Fx 8150 review: The Bulldozer Review: AMD FX-8150 Tested

IntroductionThe ArchitectureThe Pursuit of Clock SpeedPower Management and Real Turbo CoreThe Impact of Bulldozer’s PipelineCache and Memory PerformanceWindows 7 Application PerformanceGaming PerformancePower ConsumptionOverclockingFinal Words

AMD clearly states in its reviewer’s guide that CPU bound gaming performance isn’t going to be a strong point of the FX architecture, likely due to its poor single threaded performance. However it is useful to look at both CPU and GPU bound scenarios to paint an accurate picture of how well a CPU handles game workloads, as well as what sort of performance you can expect in present day titles.

Civilization V

Civ V’s lateGameView benchmark presents us with two separate scores: average frame rate for the entire test as well as a no-render score that only looks at CPU performance.

While we’re GPU bound in the full render score, AMD’s platform appears to have a bit of an advantage here. We’ve seen this in the past where one platform will hold an advantage over another in a GPU bound scenario and it’s always tough to explain. Within each family however there is no advantage to a faster CPU, everything is just GPU bound.

Looking at the no render score, the CPU standings are pretty much as we’d expect. The FX-8150 is thankfully a bit faster than its predecessors, but it still falls behind Sandy Bridge.

Crysis: Warhead

In CPU bound environments in Crysis Warhead, the FX-8150 is actually slower than the old Phenom II. Sandy Bridge continues to be far ahead.

Dawn of War II

We see similar results under Dawn of War II. Lightly threaded performance is simply not a strength of AMD’s FX series, and as a result even the old Phenom II X6 pulls ahead.

DiRT 3

We ran two DiRT 3 benchmarks to get an idea for CPU bound and GPU bound performance. First the CPU bound settings:

The FX-8150 doesn’t do so well here, again falling behind the Phenom IIs. Under more real world GPU bound settings however, Bulldozer looks just fine:

Dragon Age

Dragon Age is another CPU bound title, here the FX-8150 falls behind once again.

Metro 2033

Metro 2033 is pretty rough even at lower resolutions, but with more of a GPU bottleneck the FX-8150 equals the performance of the 2500K:

Rage vt_benchmark

While id’s long awaited Rage title doesn’t exactly have the best benchmarking abilities, there is one unique aspect of the game that we can test: Megatexture. Megatexture works by dynamically taking texture data from disk and constructing texture tiles for the engine to use, a major component for allowing id’s developers to uniquely texture the game world. However because of the heavy use of unique textures (id says the original game assets are over 1TB), id needed to get creative on compressing the game’s textures to make them fit within the roughly 20GB the game was allotted.

The result is that Rage doesn’t store textures in a GPU-usable format such as DXTC/S3TC, instead storing them in an even more compressed format (JPEG XR) as S3TC maxes out at a 6:1 compression ratio. As a consequence whenever you load a texture, Rage needs to transcode the texture from its storage codec to S3TC on the fly. This is a constant process throughout the entire game and this transcoding is a significant burden on the CPU.

The Benchmark: vt_benchmark flushes the transcoded texture cache and then times how long it takes to transcode all the textures needed for the current scene, from 1 thread to X threads. Thus when you run vt_benchmark 8, for example, it will benchmark from 1 to 8 threads (the default appears to depend on the CPU you have). Since transcoding is done by the CPU this is a pure CPU benchmark. I present the best case transcode time at the maximum number of concurrent threads each CPU can handle:

The FX-8150 does very well here, but so does the Phenom II X6 1100T. Both are faster than Intel’s 2500K, but not quite as good as the 2600K. If you want to see how performance scales with thread count, check out the chart below:

Starcraft 2

Starcraft 2 has traditionally done very well on Intel architectures and Bulldozer is no exception to that rule.

World of Warcraft

Windows 7 Application Performance
Power Consumption
IntroductionThe ArchitectureThe Pursuit of Clock SpeedPower Management and Real Turbo CoreThe Impact of Bulldozer’s PipelineCache and Memory PerformanceWindows 7 Application PerformanceGaming PerformancePower ConsumptionOverclockingFinal Words

Tweet

PRINT THIS ARTICLE

AMD Bulldozer Review: FX-8150 Gets Tested

Editor’s Note: Eager to show off what is has done with AMD’s Bulldozer architecture, system builder CyberPower PC is offering Tom’s Hardware’s audience the opportunity to win a new system based on the FX-8150 processor. Read through our review, and then check out the last page for more information on the system, plus a link to enter our giveaway!

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 favoring 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 center on AMD’s Zambezi design, manufactured on Globalfoundries’ 32 nm node and composed of roughly two 1.2 billion transistors (AMD recently revised-down its transistor estimate in a big way). 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.

• 1

Current page:
AMD Sets The Stage For FX’s Performance

Next Page Platform Support For FX: Make Sure It’s AM3+

Chris Angelini is an Editor Emeritus at Tom’s Hardware US. He edits hardware reviews and covers high-profile CPU and GPU launches.

AMD FX-8150 Review | bit-tech.net

Written by

Clive Webster

October 12, 2011 | 05:03

Tags: #bulldozer #comparative #cpu #fx #overclock #overclocking #performance #processor #socket-am3

Companies: #amd #intel

1 — AMD FX-8150 Review2 — AMD Bulldozer — What’s a Module, what’s a Core?3 — AMD Bulldozer — More Performance Per Core4 — AMD Bulldozer Front-end and Memory5 — AMD FX-8150 Test Setup6 — AMD FX-8150 Cinebench and WPrime Performance7 — AMD FX-8150 Image Editing and Video Encoding8 — AMD FX-8150 Multi-tasking and Overall Performance9 — AMD FX-8150 Gaming Performance10 — AMD FX-8150 Power Consumption11 — AMD FX-8150 Stock-speed Performance12 — AMD FX-8150 Overclocking and Performance13 — AMD FX-8150 Conclusion

Manufacturer:AMD
UK price (as reviewed):£205 inc VAT
US price (as reviewed): $245 (ex tax) MSRP

The wait is finally over

There’s been plenty of confusion surrounding Bulldozer since we first heard about the new CPU microarchitecture back in July 2007 – we were told it was a modular CPU design that would incorporate a GPU. And that there would be only two flavours of Fusion processor – one based around Bulldozer for high-performance CPUs and another Bobcat design for low-power systems.

Most of that has turned out to be true, though there’s no graphics unit in a Bulldozer CPU and we have the Llano processor design to bridge the gap between Bobcat and Bulldozer.

More confusing was whether Bulldozer was ever meant for home use. In a briefing in August 2010 we were told explicitly that, ‘[Bulldozer] delivers 33 per cent more cores and an estimated 50 per cent increase in throughput in the same power envelope as Magny-Cours’, AMD’s current top-end Opteron design.

There was also talk that Bulldozer processors should drop into G34 motherboards with a BIOS update, and that a new Llano processor was intended for desktop use. Soon after, Bulldozer was confirmed as a desktop as well as server and workstation CPU design; after a delay of several months, it’s finally on sale.

Now that we have a Bulldozer CPU to test (plus the attendant reviewers’ guides, interviews and all the rest), we can clear away all the myths and rumours that have surrounded it. The FX-8150 is the first processor we’ve seen that’s based on the Bulldozer CPU architecture, and it’s the daddy of the new lineup with a nominal frequency of 3.6GHz (boosting up to 4.2GHz).

The FX-8150 is joined by three other FX-branded processors at launch, with another three models due to arrive at some point after today. Here’s a table to summarise the models we know about, before we go on and talk about them some more.

AMD FX-series processors
Name	Nominal Frequency	Turbo Core Frequency	Max Turbo Frequency	TDP	Cores	Level 2 cache	Level 3 cache	Northbridge Frequency	SRP
FX-8150*	3.6GHz	3.9GHz	4.2GHz	125W	8	8MB	8MB	2.2GHz	$245
FX-8120*	3.1GHz	3.4GHz	4GHz	95W and 125W	8	8MB	8MB	2. 2GHz	$205
FX-8100	2.8GHz	3.1GHz	3.7GHz	95W	8	8MB	8MB	2GHz	Unknown
FX-6100*	3.3GHz	3.6GHz	3.9GHz	95W	6	6MB	8MB	2GHz	$165
FX-4170	4.2GHz	None	4.3GHz	125W	4	4MB	8MB	2.2GHz	Unknown
FX-B4150	3.8GHz	3.9GHz	4GHz	95W	4	4MB	8MB	2.2GHz	Unknown
FX-4100*	3.6GHz	3.7GHz	3.8GHz	95W	4	4MB	8MB	2GHz	$115
*Launch models

Before delving into the specs, it’s worth noting that all FX processors are fully unlocked, meaning that there’s no need for the Black Edition branding we’ve become used to. None of the FX range has an integrated graphics unit, which in understandable on one hand, as AMD has already released two new processor designs this year with integrated graphics, while the much larger Intel has only given us one. To deliver three radically new APUs in one year would be astonishing. Even more so when you look into the Bulldozer CPU design, as there’s plenty of radical new design work that has gone into it.

As with the A-series and and E-series APUs, there’s no branding other than the letter – AMD has been planning to kill as many of its brand names as possible (including ATI) for a while, and the company has done just that with this launch. As far as real brands go, AMD now only has Vision, Radeon, FirePro and Opteron.

AMD is calling the FX-8150 the world’s first eight-core desktop processor, though to some controversy – we discuss what’s in a core? later, but will stick to an overview of the CPU design here. Bulldozer CPUs are comprised of Modules, each of which has two execution units and some shared resources, such as the Fetch, Decode, floating point unit and 2MB of Level 2 cache. These Modules can then be bolted together to form 4-, 6- or 8-core CPUs – Bulldozer is a very modular design, just as Intel CPUs have been modular in their construction for a while now too (since the Nehalem-based Core i7-900 series in November 2008).

A Module isn’t just made of a pair of stripped down K10 execution cores squabbling over some shared units, though, Bulldozer is a completely new design (and design philosophy) from AMD. As such, this article is rather long.

AMD FX-8150 Specifications

• Frequency 3.7GHz
• Turbo Frequency up to 4.2GHz
• Core Bulldozer
• Manufacturing process 32nm
• Number of cores eight physical
• Memory controller Dual-channel DDR3
• Cache 8 x 16KB L1 data, 4 x 64KB L1 instruction, 4 x 2MB L2, 4 x 2MB L3
• Packaging Socket AM3+
• Thermal Design Power (TDP 125W
• Features SSE, SSE2, SSE3, SSE4a, SSE 4. 1, SSE 4.2, 256-bit AVX, AESNI, PCLMULQDQ, AMD64, Cool’n’Quiet 3.0, AMD-V, MMX, FMA4, XOP

1 — AMD FX-8150 Review2 — AMD Bulldozer — What’s a Module, what’s a Core?3 — AMD Bulldozer — More Performance Per Core4 — AMD Bulldozer Front-end and Memory5 — AMD FX-8150 Test Setup6 — AMD FX-8150 Cinebench and WPrime Performance7 — AMD FX-8150 Image Editing and Video Encoding8 — AMD FX-8150 Multi-tasking and Overall Performance9 — AMD FX-8150 Gaming Performance10 — AMD FX-8150 Power Consumption11 — AMD FX-8150 Stock-speed Performance12 — AMD FX-8150 Overclocking and Performance13 — AMD FX-8150 Conclusion

AMD FX-8150 8-Core Bulldozer Processor

Bulldozer is AMD’s latest CPU architecture featuring an overhauled 32nm chip design, updated instruction sets, and up to eight processing cores. The FX-8150 sports a maximum clock speed of 4.2 Ghz while retaining the 125W TDP of most of the Phenom II X4/X6 line.

