[VPlan] Refactor VPlan creation, add transform introducing region (NFC).

fhahn · fhahn · commit 4a3ec7486131 · 2025-02-26T11:56:02.000Z
Create an empty VPlan first, then let the HCFG builder create a plain CFG for the top-level loop (w/o a top-level region). The top-level region is introduced by a separate VPlan-transform. This is instead of creating the vector loop region before building the VPlan CFG for the input loop. This simplifies the HCFG builder (which should probably be renamed) and moves along the roadmap ('buildLoop') outlined in [1]. As follow-up, I plan to also preserve the exit branches in the initial VPlan out of the CFG builder, including connections to the exit blocks. The conversion from plain CFG with potentially multiple exits to a single entry/exit region will be done as VPlan transform in a follow-up. This is needed to enable VPlan-based predication. Currently early exit support relies on building the block-in masks on the original CFG, because exiting branches and conditions aren't preserved in the VPlan. So in order to switch to VPlan-based predication, we will have to preserve them in the initial plain CFG, so the exit conditions are available explicitly when we convert to single entry/exit regions. Another follow-up is updating the outer loop handling to also introduce VPRegionBlocks for nested loops as transform. Currently the existing logic in the builder will take care of creating VPRegionBlocks for nested loops, but not the top-level loop. [1] https://llvm.org/devmtg/2023-10/slides/techtalks/Hahn-VPlan-StatusUpdateAndRoadmap.pdf
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -9312,14 +9312,15 @@ LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(VFRange &Range) {
             return !CM.requiresScalarEpilogue(VF.isVector());
           },
           Range);
-  VPlanPtr Plan = VPlan::createInitialVPlan(Legal->getWidestInductionType(),
-                                            PSE, RequiresScalarEpilogueCheck,
-                                            CM.foldTailByMasking(), OrigLoop);
-
+  auto Plan = std::make_unique<VPlan>(OrigLoop);
   // Build hierarchical CFG.
   VPlanHCFGBuilder HCFGBuilder(OrigLoop, LI, *Plan);
   HCFGBuilder.buildHierarchicalCFG();
 
+  VPlanTransforms::introduceTopLevelVectorLoopRegion(
+      *Plan, Legal->getWidestInductionType(), PSE, RequiresScalarEpilogueCheck,
+      CM.foldTailByMasking(), OrigLoop);
+
   // Don't use getDecisionAndClampRange here, because we don't know the UF
   // so this function is better to be conservative, rather than to split
   // it up into different VPlans.
@@ -9615,13 +9616,14 @@ VPlanPtr LoopVectorizationPlanner::buildVPlan(VFRange &Range) {
   assert(EnableVPlanNativePath && "VPlan-native path is not enabled.");
 
   // Create new empty VPlan
-  auto Plan = VPlan::createInitialVPlan(Legal->getWidestInductionType(), PSE,
-                                        true, false, OrigLoop);
-
+  auto Plan = std::make_unique<VPlan>(OrigLoop);
   // Build hierarchical CFG
   VPlanHCFGBuilder HCFGBuilder(OrigLoop, LI, *Plan);
   HCFGBuilder.buildHierarchicalCFG();
 
+  VPlanTransforms::introduceTopLevelVectorLoopRegion(
+      *Plan, Legal->getWidestInductionType(), PSE, true, false, OrigLoop);
+
   for (ElementCount VF : Range)
     Plan->addVF(VF);
 
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.cpp b/llvm/lib/Transforms/Vectorize/VPlan.cpp
@@ -880,85 +880,6 @@ VPlan::~VPlan() {
     delete BackedgeTakenCount;
 }
 
