Logo   Banner   TopRight
AMD FX-8150 8-Core CPU Review: Bulldozer Is Here
Date: Oct 12, 2011
Author: Marco Chiappetta
Introduction and Specifications

When we sit down to arrange our thoughts and write an introduction for a new product launch, we typically want to put together some interesting and suspenseful prose that sets the stage for an exciting reveal of an as-yet undisclosed, eagerly anticipated product. No such luck this time around, as the product we’ll be discussing today has been one of the most talked about in tech circles for years—literally.

Today AMD is officially taking the wraps off its latest FX-Series of desktop processors, targeted at performance-minded PC enthusiasts and overclockers. The FX-Series is based on the processor core formerly codenamed Zambezi, which leverages AMD’s much anticipated Bulldozer microarchitecture. The flagship processor in the new FX-Series line-up is the FX-8150, an unlocked, 8-Core processor, with gobs of cache and peak Turbo frequencies that exceed the 4GHz mark. But there’s a lot more to the FX-Series than speeds and feeds. The Bulldozer microarchitecture is a completely new design, which was built from the ground up in an attempt to shed some weight and produce a modular, highly-efficient CPU.

We know many of you have been waiting for this day for quite some time, so we won’t delay any further with more pithy commentary. It’s time to get down to business and take the AMD FX-8150 for a spin though the lab, to see if Bulldozer’s real-world performance earns it a spot in your next system build...

AMD FX-8150 8-Core Processor, Top and Bottom

AMD FX-8150 "Zambezi" 8-Core Processor
Specifications & Features
Model Number & Frequency: FX-8150 / 3.6GHz (base), 3.9GHz (CPU Turbo), 4.2GHz (Max Turbo)
L1 Cache Sizes: 256K L1 instruction (64KB per module) / 128K L1 data cache (16K per module)
L2 Cache Sizes: 2MB of L2 data cache per module (8MB total L2 per processor)
L3 Cache Size: 8MB (shared)
Total Cache (L2+L3): 16MB
Memory Controller Type: Integrated 72-bit x 2 memory controller
Memory Controller Speed: Up to 2.2GHz with Dual Dynamic Power Management
Types of Memory Supported: Unregistered DIMMs up to PC3-14900 (DDR3-1866)
HyperTransport 3.0 Specification: One 16-bit/16-bit link @ up to 4.4GHz full duplex (2.2GHz x2)
Packaging: Socket AM3+ 938-pin organic micro pin grid array (micro-PGA)
Fab location: GLOBALFOUNDARIES Fab 1 module 1 in Dresden, Germany
Process Technology: 32-nanometer DSL SOI (silicon-on-insulator) technology
Approximate Die Size: ~315mm2
Approximate Transistor count: ~2 Billion
Max TDP: 125 Watts
AMD Codename: "Zambezi"

We have been reporting on AMD’s Bulldozer microarchitecture and Bulldozer-related topics for quite some time; years actually. As such, we have already posted a number of stories related to today’s launch that contain many pertinent details and complementary information. Below is a list of recent AMD Bulldozer and FX Series related articles we’d suggest perusing, but we’ve been talking about Bulldozer since 2007. If you want to see more, have some fun and hit the search box and news archive...

At the very least, we’d suggest perusing the articles titled, “AMD Lifts The Hood On Bulldozer At ISSCC” and “Next-Gen AMD Bobcat and Bulldozer CPU Deep Dive”. In those two articles, we cover many technical and architectural details that we won’t be repeating here. We’d also suggest checking out our AMD 990FX motherboard round-up, as it includes a number of motherboards (including the Asus CrossHair V Formula we used for testing) that are specifically designed to properly support AMD’s new FX series processors.

The Bulldozer Architecture

As we mentioned on the previous page, we won’t be rehashing many of the low-level technical details of AMD’s Bulldozer microarchitecture here, since we’ve already covered them in previous articles. We will, however, cover more product specific details and offer up a condensed refresher of some of the details presented in our previous Bulldozer-related coverage.

