[PATCH] D134354: [AMDGPU][GlobalISel] Support mad/fma_mix selection

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/CodeGen/GlobalISel/Utils.cpp:665-667
+    return isKnownNeverNaN(DefMI->getOperand(1).getReg(), MRI, SNaN) &&
+           isKnownNeverNaN(DefMI->getOperand(2).getReg(), MRI, SNaN) &&
+           isKnownNeverNaN(DefMI->getOperand(3).getReg(), MRI, SNaN);
----------------
foad wrote:
> Pierre-vh wrote:
> > foad wrote:
> > > This isn't true. You can get a NaN result even if none of the inputs are NaNs, e.g. from +inf + -inf.
> > I just copied the SDag implementation so that one would be wrong too then
> > ```
> >   case ISD::FMA:
> >   case ISD::FMAD: {
> >     if (SNaN)
> >       return true;
> >     return isKnownNeverNaN(Op.getOperand(0), SNaN, Depth + 1) &&
> >            isKnownNeverNaN(Op.getOperand(1), SNaN, Depth + 1) &&
> >            isKnownNeverNaN(Op.getOperand(2), SNaN, Depth + 1);
> >   }
> > ```
> > 
> > What is the alternative? Can this function not handle FMA/FMAD at all then?
> D50804 fixed the sdag implementation for fadd/fmul etc but apparently not for fma/fmad :(
Can you fix the DAG version? Plus this should be its own patch with its own testing


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D134354/new/

https://reviews.llvm.org/D134354