[VPlan] Add opcode to create step for wide inductions.

This patch adds a WideIVStep opcode that can be used to create a vector
with the steps to increment a wide induction. The opcode has 3 operands
* the vector step
* the scale of the vector step
* a constant indicating the target type of the VPInstruction (this is
  working around having explicit types for VPInstructions, we could also
  introduce a dedicated recipe, at the cost of a lot more scaffolding)

The opcode is later converted into a sequence of recipes that convert
the scale and step to the target type, if needed, and then multiply
vector step by scale.

This simplifies code that needs to materialize step vectors, e.g.
replacing wide IVs as follow up to
llvm#108378 with an increment of
the wide IV step.

Author: fhahn

llvm/lib/Transforms/Vectorize/VPlan.h

@@ -1213,6 +1213,7 @@ class VPInstruction : public VPRecipeWithIRFlags,
     CalculateTripCountMinusVF,
     // Increment the canonical IV separately for each unrolled part.
     CanonicalIVIncrementForPart,
+    WideIVStep,
     BranchOnCount,
     BranchOnCond,
     ComputeReductionResult,

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -719,7 +719,8 @@ bool VPInstruction::isFPMathOp() const {
   return Opcode == Instruction::FAdd || Opcode == Instruction::FMul ||
          Opcode == Instruction::FNeg || Opcode == Instruction::FSub ||
          Opcode == Instruction::FDiv || Opcode == Instruction::FRem ||
-         Opcode == Instruction::FCmp || Opcode == Instruction::Select;
+         Opcode == Instruction::FCmp || Opcode == Instruction::Select ||
+         Opcode == VPInstruction::WideIVStep;
 }
 #endif
 

llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp

@@ -2051,20 +2051,61 @@ void VPlanTransforms::createInterleaveGroups(
 }
 
 void VPlanTransforms::convertToConcreteRecipes(VPlan &Plan) {
+  Type *CanonicalIVType = Plan.getCanonicalIV()->getScalarType();
+  VPTypeAnalysis TypeInfo(CanonicalIVType);
+
   for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(
            vp_depth_first_deep(Plan.getEntry()))) {
-    for (VPRecipeBase &R : make_early_inc_range(VPBB->phis())) {
-      if (!isa<VPCanonicalIVPHIRecipe, VPEVLBasedIVPHIRecipe>(&R))
+    for (VPRecipeBase &R : make_early_inc_range(*VPBB)) {
+      if (isa<VPCanonicalIVPHIRecipe, VPEVLBasedIVPHIRecipe>(&R)) {
+        auto *PhiR = cast<VPHeaderPHIRecipe>(&R);
+        StringRef Name =
+            isa<VPCanonicalIVPHIRecipe>(PhiR) ? "index" : "evl.based.iv";
+        auto *ScalarR = new VPScalarPHIRecipe(PhiR->getStartValue(),
+                                              PhiR->getBackedgeValue(),
+                                              PhiR->getDebugLoc(), Name);
+        ScalarR->insertBefore(PhiR);
+        PhiR->replaceAllUsesWith(ScalarR);
+        PhiR->eraseFromParent();
         continue;
-      auto *PhiR = cast<VPHeaderPHIRecipe>(&R);
-      StringRef Name =
-          isa<VPCanonicalIVPHIRecipe>(PhiR) ? "index" : "evl.based.iv";
-      auto *ScalarR =
-          new VPScalarPHIRecipe(PhiR->getStartValue(), PhiR->getBackedgeValue(),
-                                PhiR->getDebugLoc(), Name);
-      ScalarR->insertBefore(PhiR);
-      PhiR->replaceAllUsesWith(ScalarR);
-      PhiR->eraseFromParent();
+      }
+
+      auto *VPI = dyn_cast<VPInstruction>(&R);
+      if (VPI && VPI->getOpcode() == VPInstruction::WideIVStep) {
+        VPBuilder Builder(VPI->getParent(), VPI->getIterator());
+        VPValue *VectorStep = VPI->getOperand(0);
+        Type *IVTy = TypeInfo.inferScalarType(VPI->getOperand(2));
+        if (TypeInfo.inferScalarType(VectorStep) != IVTy) {
+          Instruction::CastOps CastOp = IVTy->isFloatingPointTy()
+                                            ? Instruction::UIToFP
+                                            : Instruction::Trunc;
+          VectorStep = Builder.createWidenCast(CastOp, VectorStep, IVTy);
+        }
+
+        VPValue *ScalarStep = VPI->getOperand(1);
+        auto *ConstStep =
+            ScalarStep->isLiveIn()
+                ? dyn_cast<ConstantInt>(ScalarStep->getLiveInIRValue())
+                : nullptr;
+        if (!ConstStep || ConstStep->getValue() != 1) {
+          if (TypeInfo.inferScalarType(ScalarStep) != IVTy) {
+            ScalarStep =
+                Builder.createWidenCast(Instruction::Trunc, ScalarStep, IVTy);
+          }
+
+          std::optional<FastMathFlags> FMFs;
+          if (IVTy->isFloatingPointTy())
+            FMFs = VPI->getFastMathFlags();
+
+          unsigned MulOpc =
+              IVTy->isFloatingPointTy() ? Instruction::FMul : Instruction::Mul;
+          VPInstruction *Mul = Builder.createNaryOp(
+              MulOpc, {VectorStep, ScalarStep}, FMFs, R.getDebugLoc());
+          VectorStep = Mul;
+        }
+        VPI->replaceAllUsesWith(VectorStep);
+        VPI->eraseFromParent();
+      }
     }
   }
 }