AMD FX-Series Processor Die Map

What you see here is a die map of an AMD FX-Series, 8-core die, formerly codenamed “Zambezi”. It is comprised of roughly 2 billion transistors, is approximately 315mm2,  and is manufactured using Global Foundries’ 32nm DSL SOI (silicon-on-insulator) technology. At 315mm2, the Zambezi core used in the FX is somewhat than Thuban's (Phenom II X6) 346mm2, which is good for AMD, but it's still much larger than Sandy Bridge's approximate 216mm2. There is 128 KB of L1 Data Cache (16KB per core), 256 KB of L1 Instruction Cache (64KB per module), and 8MB of L2 Cache (2MB per module), along with 8MB of shared L3 cache. There are four 16-bit HyperTransport links present, although only one is enabled on desktop Bulldozer processors, the others are present for server-class products which are based on the same core design. There is also an Integrated memory controller / northbridge which features two, 72-bit wide DDR3 memory channels.

AMD refers to Bulldozer’s design as a third-way between symmetric multithreading (SMT) like Intel’s Hyper-Threading and true multi-core processing, where multiple discrete cores reside on one die. With Bulldozer, AMD started with two discrete cores, and eliminated some duplicate logic that may have gone unused with the vast majority of workloads. AMD then fused the resulting, pared down cores together into a single, shared design. As far as design efficiency was concerned, taking this route was fruitful as Bulldozer's second ALU unit increased the die size by only 12%. AMD has also emphasized the point that Bulldozer has been architected to be power-efficient. The design features extensive clock-gating throughout, numerous circuits that can be power-gated dynamically, and multiple power-saving features that are under software control (C6 State, Core P-states / AMD Turbo Core, APM, DRAM power management, low power idle state, and C1E).

AMD Bulldozer "Two-Core" Module

With Bulldozer, AMD has taken the concept of SMT and essentially added a second independent integer unit. Intel's Hyper-Threading technology improves core efficiency by scheduling multiple threads for simultaneous execution. In a situation where the processor is waiting for code from Thread A, the scheduler can send work for Thread B. This keeps the processor's execution units more fully utilized for longer periods of time, but Hyper-Threading doesn't provide the CPU with any additional execution resources. According to AMD, the company aggressively researched which core blocks needed to be duplicated and which could be combined before finalizing the design of Bulldozer. As far as the OS is concerned, however, each Bulldozer module will appear as a dual-core processor, just as an Intel Hyper-Threaded processor is shown to have double the actual number of actual physical cores.

We should also point out that Bulldozer has four x86 decoders, whereas previous AMD products had just three. And Bulldozer's branch predication units have been optimized for for high performance as well. In fact, branch prediction and instruction fetch logic has been decoupled, which means that an incorrect branch prediction won't stall the fetch unit (and vice versa). Phenom doesn’t have this ability, because the two units are tied to each other.

Bulldozer’s joint FPU unit is capable of tracking two hardware threads (one from each core) and has two MMX integer units and two 128-bit FMAC units. Bulldozer also adds support for SSE4.1, SSE4.2, AVX, AES, in addition to FMA4 and XOP extensions, though software will have to be specifically coded to leverage these resources.

AMD is positioning the FX series at the top of its desktop processor line-up. The E-Series Accelerated Processing Units (APU) are designed for low-power, small form factor, and mobile applications. AMD A-Series APUs are designed for mobile and mainstream desktop applications. And the FX Series is designed for performance-minded consumers and enthusiasts. The feature breakdown above explains what type of workloads each APU / CPU series targets, but it should be noted that there’s nothing stopping a user from plunking a discrete Radeon graphics card into an E- or A-Series APU based system and taking advantage of AMD Eyefinity technology.

More Bulldozer and the AMD FX Line-Up

Looking at the FX-8150’s stand-out features and specifications, it’s easy to see why AMD was so eager to share details over the years. To better illustrate what we mean, take a look at the comparison below, put together by AMD for use in one of their presentations leading up to today’s launch.

