A5X vs. Tegra 3 in the Real World

Even with the inclusion of GLBenchmark data, we're still arguing over theoretical advantages. Any 3D game developed for Android or iOS is going to target 30 or 60 fps and try its best to stay there. Similar to a console, on an Android or iOS tablet there's no disabling vsync and there's (almost) no tinkering with image quality settings to impact performance. The trick on Android is really ensuring that experience across all available SoCs, but if we cull the list down to the best of the best—chances are you'll have a good experience on both sides of the fence.

NVIDIA's Tegra 3 is at the heart of our current favorite in the Android tablet space: ASUS' Transformer Prime. There also happen to be some games that are available on both Android and iOS. Take Modern Combat 3, available on both iOS and Android—do we see the same ~2x performance advantage from Egypt in this title compared to ASUS' TF Prime?

NVIDIA makes two counter arguments against Apple's claim that the A5X delivers superior gaming performance. The first is that despite any theoretical performance advantages the A5X may hold, they don't manifest in games today. The second NVIDIA argument is that via Tegra Zone, Android titles can look better than their iOS counterpart. Both of these are potentially valid claims, but let's test them.

Shadowgun is an NVIDIA favorite. It's a first person shooter that's available via NVIDIA's Tegra Zone app. The Tegra specific version offers support for gamepads and stereoscopic 3D with enhanced graphics specifically for Tegra 2 and Tegra 3. It works for our little experiment here because it's also available on iOS.

Shadowgun also ends up being a great example of what the Android/iOS divide looks like for many Tegra Zone games. This particular title appears to still render at 1024 x 768 on the new iPad, we simply get an upscaled image rather than a higher resolution. In turn it means we get more aliasing and a less sharp image compared to what we get on ASUS' Transformer Prime, where the game runs at 1280 x 800.


Shadowgun—iPad (3rd gen)


Shadowgun—Transformer Prime

Apple's A5X delivers an extremely smooth frame rate in Shadowgun. Although there's no built in timedemo, frame counter or benchmark functionality, the game runs subjectively smoother on iOS compared to on the TF Prime running Ice Cream Sandwich. Although the frame rate is higher on the iPad, I wouldn't consider it unacceptably low on the TF Prime—both are definitely playable.

Where the Tegra Zone version of the game has an advantage is in its visuals. The NVIDIA enhanced version uses higher resolution textures and features what appears to be CPU accelerated cloth physics in objects that simply don't exist in the iOS version. Some scenes also include other additional details (e.g. water on the floor) that aren't present in the iOS version. None of these additions fundamentally change the gameplay at all, but they do make for a better looking game.

Is it physically possible to have the same experience on iOS? Quite possibly. What we're seeing here is a mobile representation of what NVIDIA has done in the PC industry for years. By lending its support to smaller Android developers, their games are made prettier on NVIDIA hardware, and in turn NVIDIA helps promote those games via Tegra Zone and other channels. Obviously Apple could do the same, but thus far it hasn't needed to. Apple instead prefers giving its partners what someone very smart once referred to as most favored nation status. As a MFN, these game developers get additional exposure in the app store and elsewhere in Apple's promotions. It's very similar to what NVIDIA is doing, except on a much larger scale and without the iOS specific visual enhancements.

The comparison becomes even more complicated when you take into account the iPad's Retina Display looks better than the panel on the TF Prime. It's not really the higher resolution but rather the improved color reproduction on the iPad.

Riptide GP is another example of a Tegra Zone title available on both iOS and Android, although here the Tegra optimizations are less impressive while the Retina Display's advantages are more pronounced. There's no perceivable difference in frame rate here either, making it a much closer call:


Riptide, iPad (3rd gen)


Riptide, Transformer Prime

Grand Theft Auto 3 was recently ported to both Android and iOS, and with this title we find ourselves in a unique position: the Android version offers customizable visual quality. The iPad version of the title renders at 1024 x 768 regardless of hardware generation and performance is understandably smooth. Visual quality is configurable, only on the Android version, with draw distance, screen resolution and effects quality vectors:

These sliders/options have different defaults depending on what SoC they are running on. The Transformer Prime is capable of running GTA3 at the highest quality settings with a tangible but livable drop in frame rate. The end result is a significantly better looking game on Android, although to be honest it's something that you really only notice if you are doing a side by side comparison. If all you have is an iPad or TF Prime, you'd likely just grow used to whatever platform you had.


GTA 3, iPad (3rd gen)


GTA 3, TF Prime (max quality)

The TF Prime experience doesn't map as well to other tablets unfortunately. While playing GTA 3 on a Xyboard 10.1 (OMAP 4430) even at its default settings of 50% draw distance, 60% resolution and low effects quality, there's unusual stuttering during gameplay. The frame rate is otherwise smooth, but the periods of stutter significantly impact the overall experience.

Unfortunately the Android vs. iOS gaming comparison isn't always this easy. While some apps won't run on older Apple hardware, there are only three generations of iPad to worry about. Furthermore, within a single generation there aren't multiple performance levels to worry about as Apple only offers a single SoC. By comparison, there's a far larger selection of Android devices. Simply having the latest and greatest hardware isn't a guarantee that you'll be able to play every game in the Google Play store. Take Modern Combat 3 for example. Modern Combat 3 is a Call of Duty clone available on both iOS and Android. The game won't install on an ASUS Transformer Prime or a Motorola Xyboard 10.1:

The Play store keeps track of all of the devices I've used with my Google account and the compatibility list doesn't look good. Obviously this isn't Google's fault directly as the responsibility falls upon the game developer to ensure broad platform compatibility, but it is a problem for anyone who purchases a flagship Android device like the Transformer Prime. Either Google has to enforce compatibility across all of its devices or it needs to at least force developers to support a single, flagship platform. Perhaps one reason I'm seeing this today is because there is no Nexus tablet yet. If that's the route Google is going to count on, the first iteration of any major platform needs to be a Nexus device. In other words, the Transformer Prime should have been a Nexus to begin with.

