[llvm] [LV] Use wide lane masks as the canonical form when tail-folding & interleaving (PR #209484)

[Benjamin Maxwell via llvm-commits]

================
@@ -1104,6 +1105,33 @@ Value *VPInstruction::generate(VPTransformState &State) {
 
     return Result;
   }
+  case VPInstruction::ExtractSubvectorForPart: {
+    Type *DstTy = VectorType::get(getScalarType(), State.VF);
+    unsigned Part = cast<VPConstantInt>(getOperand(1))->getZExtValue();
+
+    // Return Src if it's an ActiveLaneMask with a multiplier of 1.
+    Value *Src = State.get(getOperand(0));
+    if (Part == 0 && match(getOperand(0),
+                           m_ActiveLaneMask(m_VPValue(), m_VPValue(), m_One())))
+      return Src;
+
+    // If the VF is scalar & this is an extract of an active lane mask,
+    // generate an ICMP directly.
+    VPValue *Start, *TC;
+    if (State.VF.isScalar() &&
+        match(getOperand(0),
+              m_ActiveLaneMask(m_VPValue(Start), m_VPValue(TC), m_VPValue()))) {
+      Value *StartV = State.get(Start);
+      if (Part > 0)
+        StartV = Builder.CreateAdd(State.get(Start), State.get(getOperand(1)));
----------------
MacDue wrote:

nit:
```suggestion
      Value *StartV = State.get(Start);
      if (Part > 0)
        StartV = Builder.CreateAdd(StartV, State.get(getOperand(1)));
```

https://github.com/llvm/llvm-project/pull/209484