Sony would be so negligent not obtaining any exclusivity agreements against its competitors.
Can't believe IBM would permit such an arrangement; and carry out the release of the Cell Processor designs w/o Sony and Toshiba's willful consent. Bad Practice, Bad PR. I don't give a rip about making money at any costs. Now which major Japanese Company would be foolish enough to approach IBM's hardware team after this?
That's what happens when you delegate too much R&D, I guess...
This is really kind of misleading. The PowerPC, which is at the core of the Cell and is what MS uses as the cores of the Xbox 360, has been IBM's baby for years.
The Xbox 360 uses 3 of the cores. The Cell uses one of the cores plus 8 SPEs (6 of which you can actually use in a game). If you will recall, the Wii uses a PowerPC too, a slightly beefed up Gamecube CPU which IBM made for Nintendo even before they made Cell. And of course Apple used to use PowerPCs (and IBM itself did and does, for servers).
Anyhow, without the Cell's SPEs, there's not a lot to really 'steal'. The lack of SPEs is what makes the Xbox 360 so easy to program for, but the SPEs are what really define the Cell and make it such a floating point crunching monster (better suited for supercomputing than writing video games for in my opinion, and that's not intended as a dis here).
It looks like the engineers who actually make stuff are in charge. I know that's not as good to you as lawyer-based engineering, but some of us prefer physics-based engineering, for spice. OK?
Please don't sue me.
Help stamp out iliturcy.
Because it was a really misdirected effort when it came to a console. Sony really had no idea what the hell they were doing as far as making a chip for their console. Originally, they thought the Cell would be the graphics chip. Ya well turned out not to be near powerful enough for that, so late in the development cycle they went to nVidia to get a chip. Problem was, with the time frame they needed, they couldn't get it very well customized.
For example in a console, you normally want all the RAM shared between GPU and CPU. There's no reason to have them have separate RAM modules. The Xbox 360 does this, there's 512MB of RAM that is usable in general. The PS3 doesn't, it had 256MB for each CPU and GPU. Reason is that's how nVidia GPUs work in PCs and that's where it came from. nVidia didn't have the time to make them a custom one for the console, as ATi did for Microsoft. This leads to situations where the PS3 runs out of memory for textures and the 360 doesn't. It also means that the Cell can't fiddle with video RAM directly. It's power could perhaps be better used if it could directly do operations at full speed on data in VRAM but it can't.
So what they ended up with is a neat processor that is expensive, and not that useful. The SPEs that make up the bulk of the Cell's muscle are hard to use in games given the PS3's setup, and often you are waiting on the core to get data to and from them.
It's a neat processor, but a really bad idea for a video game console. Thus despite the cost and hype, the PS3 isn't able to outdo the 360 in terms of graphics (in some games it even falls behind).
I really don't know what the hell Sony was thinking with putting a brand new kind of processor in a console. I'm willing to bet in 10 years there are compilers and systems out there that make real good use of the Cell. However that does you no good with games today.
Thus we see the current situation of the PS3 having weak sales as compares to the 360 and Wii. It is high priced, with the idea that it brings the best performance, but that just doesn't bare out in reality.
I don't see how "Sonys" research money was used or really in question for any this.
the PowerPC both CPUs are based on is the PowerPC 970, the Processor Apple used in their G5 series- but from there the difference is that they disabled out of order execution- implemented SMT from the Power5, on sonys behalf they added 8 newly developed SIMD coprocessors known as SPEs.
For microsoft well they wrote a new version av VMX called VMX-128, something not to be found on the Cell which still uses the old VMX (Mostly Apples design)
If any thing worked against Sony it's been their high unit cost, their total failure to meet up with the advertising (full hd at 60 fps, etc)
Absent of games etc.
I bought a PS3 myself, but still today 3 years later the only reason I ever kept it was the ability to install linux so it could be put to some use in the absence of the games.
Maybe I have to read the book to get a better picture, it is possible that the article blows things out of proportion. So, I thought that the whole "deal" about the Cell are the SPE's. The Xenon CPU that powers the Xbox 360 is just a custom-made triple core PowerPC. Now, I guess the "customization" of that core is similar to what is done for the PPE of the Cell, so research there could have overlapped, but I would not think that the PPE is the "essence" of the Cell - at least that is what Sony's and IBM's own claims have made me believe.
Additionally, I have to admit that I always thought the usage of the Cell processor a very bad (or, more precisely, very arrogant) decision. It is not just that it has many "cores"; the fact that they are asymmetric and that SPE's are not your usual general-purpose cores, was bound to make it very hard for developers to utilize them. If you wanted to develop for many platforms there is no way you would want to optimize for the SPE's when all other architectures (PC, Xbox...) use symmetric, general purpose cores. So, in my book, the Microsoft engineers knew much better what they were doing than the Sony ones. I guess they are not the same engineers responsible for gems like Me, Vista or Zune firmware.
