News
  •  paul
  • 50.25% (Neutral)
  • Member Topic Starter
2014-09-12T10:28:01Z
Historically speaking, we typically see impressive performance gains each time Apple releases a new custom processor for its mobile products. Certainly that was true of the A7 System-on-Chip (SoC), the world's first 64-bit smartphone processor offering desktop-class performance. In our evaluation of the iPhone 5s, the A7 chip dominated our benchmark runs and consistently outperformed previous generation iPhone models, sometimes by an obscene margin. So, can we expect the same kind of performance bump from the iPhone 6 and iPhone 6 Plus, both of which sport a custom A8 SoC? Maybe not.

Rightware ran the iPhone 6 through its Basemark X benchmark and noted only modest gains compared to the iPhone 5s. Armed with a dual-core 1.4GHz Cyclone CPU and A8 GPU, the iPhone 6 scored 21,204.26 and a earned a place at the top of the chart, though not by much. By comparison, the iPhone 5s scored 20,253.80 in the same benchmark. In other words, the iPhone 6 is less than 5 percent faster than the iPhone 5s, at least in Basemark X.

iPhone 6 Basemark X
Source: Rightware

This is surprising, both to us and Rightware, which told HotHardware that the performance improvement wasn't as big as it was expecting. That's probably true of anyone who's familiar with Apple's past upgrades, as well as those who caught the iPhone 6 launch live stream.

iPhone 6 Side

"The all-new A8 chip is our fastest yet. Its CPU and graphics performance are faster than on the A7 chip, even while powering a larger display and incredible new features. And because it’s designed to be so power efficient, the A8 chip can sustain higher performance — so you can play graphics-intensive games or enjoy video at higher frame rates for longer than ever," Apple states.

iPhone 6 Apple Performance
Source: Apple

Apple's A8 chip is built on a 20nm process with two billion transistors. According to Apple, it offers 84x faster graphics performance than the original iPhone and is up to 50x faster in CPU performance. While that may be the case, the original iPhone is ancient technology. Of more interest is how it compares to today's devices and the previous generation iPhone. Unfortunately, early indications don't look all that promising, though we'll reserve judgement until we see more benchmarks emerge (and/or we have a chance to test it out for ourselves).
sevags
  •  sevags
  • 53.25% (Neutral)
  • Advanced Member
2014-09-12T13:04:47Z

Hopefully this is just some sort of software issue? I knew it was odd that they compared speeds to the first generation iPhone but I don't see apple releasing a new phone that is only 5% faster than the previous model. 10% maybe but not 5.... What would make the A8 special than compared to the A7? bleu either way I preordered mine.

SJobbs
2014-09-12T13:48:40Z

It's possible you're getting a bit carried away by benchmarks. Maybe Apple put more effort into improving battery life rather than outright benchmark numbers. How much faster does a smartphone need to be for most users as long as the user interface is responsive? It did run that video game rather well so what would be the point of simply jacking up benchmarks to mainly excite tech-heads.

lipe123
2014-09-12T13:48:49Z

Anyone that looked at apples charts would have noticed that they indicatea larger increase between the 5 and the 5s than the 5s and the 6.

So since we all know the 5 and 5s are not worlds apart its pretty obvious the 6 wont be 10x faster either.

Welcome to Apple PR , they just invented "bait & switch" and patented it. (also in process of suing all other mobile phone manufacturers for making phones just as good as the iphone)

RiCoFrost
2014-09-12T17:06:21Z

Look in all fairness they don't need faster they need better battery life. Pretty much all of the mid to high end CPU on phones are doing rather well. Apple phones are bad on battery life its probably the number one complaint about them. If they get 10% improvement in performance and 30% improvement in battery with the same battery size that will be good.

Dave_HH
2014-09-13T00:38:01Z

You make a good point there, [censored], and that's an interesting user name you have there. ;)

ViewRoyal
2014-09-13T11:15:11Z

Any non-graphics-intensive app that just runs on the CPU (without needing the GPU) does not need to be any faster. Opening and reading email messages, opening and using the phone app, etc., work faster than any human needs it to be.

Where I bet we will see the real speed increases of the iPhone 6 will be in gaming (where a fast GPU processor is really going to be noticeable to users).

The combination of the much faster GPU in the iPhone 6, plus the high end games written in Metal, is probably going to blow everyone away once we have some of the new 3D rendered games to benchmark.

BeeRyan
2014-09-14T03:47:29Z

llpe123 - there is so much fail in your troll post, I'm sure you are suing Apple because of your Bait & Switch patented trollnology - though it is obvious, therefore you patent is invalid.

Also the 5 and 5s are fairly different, being that one is running the much older 32bit SoC and the 5s is running the 64bit SoC and it seems to be miles better for many things that need it. The 6 has a larger display - a larger battery and a much better GPU - and it seems Apple developed "Metal" to run in place of OpenGL to get even better performance out of the GPU. Apple probably is best with the SoC, which most trolls have never figured out...

JosPedroDaz
2014-09-14T08:07:40Z

You're right benchmarks are too software specific. Most people get carried away with benchmarks, bottom cpu power is defined by cpu speed, the rest are software problems. If a game was ported, doesn't take advantage of the whole cpu, or if the game needs certain optimizations, etc etc.

RichardCookson
2014-09-14T10:07:25Z

Bad test software to begin with. Basemark X is optimized to run best on an iPhone 5 with a 32-bit CPU and OS. It isn't currently designed to properly test a 64-bit CPU with 64-bit OS as the iPhone 5S and 6 use. Therefore the results are actually quite questionable.

RiCoFrost
2014-09-14T19:16:15Z

Well consider that most apps run as 32bit the benchmark is a good test. If it cant run 32bit apps well because its a 64bit os then that's a problem.