Source: AMD

In a direct bullet-point to bullet-point comparison, the FX-8150 no doubt looks promising when compared to Intel’s Core i5 and Core i7 series processors, at least on paper. There is a lot more to designing a higher performance processor than tacking on more cache and cores, boosting frequencies, and adding support for new instructions. Of course, not all cores are created equal. As it turns out, AMD’s eight, higher-clocked cores have trouble competing against four of Intel’s lower-clocked cores—more on that in the benchmark pages ahead. For now, let’s get to some more of the FX-Series specifics...

Initial AMD FX-Series Processor Line-Up

The initial FX-Series product line-up is going to consist of seven processors, ranging from the high-end FX-8150 to the more mainstream FX-4100 (although only four will be available immediately). The processors will differ in their core counts, northbridge frequency, CPU clocks, cache compliments and TDP. Note, that the reduction in available L2 cache is a direct result of disabling a core module. Since each Bulldozer core module contains two cores and 2MB of L2 cache, as each core module is disabled, the L2 is reduced by 2MB. Please note, that all of these initial FX-Series processors will feature the same die; the quad-cores listed here will feature the same 8-core die with two modules disabled.

AMD FX-8150 Processor CPU-Z Details

Here is an up-close-and-personal look at the FX-8150 as reported by the latest version of CPU-Z. As you can see, the FX-8150 uses AMD’s existing AM3+ socket infrastructure. Although it’s pin-compatible with AM3, AM3+ adds support for CPU voltage loadline, increased ILDT current for higher frequency HyperTransport links, increased DRAM current, and two memory channels with official support for speeds of up to DDR3-1866.

If you look through the images above, you’ll notice that the CPU’s voltage and frequency varies due to AMD's Turbo technology. We took steps to capture the images while the FX-8150 was at idle, under a two-thread workload, and while being completely utilized. Doing so allows us to show the actual clocks and voltage of the chip at each “Turbo” stage.

AMD Turbo Technology

The FX-8150 has a base clock of 3.6GHz, which will drop to 1.4GHz while idling thanks to CnQ. When half or less of the FX-8150’s cores are being utilized, the chip is able to hit its max Turbo frequency of 4.2GHz. And when all of the cores are being taxed, the CPU can Turbo up to 3.9GHz to use up any available TDP headroom.

Test Systems and SiSoft SANDRA

Test System Configuration Notes: When configuring our test systems for this article, we first entered their respective system BIOSes / UEFI and set each board to its "Optimized" or "High performance Defaults". We then saved the settings, re-entered the BIOS and set the memory frequency to DDR3-1600 or DDR-1333. The hard drives were then formatted, and Windows 7 Ultimate x64 was installed.

AMD FX-8150 Installed In The Asus CrossHair V Formula

When the Windows installation was complete, we updated the OS, and installed the drivers necessary for our components. Auto-Updating and Windows Defender were then disabled and we installed all of our benchmarking software, performed a disk clean-up, defragged the hard drives, and ran the tests.

HotHardware's Test Systems
Intel and AMD - Head To Head

System 1:
AMD A8-3850
(2.9GHz - Quad-Core)

Asus F1A75-V Pro
(AMD A75 Chipset)

2x4GB G.SKILL DDR3-1866
(@ 1600MHz)

Radeon HD 6550D IGP
On-Board Ethernet
On-board Audio

WD150 "Raptor" HD
10,000 RPM SATA

Windows 7 x64

System 2:
Intel Core i3-2120
(3.3GGHz - Dual-Core)
Intel Core i5-2500K
(3.3GHz - Quad-Core)
Intel Core i5-2600K
(3.3GHz - Quad-Core)

Asus P8Z68-A Pro
(Z68 Express Chipset)

2x4GB G.SKILL DDR3-1866
(@ 1600MHz)

