8429.38MHz is the new CPU Frequency World Record claimed by a near-production desktop version of AMD’s FX Bulldozer CPU! Overclockers.com witnessed the event first hand in Austin, TX at AMD Headquarters on August 31st during an AMD FX pre-launch briefing, and the record is set to be confirmed by the Guinness Book of World Records and HWBot.org. The new AMD FX record smashes AMD’s previous best of 7378.25MHz set with a Phenom II 955 Black Edition.
 Welcome To AMD |
 AMD FX at sunrise |
Legend Of AMD FX
Read on below for details on how the record was set, video of the action, what the record means to us, as well as pictures from throughout the demonstration. Is it worth reading on? 5Ghz for Bulldozer is commonplace with air cooling for under 100 dollars…keep reading!
AMD Bulldozer World Record
It’s worth saying again folks – 8.4GHz+ at 2.02Volts. Wow! We’ve obtained an exclusive validation screenshot, something you won’t find on any other site at this point so you can see for yourself!
AMD Bulldozer World Record 8429.38MHz
One remarkable part of this world record is that it was hit in just a couple days of final testing, with just a few hours of actually going after the record under the most extreme conditions. Those doing the overclocking, Brian Mchlachlan (Chew*) and Sami Maekinen, had also done some pretesting on these chips in the week prior when they found 8 Bulldozer CPUs that would hit 8Ghz on extreme cooling – that confirmed very promising potential with high voltage tolerance and frequency scaling under cold. Ultimately, the final run was achieved through a two-stage approach in which a Liquid Nitrogen (LN2) evaporator pot was used on the CPU throughout, while the final record fell using Liquid Helium (LHe). Check out the following video to see the LHe overclocking in action!
AMD also produced their own final video cut from the demonstration:
In the first stage, LN2 was poured from a thermos into the pot to cool the Bulldozer processor down to -190C. Once at that temperature, we were observing results of 7.8GHz at 1.9V and AMD felt this Bulldozer chip was promising enough to break out the REALLY cold stuff, Liquid Helium (LHe). LHe is the ultimate in cold for subzero cooling; it boils just a few degrees Celcius above absolute zero. It is so cold in fact, that after pre-cooling to -190C, they had to ensure all the LN2 had boiled off before switching out – the liquid Helium would freeze the Liquid Nitrogen in the evaporator and interfere with optimal heat transfer!
LN2 Evaporator preparing for the record-breaking attempt
In the second cooling stage, an attachment designed by Aaron Schradin was added at the top of the LN2 evaporator to secure the pipe which would provide a constant flow of LHe into the evaporator, and a nozzle was affixed near the inner base of the container which encourages turbulence as the LHe enters. So cold that it boils violently on contact with the base of the evaporator, a constant plume of LHe fog erupts from within as you can see from all of the pictures. The fog itself is cold enough that they rigged a motherboard box to fit on top of the evaporator and used fans to blow the fog away from the motherboard in an attempt to minimize the condensation that forms on the chilled components – that is why the cooling apparatus is largely obfuscated in many pictures.
 Liquid Helium Coolant Hose and Pipe |
 Starting flow of liquid Helium |
 'Custom Fabricated Motherboard Box Fog Retention Mechanism' |
 Fog after installing liquid Helium Feed |
 Fog Plume Used to Judge Flowrate of Helium |
 -223C probe reading - temperature accuracy gets coarse below -200C |
 Liquid Helium cooling mount, iced over |
 The PCIe section of the motherboard curling from extreme temperatures |
World Record Significance
Still, unless you are intimately familiar with subzero overclocking like I am, or you just get excited by new records like I do, you may be asking what a CPU Frequency record matters to Joe Sixpack? Don’t let anyone – or any marketing – fool you. This record isn’t going to change the way you compute daily, it isn’t going to mean you hit 6GHz on air, and it isn’t confirmation of what other benchmark performance we should expect to see from Bulldozer. We’ll be bringing you the benchmark performance, air cooling OC results, as well as more subzero results soon, but you’ll have to stay tuned until we can bring you all of those tests in the not too distant future. All that said, results of “well beyond 5GHz” on air were claimed on cooling solutions priced below the $100 mark!
 The sign didn't say "Do Not Touch" |
But what does it really mean? The world record feat brings us a lot of excitement about the possibilities for Bulldozer, but we still should be asking what it really means. In recent years, the game of high frequency records was the sole domain of Intel processors, and only about 20 of their chips have ever recorded tipping the scale at over 8GHz though hundreds of overclockers have tried for years. But even Intel hasn’t had any current generation contenders on this playing field; Intel’s best record was set just last month on August 12th, 2011 when TaPaKaH hit 8308.94MHz on an old Cedar Mill chip. That still puts Intel over 100MHz behind AMD’s new record, and the latest AMD FX chips aren’t even available at retail yet.
