â€œThe 64-bit Apple chip hit us in the gut,â€ says the Qualcomm employee. â€œNot just us, but everyone, really. We were slack-jawed, and stunned, and unprepared. Itâ€™s not that big a performance difference right now, since most current software wonâ€™t benefit. But in Spinal Tap terms itâ€™s like, 32 more, and now everyone wants it.â€
The â€œIt’s not that big a performance difference right now…â€ is inaccurate. Mike Ash, again via John Gruber, points to huge improvements in object creation and destruction speeds in 64-bit mode versus 32-bit mode:
Adding it all together, itâ€™s a pretty big win. My casual benchmarking indicates that basic object creation and destruction takes about 380ns on a 5S running in 32-bit mode, while itâ€™s only about 200ns when running in 64-bit mode. If any instance of the class has ever had a weak reference and an associated object set, the 32-bit time rises to about 480ns, while the 64-bit time remains around 200ns for any instances that were not themselves the target.
In short, the improvements to Appleâ€™s runtime make it so that object allocation in 64-bit mode costs only 40-50% of what it does in 32-bit mode. If your app creates and destroys a lot of objects, thatâ€™s a big deal.
I’m not a programmer, but I take this to mean iOS apps that take advantage of the A7 CPU’s 64-bit architecture are faster, now.