[VPlan] Handle early exit before forming regions. (NFC)

Move early-exit handling up front to original VPlan construction, before
introducing early exits.

This builds on llvm#137709, which
adds exiting edges to the original VPlan, instead of adding exit blocks
later.

This retains the exit conditions early, and means we can handle early
exits before forming regions, without the reliance on VPRecipeBuilder.

Once we retain all exits initially, handling early exits before region
construction ensures the regions are valid; otherwise we would leave
edges exiting the region from elsewhere than the latch.

Removing the reliance on VPRecipeBuilder removes the dependence on
mapping IR BBs to VPBBs and unblocks predication as VPlan transform:
llvm#128420.

Depends on llvm#137709.

Author: fhahn

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -9366,7 +9366,8 @@ LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(VFRange &Range) {
   VPlanTransforms::prepareForVectorization(
       *Plan, Legal->getWidestInductionType(), PSE, RequiresScalarEpilogueCheck,
       CM.foldTailByMasking(), OrigLoop,
-      getDebugLocFromInstOrOperands(Legal->getPrimaryInduction()));
+      getDebugLocFromInstOrOperands(Legal->getPrimaryInduction()),
+      Legal->hasUncountableEarlyExit(), Range);
   VPlanTransforms::createLoopRegions(*Plan);
 
   // Don't use getDecisionAndClampRange here, because we don't know the UF
@@ -9564,12 +9565,6 @@ LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(VFRange &Range) {
     R->setOperand(1, WideIV->getStepValue());
   }
 
-  if (auto *UncountableExitingBlock =
-          Legal->getUncountableEarlyExitingBlock()) {
-    VPlanTransforms::runPass(VPlanTransforms::handleUncountableEarlyExit, *Plan,
-                             OrigLoop, UncountableExitingBlock, RecipeBuilder,
-                             Range);
-  }
   DenseMap<VPValue *, VPValue *> IVEndValues;
   addScalarResumePhis(RecipeBuilder, *Plan, IVEndValues);
   SetVector<VPIRInstruction *> ExitUsersToFix =
@@ -9667,7 +9662,8 @@ VPlanPtr LoopVectorizationPlanner::tryToBuildVPlan(VFRange &Range) {
   auto Plan = VPlanTransforms::buildPlainCFG(OrigLoop, *LI, VPB2IRBB);
   VPlanTransforms::prepareForVectorization(
       *Plan, Legal->getWidestInductionType(), PSE, true, false, OrigLoop,
-      getDebugLocFromInstOrOperands(Legal->getPrimaryInduction()));
+      getDebugLocFromInstOrOperands(Legal->getPrimaryInduction()), false,
+      Range);
   VPlanTransforms::createLoopRegions(*Plan);
 
   for (ElementCount VF : Range)

llvm/lib/Transforms/Vectorize/VPlanConstruction.cpp

@@ -474,11 +474,10 @@ static void addCanonicalIVRecipes(VPlan &Plan, VPBasicBlock *HeaderVPBB,
                        {CanonicalIVIncrement, &Plan.getVectorTripCount()}, DL);
 }
 
-void VPlanTransforms::prepareForVectorization(VPlan &Plan, Type *InductionTy,
-                                              PredicatedScalarEvolution &PSE,
-                                              bool RequiresScalarEpilogueCheck,
-                                              bool TailFolded, Loop *TheLoop,
-                                              DebugLoc IVDL) {
+void VPlanTransforms::prepareForVectorization(
+    VPlan &Plan, Type *InductionTy, PredicatedScalarEvolution &PSE,
+    bool RequiresScalarEpilogueCheck, bool TailFolded, Loop *TheLoop,
+    DebugLoc IVDL, bool HandleUncountableExit, VFRange &Range) {
   VPDominatorTree VPDT;
   VPDT.recalculate(Plan);
 