October 19, 2011 by Lawrence Lee

AMD has always been the CPU underdog, with Intel holding a substantial lead in performance except in the days of the Athlon 64 and Athlon 64 X2. Once Intel countered with Core 2 Duo line, they took the reigns and never looked back. We’ve been waiting for AMD to at least reach parity ever since.

AMD’s latest processor is Bulldozer, a revamped architecture, the first major redesign since Phenom II was released in 2009. Bulldozer has a restructured layout that AMD claims reduces some redundancies in traditional multi-core designs, creating a more efficient chip. Bulldozer uses a smaller 32 nm manufacturing process, allowing more cores to fit on the die. The desktop models (codename “Zambezi”) have up to eight cores and over two billion transistors, more than double that of the fastest Phenom II’s.

AMD is launching four Zambezi chips, the quad core FX-4100, the six core FX-6100, and the eight core FX-8120 and FX-8150. These CPUs use AMD’s latest AM3+ socket, an updated version of AM3 with the same pin count. An AM3+ motherboard or an AM3 model with listed AM3+ support is required; see your motherboard manufacturer website for details. If you have an AM3 chip, they are forwards-compatible — if for some reason you would like a new motherboard but do not wish to upgrade your processor at this time.

AMD provided us with one sample just paltry couple days before the embargo date, the top-of-the-line FX-8150 which will sell for US$245, putting in somewhere between the Intel Core i5-2500K and i7-2600K in pricing. AMD managed to keep the TDP at a reasonable 125W despite the eight cores and higher clock speeds. The FX-8150 is rated as a 3.6 GHz processor, but like Intel’s Sandy Bridge processors, always runs slightly faster on load due to its dynamic overclocking feature (Turbo Core for AMD, TurboBoost for Intel).

The FX-8150 isn’t a “true” octa core processor but rather has four Bulldozer modules packed with a pair of processing cores each — this is the biggest change from the older Phenom II architecture. The CPU has plenty of cache, 8MB of L2 (2MB per core) and 8MB of L3 (2MB per module). Bulldozer has also been updated with FMA, XOP, AES, AVX, and SSE 4.2 instruction sets giving it a boost in applications that support them. The total package has an amazing 2+ billion transistors, more than twice that of latest Phenom II X4/X6’s, fit on a ~315 mm2 die.

The lowest CPU state has a clock speed of 1400 MHz, up from 800 MHz, primarily to speed up the time it takes to reach the 3.6+ GHz performance states offered by the FX-8150. While the idle frequency has been increased, the core voltage is noticeably lower at 0.864V according to CPU-Z; Phenom II X4/X6’s typically idle at around ~1.000V.

Turbo Core is more aggressive on the FX-8150 than the Phenom II X6 line, with a maximum clock speed of 4.2 GHz. On load, idle cores are put into sleep states while active cores get pumped up clock speeds and voltages depending on how many cores are stressed, provided it does not exceed the 125W TDP. When all eight cores are stressed, they should all run at 3.6 GHz in optimal conditions.

As usual, our review kit was a bulbous, well-padded package containing a high-end motherboard, in this case, the Asus Crosshair V Formula. However, we didn’t expect the unnecessary tin box holding the CPU and a ridiculously oversized AMD FX belt buckle. It seems that AMD has taken some really odd steps to make reviewers pay attention to Bulldozer; even teens couldn’t be much impressed with the package.

PACKAGE & MOTHERBOARD

TEST METHODOLOGY

Common Test Platform:

• Corsair
  XMS3 memory 2x2GB, DDR3-1600 @ 1333MHz, 9-9-9-24
• Asus EN9400GT Silent Edition
  graphics card – 512MB
• Western Digital VelociRaptor
  hard drive – 300GB, 10,000RPM, 16MB cache
• Seasonic
  SS-400ET ATX power supply
• Microsoft
  Windows 7 operating system – Ultimate, 64-bit
• Nvidia
  Forceware 266.58 graphics driver
• Scythe Kabuto
  CPU cooler – stock fan at 800RPM

Intel LGA1155:

• Intel Core i3-2100
  processor – 3.1 GHz, 32nm, 65W (dual core)
• Intel Core i5-2400
  processor – 3.1 GHz, 32nm, 95W
• Intel Core i5-2500K
  processor – 3.3 GHz, 32nm, 95W
• Intel Core i7-2600K processor
  – 3. 4 GHz, 32nm, 95W
• Asus P8P67 motherboard
  – P67 chipset

AMD AM3:

• AMD Phenom II X4 955 Black Edition
  processor – 3.2 GHz, 45nm, 125W
• AMD Phenom II X4 965 Black Edition
  processor – 3.4 GHz, 45nm, 125W
• AMD Phenom II X4 975 Black Edition
  processor – 3.6 GHz, 45nm, 125W
• AMD Phenom II X6 1100T Black Edition
  processor – 3.3 GHz, 45nm, 125W
• Asus M4A78T-E motherboard
  – 790GX chipset

AMD AM3+:

• AMD FX-8150
  processor – 3.6 GHz, 32nm, 125W
• Asus Crosshair V Formula motherboard
  – 990FX chipset

Measurement and Analysis Tools

• CPU-Z
  to monitor CPU frequency and voltage.
• SpeedFan
  to monitor CPU temperatures.
• Real Temp
  to monitor CPU temperatures.
• CPUBurn
  processor stress software.
• Prime95
  processor stress software.
• Media Player
  Classic – Home Cinema to play x264/MKV video using DXVA.
• Adobe
  Photoshop CS2 as an image manipulation benchmark.
• Eset NOD32 as
  an anti-virus benchmark.
• WinRAR as an
  archiving benchmark.
• iTunes
  an audio encoding benchmark.
• TMPGEnc
  Xpress as a video encoding benchmark.
• HandBrake as a
  video encoding benchmark
• Seasonic
  Power Angel AC power meter, used to measure the power consumption
  of the system.
• Custom-built, four-channel variable DC power supply, used to power
  and regulate the CPU fan.

Timed Benchmark Test Details

• NOD32: In-depth virus scan of a folder containing 32 files of varying
  size with many RAR and ZIP archives.
• WinRAR: Archive creation with a folder containing 68 files of varying
  size (less than 50MB).
• iTunes: Conversion of an MP3 file to AAC.
• TMPGEnc: Encoding a XVID AVI file with VC-1.
• HandBrake: Encoding a XVID AVI file with H.264.
• Photoshop: Image manipulation using a variety of filters, a derivation
  of Driver Heaven’s Photoshop
  Benchmark V3 (test image resized to 4500×3499).

Testing Procedures

Our main test procedure is a series of benchmarks, timed tests of real-world applications. System power consumption (AC) is measured with a Seasonic Power Angel during these tests (an average of the first 10~15 seconds) as well as at idle, during playback of a 1080p H. 264 encoded clip, and during full CPU load. To stress the CPU we use either Prime95 (large FFTs setting) or CPUBurn depending on which
produces higher system power consumption. The AC system power is then later converted to DC.

Certain services and features like Superfetch and System Restore are disabled
to prevent them from affecting our results. Aero glass is left enabled if supported.
We also make note if energy saving features like Cool’n’Quiet and SpeedStep
do not function properly.

Estimating DC Power

The following power efficiency figures were obtained for the
Seasonic SS-400ET used in our test system:

This data is enough to give us a very good estimate of DC demand in our
test system. We extrapolate the DC power output from the measured AC power
input based on this data. We won’t go through the math; it’s easy enough
to figure out for yourself if you really want to.

Operating Voltages

Before we jump into our test results, please note the operating voltages
of the processors tested today as sort of a disclaimer. Different samples of
the same processor often run at slightly different operating voltages which
can affect energy efficiency. Different motherboard models do not apply the exact same core voltage either.

TEST RESULTS

System Power

Under light load the FX-8150 is a marked improvement over the X6 1100T, with a power savings of 7W when idle and 4W during H.264 video playback. It was close to X4 levels, but didn’t hold a candle to Intel’s Sandy Bridge lineup.

The FX-8150 consumed 25W more than 1100T when running our synthetic CPUBurn/Prime95 stress tester and 31W more when encoding video with HandBrake. This may be considered impressive considering it’s an eight core processor, but it’s staggering too see it use almost double the energy of Sandy Bridge.

PERFORMANCE

To test performance, we pit the processors against one another in a short series of timed tasks using real world applications. Power consumption was measured when applicable.

The FX-8150 produced a 9% gain in Photoshop compared to the 1100T but the driving force behind this is likely the higher clock speed. Despite the performance boost, it still trailed Intel’s latest Core i5’s and even Core i3’s.

A surprising result came in our NOD32 test with the FX-8150 coming in dead last. Even with Turbo Core pumping up clock speed in non-threaded applications, it still ended up 17% slower than the lowly X4 955.

The biggest improvement thus far was in WinRAR, where the FX-8150 posted a nice 17% improvement over the 1100T and with a slight power savings as well. Sandy Bridge still beat out all comers, but Zambezi narrowed the gap substantially.

PERFORMANCE (Continued)

The FX-8150 was struck by another setback in our iTunes encoding test, falling to X4 levels of performance and consuming about 10W more.

TMPGEnc is a multithreaded video encoding program, so if an eight core processor would shine, it would be here. The good news is that the FX-8150 reaches parity with Sandy Bridge here, matching the Core i5-2400’s encoding time. The bad news is it used more than twice the juice to achieve the same result.

HandBrake, which supports some of the new instruction sets included in Bulldozer’s architecture, is the only test where the FX-8150 clearly scored a win, beating out the i7-2600K by 13 seconds. However again, the power consumption was off the charts.

Overall Performance

We arrived at our overall performance score by weighing each test equally (each composing 1/6 of the total). Mathematically, a processor that finishes first in every single test receives a score of 100. As the Core i7-2600K only lost one test by a small margin, it tops the chart with 99 points.

The FX-8150’s overall performance in our test suite was lackluster compared to Intel’s Sandy Bridge quad core offerings. It was only competitive in our threaded video encoding tests. In the simpler tests, we got Jekyl and Hyde numbers which brought down the score though it was still an improvement over the 1100T.

The total power consumed by the FX-8150 running our test suite was more than 100% higher than the Core i5’s. Obviously the slower bench times inflate these numbers, but even in our video encoding tests where Zambezi drew even with Sandy Bridge in performance, the power draw was terrible. We had hoped that even if Zambezi wasn’t as fast as Sandy Bridge, it would at least be more energy efficient but sadly it’s just more of the same.

Power, Performance and Cost Analysis

We derived our average system power consumption numbers to consider both heavy and light usage. Heavy usage is defined as using the system running 75% of the time on high load (an average of the power consumption of our five measured benchmarks), while low usage is defined as running 75% of the time on light load (an average of the power consumption when sitting idle and playing H.264 video).

The standings of each processor do not vary depending on the usage pattern, but the relative differences are significant. The FX-8150 for example uses 45% more power than the i7-2600K in our light load scenario but this figure jumps to 67% on heavy load.

We arrive at our performance per watt scores by dividing the overall CPU performance by the average power consumption and adjusting the results so the best CPU scores 100 points. With better overall performance and superior energy efficiency, Sandy Bridge is firmly on top for both light and heavy usage systems. The AMD processors (the FX-8150 in particular) do slightly better on light load as the power consumption differences are lower.

Note: Motherboard pricing data was collected from Newegg’s catalog with the following criteria: retail versions, US$0~$250 after rebates if applicable, Asus/Intel/Gigabyte/MSI branded, microATX/ATX form factor, SATA 6 Gbps and USB controller. H61/H67/Z68 chipset for Core i3-2100, P67/Z68 chipset for Core i5/i7’s, AM3/AM3+ socket for Phenom II’s, AM3+ socket for FX-8150.

