AMD's Piledriver And K10 CPU Architectures Face Off

Test System Configuration And Benchmarks

System Test Configurations
CPUAMD FX-6350 (Vishera) 3.9 GHz (19.5 * 200 MHz), Socket AM3+, 8 MB Shared L3, Turbo Core enabled, Power-savings enabled, Overclocked to 4.52 GHz (22.5 * 200.92), 1.404 V load, 2612 MHz HT Link, 2210 MHz CPU-NB Frequency

AMD FX-4350 (Vishera) 4.2 GHz (21 * 200 MHz), Socket AM3+, 8 MB Shared L3, Turbo Core enabled, Power-savings enabled, Overclocked to 4.72 GHz (23.5 * 200.92), 1.440 V Load, 2612 MHz HT Link, 2411 MHz CPU-NB Frequency

AMD Phenom II X4 965 Black Edition (Deneb) 3.4 GHz (17 * 200 MHz), Socket AM3, 6 MB Shared L3, Power-savings enabled, Overclocked to 4.02 GHz (20 * 200.91), 1.392 V Load, 2008 MHz HT Link, 2411 MHz CPU-NB Frequency

AMD Athlon X4 750K (Trinity) 3.4 GHz (17 * 200 MHz), Socket FM2, No L3 Cache, Turbo Core enabled, Power-savings enabled, Overclocked to 4.30 GHz (43 * 100), 1.464 V Load, 2000 MHz CPU-NB Frequency

AMD Athlon X4 640 (Propus) 3.0 GHz (15 * 200 MHz), Socket AM3, No L3 cache, Power-savings enabled, Overclocked to 3.6 GHz (15 * 240), 1.428 V Load, 1920 MHz HT Link, 2400 MHz CPU-NB Frequency
CPU CoolerXigmatek HDT-S1283 120 mm air cooler
MotherboardsGigabyte GA-990FXA-UD3, Socket AM3+, AMD 990FX, BIOS FC  (02-05-13)