GeForce GTX 280 
On-Board Ethernet
On-board Audio

WD150 "Raptor" HD
10,000 RPM SATA

Windows 7 x64

System 3:
AMD Phenom II X4 980
(3.7GHz Quad-Core)
AMD Phenom II X6 1100T
(3.3GHz Six-Core)
AMD Phenom II X4 980
(3.6GHz Eight-Core)

Asus CrossHair V Formula
(AMD 990FX Chipset)

2x4GB G.SKILL DDR3-1866
(@ 1600MHz)

GeForce GTX 280
On-Board Ethernet
On-board Audio

WD150 "Raptor" HD
10,000 RPM SATA

Windows 7 x64

Preliminary Testing with SiSoft SANDRA 2011
Synthetic Benchmarks

We began our testing with SiSoftware's SANDRA 2011, the System ANalyzer, Diagnostic and Reporting Assistant. We ran four of the built-in subsystem tests that partially comprise the SANDRA 2011 suite with AMD's FX-8150 (CPU Arithmetic, Multimedia, Cache and Memory, and Memory Bandwidth). All of the scores reported below were taken with the CPU running at its default settings, with Turbo enabled, and with 8GB of DDR3-1600 RAM running in dual-channel mode on the Asus CrossHair V Formula motherboard.

Processor Arithmetic

Processor Multimedia

Memory Bandwidth

Cache and Memory

SANDRA's Processor Arithmetic benchmark puts the new FX-8150 on near equal footing with the Intel Core i5-2500 in ALU performance, but the FX outpaces the i5 in the FPU test, but about 20%. Things play out differently in the Processor Multi-Media benchmark, however. In the Multi-Media test, the FX outpaces the Core i5-2500 and Core i7-2600 easily in the Integer test, but falls well behind in the floating-point test. The Memory Bandwidth benchmark shows the AMD FX-8150 (when paired to DDR3-1600 RAM), offering up about 18GB/s of peak bandwidth, which is competitive with other platforms featuring dual memory channels. In the Cache and Memory benchmark tough, the FX-8150 falters somewhat and trails other platforms until the data set hits the 1MB mark and the FX is able to pull ahead by a small margin.

Futuremark PCMark Vantage
Next up, we ran our test systems through Futuremark’s total-system performance evaluation tool, PCMark Vantage. PCMark Vantage runs through a host of different usage scenarios to simulate different types of workloads including High Definition TV and movie playback and manipulation, gaming, image editing and manipulation, music compression, communications, and productivity.

Preliminary Testing with PCMark Vantage
Synthetic Benchmarks

Most of the sub-tests used to come up with the final scores in each category are multi-threaded as well, so the tests can exploit the additional resources offered by a multi-core CPU.

The FX Series support for hardware accelerated AES encryption give the FX-8150 a significant boost in performance in PCMark Vantage's Communications test, but in the remainder of the tests, AMD's new flagship eight-core chip can't quite keep pace with the previous generation Phenom II X6 six-core processor, let alone any of Intel's quad or six-core processors.

Futuremark PCMark 7 Tests
Futuremark's PCMark 7 is the latest version of the PCMark suite. It has updated application performance measurements targeted for a Windows 7 environment. Here's what Futuremark says is incorporated in the base PCMark suite and the Entertainment suite, the two modules we have benchmark scores for you here.

Futuremark PCMark 7
General Application and Multimedia Performance
The PCMark test is a collection of workloads that measure system performance during typical desktop usage. This is the most important test since it returns the official PCMark score for the system
  • Windows Defender
  • Importing pictures
  • Gaming

Video Playback and transcoding

  • DirectX 9

Image manipulation
Web browsing and decrypting

The Entertainment test is a collection of workloads that measure system performance in entertainment scenarios using mostly application workloads. Individual tests include recording, viewing, streaming and transcoding TV shows and movies, importing, organizing and browsing new music and several gaming related workloads. If the target system is not capable of running DirectX 10 workloads then those tests are skipped. At the end of the benchmark run the system is given an Entertainment test score.

