[LV] Compute register usage for interleaving on VPlan.

Add a version of calculateRegisterUsage that works estimates register
usage for a VPlan. This mostly just ports the existing code, with some
updates to figure out what recipes will generate vectors vs scalars.

There are number of changes in the computed register usages, but they
should be more accurate w.r.t. to the generated vector code.

There are the following changes:

 * Scalar usage increases in most cases by 1, as we always create a
   scalar canonical IV, which is alive across the loop and is not
   considered by the legacy implementation

 * Output is ordered by insertion, now scalar registers are added first
   due the canonical IV phi.

 * Using the VPlan, we now also more precisely know if an induction will
   be vectorized or scalarized.

Author: fhahn

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -992,7 +992,8 @@ class LoopVectorizationCostModel {
   /// If interleave count has been specified by metadata it will be returned.
   /// Otherwise, the interleave count is computed and returned. VF and LoopCost
   /// are the selected vectorization factor and the cost of the selected VF.
-  unsigned selectInterleaveCount(ElementCount VF, InstructionCost LoopCost);
+  unsigned selectInterleaveCount(VPlan &Plan, ElementCount VF,
+                                 InstructionCost LoopCost);
 
   /// Memory access instruction may be vectorized in more than one way.
   /// Form of instruction after vectorization depends on cost.
@@ -4871,8 +4872,232 @@ void LoopVectorizationCostModel::collectElementTypesForWidening() {
   }
 }
 