Gigabyte GA-F2A85X-UP4, AMD A85X, BIOS F4  (03-13-13)
RAM8 GB (2 x 4 GB) Crucial PC3-12800 kit
Stock: DDR3-1600, CL 8-8-8-24 at 1.5 V
Overclocked: Athlon II/Phenom II: DDR3-1600/1607, CL 8-8-8-24, Athlon X4 750K/FX-6350/FX-4350: DDR3-1866/1875 9-9-9-24 @ 1.6 V
Common
GraphicsSapphire Radeon HD 7970, 950 MHz GPU, GDDR5-5700
System DriveSamsung 840 Pro 256 GB, SATA 6Gb/s SSD
PowerCorsair Professional Series HX1050, 1050 W, 80 PLUS Silver
 Software and Drivers
Operating SystemWindows 8 Professional x64
Graphics DriverAMD Catalyst 13.2 Beta 7
Benchmark Configuration
3D Games
Borderlands 2Version 1.0.28.69606, DirectX 9, Custom Run, Fraps
Test Set 1: Medium Quality Settings, Low PhysX, 8x AF
Test Set 2: Highest Quality Settings, Low PhysX,  FXAA,16x AF
Crysis 3Version 1.0.0.2000, Direct X 11, Custom Run, 60-Sec. Fraps
Test Set 1: Lowest Quality Settings, No AA, 1X AF
Test Set 2: Medium Quality Preset, FXAA, 8x AF
Test Set 3: Very High Quality Preset, 2x SMAA, 16x AF 
The Elder Scrolls V: SkyrimVersion 1.8.151.0.7, Custom Run, 25-Sec. Fraps
Test Set 1: High Preset, No AA, 8x AF, FXAA Enabled
Test Set 2: Ultra Preset, 8x AA, 16x AF, FXAA Enabled
F1 2012Version 1.2, Direct X 11, Built-in Benchmark
Test Set 1: High Quality, No AA
Test Set 2: Ultra Quality, 8x AA
Far Cry 3V. 1.04, DirectX 11, 50-sec. FRAPS "Amanaki Outpost"
Test Set 1: High Quality, No AA, Standard ATC., SSAO
Test Set 2: Ultra Quality, 2x MSAA, Enhanced ATC, HDAO
Hitman: AbsolutionV. 1.0.446.0, DirectX 11, Built-in Benchmark
Test Set 1: Medium Quality Preset, No MSAA, 2x AF
Test Set 2: Ultra Quality Preset, 2x MSAA, 16x AF
StarCraft II: Heart of the SwarmVersion 2.0.9.26147, Custom Run "Harvest of Screams" Campaign Mission, 60-Sec. Fraps
Test Set 1: High Preset, No AA, 8x AF, FXAA Enabled
Test Set 2: Ultra Preset, 8x AA, 16x AF, FXAA Enabled
Tomb RaiderVersion 1.00.722.3, Direct X 11, Custom Runs, "Chasm Monastery", "Mountain Village", 45-Sec. Fraps
Test Set 1: High Quality Preset
Test Set 2: Ultimate Quality Preset
Audio/Video Encoding
HandBrake CLIVersion: 0.98, Video: Video from Canon Eos 7D (1920x1080, 25 frames) 1 Minutes 22 Seconds, Audio: PCM-S16, 48,000 Hz, Two-Channel, to Video: AVC1 Audio: AAC (High Profile)
iTunesVersion 10.4.1.10 x64: Audio CD (Terminator II SE), 53 minutes, default AAC format 
LAME MP3Version 3.98.3: Audio CD "Terminator II SE", 53 min, convert WAV to MP3 audio format, Command: -b 160 --nores (160 Kb/s)
TotalCode Studio 2.5Version: 2.5.0.10677, MPEG-2 to H.264, MainConcept H.264/AVC Codec, 28 sec HDTV 1920x1080 (MPEG2), Audio:MPEG2 (44.1 kHz, Two-Channel, 16-Bit, 224 Kb/s) Codec: H.264 Pro, Mode: PAL 50i (25 FPS), Profile: H.264 BD HDMV
Abobe Creative Suite
Adobe After Effects CS6Version 11.0.0.378 x64:Create Video, Three Streams, 210 Frames, Render Multiple Frames Simultaneously
Adobe Photoshop CS6Version 13 x64: Filter 15.7 MB TIF Image: Radial Blur, Shape Blur, Median, Polar Coordinates
Adobe Premiere Pro CS6Version 6.0.0.0, 6.61 GB MXF Project to H.264 to H.264 Blu-ray, Output 1920x1080, Maximum Quality
Adobe Acrobat X ProVersion 10.0.0.396: Print PDF from 115 Page PowerPoint, 128-bit RC4 Encyption
Productivity
ABBYY FineReaderVersion 10.0.102.95: Read PDF save to Doc, Source: Political Economy (J. Broadhurst 1842) 111 Pages
Autodesk 3ds Max 2012Version 14.0 x64: Space Flyby Mentalray, 248 Frames, 1440x1080
BlenderVersion 2.64a, Cycles Engine, Syntax blender -b thg.blend -f 1, 1920x1080, 8x Anti-Aliasing, Render THG.blend frame 1
Compression
7-ZipVersion 9.28, LZMA2, Syntax "a -t7z -r -m0=LZMA2 -mx=5"
Benchmark: THG-Workload-2012 (1.3 GB)
WinRARVersion 4.2, RAR, Syntax "winrar a -r -m3"
Benchmark: THG-Workload-2012 (1.3 GB)
WinZipVersion 17.0 Pro, Syntax "-a -ez -p -r"
Benchmark: THG-Workload-2012 (1.3 GB)
Synthetic Benchmarks and Settings
3DMark 11Version: 1.0.1, Performance Suite
PCMark 7Version: 1.0.4, System, Productivity, Hard Disk Drive benchmarks
SiSoftware Sandra 2013Version: 2013.01.19.11, Processor  Arithmetic,
Cryptography, Memory Bandwidth Benchmarks
Create a new thread in the US Reviews comments forum about this subject
This thread is closed for comments
134 comments
    Your comment
    Top Comments
  • MU_Engineer
    Kelvin, the tests showed that the Piledriver FXes are not that far off the Phenom IIs clock for clock and core for core. The Phenom II X4 965BE at 4.0 GHz was generally about as fast as the stock FX-4350 running 200-400 MHz faster so you figure about a 5% per-clock, per-core advantage for the Phenom II. However, each Piledriver core is quite a bit smaller than a K10 core and they also have a longer pipeline so they can clock quite a bit faster (K10 was pretty well tapped out.) So you get more cores and more clocks out of Piledriver with essentially the same performance per core and per clock. I'd say that the modular architecture used in the FXes finally got the vindication it deserved with this test. Way to go Tom's.
    29
  • rmpumper
    I just want some solid numbers on Steamroller already.
    15
  • Other Comments
  • KelvinTy
    So much BS, the old Phenom II X4 and X6 BE are still really competitive after all these years. Yet, if they bother to update the instruction set, and just shrink the thing, then change it to AM3+ socket, that would be great...
    K10 has so much more potential...
    0
  • radiovan
    Personally, I was surprised to see the FX-4350 do so well. The bump up, compared to the FX-4300, has really done it some good.
    8
  • MU_Engineer
    Kelvin, the tests showed that the Piledriver FXes are not that far off the Phenom IIs clock for clock and core for core. The Phenom II X4 965BE at 4.0 GHz was generally about as fast as the stock FX-4350 running 200-400 MHz faster so you figure about a 5% per-clock, per-core advantage for the Phenom II. However, each Piledriver core is quite a bit smaller than a K10 core and they also have a longer pipeline so they can clock quite a bit faster (K10 was pretty well tapped out.) So you get more cores and more clocks out of Piledriver with essentially the same performance per core and per clock. I'd say that the modular architecture used in the FXes finally got the vindication it deserved with this test. Way to go Tom's.
    29
  • Onus
    As I was going through this, at first I was worried about the absence of comparison to Intel, but was relieved to see it at the end. Especially if I don't want to push my 970BE really hard (I'd rather play on my PC than with it), the FX-63x0 looks like a viable upgrade.
    4
  • cmartin011
    I want some juice GPU news. I am aware they are not going anywhere fast with CPUs. My wallet will be open for 8 core in 2 years when performance Increases 20%
    -7
  • rmpumper
    I just want some solid numbers on Steamroller already.
    15
  • magnesiumk
    Thank you so much for writing this article. Thank you also for including the Phenom II 965 processor to this test. I use it, and it is somewhat dated, and hard to find compared to newer cores. However it still kicks a lot of butt in gaming. I bought my Phenom II 955BE C3 last year with overclocking in mind