-VPlanPtr VPlan::createInitialVPlan(Type *InductionTy,
-                                   PredicatedScalarEvolution &PSE,
-                                   bool RequiresScalarEpilogueCheck,
-                                   bool TailFolded, Loop *TheLoop) {
-  auto Plan = std::make_unique<VPlan>(TheLoop);
-  VPBlockBase *ScalarHeader = Plan->getScalarHeader();
-
-  // Connect entry only to vector preheader initially. Entry will also be
-  // connected to the scalar preheader later, during skeleton creation when
-  // runtime guards are added as needed. Note that when executing the VPlan for
-  // an epilogue vector loop, the original entry block here will be replaced by
-  // a new VPIRBasicBlock wrapping the entry to the epilogue vector loop after
-  // generating code for the main vector loop.
-  VPBasicBlock *VecPreheader = Plan->createVPBasicBlock("vector.ph");
-  VPBlockUtils::connectBlocks(Plan->getEntry(), VecPreheader);
-
-  // Create SCEV and VPValue for the trip count.
-  // We use the symbolic max backedge-taken-count, which works also when
-  // vectorizing loops with uncountable early exits.
-  const SCEV *BackedgeTakenCountSCEV = PSE.getSymbolicMaxBackedgeTakenCount();
-  assert(!isa<SCEVCouldNotCompute>(BackedgeTakenCountSCEV) &&
-         "Invalid loop count");
-  ScalarEvolution &SE = *PSE.getSE();
-  const SCEV *TripCount = SE.getTripCountFromExitCount(BackedgeTakenCountSCEV,
-                                                       InductionTy, TheLoop);
-  Plan->TripCount =
-      vputils::getOrCreateVPValueForSCEVExpr(*Plan, TripCount, SE);
-
-  // Create VPRegionBlock, with empty header and latch blocks, to be filled
-  // during processing later.
-  VPBasicBlock *HeaderVPBB = Plan->createVPBasicBlock("vector.body");
-  VPBasicBlock *LatchVPBB = Plan->createVPBasicBlock("vector.latch");
-  VPBlockUtils::insertBlockAfter(LatchVPBB, HeaderVPBB);
-  auto *TopRegion = Plan->createVPRegionBlock(
-      HeaderVPBB, LatchVPBB, "vector loop", false /*isReplicator*/);
-
-  VPBlockUtils::insertBlockAfter(TopRegion, VecPreheader);
-  VPBasicBlock *MiddleVPBB = Plan->createVPBasicBlock("middle.block");
-  VPBlockUtils::insertBlockAfter(MiddleVPBB, TopRegion);
-
-  VPBasicBlock *ScalarPH = Plan->createVPBasicBlock("scalar.ph");
-  VPBlockUtils::connectBlocks(ScalarPH, ScalarHeader);
-  if (!RequiresScalarEpilogueCheck) {
-    VPBlockUtils::connectBlocks(MiddleVPBB, ScalarPH);
-    return Plan;
-  }
-
-  // If needed, add a check in the middle block to see if we have completed
-  // all of the iterations in the first vector loop.  Three cases:
-  // 1) If (N - N%VF) == N, then we *don't* need to run the remainder.
-  //    Thus if tail is to be folded, we know we don't need to run the
-  //    remainder and we can set the condition to true.
-  // 2) If we require a scalar epilogue, there is no conditional branch as
-  //    we unconditionally branch to the scalar preheader.  Do nothing.
-  // 3) Otherwise, construct a runtime check.
-  BasicBlock *IRExitBlock = TheLoop->getUniqueLatchExitBlock();
-  VPIRBasicBlock *VPExitBlock = Plan->getExitBlock(IRExitBlock);
-  // The connection order corresponds to the operands of the conditional branch.
-  VPBlockUtils::insertBlockAfter(VPExitBlock, MiddleVPBB);
-  VPBlockUtils::connectBlocks(MiddleVPBB, ScalarPH);
-
-  auto *ScalarLatchTerm = TheLoop->getLoopLatch()->getTerminator();
-  // Here we use the same DebugLoc as the scalar loop latch terminator instead
-  // of the corresponding compare because they may have ended up with
-  // different line numbers and we want to avoid awkward line stepping while
-  // debugging. Eg. if the compare has got a line number inside the loop.
-  VPBuilder Builder(MiddleVPBB);
-  VPValue *Cmp =
-      TailFolded
-          ? Plan->getOrAddLiveIn(ConstantInt::getTrue(
-                IntegerType::getInt1Ty(TripCount->getType()->getContext())))
-          : Builder.createICmp(CmpInst::ICMP_EQ, Plan->getTripCount(),
-                               &Plan->getVectorTripCount(),
-                               ScalarLatchTerm->getDebugLoc(), "cmp.n");
-  Builder.createNaryOp(VPInstruction::BranchOnCond, {Cmp},
-                       ScalarLatchTerm->getDebugLoc());
-  return Plan;
-}
-
 void VPlan::prepareToExecute(Value *TripCountV, Value *VectorTripCountV,
                              VPTransformState &State) {
   Type *TCTy = TripCountV->getType();
@@ -1135,11 +1056,13 @@ void VPlan::printLiveIns(raw_ostream &O) const {
   }
 
