CPU Benchmarks

The dynamics of CPU Turbo modes, both Intel and AMD, can cause concern during environments with a variable threaded workload. There is also an added issue of the motherboard remaining consistent, depending on how the motherboard manufacturer wants to add in their own boosting technologies over the ones that Intel would prefer they used. In order to remain consistent, we implement an OS-level unique high performance mode on all the CPUs we test which should override any motherboard manufacturer performance mode.

HandBrake v0.9.9: link

For HandBrake, we take two videos (a 2h20 640x266 DVD rip and a 10min double UHD 3840x4320 animation short) and convert them to x264 format in an MP4 container. Results are given in terms of the frames per second processed, and HandBrake uses as many threads as possible.

HandBrake v0.9.9 LQ Film

The latest Intel processors have the lead for low quality Handbrake conversion, and despite the generational gap between the FX-4350 and the A10-7800, the extra MHz is preferred here.

HandBrake v0.9.9 2x4K

For large frame manipulation, the latest architectures mixed with the most threads perform best.

Agisoft Photoscan – 2D to 3D Image Manipulation: link

Agisoft Photoscan creates 3D models from 2D images, a process which is very computationally expensive. The algorithm is split into four distinct phases, and different phases of the model reconstruction require either fast memory, fast IPC, more cores, or even OpenCL compute devices to hand. Agisoft supplied us with a special version of the software to script the process, where we take 50 images of a stately home and convert it into a medium quality model. This benchmark typically takes around 15-20 minutes on a high end PC on the CPU alone, with GPUs reducing the time.

Agisoft PhotoScan Benchmark - Total Time

Dolphin Benchmark: link

Many emulators are often bound by single thread CPU performance, and general reports tended to suggest that Haswell provided a significant boost to emulator performance. This benchmark runs a Wii program that raytraces a complex 3D scene inside the Dolphin Wii emulator. Performance on this benchmark is a good proxy of the speed of Dolphin CPU emulation, which is an intensive single core task using most aspects of a CPU. Results are given in minutes, where the Wii itself scores 17.53 minutes.

Dolphin Emulation Benchmark

Dolphin seems to work best with high single core speed and Haswell.

WinRAR 5.0.1: link

WinRAR 5.01, 2867 files, 1.52 GB

PCMark8 v2 OpenCL on IGP

A new addition to our CPU testing suite is PCMark8 v2, where we test the Work 2.0 and Creative 3.0 suites in OpenCL mode. As this test is new, we have not run it on many AMD systems yet and will do so as soon as we can.

PCMark8 v2 Work 2.0 OpenCL IGP

PCMark8 v2 Creative 3.0 OpenCL IGP

The combination of processor graphics and OpenCL support push the AMD APUs up to the top of our PCMark tests.

Hybrid x265

Hybrid is a new benchmark, where we take a 4K 1500 frame video and convert it into an x265 format without audio. Results are given in frames per second.

Hybrid x265, 4K Video

Cinebench R15

Cinebench R15 - Single Threaded

Cinebench R15 - Multi-Threaded

Cinebench is typically Intel territory for high IPC processors, but when it comes to multithreaded rendering, extra threads help.

3D Particle Movement

3DPM is a self-penned benchmark, taking basic 3D movement algorithms used in Brownian Motion simulations and testing them for speed. High floating point performance, MHz and IPC wins in the single thread version, whereas the multithread version has to handle the threads and loves more cores.

3D Particle Movement: Single Threaded

3D Particle Movement: MultiThreaded

All the calculations in 3DPM deal with floating point numbers, a known sink for AMD compute.

FastStone Image Viewer 4.9

FastStone is the program I use to perform quick or bulk actions on images, such as resizing, adjusting for color and cropping. In our test we take a series of 170 images in various sizes and formats and convert them all into 640x480 .gif files, maintaining the aspect ratio. FastStone does not use multithreading for this test, and results are given in seconds.

FastStone Image Viewer 4.9

Web Benchmarks

On the lower end processors, general usability is a big factor of experience, especially as we move into the HTML5 era of web browsing. For our web benchmarks, we take four well known tests with Chrome 35 as a consistent browser.

Sunspider 1.0.2

Sunspider 1.0.2

Mozilla Kraken 1.1

Kraken 1.1



Google Octane v2

Google Octane v2

AMD A10-7800 Review: Testing the A10 65W Kaveri Gaming and Synthetics on Processor Graphics
Comments Locked


View All Comments

  • extremesheep49 - Thursday, July 31, 2014 - link

    Does the A10-7800 still suffer from the power delivery issue from previous articles? I thought I heard it might be related to the CPU's being from an early batch. Is this now a non-issue?