AMD has always had one advantage in its battle against Intel: Lower CPU and motherboard prices. The FX-8150 breaks this trend as its US$245 price is $35 more than the Core i5-2500K, and AM3+ motherboards also carry a slight premium over the older AM3 stock. Even with a more expensive P67/Z68 motherboard, the average i5-2500K system comes in slightly cheaper.

Focusing on performance:price alone, the FX-8150 falls short once again. The only way it reaches parity with Sandy Bridge is if only highly threaded applications are used.

FINAL THOUGHTS

Based on the tests we’ve conducted, the only end-users who could benefit from the new AMD chip are PC professionals that deal with sophisticated audio and video encoding, rendering, virtualization, and/or heavy workstation/server loads which max out CPU cores and system memory on a regular basis. If your needs are that demanding, you’ll probably want to run the system for longer durations than the average home user; undoubtedly this will drive up your electricity costs considerably. Already behind Intel in energy efficiency, Zambezi, or at least the eight core version, delivers no improvement in this regard.

For lighter usage patterns, the argument for the FX-8150 is fragile. High power consumption, albeit to a lesser degree is still a major factor and performance is lukewarm. We noted some improvements in a couple of simpler non-threaded benchmarks but in another two, the FX-8150 turned out to be slower than the X6 1100T. As the FX-8150 has a 300 MHz advantage, it seems that as a result of restructuring the chip architecture and/or splitting resources between cores/modules, per clock cycle, Bulldozer seems slower than its predecessor.

It is unfortunate for AMD that the chip lives up to its name. “Bulldozer” appears to be a big, lumbering beast that takes a lot of power to run and is only great at a few specific things. The FX-8150 excels mainly in multithreaded applications so you could argue it’s the CPU of the future, but with AMD playing catch-up they needed a hit today, not something that might outperform Sandy Bridge in a couple of years when more programs are coded to use multiple cores. Currently an Intel Core i5-2500K based system offers better, more well-rounded performance and far superior power efficiency at a slight discount compared to the FX-8150, so even AMD’s price advantage has evaporated. The less expensive FX processors may fare better, but only time will tell. Still struggling to fight in the desktop space, AMD faces further pressure as Intel’s newer, faster Sandy Bridge-E chips will debut in a month’s time.

Our thanks to AMD
and Asus for the FX-8150 and Crosshair V Formula samples used in this review.

* * *

Articles of Related Interest
AMD A8-3850 Quad Core Desktop APU (updated July 10)
Intel Core i3-2100T & Core i5-2400S Low Power CPUs
Intel Core i3-2100 vs. AMD Phenom II X2 565
Asus E35M1-M Pro: AMD Fusion Motherboard
Core i5-2400, i5-2500K and i7-2600K CPUs
AMD Athlon II X3: Affordable Compromise

* * *

Discuss
this article in the SPCR forums.

Bulldozer Arrives: AMD FX-8150 Review

AMD is kick starting the new FX lineup with seven processors, including 8-, 6- and 4-core models. The flagship processor is the FX-8150, which features a base frequency of 3.6GHz with a Turbo Core clock of 3.9GHz and a Max Turbo speed of 4.2GHz. Before delving any deeper, let us explain what the Turbo Core and Max Turbo frequencies mean.

AMD’s Turbo Core technology has been enhanced for FX processors to include a new mode that boosts allCores when there’s enough thermal headroom. This allows new highly threaded scenarios to take advantage of the extra frequency. AMD Power Manager inside the CPU monitors the processor states as seen below.The Max Turbo mode is activated on lightly threaded applications by increasing frequency on half the cores. AMD has enhanced the highest clock level of its Turbo Core Technology to remain in a higher frequency state than in previous AMD Phenom II Processors. The result is better performance in single and lightly threaded applications.

Turbo Core and Max Turbo are present on all core configurations (again, the FX series is comprised of 8-, 6- and 4-core chips). The 3.6GHz FX-8150 carries 8-cores, has a 125-watt TDP, and an 8MB L2 + 8MB L3 cache, which is standard across all 8-core FX parts. The flagship octo-core processor is accompanied by the 3.1GHz FX-8120 and 2.8GHz FX-8100.

AMD has set the FX-8150’s MSRP at $245, which is only slightly more than the Core i5-2500K’s asking price, while it is considerably lower than the Core i7-2600K. The FX-8120 is even more affordable than the i5-2500K at $205.

Along with the three 8-core processors, AMD has launched a single 6-core chip known as the FX-6100, which comes clocked at 3.3GHz with a Turbo Core frequency of 3.6GHz and a Max Turbo of 3.9GHz. While the L3 cache remains the same at 8MB, the L2 cache has been reduced to 6MB, as 1MB is allocated per core. The FX-6100 is only $175, which seems like an incredible bargain considering the Phenom II X6 1100T is currently $190.

Lastly, there are three 4-core models: the FX-4170, FX-B4150 and FX-4100. All of the quad-core CPUs have 4MB L2 cache with 8MB L3 cache. The FX-4170 is the highest clocked Bulldozer chip with a standard frequency of 4.2GHz, however, Turbo Core is disabled and the Max Turbo frequency is just 100MHz above the base clock.

Under Bulldozer’s hood

AMD’s new microarchitecture is designed to provide the perfect balance between performance, cost and power consumption for multithreaded applications. It focuses on high frequencies and resource sharing to achieve optimal throughput. As mentioned previously, the AMD FX processors offer up to eight power-efficient cores. These represent the first generation of a new execution-core family (15h) from AMD.

The Bulldozer concept is based on a 2-core design that shares latency-tolerant functionality, smoothes bursty/inefficient usage and provides dynamic resource allocation between threads. Each core has its own 16KB L1 cache with a 1MB L2 cache, while the L3 cache is shared. The other units are now effectively shared between two cores and include: Fetch, Decode, Floating-point pipelines, and the L2 cache.

This design allows two Cores to use a larger, higher-performance function unit (ex: floating-point unit) as they need it with less total die area than having separate, smaller function units for each Core. It also means that there shouldn’t be Bulldozer-based CPUs with an uneven number of cores like the Phenom X3 series.

The Zambezi Bulldozer-based processors have a die size of 315mm², which is smaller than the Phenom II x6’s 346mm² die, while it’s bigger than the Phenom II X4’s 258mm² die. The 6-core “Gulftown” Intel Core i7 processors are also smaller at 240mm2, and the complex Sandy Bridge chips such as the i7-2600K are 216 mm².

A large 32nm die means a lot of resistors and AMD tells us that the Zambezi architecture has roughly two billion of them. That’s pretty incredible given the Intel Core i7-990X Gulftown (32nm) features 1.17 billion while the Core i7-2600K has just 995 million. The older Phenom II X6 processors have 904 million and the Phenom II X4 chips just 758 million. Those numbers help convey just how complex these Bulldozer CPUs really are.

The floating-point unit has also undergone a complete redesign. It has been improved to support many new instructions and it now allows resource sharing between cores. There are two 128-bit FMACs shared per module, allowing for two 128-bit instructions per core or one 256-bit instruction per dual-core module.

AMD has also designed a shared front-end which is responsible for driving the processing pipeline and will ensure that the cores are constantly fed with information. It has been designed to work with each dual-core unit and allocate threads to individual cores themselves. AMD has made heavy changes that include decoupled predict and fetch pipelines as well as prediction-directed instruction prefetchers.

A Prediction Queue can manage direct and indirect branches that are now fed with a L1 and L2 Branch Target Buffer, which stores destination addresses. The Bulldozer modules can decode up to four instructions per cycle, which is one more than the Phenom II processors. The prediction pipeline produces a sequence of fetch addresses. The Fetch pipeline performs a look up in the instruction cache and pulls 32 bytes per cycle into the fetch queue to feed the decoders.

AMD has also built new instructions into the Bulldozer architecture. While AMD and Intel share SSE3, SSE4.1/4.2, AES, and AVX, there are two new instruction sets called FMA4 and XOP that are now unique to AMD. The former is designed for HPC applications while the latter is used for numeric and multimedia applications as well as algorithms used for audio and radio.

Unlike Sandy Bridge, which features an on-die GPU with the System Agent (aka northbridge), AMD has taken a more traditional approach with the Bulldozer architecture. The company is avoiding an IGP (Integrated Graphics Platform) all together with AM3+, leaving that functionality for its 32nm Llano processors, which feature a speedy Radeon core.

The northbridge is also separate from the processor. Even though AMD claims to include an integrated northbridge, it’s really just a memory controller. In fact, AMD pioneered this technology back in the Athlon64 days. Bulldozer’s northbridge features two 72-bit wide DDR3 memory channels and four 16-bit receive/16-bit transmit HyperTransport links.

Sticking with Chipsets

As mentioned on the previous page, AMD is sticking with a north and southbridge chipset design for the AM3+ platform and this makes sense in our opinion, particularly for such a high-end platform. By including separate chips to handle PCI Express lanes and connectivity, AMD has not only been able to simplify the processor design, allowing it to focus on performance, but it also grants the company a great deal of flexibility.

The AM3+ platform is supported by the 9-series chipsets, which currently include the 990FX, 990X and 970 northbridge with the SB950 southbridge. This chipset series features the same 65nm silicon used by AMD’s previous-generation 8-series chipsets.

In fact, the SB950 and SB850 are the same chip and therefore offer the exact same features. The reason for the name change is simply to help the user identify that one is designed for the AM3+ platform while the other supports AM3 processors.

The SB950 southbridge supports six SATA 6Gb/s ports with AHCI 1.2 as well as RAID 0, 1, 5 and 10. Additionally there is support for 14 USB 2.0 ports along with two USB 1.1 ports and gigabit Ethernet. When compared to the Intel Z68 PCH (Platform Controller Hub), there is nothing missing from the SB950 southbridge.

Meanwhile, the 990FX (codenamed RD990) is essentially the same chip as the 890FX, though there is one minor change. The 990FX has been updated with HyperTransport 3.1 to support up to 51.2GB/s bandwidth between it and the CPU. The 890FX is equipped with HT 3.0 which features a bandwidth of 41.6GB/s.

The 990X is a cut down version of the 990FX, as it reduces Crossfire support from dual x16 or quad x8 lanes to a pair of x8 lanes with no quad-fire support. Continuing with the theme, AMD’s 970 chipset is basically a rebadged 870 with HT 3.1 support added. It lacks Crossfire support as it only includes a single PCIe 2.0 x16 lane.

990FX Partner Boards

AMD 990FX boards have been on the loose for some time now — we’ve had the Asrock Fatal1ty 990FX Professional for about two months. Along with its Fatal1ty- branded board, Asrock offers two other 990FX-based motherboards: the 990FX Extreme4 and 990FX Extreme3. The company also has a couple of AMD 970 motherboards available.The Fatal1ty 990FX Professional is currently retailing for $190, which is very affordable for a high-end motherboard. The price is especially impressive considering the included features, such as USB 3.0, SATA 6Gb/s, 8-channel audio, dual Gigabit LAN with Teaming function, 12 + 2 power phase design as well as Quad Crossfire and SLI support.

Despite being a Fatal1ty-branded product, we like the look and design of Asrock’s premium board. It has an excellent layout and UEFI BIOS interface.

We also included the Asus Crosshair V Formula in our review kit. This board costs considerably more at $230, but doesn’t seem to justify that premium.

Features such as USB 3.0 remain the same, while the Crosshair V Formula drops one of the two gigabit Ethernet jacks and eSATA ports. The audio has been upgraded to the SupremeFX X-Fi 2 codec, while the board also features an extra full-length PCIe 2.0 x16 slot. Overall, we prefer Asus’ aesthetics, but its board about equal in terms of functional design.

Asus also has the Sabertooth 990FX available, as well as various 990X and 970 motherboards. The Sabertooth 990FX is a cheaper alternative to the Crosshair V Formula, as it costs just $190 yet it is still very well equipped.