@@ -505,15 +504,18 @@ void VPlanTransforms::prepareForVectorization(VPlan &Plan, Type *InductionTy,
 
   addCanonicalIVRecipes(Plan, cast<VPBasicBlock>(HeaderVPB),
                         cast<VPBasicBlock>(LatchVPB), InductionTy, IVDL);
-
-  // Disconnect all edges between exit blocks other than from the latch.
-  // TODO: Uncountable exit blocks should be handled here.
-  for (VPBlockBase *EB : to_vector(Plan.getExitBlocks())) {
-    for (VPBlockBase *Pred : to_vector(EB->getPredecessors())) {
-      if (Pred == MiddleVPBB)
-        continue;
-      cast<VPBasicBlock>(Pred)->getTerminator()->eraseFromParent();
-      VPBlockUtils::disconnectBlocks(Pred, EB);
+  if (HandleUncountableExit) {
+    handleUncountableEarlyExit(Plan, cast<VPBasicBlock>(HeaderVPB),
+                               cast<VPBasicBlock>(LatchVPB), Range);
+  } else {
+    // Disconnect all edges between exit blocks other than from the latch.
+    for (VPBlockBase *EB : to_vector(Plan.getExitBlocks())) {
+      for (VPBlockBase *Pred : to_vector(EB->getPredecessors())) {
+        if (Pred == MiddleVPBB)
+          continue;
+        cast<VPBasicBlock>(Pred)->getTerminator()->eraseFromParent();
+        VPBlockUtils::disconnectBlocks(Pred, EB);
+      }
     }
   }
 

llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp

@@ -2488,64 +2488,75 @@ void VPlanTransforms::convertToConcreteRecipes(VPlan &Plan,
     R->eraseFromParent();
 }
 
-void VPlanTransforms::handleUncountableEarlyExit(
-    VPlan &Plan, Loop *OrigLoop, BasicBlock *UncountableExitingBlock,
-    VPRecipeBuilder &RecipeBuilder, VFRange &Range) {
-  VPRegionBlock *LoopRegion = Plan.getVectorLoopRegion();
-  auto *LatchVPBB = cast<VPBasicBlock>(LoopRegion->getExiting());
+void VPlanTransforms::handleUncountableEarlyExit(VPlan &Plan,
+                                                 VPBasicBlock *HeaderVPBB,
+                                                 VPBasicBlock *LatchVPBB,
+                                                 VFRange &Range) {
+  // First find the uncountable early exiting block by looking at the
+  // predecessors of the exit blocks.
+  VPBlockBase *MiddleVPBB = LatchVPBB->getSuccessors()[0];
+  VPBasicBlock *EarlyExitingVPBB = nullptr;
+  VPIRBasicBlock *EarlyExitVPBB = nullptr;
+  for (auto *EB : Plan.getExitBlocks()) {
+    for (VPBlockBase *Pred : EB->getPredecessors()) {
+      if (Pred != MiddleVPBB) {
+        EarlyExitingVPBB = cast<VPBasicBlock>(Pred);
+        EarlyExitVPBB = EB;
