Sony & Toshiba Disclose Cell Fab Plans

sean23007 writes "InfoWorld is running an article about Sony and Toshiba's plans for new fabrication plants to build the 'Cell' chip jointly developed by Sony, Toshiba, and IBM for use in the Playstation 3 and other home entertainment uses. The new fabs will be located in Nagasaki and Oita, and both companies plan to spend $1.7 billion over the next 3-4 years in their construction. They will be capable of using 300 mm wafers with a 65 nm process. The chip is slated to be the first 1 teraflop consumer device."

Comments

But the Cel isn't going to be in the PS/3

[BancBoy]

According to IGN anyhow... To quote - Online news sites are reporting that the spring 2003 issue of Electronic Design Chain, an electronics trade magazine, features PlayStation creator Ken Kutaragi on the cover, and also contains very surprising news about the Playstation 3. According to the reports, Kutaragi mentions that final production of the "Cell" chip, originally thought to be used in the PlayStation 3, may not be ready until 2007. He also confirms that the CPU in the PlayStation 3 will in fact not be the Cell processor, contrary to earlier reports. With a targeted PlayStation 3 launch in 2005/2006, delayed production of the Cell processor may have caused Sony to find a different solution for their next-generation console.

2007 Then

[Josuah]

I guess this answers all of the speculative questions on when the PS3 will be able to come out. If Toshiba needs four years for its 65nm production lines, then 2007 is the earliest point that wafers could start coming off the line. So Christmas 2007? Looks like the PS2 still has a very long life ahead of it.

32 MB?

[Anonymous Coward]

With 1 Teraflop of processing power, I hope it'll come with more than 32MB RAM this time.

Where's IBM in all this?

[Ra5pu7in]

Why are only Sony and Toshiba reported? Does IBM not plan to produce and Cell chips or do they already have fab facilities?

Who said anything about phones???

[jayratch]

I'm sorry, but this conversation somehow went past me.

Where in the article does any reference to wireless phones occur? And where in reality does a teraflop processor have its place in a phone?

The real question here for us ignorami like myself is, how will this processor stack up against PC processors- and will it run Linux?

Joking aside- and Beowulf clusters aside- this sounds like it could be a good idea for a versatile chip. If Toshiba's involved my guess is it will not be just for PS3, perhaps we'll now have another major plaer (or two) in the PC chip market? Hmm, Sony and Toshiba, leading laptop manufacturers, making their own chips. It's like Microsoft making keyboards and mice, I suppose, but perhaps better.

Just my .02

cost justification

[ih8apple]

I used to work for Intel in the Fab automation software department and I find it hard to believe they're can justify investing this much to start up new fabrication plants for an unproven product.

Usually, with initial chip production at this scale, they lease out fab production time from other companies. Only huge production plans (like Pentiums or PowerPCs) generally justify building entire new Fabs. Plus, with the world economy slow, there's plenty of capacity at the world's fabs. Here's a good article on fab capacity

Re:cost justification

[sigep_ohio]

Well with the number of PS2's that have sold so far worldwide, I guess Sony thinks the demand for Cell will be even bigger. I know Cell won't be in the PS3, but since it is a scalar architecture it can be placed in anything from cell phones to video game machines to computers. This makes the market for Cell even larger than that of a Pentium or PowerPC or The Emotion Engine in PS2.

Re:cost justification

[watzinaneihm]

Atleast some part of the decision may be due to the culture of Sony
Sony (the original one, not their music division) have always been about making a product and then finding a market for it. They pride themselves on being the lone-wolves and hence came up with a lot of products which are completely non-standard (unless the world accepted their standards)the oft used betaMax being a good candidate. Sony's memory products today are a good example, they are tiny but are not interchangeable with others (not all prodcuts, but there are examples like their USB cables etc.) .A completely new chip for a game machine seems to fit right in, compared to MicroSoft moving to Celerons.
But then again they used to be able to come up with a product so good that they opened up whole new markets.
This post is partially based on a reading of "Made in Japan" by Akio morita, and I understand that decisions of Billions are not always decided by the "culture" of a company.

PS3 idea

[RealErmine]

They should just transcribe the Final Fantasy combat system into a hardware implementation. That's the only reason people buy these things anyway.

I propose that the limit break be implemented by some sort of register overflow.

They should do this in the Cell chips that are rumored, in the future, to be deployed in various home appliances. I, for one, would be impressed when my dryer finishes the tumble cycle and then performs a super-attack on the toaster.

Re:Make "Cell" chip Open Source!

[Dajur]

What the hell are you talking about. Even if they "open sourced" the processor, how many open source developers do you know that have access to a 65nm Fab to play around with it.

Re:it looks like scea will lose their way

[cant_get_a_good_nick]

scea has been fighting to keep the ps series as a game console only, but MS is forcing them to integrate the ps3 with dvd/music/internet technology...

More like the reverse. Sony always wanted to be a hub. MS saw that if this thing became a hub, the (relatively) cheap game console could become an alternative to a real PC, therefore an alternative to MS. Coudn't have that, came out with XBox.

makes perfect sense...

[sterno]

Even if this chip's architecture turns out to be a dud, they'll have plants ready to produce 65 nanometer processors. Eventually they'll have some chips running at 65 nanometers, and they'll have a fab ready to produce it. Worst case scenario is that they can sell their fab capabilities to other companies that want to run at 65 nanometers. The odds that these plants won't have a long run value seems pretty small to me.