I decided to dedicate an extra page to looking at two features on these Fusion boards that are, in my eyes, quite interesting to discuss. 

On the one hand, we are dealing with low power CPUs which can't process that much very fast, so if you want to overclock them, that overclock also has a significant impression on any integrated GPU gaming being used. 

On the other, we have access to a PCIe x16 slot, capable of running a full length, high-end GPU (should you want to).  This PCIe slot actually runs at 4x, which in certain circumstances would cripple the discrete GPU.  Pair this crippling with a not-so-great CPU, and we're not expecting the gaming capability to take off, so I've examined this as well.

Overclocking, and Gaming Performance

By default, we have a 1600 MHz, dual core Fusion CPU, combined with an 80 SP iGPU at 500 MHz, designated the HD 6310.  In terms of pure CPU throughput, we saw on all boards that a percentage increase in clock speed gave a direct increase in benchmark result for the 3D Particle Movement benchmark.

In terms of gaming, we need to analyze what this overclock does.  Apart from the default CPU speed increase, we're getting a direct GPU clock speed increase as well.  The DDR3 memory is also getting an increase, thus the memory bandwidth to the iGPU is increased as well.  So any overclock will increase its own effectiveness in two major areas.

I'll take the ASUS E35M1-I Deluxe for this explanation, which allowed a 10% overclock from 1600 MHz to 1760 MHz.  From the gaming perspective on the iGPU, we have a large increase in scores:

Overclocking the iGPU - 1024x768

Overclocking the iGPU - 1024x768

Out largest increase was in the DirectX 9 game, Left4Dead2 - a staggering 36.4 % increase in frame rate from 30.3 fps to 41.4 fps, making the game more playable at the 1024x768 resolution.  Even Metro2033 had a 21.0 % increase, and Dirt2 a 17.3% increase.  Is the iGPU itself capable of playing the major games?  Probably not, but at least those older ones can feel smoother.

The PCIe slot running at 4x - Is it worth using a beefy GPU, like a GTX 580?

The short answer is no, probably not.  Normally we see a full length PCIe slot run at 4x only when it's the second or third PCIe slot on the board, and usually at the detriment to SATA or USB ports that have to be switched off as a result.  Here, we have two main issues - will the CPU be fast enough to be able to navigate data across the PCIe bus to and from the discrete graphics, or will the 4x speed of the bus be the crippling factor?

(Note: I understand getting a GTX580 isn't realistic with a Fusion, but it's the most powerful GPU I have to hand and most apt for this test as GPU power should not be an issue.)

For this test, I ran the GTX 580  at the same settings as the iGPU tests, and then at the 1920x1080 resolutions and settings that we normally do for the high end motherboards (8xMSAA, 16xAF).  First, at the iGPU resolutions on the ASUS E35M1-I Deluxe:

Using a Large GPU - 1024x768

Despite using a $500 GPU, our biggest increase in frame rate, at 1024x768 resolution, is only 50%.  In Left4Dead2 on Sandy Bridge, at 1680x1050, we see over 200 fps - we know L4D2 can be fairly CPU limited, so the fact that we only see 45 fps is definitely testament to the Fusion CPU.

Now, at the full 1920x1080 resolution:

Large GPU Comparison - GTX 580

In Metro 2033, we didn't see any real decline from 1024x768 to 1920x1080, but there was a significant drop in Left4Dead2.  These results are also due to the CPU holding the GPU back, meaning that even with a GTX 580 on Fusion, only the old games will be playable, but this time at a higher resolution.

Gaming Benchmarks Final Words
POST A COMMENT

67 Comments

View All Comments

  • triclops41 - Thursday, July 14, 2011 - link

    I think Starcraft 2 benchmarks should be included. It is a popular game that can run well on mid and lower end systems.

