GlobalFoundries lays out roadmap for 28 nm—and beyond

Santa Clara — At the GlobalFoundries Technology Conference yesterday, GlobalFoundries executives spoke at length about the company’s roadmap and prospects. There was much rejoicing about shipments of the foundry firm’s first 32-nm, high-k metal gate (HKMG) chips—otherwise known as AMD Fusion A-series processors, or Llano—but the event really centered on manufacturing at 28 nm and smaller geometries.

First things first, GlobalFoundries revealed that its 28-nm HKMG process is “fully enabled and ready to ramp,” with ramping scheduled for 2012 at its fabs in Dresden, Germany and Malta, New York. A “lead 28nm HKMG product” has already taped out (i.e. the chip design is complete and is about to be manufactured), and GlobalFoundries has managed to produce a functional 28-nm HKMG test chip based on an ARM Cortex-A9 core. On that subject, GlobalFoundries said it expects the High Performance Plus version of its 28-nm HKMG process to enable ARM Cortex-A9 processors clocked as high as 3GHz. Now there’s something to make Intel sweat, if only a little.

In more general terms, compared to its existing 40-nm process, GlobalFoundries claims its 28-nm process will enable up to 40% greater performance and a reduction in switching power as great as 40% at “nominal operating voltages.” With “overdrive,” you can look forward to a 50% speed increase and a 50% switching power drop. The company expects to have a leg up on the competition, as well; it hinted that other independent foundries are struggling to get high-k metal gate processes operational, whereas GlobalFoundries has already shipped “tens of thousands” of 32-nm HKMG chips for AMD’s Fusion APUs.

Next up is the 20-nm HKMG process, which will enter production in 2013. That process, described by GlobalFoundries as a “full node shrink” from 28 nm, is said to enable a 50% reduction in die area and a performance increase of 35%. GlobalFoundries will use a gate-last approach, as opposed to the gate-first technique it’s using at 28 nm. While gate first purportedly enables die size reductions of 10-20% over gate first at 28 nm, GlobalFoundries noted that such density benefits no longer apply at 20 nm. The company doesn’t expect to support silicon-on-insulator at 20 nm, either. 

GlobalFoundries CEO Ajit Manocha.

Looking further ahead, GlobalFoundries is drawing up plans for 16- and 14-nm fab technologies. I understand the company expects to use extreme ultraviolet lithography and non-planar transistor structures—possibly of the tri-gate variety, like Intel’s 3D transistors, at those geometries. GlobalFoundries also said it’s shooting for 450-mm wafer sizes for processes smaller than 20 nm. Larger wafers will allow the foundry to squeeze more chips onto each wafer, allowing higher yields and lower costs. We were told that 40,000-45,000 450-mm wafers have a similar die yield to 100,000 300-mm wafers. Costs per die will be lower, too, on the order of 20-25%.

Now, as you may know, Intel plans to move to tri-gate transistors next year—quite a bit sooner than GlobalFoundries. When asked whether that schedule would put the foundry company at a competitive disadvantage, GlobalFoundries R&D chief Gregg Bartlett offered an interesting answer. In a nutshell, he suggested that tri-gate technology is currently immature. While Intel only has its own chips to worry about, GlobalFoundries has to offer processes that can be easily implemented by its many customers—most of whom are not AMD.

Speaking of which, GlobalFoundries provided an update on its overall business. As it turns out, the company now has over 150 customers (yes, that’s one-hundred-and-fifty), a lot of whom apparently build system-on-a-chip devices and networking products. Its portfolio of 6578 worldwide patents is also worthy of note, as are its capital expenditures, which totaled $8 billion across 2010 and 2011. Most impressively, the company says demand for its manufacturing capacity currently outstrips supply—in other words, it has to expand rapidly to satisfy its customers.

That expansion involves GlobalFoundries’ new fab in upstate New York, which is purportedly ahead of schedule. Production is set to begin there next summer. GlobalFoundries also plans to build a fab in Abu Dhabi—somewhere near the airport, we were told—but a precise timeline hasn’t been settled upon yet. (The company says its schedule will depend on ramp planning in Dresden and New York as well as market conditions.) Those fabs will complement the foundry firm’s facilities in Singapore, which it inherited after the acquisition of Chartered Semiconductor.

After attending the GlobalFoundries Technology Conference, it’s pretty clear that GlobalFoundries has rapidly evolved into much more than AMD’s spun-off manufacturing arm. GlobalFoundries seems to be growing rapidly, and its CEO talks of customers pining for an alternative to the current market leader (that would be TSMC). With what seems like a steady flow of cash from its co-owner ATIC, which belongs to the Abu Dhabi government, GlobalFoundries’ future may be a bright one indeed.

Comments closed
    • jcw122
    • 8 years ago

    You forgot the roadmap in your “roadmap” article…

    • danny e.
    • 8 years ago

    needs more chartage. reading is hard.

      • WaltC
      • 8 years ago

      It’s much easier if you don’t use your eyes.

    • abw
    • 8 years ago

    GF s CEO is a really very talented guy…
    [url<]http://en.wikipedia.org/wiki/Ajit_Manocha[/url<]

      • NeelyCam
      • 8 years ago

      Most CEOs in these high-tech companies are very talented

      • can-a-tuna
      • 8 years ago

      But I’m multi-talented. I can code and boil eggs!

