[PATCH] [AArch64] Improve and enable the SeparateConstOffsetFromGEP for AArch64 backend.

[Hao Liu]

>>! In D5864#45, @Gerolf wrote:
> Hi Hao,
> 
> could you share your current performance data + options you use? With your patch I see small gains on astar + xalancbmk, but a ~4% loss on libquantum.  The data is based on the 11/07 trunk on top of r221549, O3 + LTO, cyclone, ref input.
> In addition to cortex, could you run on x86 also?
Hi Gerolf,

I ran spec2006 4 times on my x86 machine, but the results are always fluctuating. So I can not see whether it is better or not by enabling this pass. I think it is because I don't have much experience on testing x86. 

For the AArch64 backend, recently I ran twice on r222083 at trunk and r222017 at trunk on Cortex-A57. The results are similar to the previous results. But it has about 1%-2% regression on 471.omnetpp. That benchmark is always fluctuating, so I can't measure it accurately. Anyway, we have much improvements than regressions.

Thanks,
-Hao

http://reviews.llvm.org/D5864