Although we’ve only received boards from Asrock and Asus so far, other manufacturers such as MSI and Gigabyte already have their flagship 990FX boards in stores, including the $145 MSI 990FXA-GD65 and $250 Gigabyte GA-990FXA-UD7.

How We Tested & Bandwidth

AMD has supplied us with its top-end FX-8150 processor for testing. Thankfully, the FX range is unlocked and the Asrock Fatal1ty 990FX motherboard allowed us to enable just six, four or two cores. This board also allows customization of the Turbo Core and Max Core multiplier. This allowed us to mimic the performance from the lesser three FX processors launching today: the FX-8120, FX-6100 and FX-4170.AMD AM3+ Test System Specs
– AMD Phenom II X6 1100T (3.30GHz)
– AMD Phenom II X4 980 (3.70GHz)
– AMD FX-8150 (3.60GHz)
– AMD FX-8120 (3.10GHz)
– AMD FX-6100 (3.30GHz)
– AMD FX-4170 (4.20GHz)
– x2 4GB G.Skill DDR3 PC3-12800 (CAS 8-8-8-20)
– Asrock Fatal1ty 990FX Professional (AMD 990FX)
– OCZ ZX Series 1250w
– Crucial m4 256GB (SATA 6Gb/s)
– Gigabyte GeForce GTX 580 SOC (1536MB)
Software
– Microsoft Windows 7 Ultimate SP1 64-bit
– Nvidia Forceware 285.38Intel LGA1155 Test System Specs
– Intel Core i7-2600K
– Intel Core i5-2500K
– x2 4GB G.Skill DDR3 PC3-12800 (CAS 8-8-8-20)
– Gigabyte G1.Sniper2 (Intel Z68)
– OCZ ZX Series 1250w
– Crucial m4 256GB (SATA 6Gb/s)
– Gigabyte GeForce GTX 580 SOC (1536MB)
– Microsoft Windows 7 Ultimate SP1 64-bit
– Nvidia Forceware 285. 38Intel LGA1366 Test System Specs
– Intel Core i7-975 Extreme Edition (3.33GHz)
– Intel Core i7-920 (2.66GHz)
– x3 2GB G.Skill DDR3 PC3-12800 (CAS 8-8-8-20)
– Gigabyte G1.Sniper (Intel X58)
– OCZ ZX Series 1250w
– Crucial m4 256GB (SATA 6Gb/s)
– Gigabyte GeForce GTX 580 SOC (1536MB)
Software
– Microsoft Windows 7 Ultimate SP1 64-bit
– Nvidia Forceware 285.38Intel LGA1156 Test System Specs
– Intel Core i5-750
– x2 4GB G.Skill DDR3 PC3-12800 (CAS 8-8-8-20)
– Gigabyte P55A-UD7 (Intel P55)
– OCZ ZX Series 1250w
– Crucial m4 256GB (SATA 6Gb/s)
– Gigabyte GeForce GTX 580 SOC (1536MB)
– Microsoft Windows 7 Ultimate SP1 64-bit
– Nvidia Forceware 285.38 

Compared to the Phenom II, AMD’s FX processors provide significantly more memory bandwidth. Read throughput has been increased by roughly 60%, while write performance is almost 40% better. Although the bandwidth performance has been improved greatly, it’s still considerably slower than Intel’s Sandy Bridge processors. 

The L2 cache performance has also been improved — at least when looking at the Phenom II range. The FX-8150 delivered 30% more read throughput than the Phenom II X6 1100T, though the write performance was slightly slower. As with the previous chart, Bulldozer just can’t match Sandy Bridge’s L2 cache performance.

Synthetic Performance

SPECviewperf v11 is clearly not optimized for processors with more than four cores, as the highly clocked 4.2GHz AMD FX-4170 came away with the win. Rendering an average of 10.56fps in the SolidWorks test, it was slightly faster than the FX-8120 and FX-8150 processors. The FX-8150 still managed to outpace the Phenom II X6 1100T by 39% and it held a 17% margin over the Core i7-2600K.

The Maya benchmark revealed a similar trend. AMD’s FX-4170 seized the throne, while the FX-8150 trailed with a 55% lead on the Phenom II X6 110T and a 7% jump on the Core i7-2600K.

CINEBENCH R11.5 broke Bulldozer’s momentum as the FX-8150 rendered an average of 48.96fps, which was 9% slower than the i5-2500K and i7-2600K. Nonetheless, it was 4% faster than the Phenom II X4 980 and 6% quicker than the Phenom II X6 1100T.

The FX-8150 performed exceptionally in the WinRAR benchmark, delivering a multithreading result of 4287KB/s — 18% faster than the i7-2600K and 32% faster than the i5-2500K. Moreover, it landed 52% ahead of the Phenom II X6 1100T and 66% higher than the Phenom II X4 980.

Application Performance

AMD’s flagship Bulldozer processor delivered roughly the same performance as the Core i5-2500K and Core i7-920 in Excel 2010, which is a giant leap forward compared to the Phenom II. AMD’s chips rarely do well in Excel compared to Intel’s. For example, the Phenom II X6 1100T was 30% slower than the FX-8150.

WinRAR’s built-in benchmark pegged the FX-8150 as the fastest processor by far, but the results are quite different in our own custom WinRAR compression test. The FX-8150 took 118 seconds to complete the 700MB file compression test, which was on par with the dated Core i7-920, but 17% slower than the i5-2500K and 22% behind the i7-2600K.

Compared to AMD’s last-gen hexa-core processor, the FX-8150 offers a hefty 26% boost in Adobe Photoshop CS5, placing it in the league of Intel’s i5-2500K — though the i7-2600K was still 32% faster.

The FX-8120 was only a fraction of a second slower than its snappier sibling, and although the FX-6100 saw a noticeable performance drop, it was still 8% faster than the Phenom II X6 1100T. Oddly. the FX-4170 was 4% slower than the Phenom II X4 980, which is surprising considering they’re both quad-core processors and the FX-4170 has a significant clock advantage.

When testing with Fritz Chess 12’s built-in benchmark, the FX-8150 delivered 11682 kilo nodes per second, which was only 1% faster than the Phenom II X6 1100T and 10% quicker than the i5-2500K, while being 12% slower than the i7-2600K.

Clock for clock, the FX processors are likely no faster than the Phenom II in this test, as the FX-8120 was 6% slower than the Phenom II X6 1100T. Moreover, the FX-4170 was 24% slower than the Phenom II X4 980 despite having a 14% higher frequency.

Encoding Performance

The FX-8150 was 15% quicker than the X6 1100T with 113.8fps in HandBrake, while scoring only 2% lower than the i5-2500K and 5% behind the i7-2600K.The lesser-clocked FX-8120 performed as well as the Core i7-975 Extreme Edition, while the FX-6100 was 3% slower than the X6 1100T. Clock for clock, AMD’s dated processor won the hexa-core battle. Likewise, the X4 980 was much faster than the FX-4170.

The x264 HD Benchmark 4.0 produced another interesting result. In the Pass 1 test, the FX-8150’s 121.3fps showing was 2% slower than the X6 1100T, 15% slower than the i5-2500K, and 17% slower than the i7-2600K. At the same time, the dated X4 980 was only 1% slower than the FX-8210 and it fared 11% better than the FX-4170.

Things were quite different in the Pass 2 test, as the FX-8150 scored the best with 37.1fps, beating the i7-2600K by half a percent. The FX-6100 and FX-4170 still lagged behind their Phenom II counterparts.

The last encoding benchmark uses TMPGEnc 4.0 Xpress to measure the AVI to MPG conversion time. AMD’s latest offering slipped behind Sandy Bridge again as the i5-2500K and i7-2600K outmatched the FX-8150 by 27% and 31%. The FX-8150, FX-8120 and FX-6100 all delivered roughly the same performance. The FX-4170 fell to the bottom of the chart, sitting 2% lower than the X6 1100T and 5% behind the X4 980.

Gaming Performance

Dirt 3’s results appear to be dominated by Intel as AMD occupies the bottom six slots. However, if you look closer there is a difference between 1680×1050 and 1920×1200 performance. Intel clearly controlled the 1680×1050 results (where you could say there was less of a GPU bottleneck) the AMD processors performed better at 1920×1200.At 1920×1200, the FX-8150 matched the i7-2600K and narrowly defeated the i5-2500K. The FX-8120 was in line with the i7-975 EE, while the FX-6100 kept pace with the i7-920. Despite its 4.2GHz clock rate, the FX-4170 was the slowest processor tested.

Besides the Phenom II X4 980, AMD again filled the bottom of our graph when measuring 1680×1050 performance. However, at 1920×1200 the FX-4170 was actually the fastest processor tested, delivering 88fps. The rest of the FX lineup rendered between 82 and 84fps, allowing them to deliver similar results to the Core i5 and Core i7 products.

We saw mixed results in The Witcher 2 also. At 1680×1050 the FX processors performed poorly, with the exception of the FX-8150 which managed 77.6fps, placing it in the i7-920’s territory.

The FX-8150 delivered roughly 1fps more than the FX-8120 and FX-6100 when testing at 1920×1200, and although that’s in line with the i7-975 EE and 920, it was slower than the Phenom II X4 980 and X6 1100T.

Crysis 2’s performance was also disappointing for the FX processors as it doesn’t benefit from having more than four threads available. This allowed the FX-4170 to dominate at 1680×1050, while the FX-8150, FX-8120 and FX-6100 were all slower than the Phenom II X4 980.

Power Consumption

Power consumption is still an issue for AMD, as we found the FX-8150 chugged 252 watts under full load. Although that’s 5% less than the i7-920, it was 52% (86 watts) more than the i7-2600K. Idle consumption wasn’t much better. At 100 watts, the FX-8150 gobbled 32% more power (24 watts) than Intel’s enthusiast chip.The FX-6100 was slightly better than the Phenom II X6 1100T with consumption, though we should stress only slightly. It’s a similar situation when comparing the FX-4170 and Phenom II X4 980, but there is an improvement nonetheless.

Overclocking Performance

Overclocking the FX-8150 from its base 3.6GHz clock to 4.4GHz boosted Dirt 3’s performance at 1680×1050 by 4%. The 1920×1200 performance didn’t budge a single frame.

The 4.4GHz overclock delivered just under 3% more performance in the Pass 1 test and 12% more in Pass 2. This allowed the FX-8150 to overtake the Phenom II X6 1100T, but it was still much slower than the i5-2500K and i7-2600K.

CINEBENCH R11.5 OpenGL saw no performance gain when overclocking the FX-8150, though the CPU score increased 17%.

Final Thoughts

Breaking down our benchmark results we find that the AMD FX-8150 offers huge performance improvements over the Phenom II range when testing with Excel 2010, while it matched the Core i5-2500K and Core i7 920 processors. Our custom WinRAR benchmark also heavily favored the FX-8150 over the Phenom II, matched the Core i7 920 and trailed behind Sandy Bridge processors in this test.

The Adobe Photoshop CS5 benchmark also saw the FX processors provide decent performance gains over the Phenom II. Although the six-core FX-6100 was only slightly faster than the Phenom II X6 1100T, the eight core FX-8150 and FX-8120 processors provided significant gains and were able to match the Core i5-2500K.

The encoding performance was far less impressive as we found that clock for clock the FX processors were slower than the current Phenom II processors. The FX-6100 for example was slower than the Phenom II X6 1100T in our HandBrake and x264 HD Benchmark 4.0 tests. The FX-6100 did pull ahead by a decent margin when testing with TMPGEnc 4.0 XPress however. For the most part the FX-8150 was still considerably slower than the Core i5-2500K in our encoding benchmarks.

Finally, when it came time to play games the FX range was really no better than the Phenom II. To be completely honest, gaming on these high-end processors is so similar it’s hardly worth worrying about. The FX-8150 was never more than a few frames per second slower than the Core i7-2600K at 1920×1200.

