|
From: Julian S. <js...@ac...> - 2012-09-19 18:20:48
|
> So, does anybody think there is a clean way to get VexArchInfo at > getAllocableRegs_PLATFORM, or we should just apply the change to fit > Loongson in this case (we measured it, and no performance impact has been > seen on any of the benchmarks we ran)? Or this could be resolved > differently? I suggest you apply the change to fit Loongson. I did some experiments on amd64 on the effect of limiting the number of registers, and it has very little effect. That is on a CPU with 14 allocatable integer registers in total, so in this case you are in a better situation anyway. J |