    I know it can almost run at lowest settings with the E-350 at stock. But I would really like to know how well SC2 runs when the E-350 is overclocked to 2.1Ghz, considering it was CPU limited before.
    Reply
  • Phynaz - Thursday, July 14, 2011 - link

    Not single test doing video decode and display = fail. Reply
  • Finally - Thursday, July 14, 2011 - link

    ...you are taking a Bobcat APU (that's made for netbooks, HTPC and other low power usage devices) and test it on ground of performance by pairing it with a 1000W power supply. (Ian was clever enough not to mention his batshit crazy choice by simply stating "Silverstone 80+ Silver" on the hardware page - a quick check on geizhals.at reveals that there are only 4 power supplies that fall into this category, starting @ 700W and going up to 1000W -> http://geizhals.at/deutschland/?cat=gehps&xf=1...
    To further add insult to injury he then pairs this netbook APU with a Nvidia 580GTX only to finish this ridiuculousness for good with overclocking the shit out of the CPU...
    Come on? What will be tested next? How far the SoC can be thrown when it's raining?

    The thing I like best on AnandTech is how your pro-Intel-agitprop is actually brought to words: "Hudson-M1 - why would I want it?" - Imagine this same question being asked when Intel's Atom platform is the topic of the day... mark it well, because that will be the moment hell freezes over...
    Reply
  • AnandThenMan - Thursday, July 14, 2011 - link

    You're wasting your time. AMD will never get a fair shake on this site, not going to happen. Every notice how there is never a situation where a "mistake" or other choice accidentally gave AMD an unfair advantage? Why is that? Because these choices are on purpose, and are carefully selected to minimize the AMD product as much as possible, while still trying to maintain the appearance of impartiality.

    This site is a shill of Intel, and the only reason people don't believe that is because it's a hard thing to accept. But the evidence is overwhelming. At one time, there was an entire section of this website dedicated to only Intel, anyone else remember that?
    Reply
  • Broheim - Friday, July 15, 2011 - link

    if the reviews bother you that much, then why do you come back? is your life really that empty? Reply
  • medi01 - Sunday, July 17, 2011 - link

    Somebody has to compensate for shit in articles at least in comments. Reply
  • Broheim - Sunday, July 17, 2011 - link

    if "somebody" is dissatisfied, then "somebody" can go make their own hardware review site and review stuff like "somebody" wants to...

    in the meantime, "somebody" doesn't have to "compensate for shit".
    Reply
  • IanCutress - Thursday, July 14, 2011 - link

    As I've mentioned, the PSU issue is purely due to what I have available for testing. The GTX580 test, also as I've mentioned, was to provide a plausible maximum ceiling in those tests, and to explore the CPU power with the PCIe x4 against the iGPU. Regarding overclocking - there are people who will overclock everything and anything, regardless of what it's used for. In my mind, it's a valid test - if the platform has headroom with no negative consequences, that's something to look out for, and which to a certain extent the ECS board provided.

    I'm neither pro-Intel or pro-AMD. I review what I feel is right for the time and situation, and what circumstances allow. We have a series of 9-series boards to look at in the near future, but so far this year all the releases for me to focus on have been Intel based, especially in the motherboard segment. The comment regarding 'why would I want it' was the exact speculative comment I made when the boards came through my door. It's what I ask every board that passes through my hands - if a reviewer didn't ask this, there would be no point him or her reviewing it.

    I'm more than open to suggestions by email if there are other tests you think should be added. If there is time and an apt reason to run them (and everyone will be able to interpret the results), I will take a look - the development of testing is always fluid.

    Ian
    Reply
  • AnandThenMan - Thursday, July 14, 2011 - link

    In the interest of full disclosure and proper review procedures, please correct the chart to indicate the make/model/wattage of the power supply, instead of simply "Silverstone 80 PLUS Silver". Reply
  • andymcca - Friday, July 15, 2011 - link

    ^^ This.

    And honestly, it should be noted clearly, in plain sight, that power consumption figures are totally meaningless at <5% PSU load.

    It's fine that this is the only PSU you have on hand, but (lacking DC power figures, which obviously require special equipment) a low power PSU, preferably a PicoPSU (with a decent brick) or equivalent, is the only reasonable choice here for power testing. Under-loading a PSU can give very misleading results, which deserve a footnote.
    Reply

Log in

Don't have an account? Sign up now