Is AMD's 65nm SOI process broken?

Is AMD's 65nm SOI process broken?

Summary: Since news first broke that AMD's Barcelona will be six months late (confirmed by AMD CEO) and six hundred megahertz short on clock speed, the microprocessor community began to wonder aloud whether AMD's 65nm SOI (Silicon On Insulator) process is fundamentally broken.  The fact that there are absolutely zero production AMD processors beyond the 65nm Athlon X2 desktop processor at 2.

TOPICS: Processors

Since news first broke that AMD's Barcelona will be six months late (confirmed by AMD CEO) and six hundred megahertz short on clock speed, the microprocessor community began to wonder aloud whether AMD's 65nm SOI (Silicon On Insulator) process is fundamentally broken.  The fact that there are absolutely zero production AMD processors beyond the 65nm Athlon X2 desktop processor at 2.6 GHz is adding fuel to the fire. 

To calm the analyst community and Wall Street, AMD put out some hand-picked demos of a 3 GHz "Phenom X4" which is a desktop variant of Barcelona quad-core CPU built on AMD's 65nm SOI process" at last month's analyst meeting.  That news was greeted with some controversy and debate broke out whether the existence of 3 GHz Barcelona demo CPUs settled the question.  Yesterday, Charlie Demerjian (contributor for The Inquirer) has put forth a theory that may explain this 65nm shortcoming.  Demerjian pieced his theory together based on bits and pieces of information from AMD and concluded that this was nothing more than a case of botched timing rather than a scaling problem.  I actually discussed this subject with Charlie at DEFCON 15 earlier this month and I thought it sounded plausible at the time, but other industry experts I've spoken to were less accepting of this theory.

Charlie's explanation is that AMD never "taped out" (completion of design phase and moving in to manufacturing) a 2-MB cache version of the K8 (class of processors including Athlon and Opteron) dual-core processor.  There was only a six month window of opportunity to sell those higher-end 65nm chips since Barcelona was thought to only be six months away at the time.  Therefore there was no pressing need to ship the higher-end low-volume parts on 65nm for such a short life cycle nor do server vendors want to validate an entire new line of microprocessors for a product that has a 6-month life cycle.  As a result, only a 1-MB cache version of the 65nm K8 CPU was taped out which is only used for the mainstream high-volume desktop market.

Note: The high-volume higher-yielding 65nm parts helped cut costs and increased AMD's gross margins during the last quarter despite declining ASPs (Average Selling Prices).

Anything higher than 2.6 GHz on the desktop parts and the entire line of Opteron server processors would simply have to ride out the 90nm process to the end until the 65nm K10 Barcelona CPU takes over in mid-2007.  Since mid-2007 came and went with Barcelona delayed, AMD was stuck with no choice but to keep cranking out high-end desktop parts and Opteron server processors on the same old low-yield 200mm wafer 90nm process.  Besides, as Charlie explained it, the whole 90nm process was already "paid for" and there was no point in cranking up the clock on 1-MB cache 65nm Athlon X2 processors to 2.6 to 3.2 GHz with half the cache of their 2-MB 90nm siblings since that would result in lower-performing parts at the same clock frequency.

I spoke with respected CPU analyst David Kanter (Real World Technologies) and he had a different take on the situation.  Yes it's true that there was no way AMD could have taped out a whole new 65nm K8 processor with 2-MB cache despite the possibility that AMD "probably had some idea that things might not be totally on target" with Barcelona.  AMD would have had to design a whole new L2 cache controller and L2 cache which is hardly trivial and there are far bigger engineering priorities for AMD to tackle.  As Kanter puts it:

"AMD was faced with a tough decision - they could spend engineering resources on improving the frequency for the 65nm K8, or they could use those same resources to increase frequency and yields on Barcelona."

However, the missing 2-MB K8 design alone cannot explain the reason there aren't any high frequency 65nm K8 parts.  Kanter explained that even if a higher clocked 1-MB cache 65nm Athlon X2 was a little slower (probably less than 5%) than a 2-MB cache 90nm Athlon X2 chip, it still makes a lot of sense to offer the higher-clocked 65nm version at a lower price if it was at all feasible.  This argument makes a lot of sense to me because AMD's latest "black edition" X2 6400+ 3.2 GHz 90nm processor costs a whopping $260 (street price) yet it benchmarks noticeably slower than a $200 Intel E6750 2.66 GHz Core 2 Duo processor.