The old Cedar Mill record is worth looking at closer now despite the fact no self respecting person in the modern day hardware game would be caught with one in their rig. Intel’s 8.3GHz mark on Cedar Mill is rather telling in regards to what AMD’s Bulldozer holds in store for overclockers. With Cedar Mill chips half a decade old breaking records as recently as last month, and Bulldozer breaking the World Record before it hits market – without any doubt this is only the beginning for Bulldozer. AMD will be the first to hit 8.5GHz, and it will happen before long, the only question remaining is which overclocker will hit it first!?
 Bulldozer overclocked Voltage, Frequency, & VID |
Looking forward to the horizon, what about 9GHz? Yesterday most people would have told you that isn’t realistic. Today many would likely still say I’m stupid for posing the question. But I will tell you this. Pre-production chips historically only scratch the surface of what the architecture is capable of. Given time as fabrication processes and yields improve while more people get their hands on more chips, we could hear reports of AMD seriously flirting with 9GHz soon enough. Granted however, the frequency scales with cold especially well, and we were watching liquid Helium which is as cold as it gets… But given time and liquid nitrogen, I expect the overclocking community will continue pushing these boundaries as the architecture matures!
Bulldozer Voltage Tolerance & Frequency Scaling
Bulldozer is in fact built like a Bulldozer. It will take a lot of abuse and keep on pumping! Now keep in mind the voltages discussed here were under extreme cooling – voltage tolerance under subzero cooling is considerably higher than ambient cooling. However, even on subzero hitting voltages of 2V, 2.1V, or 2.2V is especially high – those are definitely in the range where typically on Phenom II the chip could very likely never run again. The previous AMD record of 7378MHz was hit on only 1.88V. Its safe to say Bulldozer can handle quite a bit of extra voltage compared to what we may have become accustomed to!
Once you get your hands on one, watch your temps as always, and make moderate increases while confirming frequency is scaling with the increases. Do that, and you are likely to have a hard time killing one while finding a lot of headroom for your overclock. In passing conversation, Brian and Sami mentioned doing 5Ghz on air running fully multi-threaded benchmarks.
Finally on the scaling perspective, the results are confirmed that like the Phenoms, Bulldozer has no cold bug and the colder you can take it the higher the frequency and voltage tolerance climbs. In this sense, Bulldozer should receive a warm welcome from the overclocking crowd. Unlocked multipliers come standard; it’s highly tweak-able with all the settings you’ve grown accustomed to from Phenom, and it likes strong cooling so you’ll get additional headroom from your air or water cooling investments!
 Bulldozer 8.140MHz at 1.944V |
 Bulldozer 8GHz at 2V |
At this point we will leave you with that, as sometime soon we’ll have further testing and the ability to talk about results you want that aren’t mentioned here! Ask question or make comments directly below this article, as I’ll be actively joining in the conversation. Also you can read AMD’s own press release, or review our AMD Phenom Overclocking guide that also applies to Bulldozer so you are ready when these chips hit the streets!
In the forums, find constant updates on Bulldozer Rumors, AMD FX Bulldozer Socket questions, and the latest AMD Bulldozer CPU discussions. As soon as the official release date is announced you’ll hear it from us!
-Matt Bidinger (I.M.O.G.)
Tags: amd, bulldozer, cpu, frequency, FX, world record, zambezi
09-13-11 01:09 PM
09-13-11 01:10 PM
09-13-11 01:12 PM
09-13-11 01:13 PM
09-13-11 01:16 PM
09-13-11 01:17 PM
09-13-11 01:17 PM
09-13-11 01:19 PM
09-13-11 01:21 PM
09-13-11 01:28 PM
Now only a short time before other benchmarks start rolling in, let's hope for some competition!
09-13-11 01:37 PM
09-13-11 01:37 PM
Glad to hear about this for many reasons........Better top up your
09-13-11 01:47 PM
09-13-11 01:52 PM
With my luck even if I get one then I finish with something like 6GHz on 2.5V
09-13-11 01:53 PM
/me steals some LHe from the NMR lab. ...
09-13-11 01:57 PM
If Bulldozer is close to as efficient as SB, then the higher GHz could make up for any possible lack of efficiency for benchers.
09-13-11 02:05 PM
Damn... I havent been with AMD since S939 days...(runs to newegg to check out AMD mobo's)...
Did I see a 6.5Ghz Vantage labeled chip? Sexy, like Gulftown, only better.
09-13-11 02:07 PM
Chew* is going to make it difficult for me.