+        break;
+      }
+    }
+  }
+
   VPBuilder Builder(LatchVPBB->getTerminator());
-  auto *MiddleVPBB = Plan.getMiddleBlock();
-  VPValue *IsEarlyExitTaken = nullptr;
-
-  // Process the uncountable exiting block. Update IsEarlyExitTaken, which
-  // tracks if the uncountable early exit has been taken. Also split the middle
-  // block and have it conditionally branch to the early exit block if
-  // EarlyExitTaken.
-  auto *EarlyExitingBranch =
-      cast<BranchInst>(UncountableExitingBlock->getTerminator());
-  BasicBlock *TrueSucc = EarlyExitingBranch->getSuccessor(0);
-  BasicBlock *FalseSucc = EarlyExitingBranch->getSuccessor(1);
-  BasicBlock *EarlyExitIRBB =
-      !OrigLoop->contains(TrueSucc) ? TrueSucc : FalseSucc;
-  VPIRBasicBlock *VPEarlyExitBlock = Plan.getExitBlock(EarlyExitIRBB);
-
-  VPValue *EarlyExitNotTakenCond = RecipeBuilder.getBlockInMask(
-      OrigLoop->contains(TrueSucc) ? TrueSucc : FalseSucc);
-  auto *EarlyExitTakenCond = Builder.createNot(EarlyExitNotTakenCond);
-  IsEarlyExitTaken =
-      Builder.createNaryOp(VPInstruction::AnyOf, {EarlyExitTakenCond});
+  VPBlockBase *TrueSucc = EarlyExitingVPBB->getSuccessors()[0];
+  VPValue *EarlyExitCond = EarlyExitingVPBB->getTerminator()->getOperand(0);
+  auto *EarlyExitTakenCond = TrueSucc == EarlyExitVPBB
+                                 ? EarlyExitCond
+                                 : Builder.createNot(EarlyExitCond);
+
+  if (!EarlyExitVPBB->getSinglePredecessor() &&
+      EarlyExitVPBB->getPredecessors()[0] != MiddleVPBB) {
+    for (VPRecipeBase &R : EarlyExitVPBB->phis()) {
+      // Early exit operand should always be last, i.e., 0 if EarlyExitVPBB has
+      // a single predecessor and 1 if it has two.
+      // If EarlyExitVPBB has two predecessors, they are already ordered such
+      // that early exit is second (and latch exit is first), by construction.
+      // But its underlying IRBB (EarlyExitIRBB) may have its predecessors
+      // ordered the other way around, and it is the order of the latter which
+      // corresponds to the order of operands of EarlyExitVPBB's phi recipes.
+      // Therefore, if early exit (UncountableExitingBlock) is the first
+      // predecessor of EarlyExitIRBB, we swap the operands of phi recipes,
+      // thereby bringing them to match EarlyExitVPBB's predecessor order,
+      // with early exit being last (second). Otherwise they already match.
+      cast<VPIRPhi>(&R)->swapOperands();
+    }
+  }
 