The new AMD FX-8150 has no problem outrunning the Phenom II X6 1100T in PCMark7's overall system test, but it trails the six-core processor slightly in the Entertainment benchmark. The FX-8150 also competes well with the Core i7-970 and Sandy-Bridge based Core i5-2500K here, but the Core i7-2600K runs away with this one, no matter how you slice it.

LAME MT Audio Encoding and Cinebench R11.5

In our custom LAME MT MP3 encoding test, we convert a large WAV file to the MP3 format, which is a popular scenario that many end users work with on a day-to-day basis to provide portability and storage of their digital audio content. LAME is an open-source mid to high bit-rate and VBR (variable bit rate) MP3 audio encoder that is used widely around the world in a multitude of third party applications.
Audio Conversion and Encoding

In this test, we created our own 223MB WAV file (a hallucinogenic-induced Grateful Dead jam) and converted it to the MP3 format using the multi-thread capable LAME MT application in single and multi-thread modes. Processing times are recorded below, listed in seconds. Shorter times equate to better performance.

Audio encoding with LAME is not a strong point for AMD's architectures, as is evident by the Core i5's trouncing of the FX. What's interesting is that the FX-8150 trails the Phenom II X6 and X4 in the single-threaded test, where it should have an advantage due to higher peak Turbo frequencies. However, the opposite turns out to be true. It is in the MT test (which uses only two threads) that the FX puts up the fastest score of all of the AMD processors. Perhaps the ability to keep both threads running on a single core module helps the FX's performance here.

Cinebench R11.5
3D Rendering

Cinebench R11.5 is an OpenGL 3D rendering performance test based on Cinema 4D from Maxon. Cinema 4D is a 3D rendering and animation tool suite used by 3D animation houses and producers like Sony Animation and many others. It's very demanding of system processor resources and is an excellent gauge of pure computational throughput. This is a multi-threaded, multi-processor aware benchmark that renders and animates 3D scenes and tracks the length of the entire process. The rate at which each test system was able to render the entire scene is represented in the graph below.

Although the new AMD FX-8150 puts up the best score of all the AMD-built processors, and easily dominates the Core i5-2500K in the Cinebench R11.5 CPU test, its lead over the six-core Phenom II X6 1100T is relatively small. With more cache, higher clocks, and two additional cores (technically), it would seem that the FX-8150 would perform better here, but contention for shared resources within each core module and perhaps scheduling issues with Windows 7 come into play, reducing the FX's performance somewhat.
Video Encoding: Espresso, 3DMark Vantage
Next up, we tested the video encoding performance of the AMD FX-8150 using Cyberlink's MediaEspresso 6.5. Although this application is coded to take advantage of Intel Quick Sync technology and leverage GPU compute resources, we disabled hardware acceleration for these tests to ensure they were all run only on the CPU cores.

Video Encoding With Mediashow Espresso
Media Encoding

In this test, we took a 256MB AVCHD MTS file recorded using a Canon HD camcorder and converted it to an H.264 encoded MP4 designed for use on an iPhone 4 / iPad (or other portable media playback device).

The FX-8150 put up a respectable number in our Mediashow Espresso test, besting all of the other AMD-build processors and hanging right alongside the Core i5-2500K. Please note, however, we DID NOT employ Intel's QuickSync technology here. With QuickSync enabled, the Core i7-2600K encodes the same video in only 9 seconds; the Core i5-2500K does it in only 10.

We should also point out that this test does not leverage the XOP or AVX instructions available within the FX-8150, which would result in better performance.

Futuremark 3DMark Vantage
Synthetic DirectX Gaming

3DMark Vantage's CPU Test 2 is a multi-threaded test designed for comparing relative game physics processing performance between systems. This test consists of a single scene that features an air race of sorts, with a complex configuration of gates. There are aircraft in the test that trail smoke and collide with various cloth and soft-body obstacles, each other, and the ground. The smoke spreads, and reacts to the planes as they pass through it as well and all of this is calculated on the host CPU.