   O << "\n";
-  if (TripCount->isLiveIn())
-    O << "Live-in ";
-  TripCount->printAsOperand(O, SlotTracker);
-  O << " = original trip-count";
-  O << "\n";
+  if (TripCount) {
+    if (TripCount->isLiveIn())
+      O << "Live-in ";
+    TripCount->printAsOperand(O, SlotTracker);
+    O << " = original trip-count";
+    O << "\n";
+  }
 }
 
 LLVM_DUMP_METHOD
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.h b/llvm/lib/Transforms/Vectorize/VPlan.h
@@ -3505,21 +3505,6 @@ class VPlan {
     VPBB->setPlan(this);
   }
 
-  /// Create initial VPlan, having an "entry" VPBasicBlock (wrapping
-  /// original scalar pre-header) which contains SCEV expansions that need
-  /// to happen before the CFG is modified (when executing a VPlan for the
-  /// epilogue vector loop, the original entry needs to be replaced by a new
-  /// one); a VPBasicBlock for the vector pre-header, followed by a region for
-  /// the vector loop, followed by the middle VPBasicBlock. If a check is needed
-  /// to guard executing the scalar epilogue loop, it will be added to the
-  /// middle block, together with VPBasicBlocks for the scalar preheader and
-  /// exit blocks. \p InductionTy is the type of the canonical induction and
-  /// used for related values, like the trip count expression.
-  static VPlanPtr createInitialVPlan(Type *InductionTy,
-                                     PredicatedScalarEvolution &PSE,
-                                     bool RequiresScalarEpilogueCheck,
-                                     bool TailFolded, Loop *TheLoop);
-
   /// Prepare the plan for execution, setting up the required live-in values.
   void prepareToExecute(Value *TripCount, Value *VectorTripCount,
                         VPTransformState &State);
@@ -3589,6 +3574,8 @@ class VPlan {
     TripCount = NewTripCount;
   }
 
+  void setTripCount(VPValue *NewTripCount) { TripCount = NewTripCount; }
+
   /// The backedge taken count of the original loop.
   VPValue *getOrCreateBackedgeTakenCount() {
     if (!BackedgeTakenCount)
diff --git a/llvm/lib/Transforms/Vectorize/VPlanHCFGBuilder.cpp b/llvm/lib/Transforms/Vectorize/VPlanHCFGBuilder.cpp
@@ -180,7 +180,7 @@ VPBasicBlock *PlainCFGBuilder::getOrCreateVPBB(BasicBlock *BB) {
 
   // Get or create a region for the loop containing BB.
   Loop *LoopOfBB = LI->getLoopFor(BB);
-  if (!LoopOfBB || !doesContainLoop(LoopOfBB, TheLoop))
+  if (!LoopOfBB || LoopOfBB == TheLoop || !doesContainLoop(LoopOfBB, TheLoop))
     return VPBB;
 