Given that today’s latest game releases are only starting to adopt quad-core processors, having six or even eight threads available is of little consequence.

As for performance vs. power efficiency, the AMD FX processors are really not much better than the Phenom II range either, which is disappointing. When compared to Sandy Bridge CPUs, such as the Core i7-2600K and Core i5-2500K, the new FX processors stack up very poorly.

Despite the unlocked nature of the FX processors, overclocking is not fantastic. We were able to push the FX-8150 to just 4.4GHz on air (from the stock 3.6GHz). Compared to the 4.1GHz of our Phenom II X6 1100T it’s not bad, but if you consider the 5.2GHz possible with a Core i5-2500K or Core i7-2600K it’s definitely not great. Granted we were only able to achieve this extreme overclock using the Asus Maximus IV Extreme-Z, but all other P67 and Z68 motherboards reach at least 4.7 – 4.8GHz.

Then there is the question of value. At $245 the FX-8150 is pretty good, as is the FX-8120 at $205, and the FX-6100 at $165. The FX-8150 is 22% cheaper than the Core i7-2600K and this works to AMD’s favor as the FX-8150 was often less than 20% slower.

However, is the FX-8150 a better buy than the Core i5-2500K? In terms of performance the AMD CPU was more often than not slower, if only by a small margin, while it does consume considerably more power and will not provide the same overclocking results. It’s no secret who wins this round.

Considering that the FX-8120 is essentially the same processor as the FX-8150, we will look to it for the FX vs. Core i5 comparison. The FX-8120 costs $205 and it’s unlocked — all FX processors are — so it can be easily modified to match or exceed the operating specifications of the FX-8150. Therefore we feel the cheaper FX-8120 gives the Core i5-2500K a serious run for its money and it’s a worthy alternative. Meanwhile the FX-6100 is also great value at $165, as it undercuts both the Phenom II X6s but it wasn’t always faster.

We won’t deny it, we really were hoping for a lot more from Bulldozer and AMD’s eight-core processors. It’s disappointing to find these newly launched processors do little to improve AMD’s situation. The FX processors come short of competing hand to hand with the now 9-months old Sandy Bridge processors, and in certain instances surpass their own Phenom II range. Still, this is just the start for Bulldozer, and there’s much more to be seen from the FX range, or so AMD says.

Taken From http://www.techspot.com/review/452-amd-bulldozer-fx-cpus

Tags: AMD FX

testing Bulldozer GECID.

com architecture. Page 1

::>Processors
>2011
> AMD FX-8150

06-11-2011

Page 1
Page 2
One page

One of the most anticipated products of the processor market both this year and, in other words, last year was the CPU based on the new microarchitecture Bulldozer . Such excitement was associated primarily with a fairly large amount of various preliminary information and «all sorts of leaks.» One of the factors of increased attention was the rather long period of use of the K10 architecture, which was announced at the end of the distant 2007, and in essence was a correction of the shortcomings of the previous K8 and K7 architectures. At the same time, it is worth noting the fact that the K7, a decade ago, was still the base one. Due to the fact that the capabilities of the K10 architecture were actually exhausted, which we observed in various model ranges of AMD processors, the need for fundamental changes became quite logical. The most intense moment was the presentation of the brainchild of AMD developers to the public. Despite the fact that the demonstration was postponed several times, but on October 12, a significant event happened, and as many as 4 CPU models for desktop PCs based on the new Bulldozer architecture were presented. The family itself was named Zambezi .

Before moving on to the processor lineup, let’s take another look at the structure of the die itself. An important difference is the use of so-called modules (blocks), which in essence are nothing more than dual x86 processor cores. It is from this feature that the very 8 processor cores appear, although a cursory glance at the crystal structure reveals only 4, the so-called Bulldozer modules.

The processor modules themselves, in addition to two x86 cores, are also equipped with real computing units (FPU), “front end” and second-level cache (L2). Such a dual arrangement of processor cores in its essence very much resembles the idea of ​​Hyper-Threading, which used the computing capabilities of a single physical core, and in the novelty from AMD, there was actually a competitor’s technology implementation at the physical level with several common resources, such as an FPU unit. Common to all modules is the L3 cache.

An important structural component of the new architecture is the «Front end» block, which is essentially a set of logical devices that prepare instructions for execution on computing devices. Its key elements are: branch prediction blocks, the first level (L1I) instruction cache, and the decoder. The main task solved by prediction blocks is to optimize the load of processor cores in order to minimize the total number of CPU idle times due to delays in transferring data from RAM or caches. The decoder is responsible for converting x86 commands into a «understandable» form for other devices.

The main change that took place in this block in comparison with the previous architecture, in addition to improving the accuracy of predictions, is an increase in the number of instruction processing channels to four. However, if we consider the fact that, unlike the K10 architecture, the «Front end» block will actually process 2 data streams, it is likely that we can observe some shift in the strengths and weaknesses of the AMD FX family of CPUs compared to the previous generation CPUs.

Schematic diagram of the processor module

The block of floating point operations has undergone major changes. The diagram shows that it includes two 128-bit FMAC execution units, which can be combined into a single unit to process 256-bit instructions. Unlike the K10, where different devices were responsible for the addition and multiplication operations, these are universal and capable of executing the entire range of supported commands. We see that AMD is moving from an asymmetric FPU design to a symmetrical one. In the case of sharing resources between two x86 cores, each can work with its own FMAC device. In fact, the computing capabilities of the FPU are divided into two cores, but due to the greater versatility of the constituent components, in certain cases, this approach can provide close or potentially higher performance compared to other solutions.

The only drawback of this approach is that in this case the programmer is responsible for the processor load, who must initially optimize the code to execute it in two threads. For comparison, it is worth remembering that the Sandy Bridge core intelligently loads its own resources due to advanced in-processor logic that independently parses single-threaded code and executes it in parallel on a full set of its execution devices.

We have tried to cover the key differences and features in the architecture in more detail, as for other questions, you will most likely find the answers to them in the presentation materials.

The appearance of the retail box version of new products is quite intriguing. You can see that there are familiar elements of the packaging, such as a plastic window, but it has taken on a more rounded and sleeker look. But, as they say, packaging is packaging, and each of us acquires exactly its contents.

AMD FX Desktop Processor Lineup

Currently, the AMD FX lineup includes both octa-core solutions and solutions with a lower number of active modules. The «highlight» of the series is the presence of an unlocked processor multiplier and support for TurboCore2.0 technology.

The hero of this study is the Guinness World Record holder AMD FX-8150 .

Externally, the processor is absolutely no different from its predecessors made for Socket AM3, and looks very modest. The traditional marking of the processor cover tells the owner a lot of information. In this case, it is as follows — FD8150FRW8KGU:

• F — the processor belongs to the AMD FX family;

• D — the scope of this processor — workstations;

• 8150 — model number;

• FR — 125 W processor thermal package;

• W – the processor is packaged in a 938 pin Socket AM3+ package;

• 8 – total number of active cores;

• K — 1 MB L2 cache per core and 8 MB L3 cache;

• GU is the core of the OR-B2 stepping processor.

The back of the AMD FX

Right side of the AMD Phenom II

processor is essentially there are no differences in the back of the processor, even though there is no, even though that uses a fundamentally new architecture.

Specification

The AMD FX-8150 octa-core processor belongs to the Zambezi family and is manufactured according to the 32 nm process technology. The processor clock speed is 3.6 GHz, while the core voltage is 1.2 V. A distinctive feature of the new architecture is support for a wider set of instructions: AVX in the Intel implementation with the addition of XOP, as well as FMA4 (simultaneous operation with 4 operands) , which «migrated» from the SSE5 instruction set, announced in 2007, but never gained much popularity.

inaccurate, because the manufacturer indicates it at 125 W, but such an inaccuracy does not play a big role.

As you can see, even for processors with a new architecture, the frequency of overclocker memory modules is automatically set at 1333 MHz, although DDR3-1866 is native to the memory controller. The maximum efficiency of working with RAM can be obtained only after manually adjusting the motherboard’s operating parameters in the BIOS, if it allows it.

The new cache is distributed as follows. Level 1 Cache: 16 KB per 8 cores allocated for data with 4 associativity channels, with 64 KB per instruction for each 2-processor module with 2 associativity channels. Level 2 cache: 2 MB for each processor module, which, as you remember, 4, with 16 associativity channels. Level 3 cache is shared by the entire processor and is 8 MB with 64 associativity channels.

The Turbo Core 2.0 technology implemented in AMD FX processors deserves special attention. Its general characteristics were given by representatives of the company in the presentation of processors. Recall that the new products have 2 modes: Turbo Core and Max Turbo Core. The differences between the modes are that for the “classic” mode, the clock frequency of all cores is increased, and for Max Turbo Core, the frequencies of half of the cores are reduced to the lowest possible level, while the remaining cores receive the maximum increase. Operation in these modes is carried out until the CPU exceeds the declared thermal package or there is no need to increase the frequency.

If you are using an AMD FX-8150 processor, you may observe the following situations.

AMD FX-8150 operates in TURBO C O RE with all used nuclei

AMD FX-8150 operating o re

Due to the fact that all processors are equipped with this technology, and it allows you to get an additional increase in performance, it is quite reasonable to use it after all.

AMD FX-8150 processor

The flagship solution based on the new Bulldozer microarchitecture

Bulldozer… Perhaps the most long-awaited product (to be more precise, the architecture of a whole family of products) in the second half of 2011. Along with LGA2011 and SB-E from Intel, of course, but the prices of this desktop ejection of the server segment initially made even true fans of the company fall in love with the extreme platform only platonically — without hopes of physical possession 🙂 There were no such concerns about the new AMD processors: thanks to the long-standing leaks knew that even older models would cost less than, for example, the Core i7-2600, and the younger ones would completely fit into the mainstream. Plus, full carte blanche for any overclocking methods, plus the potential ability to unlock cheap «three-module» processors, plus the ability to use new processors in conjunction with already purchased motherboards (which in some places is a significant advantage in the eyes of not yet completely extinct fans of component-by-component modernization of computers) — all this attracted the attention of many enthusiasts in advance. Well, people with a healthy psyche were attracted by statements about the increased productivity of new solutions compared to the old ones. Yes, and in general, quite a common desire to see something new from AMD (and until recently, all the processors of this company dated back to K7 ten years ago, which has been developing all these years in a purely evolutionary way, which more and more began to resemble an evolutionary dead end) and hopes that even if the processors of the new family fail to take a leading position in terms of performance immediately after the start, they will at least intensify competition in the $200-$300 segment, which (what the devil is not joking!) can lead to price cuts.

That is why many people were waiting for new processors. So, as none of the AMD processors has been waiting for a long time, with the possible exception of the first Phenom. Then, however, such a long wait played a cruel joke on the company’s fans — at first, these «true quad-core» processors did not justify the hopes placed on them. They had to be worked on long enough to eventually come to a very good Phenom II, but it was already later. In general, one gets the feeling that it was easiest to develop just K7 and K8 — then few people hoped that the company would get something successful, so there were no excessive hopes (with subsequent disappointments). And then… take it out and put it in miracle. How often do miracles happen?