3DMark Vantage's CPU Test 2 has the new FX-8150 finishing just behind the six-core Phenom II X6 1100T, but ahead of the Core i5-2500K. The higher-end Intel processors hold onto a commanding lead here, however.

Low-Res Gaming: Crysis and ET:QW

For our next series of tests, we moved on to some in-game benchmarking with Crysis and Enemy Territory: Quake Wars. When testing processors with Crysis or ET:QW, we drop the resolution to 1024x768, and reduce all of the in-game graphical options to their minimum values to isolate CPU and memory performance as much as possible. However, the in-game effects, which control the level of detail for the games' physics engines and particle systems, are left at their maximum values, since these actually do place a load on the CPU rather than GPU.

Low-Resolution Gaming: Crysis and ET: Quake Wars
Taking the GPU out of the Equation

The AMD FX-8150 was easily the fastest AMD-built processor in our gaming tests. In our ET:QW test, the FX-8150 finished well ahead of the Phenoms, Llano, and the Core i5-2500K, but trailed the higher-end Intel processors. Is the Crysis CPU benchmark, the FX remained the fastest of the AMD processors, but Intel's chips jump out to a significant lead.

Overclocking, Power Consumption

Having sceen FX processors break the 8GHz mark with our own eye--using exotic cooling, of course--we were eager to see how well our particulr CPU overclocked. To that end, we also spent some time overclocking the new AMD FX-8150 processor, using a standard air cooler and AMD's own Overdrive utility. For these overclocking tests, we bumped the CPU voltage up to 1.4125v, disabled Turbo, and increased the CPU's multiplier until our test system was no longer stable.

AMD FX-8150 Overclocked to 4.4GHz

In the end, we were able to take the FX-8150 up to a stable 4.4GHz. At that speed and voltage, even with a basic air-cooler, core temps hovered around the 69'C mark, which is lower than we expected. Considering how easy it was to take our CPU over the 4.4GHz mark, and that we've seen early chips already hit much higher frequencies, we suspect that higher clocks will easoli be possible with exotic coolers and more aggressive voltage tweaking. As an interesting aside, overclocking the FX-8150 to 4.4GHz resulted in a Cinebench R11.5 score of 7.09, and increase of 1.07 or 17.5% over the stock score of 6.02.

Although it didn't arrive in time for testing, AMD also sent over one of the self contained water-coolers it will be offering with some of its FX series processors. The cooler includes a 120mm radiator, dual 120mm fans (should you want to arrange them in a push-pull configuration), and the mounting hardware necessary to fit the water-block / pump assembly to a Socket AM2/AM3/AM3+ motherboard.

Total System Power Consumption
Tested at the Outlet

Before bringing this article to a close, we'd also like to take a but about  power consumption. Throughout all of our benchmarking and testing, we monitored how much power our AMD FX-8150 based test system was consuming with a power meter, versus other test systems we used for benchmark comparisons on the previous pages. Our goal was to give you an idea as to how much power each configuration used while idling at the desktop and while under a heavy CPU workload. Keep in mind, this is total system power consumption being measured at the outlet and not the the individual power of the CPUs alone.

Our AMD FX-8150 based test system, consumed a little less power than the Phenom II X6 1100T did while idling, but while under load, the FX-8150 pulled down about 14 more watts. Considering the fact that the FX-8150 generally offers better performance than the X6 1100T, using somewhat more power probably won't turn off many users. However, the FX-8150 uses a more advanced 32nm manufacturing process (vs. the Phenom II's 45nm) and one the FX series' main claims to fame was supposed to be power efficiency. WIth that in mind, is surprising to see it using more power than AMD's previous generation desktop 6-core processor. This scenario may change in time as AMD tweaks the FX and Global Foundries' 32nm process matures, but for now it looks like high-end FX-series processors will consume somewhat more power than the Phenom II X6 it will supplanting at the top of AMD's desktop processor line-up.