   auto *RegionOfVPBB = Loop2Region.lookup(LoopOfBB);
@@ -353,29 +353,6 @@ void PlainCFGBuilder::createVPInstructionsForVPBB(VPBasicBlock *VPBB,
 // Main interface to build the plain CFG.
 void PlainCFGBuilder::buildPlainCFG(
     DenseMap<VPBlockBase *, BasicBlock *> &VPB2IRBB) {
-  // 0. Reuse the top-level region, vector-preheader and exit VPBBs from the
-  // skeleton. These were created directly rather than via getOrCreateVPBB(),
-  // revisit them now to update BB2VPBB. Note that header/entry and
-  // latch/exiting VPBB's of top-level region have yet to be created.
-  VPRegionBlock *TheRegion = Plan.getVectorLoopRegion();
-  BasicBlock *ThePreheaderBB = TheLoop->getLoopPreheader();
-  assert((ThePreheaderBB->getTerminator()->getNumSuccessors() == 1) &&
-         "Unexpected loop preheader");
-  auto *VectorPreheaderVPBB =
-      cast<VPBasicBlock>(TheRegion->getSinglePredecessor());
-  // ThePreheaderBB conceptually corresponds to both Plan.getPreheader() (which
-  // wraps the original preheader BB) and Plan.getEntry() (which represents the
-  // new vector preheader); here we're interested in setting BB2VPBB to the
-  // latter.
-  BB2VPBB[ThePreheaderBB] = VectorPreheaderVPBB;
-  Loop2Region[LI->getLoopFor(TheLoop->getHeader())] = TheRegion;
-
-  // The existing vector region's entry and exiting VPBBs correspond to the loop
-  // header and latch.
-  VPBasicBlock *VectorHeaderVPBB = TheRegion->getEntryBasicBlock();
-  VPBasicBlock *VectorLatchVPBB = TheRegion->getExitingBasicBlock();
-  BB2VPBB[TheLoop->getHeader()] = VectorHeaderVPBB;
-  VectorHeaderVPBB->clearSuccessors();
 
   // 1. Scan the body of the loop in a topological order to visit each basic
   // block after having visited its predecessor basic blocks. Create a VPBB for
@@ -386,6 +363,9 @@ void PlainCFGBuilder::buildPlainCFG(
 
   // Loop PH needs to be explicitly visited since it's not taken into account by
   // LoopBlocksDFS.
+  BasicBlock *ThePreheaderBB = TheLoop->getLoopPreheader();
+  assert((ThePreheaderBB->getTerminator()->getNumSuccessors() == 1) &&
+         "Unexpected loop preheader");
   for (auto &I : *ThePreheaderBB) {
     if (I.getType()->isVoidTy())
       continue;
@@ -406,18 +386,16 @@ void PlainCFGBuilder::buildPlainCFG(
     } else {
       // BB is a loop header, set the predecessor for the region, except for the
       // top region, whose predecessor was set when creating VPlan's skeleton.
-      assert(isHeaderVPBB(VPBB) && "isHeaderBB and isHeaderVPBB disagree");
-      if (TheRegion != Region)
+      if (LoopForBB != TheLoop)
         setRegionPredsFromBB(Region, BB);
     }
 
     // Create VPInstructions for BB.
     createVPInstructionsForVPBB(VPBB, BB);
 
-    if (TheLoop->getLoopLatch() == BB) {
-      VPBB->setOneSuccessor(VectorLatchVPBB);
-      VectorLatchVPBB->clearPredecessors();
-      VectorLatchVPBB->setPredecessors({VPBB});
+    if (BB == TheLoop->getLoopLatch()) {
+      VPBasicBlock *HeaderVPBB = getOrCreateVPBB(LoopForBB->getHeader());
+      VPBlockUtils::connectBlocks(VPBB, HeaderVPBB);
       continue;
     }
 
