The Mystery of Cell Processors

LucidBeast writes "Consumer appliances requiring more computing power Sony, IBM and Toshiba started 2001 developing "Cell"-processor that comprises of multiple processor cores and should give performance ten times of conventional processors. Now the CNN Money reports that details of the processor will be released Feb. 6-10 at the International Solid State Circuits Conference in San Francisco. Also reported by EE Times. Rumors also tell that Sonys PS3 development platform has already been shipped to some developers equipped with the cell processor."

Comments

And this article tells us WHAT?!!

[mrhandstand]

OK...so according to some marketdroid "Current PC architecture is nearing it's limits". I bet he owns stock in the company that it trying to sell you the new stuff! Last I checked AMD and a few other BILLION dollar companies were still in business.

Now it is true that multiple core chips seem to be where everyone is headed. Even so, I'm not sure how these magical chips will "converge and fuse" digital content. Remeber that this article is A) light on details, and B) put together by a person who is vying for your dollar/pound/yen etc.

Re:And this article tells us WHAT?!!

[Wesley Felter]

The Gekko in the Gamecube is not produced in volume? Millions of G4s and G5s have been sold in Macs, but I guess that's not volume either. And I don't see how high volume on Cell will make regular PowerPCs cheaper.

End Result May Disappoint

[ehack]

When PS2 was launched, incredible specs were also touted; on delivery it ended up cheaper but not more powerful than a high-spec PC with a good video card one year later. I am afraid we might end up with another mediocre product at a reasonable price point. Sony should concentrate on portable systems integration which is where its real expertise lies.

Re:End Result May Disappoint

[jmcmunn]

I think Sony also has some expertise in the console market, afterall they do have two of the best selling consoles ever. And of course they are the current king of the console market, so I would think that should stand for somthing as far as "expertise" goes.

But yes, we will likely be underimpressed with the PS3 when it comes out. But all of the "non geeks" out there who never heard the five versions of the inflated specs that we were promised will still love the machine for what it is, a good game console.

So it won't ever have the most teraflops on the worlds' supercomputer list...who cares?

Re:End Result May Disappoint

[Anonymous Coward]

Expensive as compared to what? The Xbox? Sony is profitable, Microsoft is not. A PC? Yeah right.

The one thing Sony does have going for them is that their technology IS cost effective. That's why they are making boatloads of cash while Microsoft is losing it.

Re:End Result May Disappoint

[Octagon Most]

"When PS2 was launched, incredible specs were also touted; on delivery it ended up cheaper but not more powerful than a high-spec PC with a good video card one year later. I am afraid we might end up with another mediocre product at a reasonable price point."

Frankly I like the idea of delivering power comparable to a high-end PC in a less expensive console. Those that want the most possible power will pay the price for the PC anyway so they can keep it updated. The console buyer wants simplicity and low price. As a reformed geek myself I never want to touch the guts of a computer again. My two favorite electronic devices are my iMac and iPod. When I buy another game console I will be much more concerned with the quality of the games and the ease of use than the raw specs. I'd certainly like to see what all this power could deliver, but I'd rather it be US$199 than "incredible."

Re:Please Help!

[BenjyD]

I always find it odd that so many "Nerds", people who spend their time programming in languages that demand incredibly exact syntax, can't get basic "natural language" syntax right.

Re:Please Help!

[Anonymous Coward]

Trust me, most of those people don't make much sense in programming languages, either, even if it is syntactically correct...

Re:Article text

[Anonymous Coward]

Ya know, one beauty of linking to the article is that we're not caught for c0pyright |nfringement, as the news agency still gets the hits and the ad money. Providing the full text here is a little risky...

Re:Article text

[mrhandstand]

Hey...you never know. Seriously, I post article text when appropriate because most readers/posters can't be bothered to actually read the damn thing unless it's in front of them.

Believe the hype!!!

[Anonymous Coward]

The Cell processor is going to rule!

After all, look how accurate Sony's hype about the PS2 was:

The PS2 will be able to render 75 million lit, shaded polygons per second!

The PS2 will be able to run games at HDTV resolution (1280x960) out of the box with no performance loss!

We will build professional workstations out of 32 Emotion Engine chips which will be able to render movies in realtime and take over the professional graphics industry!

Since all the hype turned out to be completely 100% accurate, I'm sure we can expect the same for the PS3 / Cell Processor.

I suppose it's also possible that it will be another massively over-hyped disappointment with builtin Sony patented lameness that sucks even harder than ATRAC. But you'd have to be a real fucking cynic to believe that!

Re:Believe the hype!!!