09-13-11 02:10 PM
Of course I jumped on a 2600K + eVGA P67 yesterday for ~$335... I'm hoping it wasn't a bad decision...
09-13-11 02:13 PM
If I dont see you hitting 8Ghz+ shortly after its release, Im going to pin you down and rub Intel products all over you.
09-13-11 02:13 PM
09-13-11 02:18 PM
2011 - 5ghz is the new standard
09-13-11 02:19 PM
09-13-11 02:23 PM
I now hope the benchmarks will hold candle to the SB architecture, that will be a breakthrough for the green coats
09-13-11 03:05 PM
Were the RAM timings being reported incorrectly by CPUz? I mean 900MHz @ 2-16-2-22???
09-13-11 03:13 PM
09-13-11 03:16 PM
09-13-11 03:17 PM
09-13-11 03:20 PM
09-13-11 03:21 PM
Looks like things could get interesting very soon
09-13-11 03:36 PM
Apologies for diverting attention away from the bulldozer, i'm sure it will be so efficient they will bring out a mobile version btw
09-13-11 03:36 PM
Can't wait to pick one of these up and abuse it
09-13-11 03:45 PM
09-13-11 03:46 PM
I'm just eager to see benchmarks other than validations.
09-13-11 03:48 PM
09-13-11 03:48 PM
09-13-11 03:50 PM
Hopefully it takes a bigger stride than the previous generation transition. If so, BD at 7.6+ on LN2 might be able to hang with SB @ 5.8+.... here's to hoping. Temporarily obviously as SB-E is on the horizon
09-13-11 04:30 PM
09-13-11 04:41 PM
09-13-11 04:56 PM
09-13-11 05:28 PM
You were not kidding when you said you had something AMAZING in store for us last nite!!!! I figured it would have to do with BD, but a WR right out of the gate?
Tapakah will be pissed once that validation makes it to the Bot for sure... He invests so much time and effort into pushing them Cedar Mills as high as they will go and now here comes AMD and trumps on that with pre-production units?... Ouch.
I really don't care much if BD is not as efficient as SB; the way I look at it:
No Coldbug + No bclck limitation + High tolerance for volts = TOTAL WIN
All that is left now is the "waiting game"... I don't know how I'm going to work the money side out, but one of these chips will find its way to my place as soon as they are available for sure...
09-13-11 05:31 PM
09-13-11 05:39 PM
09-13-11 05:50 PM
On the positive side: 4.5-4.8ghz should be do-able by the majority from what it sounds like and that's still substantial for a long time to come. And the bulldozer is supposed to be cheaper than SB? or did i red that wrong.
09-13-11 06:06 PM
09-13-11 06:13 PM
09-13-11 06:16 PM
09-13-11 06:47 PM
09-13-11 07:01 PM
I just want to see a clock for clock comparison with SB (just like everyone else). This is still VERY cool (no pun intended).
09-13-11 07:03 PM
Exactly, hype was created by the "people", not the manufacturer, realism always sets in after people try it for themselves
09-13-11 07:04 PM
(Reference.)
09-13-11 07:31 PM
Intel would not back any claim that a chip can hit 5ghz. They tell you what the chip is rated for 3.4ghz w/3.8 ghz turbo boost. Anything you assumed to be promised past that point is 100% rumor/hearsay... and never spoken by an Intel rep I can guarantee it.
AMD and Intel have different approaches to CPU's and marketing. Intel generally has faster architecture, while AMD usually rules the overall frequency. Each will exploit the work of overclocker's to their marketing gain, but will never sell you a 5ghz chip... unless they charge you for a 5ghz chip
These tests and max validations are good for one thing... fun
09-13-11 09:06 PM
So while I was standing next to the table, I'm going by memory here, but they were talking about this after they switched out the first two setups they had on the bench. So I believe this was just before the 3rd setup, and it was the 4th CPU they used for the press demo to try to get the record. I thought it was weird as I was standing there Sami and Brian were discussing what to do next and Sami said something about taking a shot in the dark, just gambling on an untested CPU next. I have no idea if they then grabbed a new CPU from the tray, or picked from the trays and trays of CPUs that had already been tested in some way at least... But I thought that was sort of weird since there were so many chips that had already been tested to some degree. There were a lot with VID marked as well as LN2 pretesting to 8GHz or so labeled and sitting in the trays next to them.
So seeing all the labeled CPUs, clearly there was a lot of testing that went into determining which chips behaved which way. Checking VID and recording clocks and voltage to determine trends in frequency results across chips. AMD had sent out CPUs a week before also, where 8 BD chips hit 8GHz - they didn't say 8 out of how many. That all occurred the week before the event reportedly, simply on LN2. An 8GHz chip on LN2 is going to be a contender with 8.3GHz on LHe.