@@ -449,16 +427,22 @@ void PlainCFGBuilder::buildPlainCFG(
     VPBasicBlock *Successor0 = getOrCreateVPBB(IRSucc0);
     VPBasicBlock *Successor1 = getOrCreateVPBB(IRSucc1);
     if (BB == LoopForBB->getLoopLatch()) {
-      // For a latch we need to set the successor of the region rather than that
-      // of VPBB and it should be set to the exit, i.e., non-header successor,
+      // For a latch we need to set the successor of the region rather
+      // than that
+      // of VPBB and it should be set to the exit, i.e., non-header
+      // successor,
       // except for the top region, whose successor was set when creating
       // VPlan's skeleton.
-      assert(TheRegion != Region &&
+      assert(LoopForBB != TheLoop &&
              "Latch of the top region should have been handled earlier");
       Region->setOneSuccessor(isHeaderVPBB(Successor0) ? Successor1
                                                        : Successor0);
       Region->setExiting(VPBB);
       continue;
+
+      VPBasicBlock *HeaderVPBB = getOrCreateVPBB(LoopForBB->getHeader());
+      VPBlockUtils::connectBlocks(VPBB, HeaderVPBB);
+      continue;
     }
 
     // Don't connect any blocks outside the current loop except the latch for
@@ -482,6 +466,9 @@ void PlainCFGBuilder::buildPlainCFG(
   // corresponding VPlan operands.
   fixHeaderPhis();
 
+  VPBlockUtils::connectBlocks(Plan.getEntry(),
+                              getOrCreateVPBB(TheLoop->getHeader()));
+
   for (const auto &[IRBB, VPB] : BB2VPBB)
     VPB2IRBB[VPB] = IRBB;
 }
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -32,6 +32,82 @@
 
 using namespace llvm;
 
