What's new
  • Please do not post any links until you have 3 posts as they will automatically be rejected to prevent SPAM. Many words are also blocked due to being used in SPAM Messages. Thanks!

AMD FX-9590 Review; Piledriver at 5GHz

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
A few weeks ago AMD announced the latest additions to their FX-series processor lineup: the FX-9590 and FX-9370. Clocked at Turbo speeds of 5GHz and 4.7GHz respectively, these new CPUs made some waves in enthusiast circles due to the high frequencies and AMD’s decision to only offer them through system builders rather than normal retail channels.

Before we get too far into this, some of you may be wondering why AMD decided to soft launch two enthusiast-level processors at such a late point in Piledriver's life cycle. Aside from the usual marketing bullet points about being the first to reach 5GHz, AMD's focus here boils down to a simple question: why not? The cores (or at least some of them) can obviously handle the extreme frequencies, the architecture is more than adaptable enough and the AM3+ / 990FX platform is still well-positioned regardless of its lack of PCI-E 3.0. While these CPUs may not have mass market appeal, AMD's engineers are demonstrating what they can do when freed from the shackles of thermal limits and efficiency. Enthusiasts should be able to appreciate that.

The problem with this so-called launch boils down to availability. While The FX-9590 and FX-9370 can be bought online if you have quick reflexes and deep pockets, AMD isn’t planning for widespread availability. Media samples are all but nonexistent as well yet but over the coming days expect to see these processors begin to show up at some retailers, likely attached to bundles.

FX-9590-1.jpg

While it is odd to see AMD shy away from adequately marketing a processor that could finally compete with the best Intel has to offer, there is some valid reasoning behind their hesitation. For the time being at least, the number of units available for a widespread launch just isn’t there, hence the limited offering to system builders and now select retailers.

The FX-9590’s high clock speeds mean each individual processor has to go through a high level screening process to validate its ability to consistently hit its Turbo target of 5GHz and base clock of 4.7GHz. Not many Vishera cores will make the grade and these “failed” CPUs will eventually be rolled into the FX-9370’s embrace and may even cascade down into other FX SKUs. Even the FX-9370 has a stringent binning process in an effort to weed out any unfit chips.

FX-9590-72.jpg

At its heart, the FX-9590 isn’t all that much different from previous FX-series CPUs. Like the FX-8350, it uses AMD’s 32nm Piledriver architecture, comes with 8MB of L2 cache and eight cores, supports DDR3 speeds of up to 1866MHz and can be used in conjunction with any supporting AM3+ motherboard. The 5GHz core frequency has been attained through the use of AMD’s Turbo Core 3.0 which allows a base clock of 4.7GHz to hit higher levels when the right conditions present themselves. Unfortunately, that doesn’t happen very often as our processor remained at 4.7GHz in most workloads.

As one might expect, actually getting a lower clocked architecture to hit such high levels requires some heavy-duty muscle alongside stringent binning. In this case, a massive amount of voltage -1.5V- has been applied and this has a secondary, nasty side effect: a substantial increase in heat production and power requirements. While the FX-8350’s TDP of 125W was deemed inefficient, the FX-9590 brings things to a whole new level with an estimated thermal output of 200W-220W. That’s an important number to remember when choosing a cooler since only the very best air-based solutions will be able to keep temperatures under control.

FX-9590-3.png

The motherboard support provides an interesting caveat to this whole equation since some manufacturers have yet to roll out BIOS updates which support the FX-9590 and FX-9370. In addition, we’re told that many boards can’t consistently supply the massive amount of input power required by these new processors. So, before assuming your board will safely run a 200W CPU over long periods of time, confirm with the manufacturer’s product page first. For our testing an ASUS 990FX Sabertooth was used.

Judging from the path this launch is taking, we can assume that AMD has refreshed their high-end FX series in an effort to drum up some attention. Steamroller-based processors are still some time away and this is an excellent opportunity to flex Vishera’s considerable multi-threaded muscles. However, other than the power and heat sacrifices we mentioned above, the FX-9590 will also come with a suitably high price. At the time of writing, it can be found for between $750 and $850 which translates to a $200 premium over an i7-3930K and $400 more than Intel's 4770K.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
Test Setups & Methodology

Test Setups & Methodology


For this review, we have prepared a number of different test setups, representing many of the popular platforms at the moment. As much as possible, the test setups feature identical components, memory timings, drivers, etc. Aside from manually selecting memory frequencies and timings, every option in the BIOS was at its default setting.

INTEL-HASWELL-300.jpg

For all of the benchmarks, appropriate lengths are taken to ensure an equal comparison through methodical setup, installation, and testing. The following outlines our testing methodology:

A) Windows is installed using a full format.