What I would like to know are the differences that the modified core has compared to a "classic" PowerPC core? So, if MS had not benefited at all from Cell research and got a triple-core whose cores were closer to the original PowerPC, would it be a much different CPU? Anybody knows? If the answer is not, the whole discussion about MS benefits from Sony is moot...
Violence is the last refuge of the incompetent. Polar Scope Align for iOS
IBM semiconductor is known to be a vulture company.
... As STMicro was looking for a replacement partner, IBM took the opportunity, and acquired the technology for a cheap deal.
For example, in the foundry business : STMicroelectronics, Philips and Motorola had a deal for the development of key technologies. But When hedge funds took over NXP and Freescale, they decided to cut their research effort.
The "Wall Street Journal ..."
I think you can stop right there and dismiss the rest of the article.
Hey I want to sell my new book why don't I utilize some people I know!! (I might get the backing of a rival company since it makes my, perhaps former? , employer look bad) [sinister laugh goes here]
"Maybe I have to read the book to get a better picture, it is possible that the article blows things out of proportion. So, I thought that the whole "deal" about the Cell are the SPE's. The Xenon CPU that powers the Xbox 360 is just a custom-made triple core PowerPC", Ecuador
.. is based on IBM's PowerPC instruction set architecture, consisting of three independent cores on a single die"
Well unless you know different we'll just have to take the points raised in the article as accurate. And if the CELL was just a custom-made core then why the need to commit $400 million over five years?
"I agree here as well, there is nothing from the Cell design which went into the Microsoft PowerPC core", IamTheRealMike
"Xenon
davecb5620@gmail.com
Slashdot users read and learn because anyone who fails to understand the following is uninformed >
The SPU's on the Cell and the PPC Altivec unit on the Xenon(X360) are very closely associated never before has IBM done a 128register 128Bit Altivec unit. The 128bit X 128register Altivec VMX128 unit on the Xenon is the best of any CPU it is also an almost perfect subset or cut down version of the Cell's SPU !.
In non braching calculations and assuming no cache misses VMX128 performance is equal to the SPU's performance this is not a coincidence it's a newly shared design feature in both the instruction sets and silicon fab and clearly shows the CPU designers shared alot.
The older VMX is only 32 registers. Only the Xenon PPC cores and Cell's SPU's have this new VMX128 type arrangement with 128 SIMD registers - especially enhanced for multimedia and gaming.
All very interesting how much more powerful the PS3 is, however, it is of diminished relevance if games creators write software for the xbox (because it was out earlier, larger user base etc) and then just port it to the PS3. They need to write specifically for it, and im sure the majority will be creating commercial suicide to do that. Most (all?) PS3 games creators dont even bother to support mouse/keyboard input...bad show!
I bought one, for HD graphics etc etc...and to be honest I should have just upgraded the Graphics card on my pc (which I have now done). Result is HD+ games usable with mouse and keyboard. At least the PS3 looks good under the telly, although the dust is starting to build up.
Let me guess, ten years ago you used to write similar idiotic garbage about how 'teh Dreamcast is more powerful than teh PS2'.
It is sad that crap sites like beyond3d and others from which you obviously are parroting your inane bullshit are so prevalent now. It used to be that morons like you would just sit around babbling about which console had 'more bits'.
Well the Ps3 has some decent games, but you can count them on one hand if you despise shooters!
Sony's payback comes when Playstation3 programmers learn to fully utilize the Cell architecture.
As someone else pointed out, if that was going to happen, it would have happened by now.
The fundamental problem with the Cell is that each SPU only has 256KB of RAM. (Not 256MB, 256KB.) Data can be moved in and out of main memory in the background with explicit DMA-like operations. Given that model, you have to turn your problem into a data-flow problem, where a data set is pumped sequentially through a Cell processor. The audio guys love this. It's useful for compression and decompression. It's a pain for everything else.
It's not good for graphics. There's not enough memory for a full frame, not enough memory for textures, not enough memory for the geometry, and not enough processors to divide the frame up into squares or bands. Sony had to hang a conventional nVidia GPU on the back to fix that. It's useful for particle systems. If you need snow, or waves, or grenade fragments, the Cell is helpful, because that's a pipelineable problem.
There are some other special-purpose situations where a Cell SPU is useful. But not many. If each SPU had, say, 16MB, the things might be more useful. But at 256KB, it's like having a DSP chip. The Cell part belongs in a cell phone tower, processing signal streams, not in a game machine. It's a great cryptanalysis engine, though. Cryptanalysis is all crunch, with little intercommunication, so that fits the Cell architecture.