Note: AMD's newer 300mm wafer with 65nm parts produces 2.5 times more chips than AMD's old 200mm wafer 90nm process.  But Kanter explained that this doesn't mean it's 2.5 times cheaper to produce a 65nm K8 chip since there are still other fixed costs like "packaging, testing, etc".  However, a 65nm processor will be significantly cheaper to produce and have a noticeably cheaper price tag which is something that AMD could use for the high-end desktop.

The reality is that if AMD could simply crank up the clock speed of the existing 65nm 1-MB Athlon X2 processor to 3 GHz or beyond despite its shortage of cache, AMD would almost certainly do it because it will put them in a better competitive position and it will lower their production costs.  So there may indeed be some speed path problems in scaling the existing K8 65nm processor but those speed path problems may or may not be difficult to solve.  Even if they were easily solvable, AMD would almost certainly commit its engineering resources on solving the scaling problems of the K10 Barcelona processor and just ride out the 90nm process.

So the sixty-four thousand dollar question remaining on everyone's mind is whether AMD's 65nm SOI manufacturing process fundamentally broken.  Unfortunately that isn't such an easy question to answer and the lack of high clocking 65nm parts doesn't necessarily prove a serious problem with AMD's 65nm SOI process.  But the lack of higher clocking 65nm parts combined with the delay and underwhelming 2.0 GHz clock speed of the initial Barcelona parts due next month doesn't exactly inspire confidence in AMD's 65nm SOI process.  The existence of air-cooled 3.0 GHz Barcelona demo units tells us that at least there is no hard-barrier but there is a world of difference between showing off hand-picked 3 GHz demo units and producing 3 GHz parts with sufficient yield within allowable TDP (Thermal Design Power).  Whether these problems are temporary snags or a disaster waiting to happen is yet to be determined and we'll have a better assessment of the situation by the end of the year when we see where AMD's clock speeds on Barcelona are.

Topic: Processors

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.


Log in or register to join the discussion
  • As soon as I read the headline...

    I knew it had to be George.

    Your bashing has become boring.
    • I'm missing ZDNet "News"

      George's incessant whining about AMD is not newsworthy in the least, but it's always headlining the news tab for some reason.

      Nobody cares about seeing the same story reported again and again with a different headline every time. There's a lot more to tech news than processor wars, but that seems to occupy a lot of time here.
      • re: I'm missing ZDNet "News"

        [i]Nobody cares about seeing the same story reported again and again with a different headline every time. There's a lot more to tech news than processor wars, but that seems to occupy a lot of time here.[/i]

        Not the same story, just the same old target. I wonder if someone at AMD insulted his dog or something. The blog asks some interesting questions, but provides no real answers, and it took a long time to do it too. I was hoping for more depth.
      • Ditto. When you click on the news link...

        all you get is blogs. Go to E-week if you want to read the news.
    • Factual reporting = Bashing?

      Since when? Somehow I bet if he were talking about Intel you would cheering him on. sigh...
      • hmm

        [i]Somehow I bet if he were talking about Intel you would cheering him on.[/i]

        Interesting point. Since I am neither beholden to Intel or AMD (since I own both), I can honestly say... it's getting old. If it was a constant stream of anti Intel articles, I would probably be just as tired of it.

        Perhaps there is just no good news to report for AMD... could be. But is Intel so perfect that there is nothing bad to report about them? Highly unlikely. Who knows, maybe he has lit up Intel recently, I'll have to go look... but the top so called "News" stories seem to be a constant bashing of AMD, and almost always from George. Doesn't that strike you as just a bit odd?
        • AMD is at fault and ASKED for this.

          AMD brought this scrutiny on themselves when they (on video to ZDNet) complained to high heaven about Intel's claims and turned around and did the same thing repetively. When ZDNet started really looking at AMDs "claims" everything on the AMD side fell completely apart because it was "estimated" performance, comparing themselves to old Intel CPUs, misdirection, and out and out lies.

          Since then they have pushed their target dates back (again), don't seem to be able to get product out the door, and are being eaten alive with pricing by Intel.

