[PATCH] D49248: [TargetLowering] Add support for non-uniform vectors to BuildUDIV

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added inline comments.


================
Comment at: lib/CodeGen/SelectionDAG/TargetLowering.cpp:3567
+    if (VT.isVector()) {
+      Q = DAG.getVectorShuffle(VT, dl, Q, NPQ, ShuffleMask);
+      Created->push_back(Q.getNode());
----------------
RKSimon wrote:
> RKSimon wrote:
> > efriedma wrote:
> > > I'm pretty sure this isn't the most efficient way to handle this case.  Would it be more efficient to use a variable-amount shift to compute NPQ, rather than shuffle afterwards?  Or is it possible to fudge the magic number to avoid the blend?
> > > 
> > > Please make sure you have test coverage for both UseNPQ=true and UseNPQ=false.
> > We do have full coverage for scalars and uniform vectors only - I'll try to add all the necessary non-uniform cases as well.
> Tests now ensure we have vector cases with all/none/some NPQ path
> I'm pretty sure this isn't the most efficient way to handle this case. Would it be more efficient to use a variable amount shift to compute NPQ, rather than shuffle afterwards? Or is it possible to fudge the magic number to avoid the blend?

@efriedma  I haven't found anything that works any better then the current shuffle - the additional SUB and ADD seem to get in the way - do you have a codegen example of what you have in mind?



Repository:
  rL LLVM

https://reviews.llvm.org/D49248