B) Chipset drivers and accessory hardware drivers (audio, network, GPU) are installed.

C)To ensure consistent results, a few tweaks are applied to Windows 7 and the NVIDIA control panel:
  • UAC – Disabled
  • Indexing – Disabled
  • Superfetch – Disabled
  • System Protection/Restore – Disabled
  • Problem & Error Reporting – Disabled
  • Remote Desktop/Assistance - Disabled
  • Windows Security Center Alerts – Disabled
  • Windows Defender – Disabled
  • Screensaver – Disabled
  • Power Plan – High Performance
  • V-Sync – Off

D) Windows updates are then completed installing all available updates

E) All programs are installed and then updated.

F) Benchmarks are each run three to eight times, and unless otherwise stated, the results are then averaged.

G) All processors had their energy saving options / c-states enabled
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
System Benchmarks: AIDA64 / Cinebench r11.5

System Benchmarks


In this section, we will be using a combination of synthetic benchmarks which stress the CPU and system in a number of different domains. Most of these tests are easy to acquire or are completely free to use so anyone reading this article can easily repeat our tests on their own systems.

To vary the results as much as possible, we have chosen a selection of benchmarks which focus upon varied instruction sets (SSE, SSE3, 3DNow!, AVX, etc.) and different internal CPU components like the floating point units and general processing stages.



AIDA64 Extreme Edition


AIDA64 uses a suite of benchmarks to determine general performance and has quickly become one of the de facto standards among end users for component comparisons. While it may include a great many tests, we used it for general CPU testing (CPU ZLib / CPU Hash) and floating point benchmarks (FPU VP8 / FPU SinJulia).


CPU ZLib Benchmark

This integer benchmark measures combined CPU and memory subsystem performance through the public ZLib compression library. CPU ZLib test uses only the basic x86 instructions but is nonetheless a good indicator of general system performance.

FX-9590-41.jpg


CPU Hash Benchmark

This benchmark measures CPU performance using the SHA1 hashing algorithm defined in the Federal Information Processing Standards Publication 180-3. The code behind this benchmark method is written in Assembly. More importantly, it uses MMX, MMX+/SSE, SSE2, SSSE3, AVX instruction sets, allowing for increased performance on supporting processors.

FX-9590-40.jpg

RESULTS: In these two benchmarks which use newer instruction sets, the two AMD processors are able to pull ahead of the Intel competition by significant amounts. Here, we actually see the FX-6300 competing against Intel’s 3570K which is a much more expensive processor.



FPU VP8 / SinJulia Benchmarks

AIDA’s FPU VP8 benchmark measures video compression performance using the Google VP8 (WebM) video codec Version 0.9.5 and stresses the floating point unit. The test encodes 1280x720 resolution video frames in 1-pass mode at a bitrate of 8192 kbps with best quality settings. The content of the frames are then generated by the FPU Julia fractal module. The code behind this benchmark method utilizes MMX, SSE2 or SSSE3 instruction set extensions.

Meanwhile, SinJulia measures the extended precision (also known as 80-bit) floating-point performance through the computation of a single frame of a modified "Julia" fractal. The code behind this benchmark method is written in Assembly, and utilizes trigonometric and exponential x87 instructions.


FX-9590-42.jpg

RESULTS: Here, the FX-9590 displays a Dr. Jekyll and Mr. Hyde performance spectrum. On one hand, it remains ahead of its predecessor, the FX-8350 but it just can’t compete against similarly priced Intel processors in the VP8 benchmark. However, SinJulia with its newer SSE3 instruction set allows AMD’s 5GHz processor to post some respectable results.



CineBench r11.5 64-bit


The latest benchmark from MAXON, Cinebench R11.5 makes use of all your system's processing power to render a photorealistic 3D scene using various different algorithms to stress all available processor cores. The test scene contains approximately 2,000 objects containing more than 300,000 total polygons and uses sharp and blurred reflections, area lights and shadows, procedural shaders, antialiasing, and much more. This particular benchmarking can measure systems with up to 64 processor threads. The result is given in points (pts). The higher the number, the faster your processor.

FX-9590-43.jpg

RESULTS: With CineBench being such a highly multi-threaded application, it shouldn’t come as a surprise that Intel’s 12-thread 3960X remains king of the hill. However, the FX-9590 is nonetheless able to reach some impressive performance levels.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
System Benchmarks: Civ V / PCMark 7

System Benchmarks (pg.2)



Civilization V: Gods & Kings Unit Benchmark


Civilization V includes a number of benchmarks which run on the CPU, GPU or a combination thereof. The Unit Benchmark simulates thousands of units and actions being generated at the same time, stresses multi core CPUs, system memory and GPU We give the non-rendered score below as it is more pertinent to overall CPU performance within the application.