    I always wanted to see how it would compare to newer models, and even intel counterparts. Thank you for this. I loved reading the article. Keep comparisons like this coming.
    6
  • magnesiumk
    I also wanted to add, thank you for listing the 965BE with overclock at 4Ghz. It's easy to clock this processor up to those speeds. That's about what I run at, and it also runs much greater than stock speeds. This is important in future comparison tests. Thanks again.
    2
  • envy14tpe
    Wanted to see i3 and i5 CPUs on the charts. Not just in the "Wrapping things up" section. Also, why not compare to a i5-3470? It's locked, cheaper, and still fast.
    -5
  • crisan_tiberiu
    if the 6350 is so close to the 3570k the 8350 eats it alive..and everybody recommends the i5 ^-. AMD has still good value
    -2
  • razor512
    You should have added some Phenom II X6 CPU's

    The main thing I hate about FX CPU's in the IPC. companies like intel have steadily increased the IPC of their CPU's while with AMD, going from Phenom II to the latest FX, they significantly reduced the IPC of their CPU's, and furthermore the resource sharing of the cores (by going with core modules instead of true cores). if similar resources are stressed, performance suffers as shown in the link below

    http://www.extremetech.com/computing/138394-amds-fx-8350-analyzed-does-piledriver-deliver-where-bulldozer-fell-short/2

    AMD would have done better by improving upon the phenom II and making an 8 core version.

    I currently use a Phenom II x6 1075t overclocked to 3.9GHz
    in cinebench 11.5 I get 7.01 points Which is still acceptable even by todays standards.

    Northbridge is at 2.6GHz and hyper transport is at 2.08GHz

    The highest I can push the CPU is about 4.4GHz but those speeds require around 1.575 volts, meaning I cant load the CPU to 100% for very long unless I take more drastic measures of connecting a vacuum hose from the case air intake to the air output of an air conditioner (to siphon off some of the cold air)

    If you want to see just how bad the fx is compared to phenom II, clock some phenom II's and some FX's at the same clock speed, then do a range of benchmarks.
    2
  • emad_ramlawi
    Athlon X4 750K is the King of budget, its replaces Phenom 955 and it gives the same performance and sells for dirt cheap = 80 USD + lowest power usage.
    2
  • emad_ramlawi
    if i had dime every time i hear :

    if Only AMD optimized there K10 arch ..., 8 core k10 will be much better ...

