By using this site, you agree to our Privacy Policy and our Terms of Use. Close

Forums - Sony - Sony confirm 45nm Cell for 2009, IBM looks to be first to 22nm

Somewhat expected, but Sony and Toshiba (their joint venture produces Cell & RSX for PS3 in Japan) have confirmed 45nm Cell will go into mass production in 2009.

In other news, IBM (who also produce Cell for products other than PS3) aim to be the first to 22nm after moving to 32nm in 2009. Intel are planning on transitioning to 22nm in 2011, so IBM could have a 22nm Cell in 2010. Sony & Toshiba seem to be a year behind IBM though (IBM have been manufacturing 45nm Cell for sometime already), so for PS3 it looks like:

2009: 45nm Cell
2010: 32nm Cell
2011: 22nm Cell

Several articles are speculating PS3 will go "slim" when 45nm Cell hits, but I'm not so sure. They could certainly make a slimmer PS3, but in the past they've traditionally waited until they've been able to make a larger reduction in size than I think will be possible with just 45nm Cell (remember, RSX has only recently gone 65nm, so 45nm RSX is still someway off). With PS3 being bigger than PS1 & PS2 I guess it's always possible that Sony could be planning two size reductions this gen, such as a "PS3 slim" and a "PS3 slimmer".

Sony, Toshiba to build 45nm Cell chip in 2009

Sony and Toshiba today said they would start producing 45 nanometer versions of the Cell processor next year. The process is 50 percent more complex than the 65 nanometer process used for most current Cell chips and will allow the PlayStation 3 to use both a much smaller and cooler-running processor but also to cost less. Versus the current manufacturing process, the two companies' new technique can produce about 50 percent more chips at a time, reducing the cost for each processor.

The update will also be important for notebooks like the Toshiba Qosmio G55, which uses a variant of the Cell processor to decode and transcode videos without taxing the main system. A shrunken, inexpensive processor would let Toshiba introduce the hardware into similarly smaller notebooks.

Neither company has outlined their specific plans, though Sony has historically released a slimline version of its PlayStation consoles most of the way into their respective lifetimes that reduces the size of the case and often adds or removes features based on the company's experience with the platform.

Link

IBM Looks to Beat Intel, AMD to 22nm Node with Chip Breakthrough


IBM's new breakthrough could allow its next generation of Cell processors to reach 22 nm before Intel does.

New techniques will allow tinier computer chips than ever before

The race to shrink circuits is a never ending one.  Having achieved 45nm with its Penryn processors, Intel is looking to move to 32nm next year for the die-shrink of its upcoming Nehalem processor.  Meanwhile, competitor AMD is struggling to get its first 45nm offering, Shanghai, ready for release later this year

However, while the back-and-forth between AMD and Intel often steals the show, the race for die shrinks has several other key competitors.  One is Texas Instruments (TI), who claims to lead Intel in 45nm deployment and performance.  While TI currently doesn't have much in the way of PC/server processor plans, IBM does.  IBM is looking to beat AMD and Intel in die-shrinks and pave the way for its processors to dominate a number of markets, including the PC/server space.

Having already shrunk its powerful Cell processor used in the PS3 to a 45nm production process, IBM is planning to quickly transition to 22nm.

At 22nm, the existing techniques for microprocessor manufacturing useful at the 45nm and 32nm nodes will become obsolete.  While currently lithography techniques cannot produce 22nm circuitry, IBM has developed a new approach called Computational Scaling, which will allow for this tiny-scale production.  The new technique uses advanced mathematical computation to adjust the shape of the masks and illuminating source during etching.

One key advantage of IBM's breakthrough is that it can advance from 32nm to 22nm without fundamental changes to its equipment.  While Intel and AMD are likely to devise similar techniques, the early breakthrough may allow IBM to seize a lead in shrinking, helping it to continue Moore's Law.

Advantages of such smaller processor are numerous.  Due to the shorter interconnects, and other factors, smaller die-sizes yield power savings.  Further, the tiny size will allow for heat reduction.  Finally, it may also allow for more cores in similar packaging.

Like Intel, IBM is planning to bring its 32nm processors to market in 2009.  However, whether it will adhere to Intel's 2011 deployment of 22nm or jump the gun is up in the air.

One thing that is clear is that IBM has plans to deploy 22nm server chips to compete with Intel's offerings.  IBM hopes to apply the new tech to its cloud computing efforts.  It hopes the greater efficiency and processing power afforded by 22nm will help to justify an increasing amount of business and private processing to be offloaded to cloud computing datacenters.

IBM also announced in August that it and its partners had developed a method of manufacturing static RAM (SRAM) cells at a 22nm node.

Link

 



Around the Network

good info. thanks



Pretty optimistic article. The PS3 won't see 32nm until at least 2010, maybe 2011, let alone 22nm. Last I checked, 2016 was the target for affordable 22nm hardware, not 2011. Nanotech isn't the pushover to bring to market that this optimistic article seems to imply.

Possible technologically, and possible economically are two entirely different beasts.  Remember that, using existing tech, IBM was first able to shrink the Cell to 45nm in February of this year (2008)... 18 months before it hits the PS3.  Again, stretching the limits of current fabrication tech, 32nm will likely first happen for the Cell in 2009... but given historical creation-to-production trends (like the recent 45nm one), it won't hit the PS3 until 2011.  

22nm is a whole different fabrication tech, not merely an advancement like 90->65->45->32 has been.  Imagining that it will just fall in line is.. well.. dreaming.



I guess Sony chose the wrong boat for its contract for buying processors if Toshiba isn't able to mass produce 45nm cells 'til 2009 for Sony while IBM is doing right now for themselves.



45nm Cell + 45nm RSX = win.



Around the Network

Cool. Get that price down Sony!



"We'll toss the dice however they fall,
And snuggle the girls be they short or tall,
Then follow young Mat whenever he calls,
To dance with Jak o' the Shadows."

Check out MyAnimeList and my Game Collection. Owner of the 5 millionth post.

cwbys21 said:
I guess Sony chose the wrong boat for its contract for buying processors if Toshiba isn't able to mass produce 45nm cells 'til 2009 for Sony while IBM is doing right now for themselves.

 

 This may be partially IBMs fault as well.  They have been trying to push their Power Architecture into being a more popular processor family, or at least to build it into a solid alternative for Linux Workstations and Servers to Intel.  If they were not willing to offer long term contracts to Sony to provide CELL processors then this may have required Sony stick with Toshiba.  This has been a long term goal for IBM going back to PowerPC days.



Proud member of the Sonic Support Squad

Interesting, I could see the PS3 getting 2 slim versions, the final one being the official PSThree.



45nm CELL in 2009, 32nm CELL in 2010 and 22nm CELL in 2011 would make PS3's CPU extremely cheap.

Now they just need to get the RSX to 45nm or 32nm.

Add to that a motherboard re-design, slimmer blu-ray drive, case re-design and boom you have your slim-PS3.

Anyway im predicting PS3-Slim will be announced E3 2009 or 2010 due out that holiday season -- it'll basically be a PS3 with 45nm CELL and it'll be smaller possibly with a external power supply.



Great info, a price cut next year.