FX-9590-45.jpg

RESULTS: Unfortunately, this test highlights one of the Piledriver architecture’s issues: disappointing 3D performance. It also shows how AMD’s latest high end processor just can’t put much distance between itself and the FX-8350 in some situations due to these limitations.



PCMark 7


PCMark 7 is the latest iteration of Futuremark’s system benchmark franchise. It generates an overall score based upon system performance with all components being stressed in one way or another. The result is posted as a generalized score. We also give the Computation Suite score as it isolates the CPU and memory within a single test, without the influence of other components.

FX-9590-46.jpg

FX-9590-47.jpg

RESULTS: Since PCMark7 tests a whole suite of platform functions, the CPU only accounts for a portion of the final score. With this in mind, it seems like the 990FX stands up relatively well while the Z87 really sets itself up as a cut above. Once pure CPU computational performance is factored into this equation, the FX-9590 paces itself well but once again it has trouble competing with lower priced CPUs.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
System Benchmarks: 3DMark (CPU) / WPrime

System Benchmarks (pg.3)



3DMark06 CPU


While 3DMark06 may be a slightly older synthetic benchmark, its CPU test still allows for multi threaded performance evaluations within a gaming environment. It effectively removes the CPU from the equation, generating a CPU-centric score.

FX-9590-59.jpg

RESULTS: 3DMark06 once again shows a modest improvement of ~12% when moving from an FX-8350 to the FX-9590 which isn’t all that significant considering the newer CPU’s premium.



WPrime


wPrime is a leading multithreaded benchmark for x86 processors that tests your processor performance by calculating square roots with a recursive call of Newton's method for estimating functions, with f(x)=x2-k, where k is the number we're sqrting, until Sgn(f(x)/f'(x)) does not equal that of the previous iteration, starting with an estimation of k/2. It then uses an iterative calling of the estimation method a set amount of times to increase the accuracy of the results. It then confirms that n(k)2=k to ensure the calculation was correct. It repeats this for all numbers from 1 to the requested maximum. This is a highly multi-threaded workload. Below are the scores for the 32M and 1024M benchmarks.

FX-9590-49.jpg

FX-9590-50.jpg

RESULTS: WPrime’s multi-threaded benchmarks allow the FX-9590 to compete well against certain Intel processors but this application certainly isn’t one of its strengths.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
System Benchmarks: Single Thread Performance

System Benchmarks: Single Thread Performance


Even though most modern applications have the capability to utilize more than one CPU thread, single threaded performance is still a cornerstone of modern CPU IPC improvements. In this section, we take a number of synthetic applications and run them in single thread mode.

FX-9590-44.jpg

FX-9590-48.jpg

FX-9590-51.jpg

RESULTS: When it comes to single thread performance, AMD’s current architectures are simply brutalized by Intel’s offerings. While fewer applications are being released with support for only one to two cores, very few can fully utilize the eight core supplied by AMD’s higher end CPUs. Luckily, the addition of Turbo Core can somewhat mitigate these shortfalls by dynamically increasing frequencies when the full core allocation isn’t required but even with this in place, the FX-9590 still finds itself trailing.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
Productivity Benchmarks: 7-Zip / MediaCoder

Productivity Benchmarks


In this section, we will avoid generalized synthetic benchmarks and instead concentrate upon CPU performance within real-world applications and standard usage patterns. Every one of the programs included here has functions that many professionals and everyday users utilize in their day to day computing lives.


7-Zip


At face value, 7-Zip is a simple compression/decompresion tool like popular applications like WinZip and WinRAR but it also has numerous additional functions that can allow encryption, decryption and other options. For this test, we are avoiding its built-in benchmark and once again only focus upon real world testing by compressing a 2.6GB folder of various files and adding an AES-256 encryption layer for good measure. The test is timed until it is complete.

FX-9590-52.jpg

RESULTS: Higher level productivity tasks are where the FX-9590 can really shine and 7-Zip is a perfect example of this. While it can’t quite match the performance of Intel’s latest eight thread Haswell CPU nor the 12-thread Sandy Bridge-E monster, AMD’s 5GHz processor puts up a valiant fight.



