Intel Corp (INTC)

[mas]

the sub-test that people say is least "game-able" by compiler trickery

If some of this 'trickery' is applicable to general application usage then it is not necessarily invalid. Most of the SpecCPU suite subtests are not affected by this anyway so the whole suite is still more valid than say GB3.

re: http://www.fool.com/investing/general/2015/11/04/just-how-fast-is-the-apple-inc-a9-cpu.aspx

In this article it was not pointed out that GB3 favors A9 with its specialized encryption instructions which C2D does not possess. Maybe GB2 would have been a better benchmark to compare these two processors more validly, at least on the integer (due to the x86 FP denormal bug) side ? As for the SpecINT2000 comparison that shows that A9 is probably more equivalent overall to a 2.0-2.3 GHz C2D which is still a fine achievement.

Finally can you perhaps see now that giving up on android x86 is not a good long-term strategy as it will prevent any future potentially good x86 mobile processors from taking hold due to software negligence ? Intel spent $5+bn with its discounts getting the current android foothold and it would be fiduciarily negligent just to give up on that now just because Atom is not the absolute best mobile processor at this moment in time. Atom guarantees software volume which should not be taken for granted.