[llvm] [VPlan] Explicitly handle scalar pointer inductions. (PR #83068)

[Florian Hahn via llvm-commits]

================
@@ -270,10 +271,47 @@ VPInstruction::VPInstruction(unsigned Opcode,
   assert(isFPMathOp() && "this op can't take fast-math flags");
 }
 
-Value *VPInstruction::generateInstruction(VPTransformState &State,
-                                          unsigned Part) {
+bool VPInstruction::doesGeneratePerAllLanes() const {
+  return Opcode == VPInstruction::PtrAdd && !vputils::onlyFirstLaneUsed(this);
+}
+
+bool VPInstruction::canGenerateScalarForFirstLane() const {
+  if (Instruction::isBinaryOp(getOpcode()))
+    return true;
+
+  switch (Opcode) {
+  case VPInstruction::BranchOnCond:
+  case VPInstruction::BranchOnCount:
+  case VPInstruction::CalculateTripCountMinusVF:
+  case VPInstruction::CanonicalIVIncrementForPart:
+  case VPInstruction::ComputeReductionResult:
+  case VPInstruction::PtrAdd:
+    return true;
+  default:
+    return false;
+  }
+}
+
+Value *VPInstruction::generatePerLane(VPTransformState &State,
+                                      const VPIteration &Lane) {
+  IRBuilderBase &Builder = State.Builder;
+
+  switch (getOpcode()) {
+  case VPInstruction::PtrAdd: {
+    auto *P = Builder.CreatePtrAdd(State.get(getOperand(0), Lane),
+                                   State.get(getOperand(1), Lane), Name);
+    return P;
+  }
+  default: {
+    Value *Res = generatePerPart(State, Lane.Part);
----------------
fhahn wrote:

This is a consequence of `generatePerLane` being responsible to generate all lanes and/or the first lane, while `generatePerPart` can either generate the vector or scalar per-part, but would need to also support PtrAdd. It seems clearer to flip around the delegation and have generatePerPart call generatePerLane for PtrAdd. Updated.

https://github.com/llvm/llvm-project/pull/83068