    Are you serious, K10 have evolved for years and reached its wall, we talking about semprons --> athlons ---> Phenoms 1 ---> Phenoms 2 ---> AMD FM1 APU`s

    And The Phenom 965 using 45nm as seen in the above chart uses 180Watts on load and upwards ...

    So wake up people, if there was any untapped resources in k10 AMD would have popped them.

    Also an index of cinebench single threaded performanc results from my research is :

    Sandy Bridge/ivy/and haswell (no real innovation since SB, and those 10% CPU improvements, only adds 0.0x) :

    i3 = ~1.3x Point
    i5 = ~1.5x point
    i7 = ~1,8x point

    AMD :

    AMD Athlon a8-3850 k10 CPU 0.8 Point
    AMD Phenom x6 1100T (BEST AMD K10 CPU) 1.08
    Richland A10-6800K ~1.11 point.

    All above results all from my research and wether you want to simply belive or better go research yourself is your choice, but AMD have problem in Single threaded perfomance, and the way they hided back day was giving more cores, like the Phenom x6 in CInebench Multi threaded it scores ~6.0 points even the lowert 1050T scores 5.9 point, and all intel i5 CPU does not go up than 5 points.

    but adding real 6 cores is trouble and problematic and too much power and resource hungry for BULK designs using BULk materical, remeber those x6 can reach 200W and upwardes, and more there costly and there prices does not budge.

    Since Bulldozer first design, there have been many fixes and improvements, and Pilediver is only the first step forward, next step is steam roller, with each step steadily enhancements are being made, not can be much said about k10 that after 3-4 steps forward it froze.
    7
  • frederico
    I have been waiting for this test since I first heard mention of it.

    Fantastic work! am always harvesting older chips to cobble together some frankenstein machines - or even just buying newer parts to do the best possible super budget machines for friends - so this is a godsend. Thanks for the wide selection of games too - some reviews just do a handful which doesn't give a broad enough picture. Icing on the cake is the comparison to the intel chips, including that 8400. Even the global (fix the spelling on the chart) wattage is v interesting. Very nice.
    1
  • lithium6
    Oh man, I would have loved to see Richland-based Athlons in the test!
    0
  • _zxzxzx_
    Thanks for the article but I would have liked to see the Thubans in action and I reckon' the 8350 would have topped the results.
    0
  • de5_Roy
    i missed the fx8320 in the crysis 3 benches. compared to the core i5 3570k stock framerates, the fx6350 (stock and o.c.) seemed ahead in these articles' crysis 3 benches.
    0
  • razor512
    Many people like the Phenom II (including me) because it had a better IPC. the FX8350 can beat many of the high end core i7 CPU's if something is perfectly multithreaded, but for most tasks, it loses out to a 4 core intel CPU (even if they disable hyper threading), and that is because current intel CPU's offer a higher IPC. a single fast core is better than 2 separate cores at half the speed each.

    Intel is offering a good balance between multi threading and single threading performance by having CPU's that can give more than 2 points per core in applications such as cinebench.

    Clock for clock, the phenom II is significantly faster than the FX series.

    If they cannot put 8 true cores on a single CPU, then they need to work on releasing a quad core with an IPC that rivals the intel CPU's.

    Lower IPC is a step in the wrong direction, FX is the wrong choice.
    0
  • Giordano Squadroni
    I want see a clock to clock single core comparison between Athlon FX 57 (939, ddr), Phenom (AM2, ddr2), Phenom II (AM2+ ddr2 and AM3 ddr 3 1333/1600), "new" Athlon FX (AM3+, ddr3 1866).
    0
  • cheesyboy
    Really enjoyed this one. Thanks Tom's

    (minor quibbles...) For completeness, it would have been nice to see the FX-8350 lining up. And perhaps include the 3570k in the individual results as a benchmark, for context (Though I realise this was an AMD roundup, of course).
    5