GPU Performance Gaming Conclusion & Controller Support: An Android Advantage
Comments Locked

234 Comments

View All Comments

  • mr_ripley - Friday, March 30, 2012 - link

    It's a shame some people argue that against the workers when over a hundred of them have committed suicide over the working conditions. How can you still say that they are being offers a better deal here??

    On the other hand, it is also unfair that Apple is being singled out here. The world of Chinese manufacturing is a dirty one and all major corporations have a part in it. I'd trust Apple over most other companies to make a difference in that regard, and I'm happy to see something is being done in that regard. Ever heard McDonalds CEO touring the slaughterhouse of the meat packing companies??
  • name99 - Friday, March 30, 2012 - link

    Reporting suicides as a number not as a rate shows you to be either a fool or a deliberate liar. How many people, over how many years, comprise the pool from which this suicide number is drawn? Everything I have read says that the actual suicide rate is not only lower than the average rate for China, it is lower than the average rate for the US.
  • mr_ripley - Friday, March 30, 2012 - link

    In 2010, 18 workers attempted sucide, 14 succeeded. To me even one in a whole year is not acceptable. If you think that is ok I hope that statistic turns out to be you!!
  • name99 - Saturday, March 31, 2012 - link

    The argument was NOT that suicide is a tragedy, it was a claim that FoxConn employees specifically tied to Apple production have such lousy lives that they commit suicide in higher numbers that other people around the world.

    You have done NOTHING to prove this claim; all you have done is bring up a very different issue.
  • mr_ripley - Saturday, March 31, 2012 - link

    There is no disputing the fact that these deths are related to working conditions. I'm pretty sure this has been well established and documented. However, I did say in my previous post that Apple is unfairly singled out. It could have been any other company.

    Comparison between suicide rates is irrelevant. Higher sucide rates elsewhere does not justify this problem. Again the fact remains that many people have died and it is directly related to the working conditions.

    Apple happens to be in a position to directly influence their lives and make it better, after all they profit in billions from the work these people do. Corporations typically place little value over human life and living conditions (IBM sold equipment to the Nazis to track the Jews in concentration camps). Somehow, I feel Apple is different.
  • doobydoo - Sunday, April 1, 2012 - link

    Dude, sorry but you're talking no sense at all.

    First of all, pretty much any product you want to buy, electronics wise, uses parts from China where conditions are far worse on average, than Apples factories. So if you actually factored working conditions into the product review, it would look favourable for Apple.

    Secondly, your argument that comparison between suicide rates is irrelevant, is absurd. Higher suicide rates where legislation is such that no jobs suffer such terrible conditions that suicide is the only option, such as is the case here, prove that even if working conditions are refined, you still get some depressed people. Your argument, therefore, is with the people who committed suicide. You say it is 'directly related to the working conditions' but where have you evidenced this, at all? You simply haven't. The fact that the suicide rates at Apple factories are lower than some American ones further backs up my point on this.

    Every company is in a position to change lives and make them better. You too, are in a position to do this. But guess what. You, just like companies, can do WHATEVER YOU LIKE with your OWN MONEY and have NO OBLIGATION WHATSOEVER to solve the worlds problems. Apple already has amongst the best conditions of factories in China. The amount of profit they make is absolutely irrelevant, if you say Apple should be putting money into this then a lot more manufacturers should also put a lot more money into this. It's very easy to decide what other people 'should' do with their money now, isn't it?

    Corporations don't have to adhere to moral values - they are not people. They are there solely to make money. Nothing else. Don't confuse them with people. And I hope you donate every single spare penny to charity and spend every spare second of your time working to build homes in the 3rd world. Oh wait, you're on here crying that other people should do it instead.

    Get a hold of yourself you illogical fool.
  • mr_ripley - Sunday, April 1, 2012 - link

    Like I have said before it is a shame some people argue with great zeal against others who are suffering and devalue human life. Fortunately, Tim Cook is not one of them.

    If scores of people killing themselves citing poor working conditions is not enough proof what is? If your claim that there are work environments in America that have higher suicide rates because of working conditions is true that needs to be investigated as well and rectified.

    You give charity to people who are in need and cannot earn for themselves. If you think giving someone fair amount of compensation for hard work is charity you are delusional.

    If working in those factories is such a pleasent experience I suggest you try it out for yourself. Maybe the experience might broaden your perspective.

    Although, I don't see the point I will attempt to educate you. Legally, a corporation is considered as a person, that is right just like a live human being. Regardless of that corporations are run by people and actions of a corporation reflect upon the morality of the people running them.

    I will stop here as there is no point in continuing but you can respond with more insults and accusations of what I do or have done which frankly is no concern of yours.
  • PeteH - Monday, April 2, 2012 - link

    I've not seen a single report of people killing themselves and citing "poor working conditions" as the reason. Can you provide a link?

    There have been reports of people killed because of unsafe working conditions, but that's a different issue. Maybe you're confusing the two.
  • mr_ripley - Tuesday, April 3, 2012 - link

    Here's a Wikipedia link: you can read some of the circumstances and judge for yourself.

    They may not have said it in so many words but it is clear they were unhappy with ther work environment.

    Imagine your boss coming and beating you up because you lost an iPhone prototype!!!
  • mr_ripley - Tuesday, April 3, 2012 - link

    http://en.wikipedia.org/wiki/Foxconn_suicides

Log in

Don't have an account? Sign up now