So the obvious question... If they had been through that many chips in pretesting, they had spent so much time learning about the architecture, how it behaves under cold, and recording results for each chip - Why throw a hail mary at crunch time in front of 20 hand picked journalists, plus me?
Maybe the first best CPU's/boards they just tried failed, had condensation problems, died in pretesting... Dunno, a lot of things can go wrong doing subzero. It doesn't totally make sense to put all that time into pretesting, then when it comes to do or die time take a hail mary pass... So what was the reason? Maybe the VIDs they found to hold the most promise in pretesting was enough to give them an idea of what the chips would do.
09-13-11 09:12 PM
EDIT - PM'ed chew* for his thoughts.
09-13-11 09:12 PM
The near term release and OCers everywhere will be pretty busy for a while. Merry 2012 to all.
09-13-11 09:16 PM
09-13-11 09:26 PM
09-13-11 09:30 PM
09-13-11 09:40 PM
09-13-11 09:48 PM
I ran tests previously on various vid chips. I found the lowest vid which was rare really sucked, second lowest not so bad and 3rd from lowest scaled decent.
Taking that info i just VID binned in front of media if you recall and labeled all chips. Post to bios with a profile with all power saving off log voltage remove chip and label simple as that......
After i got tired of testing chips we had 24 total with my personal choice of VID which is the third from lowest so not really what you would call leaky.
We tested all chips at 1.8v ( so as not to damage them ) on ln2, 7.7, second sort of a dud 7.2 third 7.7, 4th hit just under 7.9 and we decided to go under LHe at that time.
As far as personal testing prior to event I think i tested 15 chips including my 2 personal B0 samples which I might add were nothing spectacular. So 13 B2 chips in total.
4 did 8 gig on ln2.......
Now onto why we used an untested chip versus chips we had already tested prior. Quite simple beating on chips at home at 2.0 v on 32nm is bad for a cpu.....at that point it is just a fuse waiting to pop.
I actually pushed one at home purposely that was a 7875 chip to find the breaking limits.....and i found it.
Now i'm not sure about you but LHe tanks are $1000 a wack, you burn quite a bit just getting the pot down to optimal temps. My personal motto for live events is this "Failure is not an option"
Knowing this i'd hate to waste half a tank on a previously beaten on chip and since we knew what we needed clocks and volts wise we knew it would not take much to find more 8 gig chips, 4 out of 15 is preety good odds.....
09-13-11 09:57 PM
And on the subject of binning vs random pick... Me no cares one bit... You guys hit 8.4GHz and that's what matters. I can't wait for these things to be available on retail so I can play some (unless you have one of them 24 chips laying around doing nothing!)
09-13-11 10:00 PM
09-13-11 10:02 PM
09-13-11 10:52 PM
Thanks again. Hope AMD got you guys good and drunk to celebrate after we flew out.
09-13-11 11:36 PM
09-13-11 11:52 PM
I'm jumpin around my lounge room right now like 10yr old who's just been told he's going to Disneyland, and I'm way to old for that I'm gonna do myself an injury.
09-14-11 12:07 AM
Is this because the monitoring software isn't updated?
09-14-11 12:18 AM
There are other tweaks, but one of the basics if you are benchmarking CPU-Z on subzero cooling is to disable extra cores, and you get extra stability to hit absolute max clocks.
With 2 cores, you boot at a speed like 4.5-5GHz. Then you use software to increase the multi or HT-Ref to increase one of the cores to max clocks, and pray that you can save a validation with CPU-Z successfully before it crashes. Some people also do things like set explorer to run on the core at the lower frequency also, and other tweaks.
09-14-11 12:24 AM
Edit - Whoops...beaten to the punch.
09-14-11 12:37 AM
Good thing I'm not a bencher
09-14-11 02:55 AM
I guess I'll wait for the benchies....
09-14-11 05:01 AM
09-14-11 05:09 AM
The feed line for the Liquid Helium was ejected out of the container, scaring the crap out of onlookers before Simon Solotko wrangled the line and stuck it back in the dewar where it belonged! ...It only is shown for a split second but you can see the initial response where people jump back. It was really loud and startling, and in person a couple people nearly dove away from the demo. Everyone nearby at the time got a good laugh once we realized no one got hurt when the tube shot out.
09-14-11 05:09 AM
Please don't misunderstand, I have a large measure of respect for you gentlemen overclocker magicians who can find the ultimate speed in hardware. You are high performance people.
09-14-11 02:34 PM
09-14-11 02:44 PM
09-14-11 02:49 PM
09-25-11 06:19 AM
09-25-11 04:15 PM
09-25-11 05:26 PM