MediaCoder x64


Due to the varying compatibility of certain mobile devices, video transcoding performance has become something of a big deal. Transcoding allows one type of video / audio file to be converted into a different format and it typically takes up a huge amount of system resources. The MediaCoder application brings multi format transcoding to an accessible level with numerous options and acceleration for Intel’s QuickSync and NVIDIA’s CUDA technologies. In addition, its CPU support allows for full multi core utilization. In this test, we use the MediaCoder i-devices edition to convert a 600MB AVCHD file to an iPhone 4S friendly MPEG-4 format.

FX-9590-53.jpg

RESULTS: With eight cores working away and MediaCoder’s updated support structure for newer instruction sets, the FX-9590 is once again able to put up some good numbers.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
Productivity Benchmarks: Photoshop CS6 / POV Ray 3.7

Productivity Benchmarks (pg.2)



Adobe Photoshop CS6


For the image editing portion of this section, we use Photoshop CS6 in coordination with a custom benchmark script. This script automates the application of 20 different image manipulation functions to a 120MB PNG image, acting as an excellent test of CPU power and memory bandwidth. For this test, we have disabled GPU acceleration so it won’t play a factor in the areas where it would typically be used. We use Photoshop’s built-in timing feature to provide a result at each test stage.

FX-9590-54.jpg

RESULTS: Photoshop presents a unique challenge for AMD’s architecture since the program is multi core aware but it won’t fully utilize multiple threads for every action. This causes the FX-9590 to drop down in our charts to a level that’s barely better than an Intel 2600K.



POV Ray 3.7 RC6


POV Ray is a complex yet simple to use freeware ray tracing program which has the ability to efficiently use multiple CPU cores in order to speed up rendering output. For this test, we use its built-in benchmark feature which renders multiple passes of a high definition scene. In order to get the most accurate results, the second pass of the first test is logged, resulting in a benchmark score showing the average amount of pixels rendered per second.

FX-9590-55.jpg

RESULTS: Rendering workloads are one of AMD’s strengths and the FX-9590 is able to deliver here by thoroughly beating the 4770K and improving upon the FX-8350’s performance by about 20%.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
Productivity Benchmarks: TrueCrypt 7.1 / x264HD

Productivity Benchmarks (pg. 3)



TrueCrypt 7.1


Truecrypt is another freeware gem which allows for on-the-fly disk encryption. More importantly, it fully supports AES-256 encryption methods and multi core processors. For this test, we used the built-in benchmark tool are logged the data throughput for TrueCrypt’s AES-256 encryption method.

FX-9590-56.jpg

RESULTS: With full support for the AES encoding / decoding standard, the FX-9590 is able to improve upon the FX-8350’s scores but it just can’t seem to match up with Intel’s higher end offerings.


x264HD Benchmark


x264 is quickly becoming the new codec of choice for encoding a growing number of H.264/MPEG-4 AVC videos. Think of it as the new Divx of HD and you can understand why we felt it critical to include. Tech Arp's recent development of the x264 HD Benchmark takes a 30 second HD video clip and encodes it into the x264 codec with the intention of little to no quality loss. The test is measured using the average frames per second achieved during encoding, which scales with processor speed and efficiency. The benchmark also allows the use of multi-core processors so it gives a very accurate depiction of what to expect when using encoding application on a typical full length video. We use the second pass of the first test for this benchmark as it fully loads all multi core processors.

FX-9590-57.jpg

RESULTS: Once again, the FX-9590’s eight cores allow it to perform quite well in this benchmark. More importantly, it remains well ahead of its predecessor likely due to the dynamic clock speed balancing of Turbo Core 3.0.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,840
Location
Montreal
Synthetic Gaming Benchmarks: 3DMark06 / 3DMark11

Synthetic Gaming Benchmarks



3DMark11


3DMark 11 is the latest in a long line of synthetic benchmarking programs from the Futuremark Corporation. This is their first foray into the DX11 rendering field and the result is a program that incorporates all of the latest techniques into a stunning display of imagery. Tessellation, depth of field, HDR, OpenCL physics and many others are on display here. While the GPU plays a primary role here, 3DMark 11 takes full advantage of multiple CPU threads so any bottlenecks caused by the CPU will also be evident. In the benchmarks below we have included the results (at default settings) for both the Entry and Performance presets.

FX-9590-60.jpg

FX-9590-61.jpg


3DMark06


While its DX9 tests may not seem to be completely relevant in a DX11 era, 3DMark06 still provides an excellent measuring device for both multi core CPU and GPU performance. For this benchmark we are using the standard preset.

FX-9590-58.jpg


RESULTS: The first synthetic gaming benchmarks show an interesting trend and one which will continue throughout the following pages. While the actual in-game processing power of the FX-9590 lies somewhere behind some Intel offerings, once the onus is put on the graphics card, most of the processors perform almost equally.
 
Last edited:
Top