First Apple A8 Benchmarks Show... "Modest" Increase

Subject: General Tech, Processors, Mobile | September 12, 2014 - 01:30 PM |
Tagged: apple, apple a8, SoC, iphone 6, iphone 6 plus

So one of the first benchmarks for Apple's A8 SoC has been published to Rightware, and it is not very different from its predecessor. The Apple A7 GPU of last year's iPhone 5S received a score of 20,253.80 on the Basemark X synthetic benchmark. The updated Apple A8 GPU, found on the iPhone 6, saw a 4.7% increase, to 21204.26, on the same test.

View Full Size

Again, this is a synthetic benchmark and not necessarily representative of real-world performance. To me, though, it wouldn't surprise me if the GPU is identical, and the increase corresponds mostly to the increase in CPU performance. That said, it still does not explain the lack of increase that we see, despite Apple's switch to TSMC's 20nm process. Perhaps it matters more in power consumption and non-gaming performance? That does not align well with their 20% faster CPU and 50% faster GPU claims...

Speaking of gaming performance, iOS 8 introduces the Metal API, which is Apple's response to Mantle, DirectX 12, and OpenGL Next Initiative. Maybe that boost will give Apple a pass for a generation? Perhaps we will see the two GPUs (A7 and A8) start to diverge in the Metal API? We shall see when more benchmarks and reviews get published.

Source: Rightware

Video News

September 12, 2014 | 03:42 PM - Posted by Anonymous (not verified)

Anandtech disagrees

September 12, 2014 | 04:55 PM - Posted by Anonymous (not verified)

Yes they can disagree all they want but it's based on speculation. Obviously the GPU is the 6630 instead of the 6650 or whatever it is. Powervr was rumored to be having problems with it. Though this benchmark coukd be complete bs as well

September 12, 2014 | 06:48 PM - Posted by Anonymous (not verified)

Not really:

September 12, 2014 | 05:01 PM - Posted by Anonymous (not verified)

I read the Anandtech pre-review estimates, and I'll go with anandtech before this rightware sight. I am more interested in hearing about the A8, and whether the A8 may have any SMT ability in it's CPU cores, that and the usual Anand Lal Shimpi(post Anand leaving) level of analysis of the CPU cores. I am also interested in the Possibility of an A8X, with maybe 4 CPU cores, and the powerVR wizard GPU(with hardware ray tracing circuitry), maybe coming to the iPad, or a professional version of the iPad with the ability to run full OSX, and Pro, or open source, graphics software. I am tired of websites using A8 in the title, some as the main part of the title, only to click the link, and get some confused Comm. Arts, or journalism major's uneducated, in proper microprocessor systems architecture, totally incorrect attempt at writing on a high technology subject's intricacies.

Just how many of the A8 SOC's 2+ billion transistors are dedicated to the GPU, and what remains after the GPU's, and other third party on die assets', transistor counts are subtracted, is what will allow a more thorough estimate of just what the A8 may have going towards CPU compute. The single threaded and multi-threaded benchmarks will tell this, as well as being able to look at the OS's view of the CPU cores' assets, by looking at how many logical processors are present, and whether this is the same as the physical number of CPU cores. What benchmarks, that may be available, that can fill up the a processor's execution ports, and individual pipelines(floating point, integer, branch, etc. There has been no confirmation yet as to what latest ARMv8 ISA the A8 is using, Is it the ARMv8-A ISA, or newer, or with custom extensions from Apple. Is there some special Applesauce, that Apple's P.A. semiconductor boffins have thrown into the mix of the A8's cores, and again what is in store for the new iPads based on any A8 variants?

It's going to get much more difficult to tell, owing to Anand's new employment, that and the generally deplorable state of online technical journalism. Anand was one of the best, outside of a paywall, for such high grade analysis of the intricacies of microprocessor architectures.

September 13, 2014 | 12:34 PM - Posted by Anonymous (not verified)

nice to see my post removed

September 14, 2014 | 05:15 PM - Posted by Scott Michaud

?? As far as I am aware, and I checked with Ryan and others, we did not delete any comments on any article or news post except duplicates and spam (although not everyone has got back to me yet). Two possible explanations are that we saw a link in your comment and believe it was spam or it was lost during site maintenance. That said, I believe that our site was being worked on over the evening of the 11th, which is before this news post was made.

Sorry if your comment was accidentally lost!

September 14, 2014 | 06:33 PM - Posted by Jeremy Hellstrom

Can't remember if it was specifically this post but there were several negative comments which added nothing to the topic that I deleted last week.  Nuking a post kills all the comments below them, which may be how your post was lost.

September 14, 2014 | 09:49 PM - Posted by Anonymous (not verified)

This is obvious... Obviously the GPU performance won't be as good, it is driving like 40% more pixels. So only a 10% increase is expected with a GPU improvement of 50%.

November 8, 2014 | 12:42 AM - Posted by Melinda (not verified)

You may also go for different types of stakes and not only,
this blender making your job inside the kitchen very
easy and transforming cooking into each of your hobbies, while you might not be employed to that.
If you only want a quick drink then the hand-held Kenwood blender is fast
and perfect. If you're making milk frothing for the chocolate fondant, an immersion blender (that's another
name to the hand blender (Melinda)) may even be used.

Post new comment

The content of this field is kept private and will not be shown publicly.
  • Lines and paragraphs break automatically.
  • Allowed HTML tags: <a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd> <blockquote><p><br>
  • Web page addresses and e-mail addresses turn into links automatically.

More information about formatting options

This question is for testing whether you are a human visitor and to prevent automated spam submissions.