Initially, the Network was disturbed by rumors that the processors of the FX family (AMD believed in the capabilities of the new CPUs in advance, so they added fuel to the fire of anticipation by reviving the trademark under which the company once shipped the fastest processors on the market, at a price of about $ 1,000 each ) will appear in the summer. By this time, motherboard manufacturers have already managed to update their model lines with products with the AM3 + connector (and on new chipsets too), as well as compete with announcements about the support of new processors by old models — which are “just” AM3. In general, everyone froze in anticipation, and … The processors were not presented to the general public. It turned out that they are “not quite ready”, so they need to be finalized. However, by that time a lot of engineering samples fell into the hands of various «independent» testers, so, without having accurate information about the performance of new processors, all resources began to race to publish «preliminary» data. To put it bluntly, not too shiny. Together with the delay in the announcement, this caused the effect that we warned about back in the spring: Bulldozer also runs the risk of being a good processor, but not good enough given the advances given to it. After that, as often happens, his most active supporters are the first to migrate to the camp of opponents — unsatisfied expectations often do other things to people. Somehow, those who expected victories over the more expensive Core i7-2600 immediately calmed down, but there were many who wanted to gloat about the fact that, they say, they couldn’t even make the processor on time, and what they did was no good. In general, the second stage of waiting for the official announcement, unlike the first, was filled not with optimism, but with sarcasm. But finally it ended — no matter what happens, the company seems to have decided that the processor will not survive another postponement of the announcement, so it’s time.

What really happened? In practice, AMD managed to step on the same rake that caused great damage to Intel when working on Prescott: both introduce a new architecture and master a new technological process for manufacturing crystals. But before gloating about the fallacy of this path, it was worth considering: did the company have another way out? It didn’t make much sense to make a simple “shrink” of Stars at 32 nm — this architecture has already exhausted the modernization reserve. They did it in Llano, so what? The new (desktop and mobile) platforms are saved only by a very high degree of component integration, which allows using only two chips to create completely modern computers, not without the possibility of even gaming use, but by no means the attractiveness of the processor part itself, which is completely absent. And it doesn’t make much sense to continue releasing Phenom II either. The quad-core Deneb has an area of ​​258 mm² with 758 million transistors, the six-core Thuban is all 346 mm² and 904 million transistors. But in fact, that one that the other is no longer able to compete with Sandy Bridge with an area of ​​\u200b\u200bonly 216 mm².

Suppose thinner norms would make it possible to equalize in area and slightly increase clock frequencies, but this would be a solution only for a few months — at best, until the release of Ivy Bridge (or maybe this would not have happened — current Intel processors have a considerable margin for increasing clock frequencies without any significant alterations). Zambezi (the basis of the new FX) already contains about two billion transistors, so the release of such a processor according to 45 nm standards is almost impossible (or the prices should be four-digit — as observed in Intel Beckton server processors). But when using the 32 nm process technology, the area was made equal to only 315 mm²! Not so little, but it’s already obvious that if the processor is immediately at least equal to or slightly better than the Phenom II X6, it makes sense. Albeit not from the point of view of fans, but according to market realities — it can be cheaper to manufacture than Thuban. Well, then — a simple «licking» of the architecture already in the process of selling finished devices, which the company knows how to do. Yes — the fans will not be too happy: they wished for a miracle. And for everyone else, such progress will suit.

In general, the three new processors of the new family, one way or another, are starting to be sold in stores from today. This architecture, we repeat once again, is new, it is she who will soon become the basis of all AMD processors (including the APU), so lovers of theoretical research will have a huge field for activity. We won’t interfere with them 🙂 Today, a practical question is on the agenda: does it follow from the possibility of buying a new processor that it is justified from the point of view of using completely ordinary everyday programs? That is, translating from Russian into Russian, we will test the oldest of the presented models using our standard testing methodology. 8/8 4/4 6/6 4/4 4/8 cache L1, I/D, KB 4 × 64/8 × 16 4 × 64/4×64 6×64/6×64 4×32/4×32 4×32/4×32 L2 cache, KB 4×20048 6 × 512 4 × 256 4 × 256 L3 cache, MIB 6 6 8

9009 9009 Frequency Uncore, GHC 2. 2 2 2 3.3 3.4 RAM 2 × DDR3-1866 2 × DDR3-1 2 × DDR3-1333 2 × DDR3-1333 2 × DDR3-1333 Video — — GMA HD 2000 9009

GMA HD HD HD HD 20009, GMA HD HD HDA HD AM3+ AM3 AM3 of the new core’s own is a first-level data cache with a capacity of 16K. But two such cores are combined into a module. The latter also has one FPU / MMX / SSE block, etc. (for two), a 64K instruction cache and 2 MiB of L2 cache. Three or four modules combined makes for a full processor at the moment after another 6/8 MiB of L3 is added to them (2 MiB per module, i.e. in the six-core FX-6100, priced at only $165, or in the FX-4100, which is expected a little later, for «mere pennies» in the amount of 115 of these same kopecks, you can try to unlock not only the «cores», but also the cache), as well as memory controllers and HT.

In principle, the weaknesses of the new design are immediately visible. In particular, processors will suffer from single- and dual-threaded applications even more than Phenom II X6: previously, each thread had 64K fast data cache, and now the capacity has decreased by four times. True, the L2 cache potentially available to one thread has increased by the same four times, but will one compensate for the other? Complex issue. And there are as many blocks for working with floating point as well as integer vector instructions as in Phenom II X4, which can be considered a step back from Phenom II X6. True, they should work faster, and in the limit just twice … But okay — let’s not take bread from microarchitecture researchers 🙂 As mentioned above, today we have a quite practical goal: to see how all these bold decisions will behave in practice — in real software packages. What will we do.

Luckily, you don’t have to spend a lot of time introducing competitors — of course, they simply have to be the fastest Phenom II X4 and X6, as well as two LGA1155 processors, between which the FX-8150 is positioned in terms of price. And not only on it — in its materials, AMD compares the new flagship with the i5-2500 and i7-2600. So we’re not going to reinvent the wheel.

	System board	RAM
LGA1155	Biostar TH67XE (H67)	Corsair Vengeance CMZ8GX3M2A1600C9B (2×1333; 9-9-9-24)
AM3	ASUS M4A78T-E (790GX)	Corsair Vengeance CMZ8GX3M2A1600C9B (2×1333 ; 9-9-9-24-2T, Unganged Mode)
AM3+	ASUS Crosshair V Formula (990FX)	G.Skill [RipjawsX] F3-14900CL9D-8GBXL (2×1866; 9-10- 9-28)

Testing

Traditionally, we divide all tests into a certain number of groups and show the average result for a group of tests/applications on the diagrams (for details on the testing methodology, see a separate article). The results on the diagrams are given in points, the performance of the iXBT.com reference test system of the 2011 sample is taken as 100 points. It is based on the AMD Athlon II X4 620 processor, but the amount of memory (8 GB) and the video card (NVIDIA GeForce GTX 570 1280 MB by Palit) are standard for all tests of the «main line» and can only be changed as part of special studies. Those who are interested in more detailed information are again traditionally invited to download a table in Microsoft Excel format, in which all the results are shown both in converted points and in «natural» form.

Interactive work in 3D packages

Initially, there were many predictions that the new architecture would still increase per-thread performance. In this group of applications, a similar effect would be clearly visible (and it was well manifested in the example of Sandy Bridge). If only it existed in practice. What, as we see, is not observed — this is bad news. But there is also a good one: apparently, the simplification of each “core” in many cases can be compensated for by architectural improvements or clock speed (the second is more likely), so the processor even in this group turned out to be even slightly better than Phenom II. Moreover, as we can see, here the older Phenom II X6 was (also slightly) worse than the older Phenom II X4, but the FX-8150 has no such problems. But, of course, it’s too early to talk about competition with processors based on the Sandy Bridge core. Or rather, you can talk, but only talk.

Final rendering of 3D scenes

Most likely, this is the best illustration of the difference between cores and «cores» — we recall that there are just as many non-integer modules (namely, they are involved here) in the processor as many modules (pun intended), i.e. not eight, but only four. But the Phenom II X6 still has six of them, so it’s faster, but they are slow, so it’s a little slower than the Core i5-2500, where the cores are fast, even if there are only four of them. Ultimately, the result of the novelty is still closer to Phenom II X4, albeit with a slightly more than ten percent advantage over the older representative of the latest line.

However, a lot can still change in this group. Apparently, AVX is definitely not used in the versions of render engines we use (which is why, for example, the Core i7-870 is faster than the Core i5-2500), and the new SSE versions are also poorly used (otherwise the Phenom II X6 1100T would lag behind the same Core i5-2500 would not be nominal, but quite noticeable). As support for modern instruction set extensions becomes more widespread, “phenomena” will begin to fall more and more in performance, but this does not threaten the “bulldozer”: it supports AVX and SSE 4.2 too. Of course, this is unlikely to help competition with Sandy Bridge (it’s hard to imagine that Intel implements its “favorite” instruction sets worse), but the secret weapon in the form of FMA4 can fire. How it will turn out in practice is a question of the future, of course. But the prerequisites for the fact that in this very future the FX will at least be able to «smash» the six-core Phenom II, there are considerable ones. However, this is in the future — for now, we note a serious loss to our own predecessors on some types of load in the present.

Packing and unpacking

The FX-8150 received support for fast memory, and the total amount of cache exceeds 15 MB — this is in the asset, as well as the ability of 7-Zip to use a large number of computational threads. On the downside, WinRar is still in real work (and not in the built-in benchmark, which is still used in some remote places from civilization) is limited to two streams, and unpacking in both cases (i.e., two subtests out of four ) is generally single-threaded, which gives a considerable head start to Sandy Bridge, where the computational threads are the fastest, as we have seen more than once. Taken together, this provides the new top-end FX with a very slight lag (although still behind) from the Core i5-2500. And our newcomer is less inferior to the older Core i7-2600 than it outperforms the Phenom II X6 1100T — in absolute terms, both there and there 24 points, but the bases for relative comparison are different. In general, the absence of miracles continues, but within the framework of intra-company competition, we can assess an increase of about 20% as very good.

Audio encoding

Perhaps the best application for new processors, especially since, as we have said more than once, the test specifically «plays along» with multi-threaded devices. However, even this did not allow the Phenom II X6 1100T to keep up with the Core i5-2500, but the results of the FX-8150 exactly correspond to its positioning. It would always be like this, and not like in the previous three cases! However, the test set (and indeed the software on the market in general) does not end there, so let’s see what happens in other groups.

Compilation

And one more undoubted success of the new AMD processors, strengthened by the fact that Core i5 does not shine at all in compilers. True, the increase relative to Phenom II X6 is not too great, but do not forget that until recently this group of tests was the «swan song» of processors based on Thuban, which actually lost here only to the «full-fledged» Core i7. And Zambezi is even better suited for this application, which no one doubted — more integer streams (which are exactly what you need), more cache memory, high speed of working with RAM. Although in general, if you look at the detailed results … It is clear that not everything is so smooth: the Microsoft compiler gave preference to 1100T, and in GCC it is almost equal. In general, ironically, the maximum contribution to the high final result of the FX-8150 was made by … the compiler of Intel itself! By the way, it is also the main culprit for the loss of all Core i5s in this group. A provocative thought arises: does AMD need to make its own compiler with such and such support from a competitor? 🙂 Let at least in terms of the speed of project development, and not their final performance, but there will definitely be one target group of buyers as a result. And, by the way, along the way, you can hammer a nail into the conspiracy theories about the special de-optimization of the programs of some developers in order to “lower” unusable processors commissioned by a competitor. What kind of order is there — rather, a mess! If no one at Intel has taken up the task of finalizing their own compilers for their own processors (so that the former work the fastest on the latter, no matter what), then what is the probability that someone will better approach the issue of special sabotage in the code they issue?

Mathematical and engineering calculations

Taking into account almost no optimization of this group for multithreading, it is not surprising that the FX-8150 does not shine here, to put it mildly, demonstrating results only at the level of the previous generation processors. Even slightly lower, but not significantly.