We're back to a historical truth about multi-CPU architecture - there are only two things that work. Shared-memory multiprocessors ("multi-core" CPUs, or the Xbox 360) work; they're well understood and straightforward to program. Clusters, like Google/Amazon/any web farm, also work; each machine has enough resources to do its own work and can live with limited intercommunication. Everything in between those extremes has historically been a flop: SIMD machines (Illiac IV through Thinking Machines), dataflow machines (tried in the 1980s), and mesh machines (nCube, BBN Butterfly). The only exception to this are graphics processors and supercomputers derived from them. That, not the Cell, is cutting edge architecture.
I've met one of the architects of the Cell processor, and his attitude was "build it and they will come". They didn't.
I was watching interviews with PS3 developers, and one who had made a decent-looking game said all they used was the PowerPC core and none of the SPEs.
Any performance deficiency compared to the 360 is just a programming issue. The hardware is there.
Could you please provide a link to a valid source? I tried to find something, but I always come up with statements like "Xbox 360 has VMX128 while PS3 only has VMX", and on the IBM website the only mentions of VMX128 are about the Xbox's Xenon CPU.
Violence is the last refuge of the incompetent. Polar Scope Align for iOS
Japan has always been like this. Take a look at the PS3 and Wii. Both offer highly proprietary, custom built, in ways convoluted technology to the same problem. But for some reason Sony is treated as idiots while the author sort of forgets Wii takes the prize. For whatever reason Japanese engineers like doing this: When there is no technology that exists that exactly fits to solve a problem, their engieneers tend to build a new one even if there are other pre-existing solutions that almost achieve it. Just like other capital projects, it sometimes pays off and sometimes fails.
Another thing not considered is the fact the XBox 360 is most conservative console out of the three. The software and hardware technology in the Wii and PS3 are dramatically different then their predecessors where they have features that simply don't exist in the ancestors. On the other hand the XBox 360 is more like a beefier XBox. I think the real story is that Sony gambled on some fundamental technology shifts and it didn't pan out. Microsoft on the other hand "played safe" and iterated. There is nothing wrong with that but to claim its some technology shift or special insight, especially given their production and software problems is a bit much.
At first glance, the Xbox CPU doesn't really resemble Cell, but if you just compare Cell's PPE to one of Xenon's three cores the similarity is striking: Xenon, Cell
My server
There are still people who believe the PS3 has a chance of coming anywhere other than last place in the current generation console face-off?
That's point of view is so 2008 and oh so backwards! Sony's killers were MGS4, LBP and FFXIII, the first two are out and haven't caused any gain on the 360 (in fact, the PS3 is losing more ground now than it was a year ago) and FFXIII is now coming out on the 360 too.
The PS3 has failed, perhaps TFA is right as to why, perhaps not, but whatever, one things for certain, Sony made serious mistakes with the PS3 that have sent them flying from 1st place to last place and that aint gonna change this console generation.
This is total bullshit, while it's true Xbox 360s VMX-128 is about identical in performance to a single SPU, that's also just as valid as the 32 bit VMX used on the Cell can reach exactly the same performance as the SPUs do.
We already know the SPUs are based on Altivec / VMX.
I have no patience with inflicting lawyerese on mass market consumers, but these are big boys playing in a big money game. They can afford to hire the best lawyers, especially when they're slinging this kind of money around.
A good lawyer doesn't stand in the way of a business deal, he just makes what you assume about the business relationship explicit. If Sony was surprised by what IBM did, they have nobody to blame but themselves.
Post may contain irony: discontinue use if experiencing mood swings, nausea or elevated blood pressure.
Yes, yes, everyone who disagrees with you is a fanboy and an idiot.
I suppose on learning I've actually written programs using the SPEs on the PS3 under linux (it's 'easy', YDL supplies the tools like spu-gcc and elfspe, but you have to write in assembly language or did at the time) you'll just be horrified that I could have done that but not learned anything about how unconditionally AWESUM the PS3 is.
I meant what I said and I think it's a reasonable statement. The Cell is unparalleled at crunching floating point numbers if you can keep the SPEs supplied with data - unfortunately that's also the problem, and one that is far more easily solved in the supercomputing scenario.
This is just patently false.
Wii: 24,658,719
Xbox 3: 21,774,542
Playstation 3: 12,769,838
Approximate numbers from nexgenwars.com, methodology is here.
Further to this, the Xbox division is earning $178 million per quarter..
By the way, did you know that the Xbox 360 is a PowerPC box too?
