Android always enabled completely general multiprocessing and multithreading, initially at the expense of smooth visual effects, and Android was implemented on a variety of CPUs and GPUs. Secondarily, Android didn't used to have concurrent GC. Thirdly the animations were not tuned (q.v. Butter). Fourthly, the graphics stack was tuned to use more GPU-based operations as mobile GPUs improved. If you know you have only OS overhead when you are the foreground task, lots of things get more deterministic. But that does not mean you have more total throughput.
For that matter, Android didn't have low-latency audio until 4.2.
Try taking a look at how many processes, and Dalvik instances, are running concurrently at boot time on an Android device. Then try just starting that many VM instances, of any VM, on any other OS. The reason Microsoft has gone to pre-compiling "in the cloud" is that otherwise the CLR has a miserable startup time and mediocre performance. The CLR architecture is much more like a conventional Java VM. You can't build a whole OS on a managed language implementation of OS features with that level of performance.
I'd wager Microsoft has a much rougher road ahead stuffing a real Windows kernel into handsets and maturing CLR performance, memory efficiency, and battery life for comparable computing tasks that Android handles well in all performance dimensions.
The person who posted that comment is behind the times re audio on Android.
Android can deliver very low audio latency and do it consistently, but the OEM has to test that their CPU power management and other kernel configurations have not screwed it up, and those tests are not baked into ACS.
The OEM should, at least, correctly use the feature flag for low-latency audio, leaving is off if they don't actually know. But specifying that flag in your manifest means your app loses access to devices where good enough is good enough.
> The person who posted that comment is behind the times re audio on Android.
No, that person has real life experience what means to develop for Android while targeting the majority of devices available to consumers.
All your answers so far were very good and I appreciate the time you took to answer them.
However, those of us that target all three major mobile OS across multiple OEMs, have a different experience of what Android's performance on real devices looks like.
And to conclude this thread, Google agrees with us, otherwise they wouldn't have spent $23 Million buying FlexyCore if Android's performance on real devices was so good as you have been defending.
Android always enabled completely general multiprocessing and multithreading, initially at the expense of smooth visual effects, and Android was implemented on a variety of CPUs and GPUs. Secondarily, Android didn't used to have concurrent GC. Thirdly the animations were not tuned (q.v. Butter). Fourthly, the graphics stack was tuned to use more GPU-based operations as mobile GPUs improved. If you know you have only OS overhead when you are the foreground task, lots of things get more deterministic. But that does not mean you have more total throughput.
For that matter, Android didn't have low-latency audio until 4.2.
Try taking a look at how many processes, and Dalvik instances, are running concurrently at boot time on an Android device. Then try just starting that many VM instances, of any VM, on any other OS. The reason Microsoft has gone to pre-compiling "in the cloud" is that otherwise the CLR has a miserable startup time and mediocre performance. The CLR architecture is much more like a conventional Java VM. You can't build a whole OS on a managed language implementation of OS features with that level of performance.
I'd wager Microsoft has a much rougher road ahead stuffing a real Windows kernel into handsets and maturing CLR performance, memory efficiency, and battery life for comparable computing tasks that Android handles well in all performance dimensions.