          If indeed there is something fundementaly broken with SOI that is going to really set AMD further back and consumers want to know about it. Hmmm, would you want to be the last guy to buy an Oldsmobile just before they shut the factory down permenently? No, and neither would most people. If I had an all AMD shop I too would be following their trials and tribulations very closely.
          • re: AMD is at fault and ASKED for this.

            So since AMD screwed up, they deserve the abuse... I'm actually okay with that premise. So since I don't see any Intel bashing I can assume they are the perfect company, Right? Yeah, and I have a bridge to sell you.

            You seem to be somewhat invested in seeing AMD fall apart, since you comment in favor of everyone of George's AMD bashing blogs.

            Well most of our PC's are used for nothing more than general office work. So if AMD hits the toilet for good, it's no big deal to replace them with Intel PC's when they are due for replacement. So it really doesn't matter to me. I have a budget to work within. If AMD fits that budget better for now, for what I get... that's what I buy. Same exact thing for Intel. I'm not invested emotionally one way or the other. Personally, I'd like to see AMD do well, just to keep Intel in line.
          • They didn't screw up...

            They went crying to the press demanding attention. They got it...

            Like you, it makes no real difference to me at all, I buy what meets the users needs and costs the least to do it.

            And no, I don't think Intel or AMD have many angels working with them, but when one goes crying to the press for attention you have to accept that they may give it to you.
          • Gimme that Olds

            That was a good car and we are still not for sure why GM killed it off of all cars. I mean right now, I would rather have an Olds verses the new "G" line up of cars from Pontiac.

            AMD is just having growth issues. I worried about this when they sued Intel, then turned around and bought ATI. I thought both ideas were fundamentally flawed. But I don't sit on the board of AMD, so what I say means jack.
          • You try competing with INtel.

            At least they are trying. No other chip maker was able to compete in the x86 market.

            AMD has a good product. It is all I sell and have no problems moving the product. In the business environment, Intel has nothing to offer bu higher prices. If you are a gamer, you may enjoy some performance advantage from Intel... a price. Fact is, AMD's chip perform great.

            I'm ready for Barcelona like everyone else. But I doubt I will sell any of the chips until their prices come down to earth.

            Unless you are a gamer, there is no appreciable difference between Intel and AMD...except price.

            Are you sure you are not really George?
    • Typical, you judge it based on the headlines?

      The headline asks the $64K question that has been buzzing in the industry. I spent day tracking down people and analyzing the question. It gives you all the facts so you can make your own assessment. It's only "boring" because you can't read beyond the headline.
      • I noticed and appreciated the extra effort and expert opinions

  • Yepper...

    It must be his week to pick on AMD, he just finished with Apple.
    • That was funny too

      What were there... 500+ comments on that matter. I didn't even contribute my 20 posts to that matter. Had I flung some insults out there, you might have pushed the talk back number over 1000 posts and set an all time record.

      Oh well.
  • Seems to be..and after all the SOI hubbub, too!

    Good topic. AMD made a huge stink about it's incredible and innovative SOI process a few years ago. That along with inventing 64bits, Integrated memory controller and did I say, invented 64bits?

    Anyway, here we are. They fell on the sword - and it seems they backed into it, too. I think AMD needs to invent 128bits, and the new secret process POI (Peanutbutter over Insulator) and try once again.
    • SOI works

      Something else has to be gumming up the works. Yet if we remember years ago Intel had something about NetBurst and Itanium. Two very theoretically sound ideas that worked for about four years and no more.

      Time for something new. AMD never claimed to invent 64 bits, they claimed to invent 64 bits on the x86 platform. Get your information straight.
      • Invented 64bits on x86?

        My point was humor. You actually believe in the notion that AMD or anybody for that matter "invented" 64 bits on the X86 ISA?

        That is even more laughable although it does prove that AMD marketeers actually reached what presumably is the technical crowd!
        • creationists even here

          x64 was an intelligent design and is not the result of an evolution of x86... lol
        • 48 bits?

          Either way, AMD extended the x86 architecture when Intel was ready to move on to something else.

          So AMD didn't "Invent" it. They extended it. They allowed this to happen. They brought 64 bit (48 bit) computing to the desktop.
          They gave us the hardware that allowed this to happen.

          So we are waiting for the true 64 bit computing. Won't happen today, may be later. Who really knows.