On Tue, May 31, 2016 at 2:56 AM, James Greenhalgh <james.greenha...@arm.com> wrote: > As you're proposing to have this on by default, I'd like to give a chance > to hear whether there is consensus as to this being the right choice for > the thunderx, xgene1, exynos-m1 and qdf24xx subtargets.
I tested this on qdf24xx using SPEC 2006. I'm seeing a very small performance decrease on the int benchmarks which may just be noise, and an even smaller decrease on the FP side which is definitely in the noise. This is an out-of-order part with hardware register renaming, so this optimization probably doesn't do much for this target. I may also be seeing secondary issues, e.g. the pipeline description isn't as good as I would like yet. Jim