Raster graphics

And here the combined result is slightly higher than that of Phenom II, which, of course, is still completely insufficient to compete with Sandy Bridge. But taking into account the fact that applications are different in their preferences, you can (if you wish) find positive trends. For example, one of the main «lawyers» of the FX-8150 (and, concurrently, the most significant program in the group — if only because it costs like a computer, and is not distributed free of charge to everyone) is Adobe Photoshop. Previously, the best AMD processor in terms of this program was the Phenom II X6 1100T, which even lagged behind the Core i3-2100 or Core i5-660 (recall: these are dual-core processors, although with HT support). But the FX-8150 rose to about the level of the Core i5-2300, outperforming even the Core i7-860 from the «oldies». That is, a miracle, of course, did not happen, but the growth is good — just where it should be. And in the ACDSee test, the new processor even managed to overtake the Core i5-2400, and only slightly lagged behind the Core i7-870, while the strength of the 1100T was also lacking to overtake the i7-920. It is clear that in a good way the FX-8150 would have to reach a level higher than the i5-2500 (and from the point of view of the fans, it would absolutely crush the i7-2600 everywhere), but against the backdrop of a failure in some programs, this is a good result. Especially if you look at the next group…

Vector graphics

And yet, no matter what they say in Corel and Adobe, but we are increasingly convinced that these two programs are single-threaded. Still. Well, one Bulldozer stream is, as we have already said, even less than one Stars stream. So no increase in clock frequencies (including due to the turbo mode) can sometimes compensate for some architectural changes — it may very well be that a sharp decrease in the size of the first level cache turned out to be critical here. Or something else. Ultimately, the fact remains that the performance of the flagship FX-8150 is even lower than that of the Pentium G620. True, it is higher than any Athlon II or A-series there … if this, of course, at least consoles someone.

Video encoding

On the other hand, in the case of video encoding, consolations are more likely not required than vice versa. Not in the sense that the FX-8150 suddenly managed to accomplish the impossible and overtook everyone — in fact, in aggregate, it again lagged even behind the Core i5-2500. But, recall, its eight cores are «x86-cores», but the processor has half the number of floating-point calculation units (and, in general, any vector data). In rendering tests, this had an impact, and very strongly, but video encoders approached the new architecture much more loyally. In fact, the new processor managed to lose the Phenom II X6 1100T only in the rather ancient XviD 1.30, also «glorious» in that the Core i7-2600 lags behind the Core i5-2500 in it (in general, it seems that a new «enemy» has formed in the video part of the technique progress” as the single-threaded Canopus ProCoder once was). By the way, Hyper-Threading and Microsoft Expression Encoder 4 “votes against” in the same way, but even in it the FX-8150 is faster than the 1100T. Sony Vegas Pro accelerated in a particularly radical way (compared to its predecessors), which allowed the FX-8150 to reach the level of the younger modern Core i5 or Core i7 of the previous generation. In general, of course, it is not worth talking about the victory of the new AMD processor, but the current state of affairs cannot be attributed to defeats either. Still, this is a way out of the impasse into which Phenom II got into at the end of its life, which even has an advantage of of the most real cores has ceased to help fight on equal terms with Intel processors. But «Bulldozer» still knows how to do something. Not perfect, but it does. Especially since, at a minimum, it supports the same instruction set extensions as the current Core, which, as we have said, will become more and more important as software updates.

Office software

Again we have a group of low-threaded (for the most part) programs without any optimization for newfangled «chips», and again approximate equality of new and old processors against the backdrop of a significant gap (in a negative sense) from competitors’ products. Just a statement of fact, of course — for these programs and Celeron, some of the previous families are enough in practice, so this diagram is purely illustrative for top processor models 🙂

Java

the fact that it practically repeated the result of the Phenom II X6 1100T, on the other hand, this is just another example of a case when nothing needed to be improved — and the 1100T was enough to outperform the Core i5-2500, so the FX-8150 has its own positioning justified. But in general, we had somewhat higher hopes for the Java machine — based on the experience of past testing. However, this is just an obvious confirmation that sometimes you should not trust worldly wisdom. Especially when new entities begin to hide under old names.

Games

Despite the fact that in its promotional materials AMD actively emphasizes the success of the new family of processors in gaming applications, as we can see, there is no breakthrough here either. However, was it worth relying on it after the very first diagram showing that the performance of one computation thread in new processors did not increase (not to mention some other diagrams, according to which it sometimes turns out to be even lower than it was)? In recent years, game engines (more precisely, their developers) have made great progress in the field of multithreading, but . .. So far, their most significant achievement has been only the relevance of installing a processor in a gaming computer that is more productive than the «classic» dual-core one. But for the time being, it’s not necessary to chase a quad-core one — the new Core i3 are just fine for this application. Therefore, count on a serious increase from any additional computation threads … Yes, to completeness! Here, to put it mildly, an outstanding amount of cache memory, theoretically, could help with something (games are very susceptible to it), but apparently it turned out to be too outstanding 🙂 And the results of Intel processors, by the way, confirm the pointlessness of improving parameters above the threshold value : The 2600 has more cache than the 2500, twice as many computational threads, even a 100 MHz higher frequency, and all this gave only a 1% increase in performance. Well, AMD when comparing 8150 with 980 turned out somewhere and a half percent. True, alas, at a significantly lower level than that of the «second generation Core» level — so you should not hope that this is a video card or something else interfered.

Multitasking environment

As we remember, in this experimental test the effect of Hyper-Threading was very well traced. AMD technology is more «advanced», so it will be interesting to see how it helps to get high results in such a somewhat synthetic, but interesting situation. The essence of the test is simple: five benchmarks are launched almost simultaneously (with a pause of 15 seconds), while all tasks are assigned a “background” status (no window is active). The result is the geometric mean of the execution times of all tests. More detailed information can be obtained from the description of the testing methodology, but for now let’s just look at the results.

Commenting in the usual way: nothing essentially new compared to other multi-threaded groups. The Core i5-2500 was already outperformed by the Phenom II X6 here, but we are still not talking about comparing the newcomer with the Core i7-2600, regardless of whether doubling the number of “x86 cores” is more effective than Hyper-Threading or not. This is how it looks in the first approximation. But if you look closely, then a modest couple of percent superiority of the FX-8150 over the Phenom II X6 1100T turns into a resounding victory 🙂 Indeed, let’s remember which five subtests we use:

1. Raster graphics: GIMP — «in its purest form» The FX-8150 is faster here than the 1100T, but the application itself is single-threaded, so it does not create too much background load.
2. Final rendering of 3D scenes: Maya — and here «in its purest form» the FX-8150 is about 15% slower than the 1100T!
3. Compilation: MSVC — FX-8150 is about 3% behind.
4. Video encoding: XviD — FX-8150 falls behind by the same 3%.
5. Packing and unpacking: packing 7-Zip — here the FX-8150 «in its pure form» is much faster, but do not forget that when «simulating vigorous activity» it will not get all the streams at all.

That’s it — creating the methodology and this additional experimental test within its framework, we still knew practically nothing about the new AMD architecture, but, ironically, three out of five applications that got into the test do not tolerate this architecture. However, if you run five «bad» applications at the same time, the end result is similar to that which can be obtained from one «good» one. It doesn’t pull on the opening, but here’s another confirmation of where multi-core / multi-threading can come in handy — it’s quite: best of all, its effect is visible where there are “many” applications themselves. It doesn’t even matter which ones.

Total

It seems to us that those who were waiting for a miracle, either did not read the article at all, having familiarized themselves with brief results from other sources, or stopped reading a long time ago (especially after the second diagram :)). Those who expected a complete and unconditional failure from the new architecture also, we think, have long since satisfied their thirst. Therefore, let us try together with the rest to reason calmly and impartially.

As you can see, the picture does not at all resemble the solemn appearance of Sandy Bridge on the market in January of this year (the only analogy is that then some were also waiting for some kind of miracle, so they considered themselves deceived when they saw that the new processors were only noticeably faster than the old ones, and not tear them to shreds). The reason is that the companies once again went different ways. Intel decided to freeze the number of cores in mass processors, spending energy on finalizing integrated graphics and increasing “single-threaded performance”. The company explained the logic of its actions directly and clearly: desktop users do not yet have a need for more than quad-core processors, so there is no point in wasting transistors and increasing power consumption. Let there be no more than four cores, as before, but each will be faster than before. This will provide the desired effect everywhere — even in old, even in new programs. And for the most demanding ones, there is Hyper-Threading, which is much “cheaper” than full-fledged cores, but if necessary, can replace them to some extent. We get cheap and fast processors. We only note that we didn’t get them exactly like that right away: Intel’s modular architecture appeared at the end of 2008 (by the way, there were also a lot of questions before its entry into the market) — the same Core that replaced the monolithic Core 2. And its representatives were produced according to an already well-established technical process, the first models amazed even the worldly-wise (and various “pentivums four”) aksakals with their energy consumption, but at the same time they often managed not to overtake their predecessors too much (especially in poorly optimized software, which still manages to slow down when enabling Hyper-Threading). Then there was the debugging of a new technical process, from simple to complex — the first “debugging object” was not even a processor, but a piece of a processor on the Clarkdale core. And only then — the triumphant release of the second generation Core.

To better understand the difference between AMD’s position, let’s first recall that today we saw both new processors and a new architecture. Completely new — this is not many times updated and built-on K7. Accordingly, it was originally designed to use dynamic frequency control technology, support for non-integer vector instructions, and much, much more, which no one thought about ten years ago. Including about processors for tablets and netbooks or about APUs, where Athlon cores, despite all the tricks, look unconvincing, but one or two modules of a new type can come in handy. And in the server segment, where the number of simultaneously running computation threads is usually large, the new architecture can give AMD a second wind, especially if over time it is possible to increase the number of modules, even if sacrificing frequency. And there is a possibility of this — after all, the Bulldozer module is simpler than the Core module: the latter includes two full-fledged processor cores, and even flavored with Hyper-Threading. Previously, the single-threaded Athlon core, whose age has already entered the second decade, was the elementary brick from which AMD processors were built. And one such core is not enough for modern software — two are needed. And in order to get a more or less decent level of performance, we had to “fasten” the third-level cache, which was not originally discussed, so it was not so easy to ensure the full operation of such an architectural hodgepodge (we recall, by the way, that as a result, the first Phenom turned out to be almost a failure, albeit allowing the creation of Phenom II on its basis). And in budget processors, L3 was too expensive an excess, so various Athlon II and variations on their theme had problems with inter-core data exchange, and indeed with a low cache memory capacity (over the years, AMD has not managed to fasten more than a megabyte of L2 to Athlon) in many applications pretty spoiled life.

But today we did not test the updated APU at all in order to find out whether the four new «cores» are better than the four old cores, but the new top AMD processor. The performance of a single thread in the new architecture could not be increased. Moreover, some solutions are generally potentially dangerous in terms of «old» code (for example, FPU instructions). However, at the same time, it is necessary to make sure that the new flagship looks better than the old one and is not inferior to competitors. And how to achieve this if the intensive path was not available? Naturally, extensive: «rolling out» the processor in the maximum configuration possible today with four modules, a full amount of cache memory and a maximum clock frequency. In terms of the latter, by the way, there is another victory for the human mind — the company kept its word to release a processor with a frequency of more than 4 GHz. Intel did not succeed in the latter in normal mode, but AMD did. Let only in turbo mode, but at least something. True, there is not much sense in this — the new Intel processors have a higher specific performance. And eight cores are not too much use — maybe AMD’s approach is more efficient than Hyper-Threading, but where can you find this type of load in a desktop computer to see it? In general, the fans hoped to win over the Core i7-2600, but in fact, the delay in the release did not allow to bypass the cheaper Core i5-2500 in the overall standings (moreover, it is cheaper in price — and its cost is generally one and a half times lower). Now, if it were possible to make frequencies in the region of 4 GHz not the maximum achievable, but the starting ones (as it was once predicted), it would be a little more fun. But here already the technical process “at the debugging stage” interferes.