Performance Summary and Conclusion

Performance Summary: Summarizing the new AMD FX-8150’s performance is somewhat difficult for a number of reasons. Generally speaking, the FX-8150 is the fastest desktop processor AMD has released to date. In the majority of our tests, the FX-8150 was able to outrun the company’s previous flagship desktop CPU, the six-core Phenom II X6 1100T, and sometimes by a wide margin, as we saw in someof our game tests and in PCMark Vantage’s Communication benchmark. In a handful of tests, however, the 8-core FX-8150 actually trailed the lower-clocked, 6-Core Phenom II 1100T due to lower single-threaded performance or potential scheduling issues with Windows 7 (which will likely be resolved with Windows 8). Looking back at the numbers, it's clear the FX is better suited to highly parallel workloads, although its advantages over Phenom in this area vary. In comparison to Intel’s processors, the AMD FX-8150 performed right about on par with the quad-core Core i5-2500K. The Core i5-2500K was faster than the FX in our encoding tests, some of the game tests, and in most of the PCMark Vantage tests. Whereas the FX took the lead in PCMark7’s Entertainment benchmark, a couple of game tests, and in Cinebench. Versus higher-end Intel processors like the Core i7-2600K or i7-970, however, the FX generally couldn’t compete. It should also be noted that the FX-8150 consumed considerably more power than Intel’s current Sandy Bridge-based processors too. At this point it’s clear that Intel maintains not only a performance lead, but a significant advantage in power efficiency as well.

8-Core FX Series Processor Die

AMD will be launching four FX series processors today, the flagship 125W FX-8150 we’ve shown you here, along with another a lower-clocked, 125W 8-core chip dubbed the FX-8120, a 95W 6-core processor called the FX-6100, and finally the 95w quad-core FX-4100. Pricing, TDP, frequencies (both stock and Turbo), and core counts are listed in the chart below. (In case it wasn’t apparent, the first digit in the model number denotes core count.)

AMD FX Series Processors Available At Launch

For the die-hard AMD fans that have been waiting for this day since the company first started hinting at Bulldozer, the performance exhibited by this first batch of FX series processors is probably somewhat puzzling. This was supposed to be the architecture that propelled AMD back into a strong, competitive position versus Intel’s desktop processors. Alas, that is obviously not the case. The FX-8150 is very competitive with Intel’s upper-mainstream Core i5 processors, but the Core i7 remains the ultimate performance champion. No if, ands, or buts about it.

With that said, AMD still has a good product on its hands with the FX series. Performance is good; in some workloads the processor significantly outpaces the previous-gen Phenom II. And while it’s true that in some areas the Phenom II can still be faster, the Phenom II’s margin of victory is generally small. Although we didn’t have time to test it for ourselves just yet, performance improvements should be coming with future versions of Windows as tweaks are made to the scheduler to better utilize the resources afforded by the Bulldozer microarchitecture. As more software is optimized for the FX series, it’s architectural and feature enhancements (like XOR, AVX, etc.) should afford it a big edge over previous-generation processors as well.

Ultimately, although AMD wasn’t able to overtake Intel with the FX series, this launch is important for the company. It has been over a decade since AMD has completely redesigned its desktop processors. And the company needed a more forward-looking microarchitecture to lay the foundation for the future. Bulldozer may not have been able to put AMD back into the leadership position it was in when the original Athlon and Athlon 64 processors hit the scene, but it may be the launching pad AMD needs to better tweak and optimize its desktop processors moving forward in preparation for the Piledriver, Steamroller, and Excavator microarchitectures AMD has slated for release over the next few years, all of which are reported to offer IPC and frequency ehancements that will increase performance.

  • Good MT Performance
  • 8-Cores, 32nm Process
  • Fairly Overclockable
  • Affordably Priced


  • Consumed More Power Than 45nm Phenom II
  • Intel Still Offers Better Overall Performance and Power
  • Questionable Single Thread Performance


Content Property of HotHardware.com