Thats a GPU task, generally.
You do the typical mistake of assuming that clock speed is the sole determinant of a processor's speed.
It isn't a typical mistake, CPU performance can scale with clock speed if the supporting circuitry keeps up.
Cyclone (and indeed all ARM CPUs) only attains its 'reasonable' speed if its workload is very narrow and very focused.
This is baloney, Cyclone has proven itself in a wide array of workloads on the iPad.
Its branche prediction is vastly inadequate and inferior. This causes two problems:
Well for one it isn't that bad considering the size of the chip and two you assume it won't get better.
1) It limits how well the CPU scales at higher frequencies. At higher frequencies, the prediction falls more and more behind - and the performance bottleneck gravitates towards its memory bandwidth. Intel devices are significantly better when working with larger datasets.
Apple can easily address this with improvements to the Memory interface and the caches supporting the GPUs. RAM and caches play a significant role in keeping Intels cores running and are in fact bottlenecked through the RAM interface. In Apples A7 case the bottleneck is significant due to the GPU load on that interface.
In a nut shell the A7 cores could do much better with improvements to memory and caching without touching the core at all. However I don't think Apple will leave those cores untouched in future A series SoC.
2) It limits how well the processor handles larger and more diverse workloads (which are most of your 'everyday' things).
Maybe to some extent but you fail to realize that the cores are small allowing many onto a piece of silicon. Cores are an advantage in portable devices because in a good desiring they are near zero power when not in use.
Geekbench is a very poor benchmark for a CPUs overall capacity because the benchmark itself is extremely small. A significant parts of the CPU is never actually tested in Geekbench.
Well that we agree with. Get away from Geekbench and we see that A7 is in fact a good core. It is a core that needs a much better I/O subsystem to deliver goi results.
There isn't any ARM CPU even close to currently matching one Intel's 'Big Core' x86. Forcing them to that performance results in dreadful power efficiency.
(Heck, even at the iPad speeds Haswell sports superior performance-per-watt, it just can't do extreme sleep levels as well)
This isn't true either. Years ago Global Foundries was touting ARM core running on what is now an old process, they where able to hit very high clock rates on those processes. Currently Haswell does well because Intel does have a process lead not an architecture design lead. Intel is also blowing its chances to maintain that lead at 14 nm so we could very well see 14 nm ARM based machines early in 2015.
Oh and by the way the ability to sleep a processor is far more important these days than a slight power advantage at full performance.
You're making the assumption that the software actually scales with more cores. This is not the norm.
It is also a mistake to assume that one app is important to most users. On the contrary most people do multiple things at the same time on their machines even if the don't realize it. Overall system performance is enhanced by more cores.
Some workloads can be scaled quite easily, but a lot can't. And most workloads see an increasing amount of dependency collisions the more cores you shove in. Thats also before considering the increasing overhead cost on the CPU scheduler.
Obviously the benefits of cores depends upon the application but you have to separate that from the benefits to the system. Most user apps though do benefit from more cores as they are multithreaded or use supporting processes. The proof is in the pudding and the fact that nobody is going back to single core machines.
Indeed, one of Apple's advantages in their iOS devices is that they only have two cores. It benefits many types of workloads which cannot be parallelized (e.g. they can only run on 1/2 cores), and also provides a more consistent performance profile.
It isn't an advantage at all for apps, it instead allows Apple simple hardware solutions to power management. In fact due to Apples low clock rates used to manage power single threaded apps are at a real disadvantage on iOS devices. This is why Apple pushes GCD and other technologies that use both cores.
It also makes it easier for the software developers, since they only need to keep two cores in mind - rather than 3 or 4. Its very easy to introduce non-obvious or downright weird bugs when parallelizing.
The number of cores has no bearing on parallelizing bugs. More cores just means the bugs pop up more. In general though many of the parallelizing features in iOS reduce the complexity for developers.
Its pretty much the reason AMD has completely failed in the x86 market: They over-emphasized many weak cores over few strong like Intel did.
Well no, their engineers failed to deliver the cores promised, a big difference. In the end they had to market what they had. By the way the story is much different when BRAZOS is compared to ATOM, in a real sense AMD hit that one out of the ball park. AMD hasn't completely failed in the market, they just haven't competed well at the high end. In the middle and low end I have no problem with AMD's chips. Mullins, Kaveri and the other recent chips are very worthy of consideration.
----------
Well, this is disheartening news, if true.
Then you don't understand what is happening here. In a nut shel to continue to innovate they need access to the silicon! It really is that simple.
I think it would be a mistake for Apple to do this, but I wouldn't be surprised if they did it.
What choice do they have if Intel won't open up its silicon. Their only choice is AMD if they stay i86. Go to ARM and they have basically unlimited solutions they can leverage. Everything from in house solutions to products from AMD, Samsung, TI, Qualcom and a long list of others. Companies by the way willing to partner with Apple.
Frankly it would be a mistake not to go ARM long term.
I just don't understand what the hell is going on over there these days.
Try a little harder. Look at a motherboard from an Apple PC from 10-20 years ago an imagine all of that innovation built into one piece of silicon. That is where the industry is going.
. Mouse-based apps present targets that are too small or hard to see on touch devices. But touch apps present easy to hit, well organized targets for a mouse or a trackpad, and are thus even easier to use by older people who need reading glasses (the biggest growth populace these days).