One has to be careful with SPEC results: Intel is known to tune icc with it, while I doubt LLVM is being tuned with SPEC, so there's some bias (other companies such as Sun did/do the same). Also between the i3 and Core Duo there are more than 7 years of compiler tuning
OTOH I have little doubt that Haswell IPC is higher for bigger workloads than A8, as I think the uncore performance is much higher. But as a reminder, A8 gains more on SPEC than on Geekbench, so this might hint that Apple is starting to push uncore (wish them the best to catch up with Intel who have a huge lead there :biggrin.
Oh don't get me wrong, SPEC has plenty of failings as a benchmark as well. It's just fun to point out how on SPEC Intel has a massive lead over Apple's A8 while Geekbench claims that they're on par. Neither is a 'fair' comparison.
Interesting to compare memory access latencies. Note that the tests (Sandra and whatever AT is using are different).
Note that L1 latencies are roughly equal at ~4ns. L2 is roughly equal at ~14-17 ns.
However Haswell's L3 is only a tad bit slower than L2 and significantly faster than Apple's L3. Edram, despite being located on a separate die is faster (55 vs. 75 ns). Access to system Ram is nearly twice as fast on Haswell.
Not sure what A9 will bring.
Is the above meant to be a comparison between Haswell and A8 cache latencies? If so, you missed the point of the Haswell chart being measured in number of clock cycles rather than ns. If Anandtech's iPhone 5s commentary is correct and A8 is the same 3 clocks for L1, then it'd be roughly 2ns compared to Haswell's 1ns. It's difficult to guess where the A8 L2 latency is, going by the graph it'd be something around 14ns... compared to Haswell's 3ns. And once you get to L3 it's something like 75ns versus 5ns. But that's what's necessary in order to feed more execution resources running at almost 3x the frequency.