Perhaps the most hotly-anticipated launch in 2011, AMD’s FX processor line-up is finally ready for prime time. Does the company’s new Bulldozer architecture have what it takes to face Intel’s Sandy Bridge and usher in a new era of competition?
How much CPU do you really need? Two cores? Four? Six? In many ways, the answer depends on what you’re doing with your PC. We’ve found that most games run best on machines with at least three cores. We know that many video editing apps use as much processing horsepower as you give them. And many productivity-oriented titles don’t take advantage of parallelism at all.
Really, the key to a healthy machine is balance. Balance prevents bottlenecks. We’re long-time proponents of balance (see Paul Henningsen’s Building A Balanced Gaming PC series). And now, as a purveyor of processors and graphics, AMD stands to profit handsomely from preaching the very same message.
But when the marketing slides detailing a company’s upcoming flagship desktop processor demonstrate a trend favouring cheaper PCs, you have to expect a CPU designed for cheaper PCs. I hope this isn’t too much of a spoiler, but enthusiasts who were hoping to see AMD’s Bulldozer architecture decimate Sandy Bridge and do battle with Sandy Bridge-E have to adjust their expectations. Instead, the company is going after a burgeoning chunk of the market looking to spend less on hardware than they did in the past.
That’s cool though, right? Sandy Bridge showed the power user community that they didn’t need a $1000 processor to get blazing-fast performance. An unlocked $200 chip capable of reliably hitting 4.5 GHz smoked Intel’s Gulftown-based Extreme Edition parts in a number of desktop-oriented tests (including the ever-important gaming scenarios). If AMD can offer a better value in that market, you won’t hear me (or anyone else) complain.
Meet The FX Family
At least on paper, the line-up of processors AMD plans to roll out looks both comprehensive and competitive. There are seven models in the FX family, ranging from the FX-8150 down to the FX-4100. They all centre on AMD’s Zambezi design, manufactured on Globalfoundries’ 32 nm node and composed of roughly two billion transistors. The 315 mm² die is smaller than Thuban (at 346 mm²), but larger than Deneb (at 258 mm²). Sandy Bridge, in comparison measures 216 mm².
| Model | Base Clock | Turbo Core Clock | Max. Turbo Core | TDP | Cores | Total L2 Cache | Shared L3 Cache | Northbridge Freq. |
|---|---|---|---|---|---|---|---|---|
| FX-8150 | 3.6 GHz | 3.9 GHz | 4.2 GHz | 125 W | 8 | 8 MB | 8 MB | 2.2 GHz |
| FX-8120 | 3.1 GHz | 3.4 GHz | 4.0 GHz | 125 / 95 W | 8 | 8 MB | 8 MB | 2.2 GHz |
| FX-8100 | 2.8 GHz | 3.1 GHz | 3.7 GHz | 95 W | 8 | 8 MB | 8 MB | 2.0 GHz |
| FX-6100 | 3.3 GHz | 3.6 GHz | 3.9 GHz | 95 W | 6 | 6 MB | 8 MB | 2.0 GHz |
| FX-4170 | 4.2 GHz | - | 4.3 GHz | 125 W | 4 | 4 MB | 8 MB | 2.2 GHz |
| FX-B4150 | 3.8 GHz | 3.9 GHz | 4.0 GHz | 95 W | 4 | 4 MB | 8 MB | 2.2 GHz |
| FX-4100 | 3.6 GHz | 3.7 GHz | 3.8 GHz | 95 W | 4 | 4 MB | 8 MB | 2.0 GHz |
The portfolio is most easily broken down into eight-core, six-core, and four-core CPUs (corresponding to four, three, and two Bulldozer modules). Model numbers do help you identify the chips somewhat: an FX-8xxx is an eight-core SKU, for instance; FX-4xxx is a four-core product.
The three digits that follow the core designator arbitrarily indicate performance within the stack. They aren’t consistent with clock rate, TDP, or L2 cache. You simply have to remember that, within the FX-8xxx segment, -8150 is better than -8120, which is better than -8100.
All of the FX processors are multiplier unlocked up and down the line-up, so there may turn out to be some interesting bargains, depending on how aggressively AMD is speed-binning these CPUs. Remember back to 2008, when Intel launched Nehalem? Enthusiasts jumped all over the 4 GHz-capable Core i7-920 because it was cheap. It remains to be seen whether Globalfoundries’ 32 nm process can achieve the same notoriety.
