Tobias Grosser wrote: > On 09/29/2015 06:26 PM, Sebastian Pop wrote: > >This code is not used anymore after we removed the previous loop optimizer > >(not > >based on the ISL scheduler.) We will add back the detection of commutative > >reductions after we improve the code generation of scalar dependences (by not > >going out of SSA for scalar dependences just to expose them to the data > >dependence graph.) > > > >Patch passed bootstrap and check on x86_64-linux with ISL-0.15. > >I will commit this patch to trunk. > > LGTM. > > Regarding the handling of scalars, Polly does this now by only virtually > modeling > them as memory dependences, but leaving them as registers until code > generation. > The final code generation is still done by alloca(ing) a memory slot and then > generating loads/stores from this memory slot. This is significantly easier > than > trying to directly generate SSA again.
Thanks Tobi for the review and the hint. Sebastian