[getch();]

I'm not sure why this comment got modded down. Fact is, Sony hyped the "Emotion Engine" until it was blue in the face. That undeniably helped kill the Dreamcast, despite the PS2 having a far poorer library of games (and inferior) graphics for at least the first year of its existence.

I think it's reasonable to assume that there's some serious hype going on with Cell too. Short of some revolutionary SDK, I don't see how all these processing elements will be able to work together efficiently for gaming.

Re:Playstation3 vs. XBox2

[TheRaven64]

XBox2: PowerPC-based CPU made by IBM.

PS3: POWER-based CPU made by IBM.

Looks like a good time to own IBM stock...

Re:Please Help!

[pla]

I always find it odd that so many "Nerds", people who spend their time programming in languages that demand incredibly exact syntax, can't get basic "natural language" syntax right.

We can. The problem arises in that other people cannot (or rather, do not, since most adults can form grammatically correct sentences if you force them to).

Another, humorous, response to the parent post nicely illustrates the problem... The only way to parse it such that it remains (almost) grammatically correct runs along the lines of "three consumer appliances named Sony, IBM and Toshiba that are inneed of more computing power".

Now, you can say that any human reader would get the correct meaning. And in this situation, I'll grant that as most likely true. But if people use sloppy grammar in "obvious" sentences, they most likely will carry that into more subtle sentences as well.

So when a geek chides someone for misuse of a natural language, insisting on an exactness bordering on formal logic - They/We do so because it improves comprehension.

A non-geek might feel comfortable trying to divine a sloppy author's intended meaning. But we realize the consequences... Do that in a programming language, and at best you'll get buggy code. Do that in real life, and you get ambiguities such as (no political commentary intended) whether or not Bush said/implied a link exists between Saddam and Osama.

Think BIGGER!

[Anonymous Coward]

First thing that a game console should get is a mouse and keyboard standard with the joystick.

Why choose a keyboard designed to put letters on a piece of paper? Why not deliver a unique keypad with dynamic reprogrammable key labels to provide a tailored input device to the game your playing? I would rather see "Thrust", "Reload", "Switch", "Comm", etc depending on which game I'm playing rather than qwerty...

Re:Why does a game console need such a monster CPU

[n3k5]

Yes indeed, a console doesn't need a powerful CPU any more than a bathtub needs a good amount of warm water. But people who use it will want it anyway.

Real-time 3d graphics of cinematic quality will always be too slow for general purpose CPUs.

This statement is so silly, it's not even wrong.

developing a game with AI that needs ten times the power of todays CPUs will take many man years and may not be that welcomed by the console audience.

A typical PS3 game takes many person-years to develop, regardless of wheter it uses any AI. For many games, it's a matter of days to develop an AI that needs ten times the power of today's CPUs. Making it so it uses only a fraction of the power of a current CPU is the difficult and time-intensive task. Console-gamers play much more single player games than PC users, so it is particularly them who welcome a sophisticaed AI.

It's very difficult to do multithreaded apps, and the difficulty rises exponentially with the number of threads.

It's very easy to make multimedia-processing apps multi-threaded and rendering scales particularly well over multiple CPUs. If the engine uses an API like OpenGL or D3D, it doesn't even have to know how many threads are used to render the visuals, the programmer doesn't have to do anything. Many AI algorithms also scale pretty well over multiple threads and/or closely coupled CPUs.

[Sony should concentrate on graphics chips instead of general purpose CPUs.] They could save millions of dollars from developing and advertising the new console. [Instead of re-using the old one, just with more GFC chips.]

These CPUs aren't 'general purpose' in the sense like a 486 is general purpose. They are specifically optimised for parallel operations, floating point calculations, vector math ... So they can save even more money the way they're ding it, because they can re-use the same architecture in lots and ltos of media processign devices, not just gaming consoles, and they can not just scale pure graphics performance, but also audio performance, video performance, whatever is suited to the Cell architecture.

Re:Article text

[upsidedown_duck]

In addition to the obvious obsurdity of saying "all", the naive optimism of the broadband convergence prophets puts them into denial about the fact that many people often don't want gaming to be on-line. I've seen some of the sneaky things companies do to glean marketing data off of their paying customers, and it is rather annoying. I don't want my PC phoning home every time it boots (my ISP trys this), nor do I opt to plug a DirecTV unit into the phone jack, for example. Already, people report their life and soul to the tax agencies, their employers, etc., and, at least, people should be able to find entertainment with a respectable amount of freedom. The market will very likely show that people will choose not to have an always-networked gaming machine. Networking is certainly a good choice, but it shouldn't be the only choice in order for companies like Sony and Microsoft to capture as many customers as possible.