llvm/lib/Transforms/Vectorize/VPlanUnroll.cpp

@@ -155,33 +155,15 @@ void UnrollState::unrollWidenInductionByUF(
   if (isa_and_present<FPMathOperator>(ID.getInductionBinOp()))
     FMFs = ID.getInductionBinOp()->getFastMathFlags();
 
-  VPValue *VectorStep = &Plan.getVF();
-  VPBuilder Builder(PH);
-  if (TypeInfo.inferScalarType(VectorStep) != IVTy) {
-    Instruction::CastOps CastOp =
-        IVTy->isFloatingPointTy() ? Instruction::UIToFP : Instruction::Trunc;
-    VectorStep = Builder.createWidenCast(CastOp, VectorStep, IVTy);
-    ToSkip.insert(VectorStep->getDefiningRecipe());
-  }
-
   VPValue *ScalarStep = IV->getStepValue();
-  auto *ConstStep = ScalarStep->isLiveIn()
-                        ? dyn_cast<ConstantInt>(ScalarStep->getLiveInIRValue())
-                        : nullptr;
-  if (!ConstStep || ConstStep->getValue() != 1) {
-    if (TypeInfo.inferScalarType(ScalarStep) != IVTy) {
-      ScalarStep =
-          Builder.createWidenCast(Instruction::Trunc, ScalarStep, IVTy);
-      ToSkip.insert(ScalarStep->getDefiningRecipe());
-    }
+  VPBuilder Builder(PH);
+  VPInstruction *VectorStep =
+      Builder.createNaryOp(VPInstruction::WideIVStep,
+                           {&Plan.getVF(), ScalarStep,
+                            Plan.getOrAddLiveIn(Constant::getNullValue(IVTy))},
+                           FMFs, IV->getDebugLoc());
 
-    unsigned MulOpc =
-        IVTy->isFloatingPointTy() ? Instruction::FMul : Instruction::Mul;
-    VPInstruction *Mul = Builder.createNaryOp(MulOpc, {VectorStep, ScalarStep},
-                                              FMFs, IV->getDebugLoc());
-    VectorStep = Mul;
-    ToSkip.insert(Mul);
-  }
+  ToSkip.insert(VectorStep);
 
   // Now create recipes to compute the induction steps for part 1 .. UF. Part 0
   // remains the header phi. Parts > 0 are computed by adding Step to the