+  EarlyExitingVPBB->getTerminator()->eraseFromParent();
+  VPBlockUtils::disconnectBlocks(EarlyExitingVPBB, EarlyExitVPBB);
+
+  // Split the middle block and have it conditionally branch to the early exit
+  // block if EarlyExitTaken.
+  VPValue *IsEarlyExitTaken =
+      Builder.createNaryOp(VPInstruction::AnyOf, {EarlyExitTakenCond});
   VPBasicBlock *NewMiddle = Plan.createVPBasicBlock("middle.split");
   VPBasicBlock *VectorEarlyExitVPBB =
       Plan.createVPBasicBlock("vector.early.exit");
-  VPBlockUtils::insertOnEdge(LoopRegion, MiddleVPBB, NewMiddle);
+  VPBlockUtils::insertOnEdge(LatchVPBB, MiddleVPBB, NewMiddle);
   VPBlockUtils::connectBlocks(NewMiddle, VectorEarlyExitVPBB);
   NewMiddle->swapSuccessors();
 
-  VPBlockUtils::connectBlocks(VectorEarlyExitVPBB, VPEarlyExitBlock);
+  VPBlockUtils::connectBlocks(VectorEarlyExitVPBB, EarlyExitVPBB);
 
   // Update the exit phis in the early exit block.
   VPBuilder MiddleBuilder(NewMiddle);
   VPBuilder EarlyExitB(VectorEarlyExitVPBB);
-  for (VPRecipeBase &R : VPEarlyExitBlock->phis()) {
+  for (VPRecipeBase &R : EarlyExitVPBB->phis()) {
     auto *ExitIRI = cast<VPIRPhi>(&R);
-    // Early exit operand should always be last, i.e., 0 if VPEarlyExitBlock has
+    // Early exit operand should always be last, i.e., 0 if EarlyExitVPBB has
     // a single predecessor and 1 if it has two.
     unsigned EarlyExitIdx = ExitIRI->getNumOperands() - 1;
-    if (!VPEarlyExitBlock->getSinglePredecessor()) {
-      // If VPEarlyExitBlock has two predecessors, they are already ordered such
-      // that early exit is second (and latch exit is first), by construction.
-      // But its underlying IRBB (EarlyExitIRBB) may have its predecessors
-      // ordered the other way around, and it is the order of the latter which
-      // corresponds to the order of operands of VPEarlyExitBlock's phi recipes.
-      // Therefore, if early exit (UncountableExitingBlock) is the first
-      // predecessor of EarlyExitIRBB, we swap the operands of phi recipes,
-      // thereby bringing them to match VPEarlyExitBlock's predecessor order,
-      // with early exit being last (second). Otherwise they already match.
-      if (*pred_begin(VPEarlyExitBlock->getIRBasicBlock()) ==
-          UncountableExitingBlock)
-        ExitIRI->swapOperands();
-
+    if (!EarlyExitVPBB->getSinglePredecessor()) {
       // The first of two operands corresponds to the latch exit, via MiddleVPBB
       // predecessor. Extract its last lane.
       ExitIRI->extractLastLaneOfFirstOperand(MiddleBuilder);

llvm/lib/Transforms/Vectorize/VPlanTransforms.h

@@ -69,7 +69,8 @@ struct VPlanTransforms {
                                       PredicatedScalarEvolution &PSE,
                                       bool RequiresScalarEpilogueCheck,
                                       bool TailFolded, Loop *TheLoop,
-                                      DebugLoc IVDL);
+                                      DebugLoc IVDL, bool HandleUncountableExit,
+                                      VFRange &Range);
 
   /// Replace loops in \p Plan's flat CFG with VPRegionBlocks, turning \p Plan's
   /// flat CFG into a hierarchical CFG.
@@ -179,9 +180,8 @@ struct VPlanTransforms {
   ///    exit conditions
   ///  * splitting the original middle block to branch to the early exit block
   ///    if taken.
-  static void handleUncountableEarlyExit(VPlan &Plan, Loop *OrigLoop,
-                                         BasicBlock *UncountableExitingBlock,
-                                         VPRecipeBuilder &RecipeBuilder,
+  static void handleUncountableEarlyExit(VPlan &Plan, VPBasicBlock *HeaderVPBB,
+                                         VPBasicBlock *LatchVPBB,
                                          VFRange &Range);
 
   /// Lower abstract recipes to concrete ones, that can be codegen'd. Use \p

llvm/unittests/Transforms/Vectorize/VPlanTestBase.h

@@ -13,6 +13,7 @@
 #define LLVM_UNITTESTS_TRANSFORMS_VECTORIZE_VPLANTESTBASE_H
 
 #include "../lib/Transforms/Vectorize/VPlan.h"
+#include "../lib/Transforms/Vectorize/VPlanHelpers.h"
 #include "../lib/Transforms/Vectorize/VPlanTransforms.h"
 #include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/BasicAliasAnalysis.h"
@@ -72,8 +73,9 @@ class VPlanTestIRBase : public testing::Test {
     PredicatedScalarEvolution PSE(*SE, *L);
     DenseMap<VPBlockBase *, BasicBlock *> VPB2IRBB;
     auto Plan = VPlanTransforms::buildPlainCFG(L, *LI, VPB2IRBB);
+    VFRange R(ElementCount::getFixed(1), ElementCount::getFixed(2));
     VPlanTransforms::prepareForVectorization(*Plan, IntegerType::get(*Ctx, 64),
-                                             PSE, true, false, L, {});
+                                             PSE, true, false, L, {}, false, R);
     VPlanTransforms::createLoopRegions(*Plan);
     return Plan;
   }