+void VPlanTransforms::introduceTopLevelVectorLoopRegion(
+    VPlan &Plan, Type *InductionTy, PredicatedScalarEvolution &PSE,
+    bool RequiresScalarEpilogueCheck, bool TailFolded, Loop *TheLoop) {
+  auto *HeaderVPBB = cast<VPBasicBlock>(Plan.getEntry()->getSingleSuccessor());
+  VPBlockUtils::disconnectBlocks(Plan.getEntry(), HeaderVPBB);
+
+  VPBasicBlock *OriginalLatch =
+      cast<VPBasicBlock>(HeaderVPBB->getSinglePredecessor());
+  VPBlockUtils::disconnectBlocks(OriginalLatch, HeaderVPBB);
+  VPBasicBlock *VecPreheader = Plan.createVPBasicBlock("vector.ph");
+  VPBlockUtils::connectBlocks(Plan.getEntry(), VecPreheader);
+
+  // Create SCEV and VPValue for the trip count.
+  // We use the symbolic max backedge-taken-count, which works also when
+  // vectorizing loops with uncountable early exits.
+  const SCEV *BackedgeTakenCountSCEV = PSE.getSymbolicMaxBackedgeTakenCount();
+  assert(!isa<SCEVCouldNotCompute>(BackedgeTakenCountSCEV) &&
+         "Invalid loop count");
+  ScalarEvolution &SE = *PSE.getSE();
+  const SCEV *TripCount = SE.getTripCountFromExitCount(BackedgeTakenCountSCEV,
+                                                       InductionTy, TheLoop);
+  Plan.setTripCount(
+      vputils::getOrCreateVPValueForSCEVExpr(Plan, TripCount, SE));
+
+  // Create VPRegionBlock, with empty header and latch blocks, to be filled
+  // during processing later.
+  VPBasicBlock *LatchVPBB = Plan.createVPBasicBlock("vector.latch");
+  VPBlockUtils::insertBlockAfter(LatchVPBB, OriginalLatch);
+  auto *TopRegion = Plan.createVPRegionBlock(
+      HeaderVPBB, LatchVPBB, "vector loop", false /*isReplicator*/);
+  for (VPBlockBase *VPBB : vp_depth_first_shallow(HeaderVPBB)) {
+    VPBB->setParent(TopRegion);
+  }
+
+  VPBlockUtils::insertBlockAfter(TopRegion, VecPreheader);
+  VPBasicBlock *MiddleVPBB = Plan.createVPBasicBlock("middle.block");
+  VPBlockUtils::insertBlockAfter(MiddleVPBB, TopRegion);
+
+  VPBasicBlock *ScalarPH = Plan.createVPBasicBlock("scalar.ph");
+  VPBlockUtils::connectBlocks(ScalarPH, Plan.getScalarHeader());
+  if (!RequiresScalarEpilogueCheck) {
+    VPBlockUtils::connectBlocks(MiddleVPBB, ScalarPH);
+    return;
+  }
+
+  // If needed, add a check in the middle block to see if we have completed
+  // all of the iterations in the first vector loop.  Three cases:
+  // 1) If (N - N%VF) == N, then we *don't* need to run the remainder.
+  //    Thus if tail is to be folded, we know we don't need to run the
+  //    remainder and we can set the condition to true.
+  // 2) If we require a scalar epilogue, there is no conditional branch as
+  //    we unconditionally branch to the scalar preheader.  Do nothing.
+  // 3) Otherwise, construct a runtime check.
+  BasicBlock *IRExitBlock = TheLoop->getUniqueLatchExitBlock();
+  auto *VPExitBlock = Plan.getExitBlock(IRExitBlock);
+  // The connection order corresponds to the operands of the conditional branch.
+  VPBlockUtils::insertBlockAfter(VPExitBlock, MiddleVPBB);
+  VPBlockUtils::connectBlocks(MiddleVPBB, ScalarPH);
+
+  auto *ScalarLatchTerm = TheLoop->getLoopLatch()->getTerminator();
+  // Here we use the same DebugLoc as the scalar loop latch terminator instead
+  // of the corresponding compare because they may have ended up with
+  // different line numbers and we want to avoid awkward line stepping while
+  // debugging. Eg. if the compare has got a line number inside the loop.
+  VPBuilder Builder(MiddleVPBB);
+  VPValue *Cmp =
+      TailFolded
+          ? Plan.getOrAddLiveIn(ConstantInt::getTrue(
+                IntegerType::getInt1Ty(TripCount->getType()->getContext())))
+          : Builder.createICmp(CmpInst::ICMP_EQ, Plan.getTripCount(),
+                               &Plan.getVectorTripCount(),
+                               ScalarLatchTerm->getDebugLoc(), "cmp.n");
+  Builder.createNaryOp(VPInstruction::BranchOnCond, {Cmp},
+                       ScalarLatchTerm->getDebugLoc());
+}
+
 void VPlanTransforms::VPInstructionsToVPRecipes(
     VPlanPtr &Plan,
     function_ref<const InductionDescriptor *(PHINode *)>
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.h b/llvm/lib/Transforms/Vectorize/VPlanTransforms.h
@@ -52,6 +52,21 @@ struct VPlanTransforms {
       verifyVPlanIsValid(Plan);
   }
 
+  /// Introduce the top-level VPRegionBlock for the main loop in \p Plan. Coming
+  /// in this function, \p Plan's top-level loop is modeled using a plain CFG.
+  /// This transforms replaces the plain CFG with a VPRegionBlock wrapping the
+  /// top-level loop and creates a VPValue expressions for the original trip
+  /// count. It will also introduce a dedicated VPBasicBlock for the vector
+  /// pre-header as well a VPBasicBlock as exit block of the region
+  /// (middle.block). If a check is needed to guard executing the scalar
+  /// epilogue loop, it will be added to the middle block, together with
+  /// VPBasicBlocks for the scalar preheader and exit blocks. \p InductionTy is
+  /// the type of the canonical induction and used for related values, like the
+  /// trip count expression.
+  static void introduceTopLevelVectorLoopRegion(
+      VPlan &Plan, Type *InductionTy, PredicatedScalarEvolution &PSE,
+      bool RequiresScalarEpilogueCheck, bool TailFolded, Loop *TheLoop);
+
   /// Replaces the VPInstructions in \p Plan with corresponding
   /// widen recipes.
   static void
diff --git a/llvm/unittests/Transforms/Vectorize/VPlanTestBase.h b/llvm/unittests/Transforms/Vectorize/VPlanTestBase.h