"It does not do to leave a live dragon out of your calculations, if you live near him." - Tolkien
Note that the PPC on the cell only has VMX. But how odd that Xenon is the only PPC with "VMX128". Where did VMX128 come from all of a sudden and it just so happens to be great for multimedia and gaming ?. No supprise here VMX128 is a cut and paste subset of the SPU functionallity from on the Cell. Sure a full SPU operates decoupled from the PPC which allows 1 PPC to mediate 7 or 8 SPU's and it's local VMX while the Xenon's VMX128 replaces the traditional VMX. VMX128 is a cut and paste of the Cell SPU's.
http://en.wikipedia.org/wiki/AltiVec#VMX128
http://en.wikipedia.org/wiki/Cell_software_development
Only two processors in existance have SIMD with a 128register 128bitdesign with multimedia and gaming enhancements they are the X360's Xenon and the PS3's Cell. Need i say more !
http://arstechnica.com/articles/paedia/cpu/xbox360-2.ars/4
Read down and yes i am not the only person to notice - the author of this article notices the coincidences about the VMX and the Cell SPU's.
Anyone who programmes the Xenon's VMX128 will be plesantly supprised with the Cell SPU's similarity. It's like having 7 or 8 decoupled super VMX128 units instead of just one locally coupled one. !
The only description I've seen on VMX128 is this one. Someone familiar with SPE assembly could do a comparison between the two. The Cell architecture specification is public.
Only single-precision though. Double-precision performance pretty pathetic. IBM have released an updated CBE spec with better double-precision performance and some other improvements but AFAIK these chips are not used in the PS3, only in IBM's Cell blades and the like.
VMX128 on the Xenon PPC's is brand new and borrows from the design of the SPU's on the Cell these 2 chips are like brothers, they share more than just the same PPC origin they both feature this new type of 128register X 128bit SIMD feature. It's called VMX128 on the Xenon and the basis of the SPU's execution unit on the Cell.
I am familar with SPU assembly and they share much in common - VMX128 is a completly new language extension to the PPC instructions it's unlike traditional VMX instructions which only supported 32 registers. SPU also has a completly new 32bit word instruction set they both feature 3x128bit SIMD operands with multiple word sizes. Both have new adaptations for multimedia and simulation including 128registers and both share similar silicon the SIMD ALU units have almost identical theoretical performance. PS3's Cell has 7 and Xenon has 3 and the theoretical performance of the chips is directly related to the number of VMX128 or SPU's as these account for the bulk of the theoretical performance.
As for the Cells PPC it is typical dual thyperthreaded with standard VMX, in this respect is quite unlike the VMX128 hybrid PPC's used in the Xenon - these Xenon PPC's are a fusion of SPU and traditional PPC technology. The common features they share are clearly a result of idea sharing. What do you expect ! they both come from the same IBM design house. IBM would not want to admit it but the VMX128 is a cut and paste of subset of the SPU.
VMX128 is directly coupled to the PPC and replaces VMX,While the SPU implementation is a fully de-coupled superset of VMX128 which no longer requires a coupled PCC to operate !. They may look a little different but when you look close they share alot more in common than people realise.
It's not a xenophobia thing, but rather Microsoft's poor effort, overall, to appeal to that market. The 360's top games are mostly the type of games popular with Americans (first person shooters, sports, "extreme" sports).
Related to this point, I was thinking of buying a Zune 2 a few months after they came out in the US, but I couldn't find even a first generation Zune anywhere in Tokyo. Sony and MS's mistakes in Japan has worked out unbelievably well for Nintendo. Unfortunately, Nintendo is still focused on family/kid-friendly games and gimmicks, so gamers on a budget here are a bit screwed this generation (not counting handhelds).
I always understood the playstation was a joint effort by nintendo and sony to create a nes with an optical drive. But for some reason sony decided to keep it for itself.
Isn't it true that at this point the differences in processing power do not translate into that big of a difference when it all gets rendered? Even if the PS3 is able to render more polygons or process more lighting effects, the 360 has enough power to render really decent looking games. The differences are pretty subtle. I'm looking at the Kill Zone 2 video that was posted earlier and it looks really great. Tons of shit is happening and there are a lot of neat effects. But the advantages are pretty subtle over GOW2 or even Half-Life 2 (5 years old!) for the 360.
By the way, did you know that the Xbox 360 is a PowerPC box too?
As is the wii..............
note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
But it is just more complicated.
Game developers had a hard time learning to take advantage of multi-core, so even earlier 360 titles weren't that hot. It's even harder with the PS3 with one CPU plus 6 processing elements.
Not so much the tools, but a complete philosophy change in the design of the code.
The Playstation started as a joint project between Nintendo and Sony to create a CD addon for the SNES. Nintendo, pretty far into the project, decided to go with Philips instead. Sony felt betrayed because Nintendo not only went with another company for the project, but one that was not Japanese. Sony decided to develop the Playstation further and release as a game console. The CD-i was the end result of Nintendo-Philips partnership.
"Our opponent is an alien starship packed with atomic bombs. We have a protractor."