        • designerfx
        • 8 years ago

        At the same time?

      • Sam125
      • 8 years ago

      Tech CEOs are usually very different from your garden variety traditional CEO. It’s not really that surprising considering that leading a tech company often requires a keen eye of where the future is headed or how it can be shaped to your advantage or at least have a good understanding of it.

      That’s very different from an ordinary CEO where they’re basically overpaid cheerleaders.

    • NeelyCam
    • 8 years ago

    I’m a bit confused. Some of this information is conflicting with rumors, and some of it just doesn’t make sense.

    [quote<]In more general terms, compared to its existing 40-nm process, GlobalFoundries claims its 28-nm process will enable up to 40% greater performance and a reduction in switching power as great as 40% at "nominal operating voltages." With "overdrive," you can look forward to a 50% speed increase and a 50% switching power drop.[/quote<] 40% and 40% are unlikely to be simultaneous... it's probably one or the other. But if "overdrive" means higher than 'nominal operating voltages', why would you get a larger switching power drop? Doesn't make sense... higher voltage should mean higher power consumption. (And, most certainly you wouldn't get both 50% speed increase and 50% power drop with high voltage, especially if at nominal voltage you got 40% and 40%) [quote<]The company doesn't expect to support silicon-on-insulator at 20 nm, either. [/quote<] This is a major change... so far all I've heard was FD-SOI. Or, could it be that the [i<]rumors were [u<]wrong[/u<][/i<]..!?

      • derFunkenstein
      • 8 years ago

      I have to think it’s comparing overdrive at 28nm vs overdrive at 40nm. That’s the only way it makes sense.

        • NeelyCam
        • 8 years ago

        Ah – [i<]that[/i<] makes sense.

          • Game_boy
          • 8 years ago

          I agree it is one OR the other though.

    • ronch
    • 8 years ago

    Money comes first, everything else follows. The reason why Intel can continuously outpace everyone is because it’s got the cash to pump into its fabs. That cash is the accumulation of generations of PC processor leadership as well as the ability to spend less to manufacture each chip using a smaller process than the competition. With AMD having to sell cut-rate chips until the Athlon and again since the Barcelona foul-up, funding their fabs just wasn’t that easy. It’s just too difficult to stop Intel’s snowball.

      • NeelyCam
      • 8 years ago

      That was true in the past. Now with GloFo and AMD separated, the situation can change. ATIC is looking at long-term returns, and is investing heavily without worrying about short-term losses (something AMD couldn’t do). The influx of funding can help GloFo catch up for years of R&D funding disadvantage, in order to beat TSMC and bridge the gap with Intel.

        • Game_boy
        • 8 years ago

        Like with TSMC though, that development will be skewed away from high performance processes that AMD CPUs need. Even if GF had the whole foundry market’s customers for R&D money they could not match Intel in ROI in CPU-grade processes. Note I said ROI not that they couldn’t do it technically.

        • ronch
        • 8 years ago

        I guess AMD’s move to spin off its fabs was a good move after all. It’s practically like they asked ATIC to fund their fab R&D and in return giving them the right to take part in the profits. I understand AMD would have to pay GF to fab their chips but since they’re still a shareholder, part of what they pay goes back to them. Long term, if GF manages to catch up to Intel, AMD will be able to match Intel’s Tock every year. AMD will just have to put better systems in place to make their design processes nimble, but I’m optimistic about their future under their new CEO.

          • NeelyCam
          • 8 years ago

          I think it was the best move out of the few bad options they had. They lost the control of the process, have to compete for capacity, and have to pay for GloFo profit margins on silicon…

          But, because they don’t own fabs anymore, they don’t have to directly pay for R&D and fab investments. They also got a lot of cash to pay off loans, improving their cash flow.

          In essence, they couldn’t afford the fabs. They were too far behind Intel (in process technology and in profits), with too much debt. Selling the fabs was the right move, much like buying ATI (which I wrongly ridiculed as a horribly expensive boneheaded move at the time…)

    • Farting Bob
    • 8 years ago

    [quote<]First things first, GlobalFoundries revealed that its 28-nm HKMG process is "fully enabled and ready to ramp," with ramping scheduled for 2012[/quote<] Does not compute. Either its fully ready for ramping NOW or its not fully ready but will be in 5 months. I cant see that they would want to wait 4 months before moving on just for the hell of it.

      • Risme
      • 8 years ago

      What Cyril probably meant was that ramping 28nm for initial production is scheduled to begin in very late Q4 2011/early Q1 2012. and 28nm ramping for high volume manufacturing starting sometime in Q2. That’s what i’ve heard at least.

      • flip-mode
      • 8 years ago

      Just a guess: the process may well be completely ready to ramp now, but the products that will be manufactured on that process may not be, and there can be no ramp without a product.

      • NeelyCam
      • 8 years ago

      (yes – a process tech related thread, so I have to comment…)

      To me it sounds like the various features and devices of the process are working with good yields in semi-high volume test runs. Ramp means getting the full capacity up and running (potentially in multiple fabs) with good yields.

      So, timeline-wise, looks more or less the same as TSMC’s 28nm.

Pin It on Pinterest

Share This