Of course, you can count on an increase in Turbo Core efficiency as motherboard BIOSes are debugged: we have already witnessed how LGA1156 processors received an extra 5% performance after a few months of the platform’s existence, so there is nothing impossible in this. There will be an increase in performance (especially relative to the Phenom II) as new optimized software versions become available. There will be new steppings and manufacturing process improvements so there will be new faster models in the family. It may very well be that somewhere else there are some hidden reserves. But it is simply impossible to hope for a fundamental change in the situation in the near future. FX-8150 is a good processor. But not as good as required and as expected. The revolution did not take place — thanks to everyone, everyone is free.

We would like to thank Corsair and Palit
for their help in setting up the test benches.

AMD FX-8150 — 26 secret facts, review, specifications, reviews.

Top specifications and features

• PassMark CPU score
• Heat dissipation (TDP)
• Technological process
• Number of transistors
• Number of Cores

PassMark CPU

AMD FX-8150 score:
4873
Best score:
89379

Test results for

AMD FX-8150:
38164
Best score:

AMD FX-8150 technologies:
500
Best score:

Performance

AMD FX-8150:
4132
Best score:

Interfaces and communications

AMD FX-8150:
567
Best score:

Description

AMD FX-8150 processor running at 3.6 Hz. At the same time, the maximum frequency in Boost mode reaches 4.2 Hz. 8 cores available. L1 cache size is 384 KB, L2 8 MB and L3 8 MB. Power consumption at peak times can reach 125 watts.

The maximum number of threads that AMD FX-8150 can handle is 8.

AMD FX-8150 works on 32nm architecture. Total number of transistors 1200 million

Regarding memory specification. The AMD FX-8150 processor supports DDR3.

If we talk about the AMD FX-8150 integrated graphics, then the Discrete Graphics Card Required core is installed here.

Now about the AMD FX-8150 tests. According to PassMark, the processor scored 4873 of the possible points. Based on the analysis of more than 4000 processors, AMD FX-8150 ranked 1051 in the ranking of the best.

Why the AMD FX-8150 is better than others

• 32 nm process technology. This parameter is lower than that of 45%
• Number of cores 8 . This parameter is higher than 78%
• L2 cache size 8 MB. This parameter is higher than that of 68%
• L1 cache size 384 KB. This parameter is higher than that of 43%

• PassMark CPU score 4873 . This parameter is lower than 20%
• Thermal Dissipation (TDP) 125 W. This parameter is higher than 85%
• Number of transistors 1200 million. This parameter is lower than that of 21%
• Number of threads 8 . This parameter is lower than that of 39%

AMD FX-8150 Review

Test results

Technology

Performance

Interfaces and communications

Main characteristics

AMD FX-8150 Review Highlights

PassMark CPU score

The PassMark benchmark considers read speed, write speed, and seek time when testing SSD performance.
Show all

4873

max 89379

Average: 6033.5

89379

AES

Yes

Number of threads

The more threads, the higher the performance of the processor, and it will be able to perform several tasks at the same time.
Show all

eight

max 256

Average: 10.7

256

L1 cache size

Large amount of L1 memory accelerates results in CPU and system performance settings
Show all

384KB

max 4608

Average: 299.3 KB

4608KB

L2 Cache Size

L2 cache with large scratchpad memory to increase processor speed and overall system performance.
Show all

8MB

max 512

Average: 4.5 MB

512MB

L3 cache size

Large amount of L3 memory accelerates results in CPU and system performance settings
Show all

8MB

max 768

Average: 16. 3 MB

768MB

Maximum Turbo Clock Speed ​​

When the processor’s speed drops below its limit, it can jump to a higher clock speed to improve performance.
Show all

4.2GHz

max 5.5

Average: 3.2 GHz

5.5GHz

Number of cores

eight

max 72

Mean: 5.8

72

Processor base clock speed

3.6GHz

max 4.7

Average: 2.5 GHz

4.7GHz

Unlocked CPU multiplier

Some processors have an unlocked multiplier, which makes them faster and better in games and other applications.
Show all

Yes

Graphics System

Discrete Graphics Card Required

Max. number of processors in the configuration

one

Mean: 1.3

8

DDR version

3

Mean: 3.5

5

Intel® AES-NI Commands

AES is needed to speed up encryption and decryption.

Yes

Socket

AM3+

Manufacturing process

The small size of the semiconductor means it is a new generation chip.

32 nm

Average: 36.8 nm

5nm

Number of transistors

1200 million

max 57000

Average: 1517.3 million

57000 million

Heat Dissipation (TDP)

The Heat Dissipation Requirements (TDP) is the maximum amount of energy that can be dissipated by the cooling system. The lower the TDP, the less power will be consumed.
Show all

125W

Average value: 67.6W

0.025W

Line

AMD FX-Series Processors

Maximum processor temperature

A reset may occur if the maximum temperature at which the processor operates is exceeded.
Show all

61°C

max 110

Average value: 96 °C

110°C

Code name

Zambezi

Purpose

Boxed Processor

FAQ

How fast is the AMD FX-8150 5600X?

The processor runs at 3.6 GHz.

How many cores does the AMD FX-8150 have?

8 cores.

Does the AMD FX-8150 have integrated graphics?

Discrete Graphics Card Required

What RAM does AMD FX-8150 support

AMD FX-8150 supports DDR3.

What is the socket of AMD FX-8150

AMD FX-8150 is installed using AM3+.

Is the AMD FX-8150 multiplier unlocked?

Yes

How does the AMD FX-8150 processor perform in benchmarks?

According to PassMark, the AMD FX-8150 scored 4873 points.

What is the frequency of the AMD FX-8150 processor?

AMD FX-8150 processor running at 3.6 Hz.

What is the maximum frequency of the AMD FX-8150 processor?

In this case, the maximum frequency in Boost mode reaches 4.2 Hz.

How much cache is the AMD FX-8150?

L1 cache is 384 KB, L2 8 MB and L3 8 MB.

How many watts does the AMD FX-8150 consume?

Power consumption at peak times can be up to 125 watts.

leave your feedback

AMD FX 8150 processor — specifications, benchmarks, comparison

Home / Processors / AMD FX 8150

• Edelmark rating — 4.9 out of 10;
• Release date: October, 2011;
• Number of cores: 8;
• Frequency: 3. 6 GHz;
• Power consumption (TDP): 125W;
• Maximum RAM: 24,576 MB.

AMD FX 8150 Specifications

General Specifications

Clock frequency	3.6 GHz
Maximum clock frequency	4.2 GHz
Cores	8
Socket	AM3+
Unlock cores	Yes

Functions

NX-bit (XD-bit) available	Yes
Virtualization support	Yes
Instructions supported	ABM AES AMD-V AMD64 AVX CLMUL CVT16 F16C FMA4 MMX SSE SSE2 SSE3 SSE4.1 SSE4.2 SSE4a Supplemental SSE3 XOP
Support for dynamic frequency scaling (CPU Throttling)	Yes

Integrated (integrated) graphics

Graphics core	No
Brand	No
Latest DirectX	No
Number of displays supported	No
Graphics core clock speed	No
Maximum clock frequency	No
3DMark06	No

Memory module

Memory controller	Integrated
Memory type	DDR3-1866
Channels	Double channel
ECC support (error correction)	Yes
Maximum flow	29,866. 66 MB/s
Maximum memory	24.576 MB

Parts and features

Architecture	x86-64
Threads	8
Second level cache (L2)	8MB
Second level cache per core (L2)	1 MB/core
L3 cache	8MB
Level 3 cache per core (L3)	1 MB/core
Process	32 nm
Number of transistors	1,200,000,000
Maximum processors	1
Matrix size	319 mm²
Processor multiplier	21
Voltage range	1.22 — 1.52V
Operating temperature	Unknown — 61°C

Overclocking FX 8150

Overclock review core	4. 5
Overclocking clock	4.71 GHz
Water-cooled boost clock	4.66 GHz
Air cooled boost clock	4.71 GHz

Power consumption

Power consumption	125W
Annual cost of electricity (NON-commercial use)	67.45 $/year
Annual cost of electricity (commercial use)	200.6 $/year
Capacity per W	4.14pt/W
Standby power consumption	104W
Peak power demand	229W
Average energy consumption	197.75W

Tire

Architecture	HyperTransport 3.1
Data rate	10,400 MB/s
Transfer rate (transactions per second)	5,200MT/s
Clock frequency	2. 600 MHz

Comparison of FX 8150 with similar processors

Performance

Performance using all cores.

Tests used: PCMark 8 Home 3.0 Accelerated, PassMark, Geekbench 3 Multi-Core.

FX 8150	6.4 out of 10
FX 8350	7.1 out of 10
FX 6300	5.7 out of 10

Performance per core

Base performance per processor core.

Tested on: PassMark (Single Core), Geekbench 3 Single Core, Geekbench 3 AES Single Core.

FX 8150	5.3 out of 10
FX 8350	5.8 out of 10
FX 6300	5.5 out of 10

Integrated Graphics

Integrated GPU performance for graphics tasks.

FX 8150	0.0 out of 10
FX 8350	0.0 out of 10
FX 6300	0. 0 out of 10

Integrated graphics (OpenCL)

Integrated GPU performance for parallel computing.

Tested on: CompuBench 1.5 Bitcoin mining, CompuBench 1.5 Face detection, CompuBench 1.5 Ocean Surface Simulation, CompuBench 1.5 T-Rex, CompuBench 1.5 Video composition.

FX 8150	0.0 out of 10
FX 8350	0.0 out of 10
FX 6300	0.0 out of 10

Performance per W

How efficiently the processor uses electricity.

Tests used: Fire Strike, CompuBench 1.5 Bitcoin mining, CompuBench 1.5 Face detection, CompuBench 1.5 Ocean Surface Simulation, CompuBench 1.5 T-Rex, CompuBench 1.5 Video composition, PCMark 8 Home 3.0 Accelerated, PassMark, Geekbench 3 Multi-Core , PassMark (Single Core), Geekbench 3 Single Core, Geekbench 3 AES Single Core, TDP.

FX 8150	4.9 out of 10
FX 8350	5. 0 out of 10
FX 6300	5.3 out of 10

Price-performance ratio

How much you overpay for performance.

Tests used: Fire Strike, CompuBench 1.5 Bitcoin mining, CompuBench 1.5 Face detection, CompuBench 1.5 Ocean Surface Simulation, CompuBench 1.5 T-Rex, CompuBench 1.5 Video composition, PCMark 8 Home 3.0 Accelerated, PassMark, Geekbench 3 Multi-Core , PassMark (Single Core), Geekbench 3 Single Core, Geekbench 3 AES Single Core, Price.

FX 8150	5.9 out of 10
FX 8350	6.4 out of 10
FX 6300	6.6 out of 10

Total Edelmark rating

Total processor rating.

FX 8150	4.9 out of 10
FX 8350	5.3 out of 10
FX 6300	5.2 out of 10

FX 8150 9 benchmarks1046

GeekBench 3 (Multi-core)

FX 8150	10. 087
FX 6300	7.871
FX 8350	11.483

GeekBench 3 (Single Core)

FX 8150	1.990
FX 8350	2.193
FX 6300	2.053

GeekBench 3 (AES single core)

FX 8150	2,265,000 MB/s
FX 8350	2,470,000 MB/s
FX 6300	2,290,000 MB/s

GeekBench (32-bit)

FX 8150	9.664
FX 6300	7.447
FX 8350	10.956

GeekBench (64-bit)

FX 8150	10.251
FX 6300	8.232
FX 8350	12.126

GeekBench

FX 8150	11. 782
FX 6300	9.503
FX 8350	12.796

PassMark

FX 8150	7.747
FX 8350	9.134
FX 6300	6.444

PassMark (Single Core)

FX 8150	1.355
FX 8350	1.525
FX 6300	1.446

Video reviews

Budget, Gaming 8-core PC from AliExpress on AMD FX-8150 for $500

AMD FX 8150 processor operation temperature