[SelectionDAG][x86] turn insertelement into undef with variable index into splat

I noticed this along with the patterns in D51125, but when the index is variable, 
we don't convert insertelement into a build_vector.

For x86, that means these get expanded at legalization time into the loading/spilling 
code that we see in the tests. I think it's always better to avoid going to memory on 
these, and we get the optimal 'broadcast' if it's available.

I suspect other targets may want to look at enabling the hook. AArch64 and AMDGPU have 
regression tests that would be affected (although I did not check what would happen in 
those cases). In the most basic cases shown here, AArch64 would probably do much 
better with a splat.

Differential Revision: https://reviews.llvm.org/D51186

llvm-svn: 340705

1 files changed, 10 insertions, 3 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 3df040459ed..d894d8d5530 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -15045,12 +15045,19 @@ SDValue DAGCombiner::visitINSERT_VECTOR_ELT(SDNode *N) {
       InVec == InVal.getOperand(0) && EltNo == InVal.getOperand(1))
     return InVec;
 
-  // We must know which element is being inserted for folds below here.
   auto *IndexC = dyn_cast<ConstantSDNode>(EltNo);
-  if (!IndexC)
+  if (!IndexC) {
+    // If this is variable insert to undef vector, it might be better to splat:
+    // inselt undef, InVal, EltNo --> build_vector < InVal, InVal, ... >
+    if (InVec.isUndef() && TLI.shouldSplatInsEltVarIndex(VT)) {
+      SmallVector<SDValue, 8> Ops(VT.getVectorNumElements(), InVal);
+      return DAG.getBuildVector(VT, DL, Ops);
+    }
     return SDValue();
-  unsigned Elt = IndexC->getZExtValue();
+  }
 
+  // We must know which element is being inserted for folds below here.
+  unsigned Elt = IndexC->getZExtValue();
   if (SDValue Shuf = combineInsertEltToShuffle(N, Elt))
     return Shuf;