    From http://www.anandtech.com/show/7914/msi-a88xme35-re...
    "In our recent FM2+ motherboard reviews [1,2], one of the common themes has been the ability of the motherboard power delivery to cope with temperature. When the power delivery is too hot, the system may cease to function or various benchmarks fail. Over-engineering the power delivery to be efficient has benefits, but increases the cost of the product. When I pulled the A88XM-E35 out of the box and saw no heatsink present, I was worried that the same issue would rear its head, and it did. Without additional VRM cooling, the A88XM-E35 caused an instant reboot on some of our more strenuous benchmarks (Agisoft, Handbrake). Therefore it should be noted that the results of this review were taken with an additional fan on the VRM cooling, and users of the A88XM-E35 should bare this in mind."

    Also, it would be awesome if you covered Dota 2 for these IGPU's because it is the most popular game in the world. On a A10-5700 at 1920x1200 I need to run almost minimum settings to insure I never go under 10 FPS. I would have expected better from the best IGPU's around.

    Tom's hardware covers Dota 2 and it seems like it might be poorly optimized because it's getting half the FPS of the intel card. Not sure. If it is poorly optimized...
  • R3MF - Friday, August 1, 2014 - link

  • extremesheep49 - Wednesday, August 6, 2014 - link

    By the way, the min FPS in that Dota 2 performance article seem too high. They may not have had any really big visible fights in that test. Here's how I test Dota 2:

    0. Enable Fraps benchmarking on F12; record frametimes at least; stop bench after 500 sec or so
    1. Dota 2 -> Play -> Create a lobby -> Create Lobby (not local; local is CPU intensive and reduces FPS)
    2. Join a slot
    3. Edit settings:
    - Game mode: all pick
    - Check `Enable Cheats`
    - Check `Fill empty slots with bots`
    4. Start game and choose `Faceless Void` (`Warlock` is another good choice). Both have ults which can slow down a slow computer when the ult happens
    5. Use these cheats (hit enter to bring up chat box; type `-gold 100` in chatbox to get 100 gold for example)
    - `-lvlup 24` (level yourself up to level 25)
    - `-item item_travel_boots`
    - `-item item_assault`
    - `-item item_refresher`
    - `-item item_mjollnir`
    - `-item item_butterfly`
    - `-item item_bloodstone`
    - `-levelbots 24` (level all the bots up to level 25)
    - `-givebots item_shivas_guard`
    - `-givebots item_bloodstone`
    6. Note these cheats:
    - `-respawn` to bring yourself back to life
    - `-refresh` to give everyone full health, mana, and to remove item cooldowns
    6. Start the benchmark
    7. Teleport to mid and attack until benchmark ends. Make sure to use `Chronosphere` and `Refresher Orb` so you can place 2 Chronospheres at once. Use `-refresh` to reset cooldowns to continue the attack. Bots will use `Shivas guard` a lot so there's a lot of special effects occurring.
    7 - alternate. Using `Warlock` is a little different. You need `Aghanim Sceptor` to get the full effect from his ult.

    On my A10-5700 with graphics maxed at 1920x1200, I will get less than 5 FPS during these fight scenes. These are not infrequent occurrences. These are the most important moments of the fight.
  • FriendlyUser - Thursday, July 31, 2014 - link

    Looks good and the adjustable TDP is a great feature for different applications (NAS or media server etc). It seemed really improbable a little time ago, but we are really approaching playable territory for many modern games without a dGPU. I would really love to see TrueAudio and HSA work in more games and applications...
  • GreenMeters - Thursday, July 31, 2014 - link

    Someday, I will be able to read the name of this processor without then spending 10 minutes singing to myself: NANA-NANANANANA-NA-NA-NA, Ka[ta]veri Damacy.

    This is not that day.
  • ssj3gohan - Thursday, July 31, 2014 - link

    So... when is this AMD center bullshit going to stop? Because I really can't help thinking anything else than that I'm reading an advert instead of a quality review. I'm seriously avoiding reading any AMD-related Anandtech articles in fear of ending up here.
  • tcube - Friday, August 1, 2014 - link

    Fair enough... now complain the same about intel center and nvidia center... geez you fanboys
  • austinsguitar - Thursday, July 31, 2014 - link

    amd needs something up there sleves... this is not it. An intel (i7 4500U 15W!)cpu in my laptop out-performs this disgrace.... i miss amd. APU or not, i dont think people care that much about trivial performance like this. it pains me.
  • leopard_jumps - Thursday, July 31, 2014 - link

    it is an ultra low voltage CPU . i7 4700MQ is a great deal but for me i5 3230M + Geforce GT 740M/Radeon 8750M is a good deal . Of course , the more the better .
  • medi02 - Saturday, August 2, 2014 - link

    APU is what it has at the moment. (actually closing TDP gap is a nice step forward)
    What is it, that I can do with i7, but can't do with A10?

Log in

Don't have an account? Sign up now