AMD's Barcelona: Why we haven't published benchmarks

A month ago we were able to present to you a rare look at AMD's forthcoming roadmap, detailing everything from new plans for the mobile space to giving a better idea of AMD's reasoning behind the ATI acquisition. We left that article with a positive and hopeful note for AMD:

"For a while we had lost confidence in AMD, like many of you had as well, and although AMD's position in the market hasn't changed we are more confident now that it can actually bounce back from this. Intel seemed to have the perfect roadmap with Conroe, Penryn and Nehalem all lined up back to back, and we saw little room for AMD to compete. Now, coming away from these meetings, we do believe that AMD may have a fighting chance. Over the coming months you'll begin to see why; it won't be an easy battle, but it will be one that will be fought with more than just price."

A strong roadmap alone does not make for a successful company; we need to see near term execution as well. For AMD, that means Barcelona has to be competitive. The interesting part of AMD's disclosures as of late is that as much information as AMD has given us about its roadmap for 2008, 2009 and beyond, we have little to no details about when we can expect Barcelona and how fast it will be.

When we headed out to Taiwan, a country of leaked processors and benchmarking opportunities, for Computex we surely expected to return with some Barcelona performance figures. We were hoping we'd come back with the very data that AMD hadn't allowed us to get ourselves when we visited the company over a month ago. And while there were some performance results reported from Taiwan, there was an eerie silence about AMD's updated micro-architecture.

We were determined not to leave the island without running at least one test on Barcelona. We worked long and hard, and we were finally able to spend some time alone with Barcelona in Taiwan. But the story doesn't end there; it's unfortunately not that simple.

Motherboard Problems

We know that Barcelona works and runs benchmarks, as we saw back at AMD in May. But the demos that AMD ran were on its own motherboards, not on motherboards from its partners. AMD's partners just recently received their first "production quality" Barcelona samples, and as expected, the current boards required some heavy BIOS work before the new chips would even work, much less perform up to the expectations set by AMD.

The motherboard we tested on had minimal HT functionality and wouldn't run at memory speeds faster than DDR2-667; most 3D video cards wouldn't even work in the motherboard. Memory performance was just atrocious on the system, but the motherboard manufacturers we worked with attributed this to BIOS tuning issues that should be fixed in the very near future.

In the end, performance was absolutely terrible. We're beginning to understand why AMD didn't let us test Barcelona last month. It's not that AMD is waiting to surprise Intel; it's that the platform just isn't ready for production yet.

More Barcelona


View All Comments

  • TA152H - Monday, June 11, 2007 - link

    And if they had, they would have probably gone with the memory disambiguation of the Core 2, instead of the non-speculative load reordering of the Pentium Pro to III. They may not have realized when they were making it Intel was going to raise the bar.

    Either way, it's impossible.
  • Regs - Monday, June 11, 2007 - link

    Sure..maybe they just decided to pick up a plan that was considered dead and go through with it. It was all ready reported they were trying to re-spin the K8 before the Core Duo was ever announced though it was cancelled because it was dependent on highly-threaded applications that are simply not coming any time soon. Reply
  • TA152H - Monday, June 11, 2007 - link

    That's a different processor design that they killed. But, you bring up a huge misconception that most non-programmers have, that with more work you can get really great performance out of threading. All you have to do is put in the time and rethink how to code. It's utter nonsense, and there is something called Amdahl's Law that is worth reading for people that don't understand or believe this.

    Some algorithms will work well with threading, many, many will not. So, yes, AMD killed that dog and luckily so. If they came out with that, I'd be really, really worried for the company.

    But this new processor isn't anything particulary risky or scary. It's a very nice upgrade in many areas, and considering the K8 is obsolete, but not horrible like the P7, it should turn out to be a fine processor and at the minimum competitive for a while.

    6-12 months is absolutely incorrect. If you're saying that because you believe it, you need to do a little more research on this type of thing because it's entirely implausible. If you're saying it because you're frustrated with AMD and just lashing out, I can understand that completely. But, try to keep it in perspective; it's still a good processor but it just has a few problems before it's release.
  • Regs - Monday, June 11, 2007 - link

    Highly frustrated. If this was a long planned project then their execution is well, I guess we have to see. Like the bias before the Opteron launched I guess we should not make the same mistake twice. Reply
  • TA152H - Monday, June 11, 2007 - link

    While I can understand your frustration, try to keep a few things in common.

    This is pre-release silicon, of course, and that might not seem like such an important thing, but keep in mind that EVERY processor on that core has to run at the designated speed. So, if one can run at 2.8 GHz, one at 2.6 GHz, another at 2.3 GHz, and one at 1.8 GHz, you're stuck at 1.8 GHz for the entire part. The margin for error is so small because of native quad core decision, it's not surprising the numbers are so low considering the stage of development it's in. At this point, the manufacturing is still fairly new, the processor is of course very new, and with the low margin for error it's going to look bad. But, AMD is a weird bird, they seem to come out with terrible processors on the first version of a new lithography, and continue to improve it quite a bit, much moreso than Intel does. This and getting less scatter with regards to maximum frequency should allow the Barcelona to improve pretty quickly through the iterative improvements AMD does with their manufacturing.

    I can understand why you'd be frustrated, but I think it's early to give up on them compeletely. I think most of it is the sting of going native quad-core right off the bat with a brand new processor architecture. It's a lot to deal with in one shot, especially with a fairly new manufacturing process. They probably should have done one thing at a time, but sooner or later they'll get it right. I don't think it will be too late for it to matter either, but who knows?
  • Regs - Monday, June 11, 2007 - link

    Yes trust me I read a lot of articles about the "Bark". From its symmetric ALU's, down to the non-speculative memory access reordering.

    I'm not giving up on AMD at all but it's a ton of fun seeing too CPU manufactures diverge. Just like how you talk about how badly your team is doing mid-season, it some how enlightens your hope for them during the post-season.
  • TA152H - Tuesday, June 12, 2007 - link

    Go Yankees? Reply
  • TowerShield - Monday, June 11, 2007 - link

    I was figuring the product might have died after it didn't show up in May. Reply
  • Gary Key - Monday, June 11, 2007 - link

    It worked beautifully under XP Pro with my laptop, Vista compatibility still needs some fine tuning before the unit is launched. ASUS is intent on completing the project within the next four to six weeks. Reply
  • poisondeathray - Monday, June 11, 2007 - link

    Is the XG Station still designed with the Express Card interface (480Mbit or 2.5Gbit depending on USB or PCI Express)?

    What impact on high resolution gaming does this limited interface bandwith present?

Log in

Don't have an account? Sign up now