Before every major architecture launch from AMD or NVIDIA, the companies typically hold an editor's or tech day. These events usually last about a day (sometimes two) and involve a bunch of press sitting in a conference room while they get peppered with presentations and pepper back with questions. Engineers and key architects are usually present. The goal behind these tech days is to help the press understand, at least from the manufacturer's perspective, what makes their new architecture tick. Benchmarking usually doesn't happen at these events, but typically we get hardware at the event or shortly thereafter. If you're curious, Intel doesn't typically do a tech day - that's what IDF is for.

Two weeks ago AMD held one of these tech days for its upcoming Bulldozer architecture, which will be sold under the FX brand (e.g. AMD FX-xxxx CPU). Although it'll still be a little while before I can talk about most of what transpired at the Bulldozer tech day, there is one thing I'm allowed to share today: overclocking potential.

AMD was conducting overclocking experiments at the tech day and had three different stations setup for us to look at. The first used a sub-$100 closed-loop waster cooling solution from Antec (Kühler series). I can't tell you much about the chip itself other than it is an 8-core FX processor that AMD was able to overclock to 4.8GHz using the Antec Kühler.

Next up was phase change cooling. Armed with a phase change cooler AMD pushed another 8-core FX CPU up to 5.894GHz at 1.632V.

AMD ended on its most aggressive cooling solution: liquid helium. Using liquid helium AMD was able to take Bulldozer to a new world record of 8.429GHz. The resulting overclocked frequency was high enough to get AMD's FX processor inducted into the Guiness Book of World Records for the highest frequency for a computer processor.

None of this tells us much about how Bulldozer will perform unfortunately. The most interesting number is likely the first number (4.8GHz) which gives you the upper bound of what to expect from an overclocked Bulldozer at home without any exotic cooling.

AMD recently announced it started shipping server versions of its Bulldozer CPU and that desktop parts will be available in Q4.

Comments Locked

43 Comments

View All Comments

  • silverblue - Tuesday, September 13, 2011 - link

    "if". Not sure I'm quite that optimistic. :)

    I didn't expect Bulldozer to be a dynamite overclocker on air due to its complexity, so if it can realistically do 4.5GHz, that's not bad. I'm a bit concerned that their higher clocked tests are only showing a single module.

    Any word on the stepping of those Zambezis?
  • fic2 - Tuesday, September 13, 2011 - link

    Not to mention the lowest overclock is done on water. From what I understand SB can do 4.5GHz pretty easily on air. Not sure whether 4.8GHz oc on water equates to 4.5GHz on air - especially since they don't share an air oc.

    Pretty sure that SB is just as complex as BD.

    Good point that this might be oc of a single module since AMD's turbo can shutdown other modules (or was that cores?) to allow a single one to go higher.
  • wgmann03 - Tuesday, September 13, 2011 - link

    If you check the CPU-Z, You'll see 6 cores were disabled for the benchmark. This is very misleading.

    So essentially you have AMD 8 core Processor @ 2 cores 2 Threads @ 8.429 GHz.

    You have an i7 980x with 6 Cores @ 6 Cores and 12 threads @ 7.195 GHz

    http://img42.imageshack.us/img42/5084/amdlies.jpg
  • Malih - Tuesday, September 13, 2011 - link

    The record is for highest overclock, not highest overclock on 8 cores or 6 cores or whatever number of cores. You might feel tricked, but I don't think they're lying there.
  • wgmann03 - Tuesday, September 13, 2011 - link

    It's all or none. You can't half-ass it. 7.195GHz with 6 CORES and 12 THREADS is a far superior overclock than 8.429GHz with 2 Cores and 2 threads. AMD cheated.

    Just goes to show you this is all a marketing ploy and AMD will try everything possible to skew the data and mislead their consumers. Shame on you AMD.
  • mga318 - Tuesday, September 13, 2011 - link

    I don't know if its intentional or not, but the tone of your written sounds *really* angry...and that just makes you really ridiculous sounding.

    In any case, your right. 7.195GHz with 6 CORES and 12 THREADS is indeed a superior overclock, but its also an overclock that won't get any world record. That's all AMD was going for and I don't think they have claimed otherwise. And if you notice, the previous record was only 1 core, too (which is incidentally, one core less than AMD).

    You're making a mountain out of a mole hill.
  • wgmann03 - Wednesday, September 14, 2011 - link

    Fair enough, My tone is angry because AMD cheated yet they claim they have a world record cpu. They handicapped their processor for a higher number. That is not how you conduct a scientific experiment. The overall data is skewed to represent their product is superior.

    The difference between the Celeron and the Bulldozer was that the Celeron was used to it's fullest technological capabilities and beyond where as you had to disable to features in the bulldozer to beat a number from a chip developed in 2006.

    Also, you set a precedent for future world record overclocks to not use the full features of CPU to accurately measure performance. Also, the fact that every person that attended the overclock session is under NDA. Meaning the press is redtaped, which is complete BS.

    What is there to hide AMD?
  • silverblue - Wednesday, September 14, 2011 - link

    Somebody replied to this sort of argument on Toms' saying that BD had been clocked to "8.036 GHz on 8 cores". I'm not sure of the validity of this particular statement and I don't have the time to check every video to see if it appears or not... :p
  • seapeople - Saturday, September 17, 2011 - link

    AMD Bulldozer overclocks to 8.429GHz on liguid helium!

    Subsequent CPU testing indicated this was roughly equivalent to an Intel Core i3-380m in single threaded performance.
  • analog1 - Tuesday, September 20, 2011 - link

    I wonder?

Log in

Don't have an account? Sign up now