AMD makes it super-easy to avoid naming confusion at launch by making four CPUs available: the FX-8150, the -8120, the -6100, and the -4100.
| Model | Base Clock | Turbo Core Clock | Max. Turbo Core | TDP | Cores | Suggested Price (U.S.*) |
|---|---|---|---|---|---|---|
| FX-8150 | 3.6 GHz | 3.9 GHz | 4.2 GHz | 125 W | 8 | $245 |
| FX-8120 | 3.1 GHz | 3.4 GHz | 4.0 GHz | 125 W | 8 | $205 |
| FX-6100 | 3.3 GHz | 3.6 GHz | 3.9 GHz | 95 W | 6 | $165 |
| FX-4100 | 3.6 GHz | 3.7 GHz | 3.8 GHz | 95 W | 4 | $115 |
That quartet of FXes picks up from where the Phenom II family left off, price-wise. AMD's FX-4100 overlaps the prior generation with a $115 price tag, serving up four cores and clocks between 3.6 and 3.8 GHz (max. Turbo Core). FX-6100, running at a base 3.3 GHz and maxing out at 3.9 GHz, sells for $165. The -8120, armed with eight cores, a 3.1 GHz base, and 4 GHz peak Turbo Core clock, is expected to go for $205. And the flagship -8150, which pushes frequency up to 3.6 GHz base and 4.2 GHz maximum Turbo Core, bears a $245 suggested retail price.
AMD only sent one of the four models for evaluation: the -8150. Our impressions on the other three processors will have to wait, unfortunately (that’s a hint, System Builder Marathon team). We don’t have any additional details as to when the other three FX processors will hit the channel, or how much they’ll cost. But we're finding it hard to care right now. We have the fastest model sitting on our test bench and a list of updated apps with which to test, based on your feedback. So, let's get to it.
*UK pricing not yet available.
- AMD Sets The Stage For FX’s Performance
- Platform Support For FX: Make Sure It’s AM3+
- The Idea Behind AMD’s Bulldozer
- A Shared Front-End And Dual Integer Cores
- Single Floating-Point Unit, AVX Performance, And L2
- Per-Core Performance
- Power Management
- Enabling Turbo Core
- AMD’s Roadmap Through 2014
- Meet AMD Zambezi, Valencia, And Interlagos
- Hardware Setup And Benchmarks
- Benchmark Results: PCMark 7
- Benchmark Results: 3DMark 11
- Benchmark Results: Sandra 2011
- Benchmark Results: Content Creation
- Benchmark Results: Productivity
- Benchmark Results: Media Encoding
- Benchmark Results: Crysis 2
- Benchmark Results: F1 2011
- Benchmark Results: World of Warcraft: Cataclysm
- Overclocking FX-8150 (On Air)
- Power Consumption
- Sneak Peek: AMD’s Bulldozer Architecture On Windows 8
- AMD FX-8150: The Bottom Line


Unfortuante that there wasn't a more competitive showing by AMD. Up until recently we could still say that performance pre dollar was still with them in alot of cases. Now it seems even that point is going to Intel for some time to come.
One the bright side it appears that here in Oz that a new segment in the full size (14-15") notebook market in the last few months created by the release of the AMD Radeon on die processor powered notebooks in the $330-$450 space, where previously new notebooks could barely be had under $500, and even then they were powered by awful Celeron processors with even worse graphics. If AMD can move enough of these low end units then maybe they'll have a chance to improve their line up, if the talk of scaling isn't just hot air.
Be that with their roadmap of promised performance increases or the promise of increased performance on apu's via gpgpu applications.
I will believe it when I see it if ever.
I don't think they are even plan that effectively, I mean their proposed utilization of core/module parking in win8, great for power efficiency, but what about performance? For that you would need to spread the threads evenly across the single cores of each module so they don't share resources and only start using the second core in each module when the first core approaches max load.
The implementation in win8 will only reduce performance and enhance power efficiency.
Can we all afford these super computers sucking 1000 watts from the socket, no, I would rather wait a fraction of a second and save a few quid each month.
Future chips may just come with a few surprises, once AMD wake up and smell the coffee.
im pretty sure the current business models for both amd and intel are not "spend 200 squillin dollars" in r&d on making processor chips that can run the main computer of a galaxy class starship, using exotic materials (other than silicon) etc etc
im running an amd64 3200+ single core (venice) in my rig, and it does everything and more than i want it to do.. i can play all the latest games run the most demanding software.. my point is my pc 7 years old im running windows 7 on it and it does me fine.. the market does not need nor are consumers ready for a leap in processor tech so for a business model why not realease minor improved chips and keep the dollars rolling in? than gamble everything on something that might break your company before it is even ever realeased?
not only does the part not perform consistently and never will in a gaming environment. its power inefficient to the tune of 180+watts. seriously guy rethink your choice... you would be no worse off performance wise buying a P'II 970 and waiting for the next iteration that will still underperformed against intels ivy bridge...
as for your theory on how WOW is processed your off the mark there too.. intel only use hyper threading when a game/application asks for it. on a single core wow will use hyper threading (if available) as i needs 2 Cores to work best, on a dual core it will use 2 cores without hyper threading and on a quad it will use 2 cores without hyper threading. just because a core shows 75 percent usage doesn't mean its using 25 percent hyper threading.
case in point wow performs no better on an intel 2500k than it does on the intel 2600k 1 has hyper threading the other doesnt.
seriously m8 i aint trying to be a jerk, but it defiantly looks like you have a case of "thinks he knows"... you seem to be operating on assumptions about intel rather than fact... use places like wiki, toms, hardware secrets and other places to get the rite info b4 you make a misinformed choice.