[VectorCombine] Handle shuffle of selects

(shuffle(select(c1,t1,f1)), (select(c2,t2,f2)), m)
-> (select (shuffle c1,c2,m), (shuffle t1,t2,m), (shuffle f1,f2,m))

The behaviour of SelectInst on vectors is the same as for
`V'select[i] = Condition[i] ? V'True[i] : V'False[i]`.

If a ShuffleVector is performed on two selects, it will be like:
`V'[mask] = (V'select[i] = Condition[i] ? V'True[i] : V'False[i])`

That's why a ShuffleVector with two SelectInst is equivalent to
first ShuffleVector Condition/True/False and then SelectInst that
result.

This patch implements the transforming described above.

Proof: https://alive2.llvm.org/ce/z/97wfHp
Fixed: #120775

Author: ParkHanbum

llvm/lib/Transforms/Vectorize/VectorCombine.cpp

@@ -119,6 +119,7 @@ class VectorCombine {
   bool foldConcatOfBoolMasks(Instruction &I);
   bool foldPermuteOfBinops(Instruction &I);
   bool foldShuffleOfBinops(Instruction &I);
+  bool foldShuffleOfSelects(Instruction &I);
   bool foldShuffleOfCastops(Instruction &I);
   bool foldShuffleOfShuffles(Instruction &I);
   bool foldShuffleOfIntrinsics(Instruction &I);
@@ -1899,6 +1900,56 @@ bool VectorCombine::foldShuffleOfBinops(Instruction &I) {
   return true;
 }
 
+/// Try to convert,
+/// (shuffle(select(c1,t1,f1)), (select(c2,t2,f2)), m) into
+/// (select (shuffle c1,c2,m), (shuffle t1,t2,m), (shuffle f1,f2,m))
+bool VectorCombine::foldShuffleOfSelects(Instruction &I) {
+  ArrayRef<int> Mask;
+  Value *C1, *T1, *F1, *C2, *T2, *F2;
+  if (!match(&I, m_Shuffle(
+                     m_OneUse(m_Select(m_Value(C1), m_Value(T1), m_Value(F1))),
+                     m_OneUse(m_Select(m_Value(C2), m_Value(T2), m_Value(F2))),
+                     m_Mask(Mask))))
+    return false;
+
+  auto *DstVecTy = dyn_cast<FixedVectorType>(I.getType());
+  auto *C1VecTy = dyn_cast<FixedVectorType>(C1->getType());
+  auto *C2VecTy = dyn_cast<FixedVectorType>(C2->getType());
+  if (!C1VecTy || !C2VecTy)
+    return false;
+
+  auto SK = TargetTransformInfo::SK_PermuteTwoSrc;
+  auto SelOp = Instruction::Select;
+  InstructionCost OldCost = TTI.getCmpSelInstrCost(
+      SelOp, T1->getType(), C1VecTy, CmpInst::BAD_ICMP_PREDICATE, CostKind);
+  OldCost += TTI.getCmpSelInstrCost(SelOp, T2->getType(), C2VecTy,
+                                    CmpInst::BAD_ICMP_PREDICATE, CostKind);
+  OldCost += TTI.getShuffleCost(SK, DstVecTy, Mask, CostKind, 0, nullptr,
+                                {I.getOperand(0), I.getOperand(1)}, &I);
+
+  auto *C1C2VecTy = cast<FixedVectorType>(
+      toVectorTy(Type::getInt1Ty(I.getContext()), DstVecTy->getNumElements()));
+  InstructionCost NewCost =
+      TTI.getShuffleCost(SK, C1C2VecTy, Mask, CostKind, 0, nullptr, {C1, C2});
+  NewCost +=
+      TTI.getShuffleCost(SK, DstVecTy, Mask, CostKind, 0, nullptr, {T1, T2});
+  NewCost +=
+      TTI.getShuffleCost(SK, DstVecTy, Mask, CostKind, 0, nullptr, {F1, F2});
+  NewCost += TTI.getCmpSelInstrCost(SelOp, DstVecTy, DstVecTy,
+                                    CmpInst::BAD_ICMP_PREDICATE, CostKind);
+
+  if (NewCost > OldCost)
+    return false;
+
+  Value *ShuffleCmp = Builder.CreateShuffleVector(C1, C2, Mask);
+  Value *ShuffleTrue = Builder.CreateShuffleVector(T1, T2, Mask);
+  Value *ShuffleFalse = Builder.CreateShuffleVector(F1, F2, Mask);
+  Value *NewSel = Builder.CreateSelect(ShuffleCmp, ShuffleTrue, ShuffleFalse);
+
+  replaceValue(I, *NewSel);
+  return true;
+}
+
 /// Try to convert "shuffle (castop), (castop)" with a shared castop operand
 /// into "castop (shuffle)".
 bool VectorCombine::foldShuffleOfCastops(Instruction &I) {
@@ -3352,6 +3403,7 @@ bool VectorCombine::run() {
       case Instruction::ShuffleVector:
         MadeChange |= foldPermuteOfBinops(I);
         MadeChange |= foldShuffleOfBinops(I);
+        MadeChange |= foldShuffleOfSelects(I);
         MadeChange |= foldShuffleOfCastops(I);
         MadeChange |= foldShuffleOfShuffles(I);
         MadeChange |= foldShuffleOfIntrinsics(I);