+/// Estimate the register usage for \p Plan and vectorization factors in \p VFs.
+/// Returns the register usage for each VF in \p VFs.
+static SmallVector<LoopVectorizationCostModel::RegisterUsage, 8>
+calculateRegisterUsage(VPlan &Plan, ArrayRef<ElementCount> VFs,
+                       const TargetTransformInfo &TTI) {
+  // This function calculates the register usage by measuring the highest number
+  // of values that are alive at a single location. Obviously, this is a very
+  // rough estimation. We scan the loop in a topological order in order and
+  // assign a number to each recipe. We use RPO to ensure that defs are
+  // met before their users. We assume that each recipe that has in-loop
+  // users starts an interval. We record every time that an in-loop value is
+  // used, so we have a list of the first and last occurrences of each
+  // recipe. Next, we transpose this data structure into a multi map that
+  // holds the list of intervals that *end* at a specific location. This multi
+  // map allows us to perform a linear search. We scan the instructions linearly
+  // and record each time that a new interval starts, by placing it in a set.
+  // If we find this value in the multi-map then we remove it from the set.
+  // The max register usage is the maximum size of the set.
+  // We also search for instructions that are defined outside the loop, but are
+  // used inside the loop. We need this number separately from the max-interval
+  // usage number because when we unroll, loop-invariant values do not take
+  // more register.
+  LoopVectorizationCostModel::RegisterUsage RU;
+
+  // Each 'key' in the map opens a new interval. The values
+  // of the map are the index of the 'last seen' usage of the
+  // recipe that is the key.
+  using IntervalMap = SmallDenseMap<VPRecipeBase *, unsigned, 16>;
+
+  // Maps recipe to its index.
+  SmallVector<VPRecipeBase *, 64> IdxToRecipe;
+  // Marks the end of each interval.
+  IntervalMap EndPoint;
+  // Saves the list of recipe indices that are used in the loop.
+  SmallPtrSet<VPRecipeBase *, 8> Ends;
+  // Saves the list of values that are used in the loop but are defined outside
+  // the loop (not including non-recipe values such as arguments and
+  // constants).
+  SmallSetVector<VPValue *, 8> LoopInvariants;
+  LoopInvariants.insert(&Plan.getVectorTripCount());
+
+  ReversePostOrderTraversal<VPBlockDeepTraversalWrapper<VPBlockBase *>> RPOT(
+      Plan.getVectorLoopRegion());
+  for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(RPOT)) {
+    if (!VPBB->getParent())
+      break;
+    for (VPRecipeBase &R : *VPBB) {
+      IdxToRecipe.push_back(&R);
+
+      // Save the end location of each USE.
+      for (VPValue *U : R.operands()) {
+        auto *DefR = U->getDefiningRecipe();
+
+        // Ignore non-recipe values such as arguments, constants, etc.
+        // FIXME: Might need some motivation why these values are ignored. If
+        // for example an argument is used inside the loop it will increase the
+        // register pressure (so shouldn't we add it to LoopInvariants).
+        if (!DefR && (!U->getLiveInIRValue() ||
+                      !isa<Instruction>(U->getLiveInIRValue())))
+          continue;
+
+        // If this recipe is outside the loop then record it and continue.
+        if (!DefR) {
+          LoopInvariants.insert(U);
+          continue;
+        }
+
+        // Overwrite previous end points.
+        EndPoint[DefR] = IdxToRecipe.size();
+        Ends.insert(DefR);
+      }
+    }
+    if (VPBB == Plan.getVectorLoopRegion()->getExiting()) {
+      // VPWidenIntOrFpInductionRecipes are used implicitly at the end of the
+      // exiting block, where their increment will get materialized eventually.
+      for (auto &R : Plan.getVectorLoopRegion()->getEntryBasicBlock()->phis()) {
+        if (isa<VPWidenIntOrFpInductionRecipe>(&R)) {
+          EndPoint[&R] = IdxToRecipe.size();
+          Ends.insert(&R);
+        }
+      }
+    }
+  }
+
+  // Saves the list of intervals that end with the index in 'key'.
+  using RecipeList = SmallVector<VPRecipeBase *, 2>;
+  SmallDenseMap<unsigned, RecipeList, 16> TransposeEnds;
+
+  // Transpose the EndPoints to a list of values that end at each index.
+  for (auto &Interval : EndPoint)
+    TransposeEnds[Interval.second].push_back(Interval.first);
+
+  SmallPtrSet<VPRecipeBase *, 8> OpenIntervals;
+  SmallVector<LoopVectorizationCostModel::RegisterUsage, 8> RUs(VFs.size());
+  SmallVector<SmallMapVector<unsigned, unsigned, 4>, 8> MaxUsages(VFs.size());
+
+  LLVM_DEBUG(dbgs() << "LV(REG): Calculating max register usage:\n");
+
+  VPTypeAnalysis TypeInfo(Plan.getCanonicalIV()->getScalarType());
+
+  const auto &TTICapture = TTI;
+  auto GetRegUsage = [&TTICapture](Type *Ty, ElementCount VF) -> unsigned {
+    if (Ty->isTokenTy() || !VectorType::isValidElementType(Ty) ||
+        (VF.isScalable() &&
+         !TTICapture.isElementTypeLegalForScalableVector(Ty)))
+      return 0;
+    return TTICapture.getRegUsageForType(VectorType::get(Ty, VF));
+  };
+
+  for (unsigned int Idx = 0, Sz = IdxToRecipe.size(); Idx < Sz; ++Idx) {
+    VPRecipeBase *R = IdxToRecipe[Idx];
+
+    //  Remove all of the recipes that end at this location.
+    RecipeList &List = TransposeEnds[Idx];
+    for (VPRecipeBase *ToRemove : List)
+      OpenIntervals.erase(ToRemove);
+
+    // Ignore recipes that are never used within the loop.
+    if (!Ends.count(R) && !R->mayHaveSideEffects())
+      continue;
+
+    // For each VF find the maximum usage of registers.
+    for (unsigned J = 0, E = VFs.size(); J < E; ++J) {
+      // Count the number of registers used, per register class, given all open
+      // intervals.
+      // Note that elements in this SmallMapVector will be default constructed
+      // as 0. So we can use "RegUsage[ClassID] += n" in the code below even if
+      // there is no previous entry for ClassID.
+      SmallMapVector<unsigned, unsigned, 4> RegUsage;
+
+      if (VFs[J].isScalar()) {
+        for (auto *Inst : OpenIntervals) {
+          for (VPValue *DefV : Inst->definedValues()) {
+            unsigned ClassID = TTI.getRegisterClassForType(
+                false, TypeInfo.inferScalarType(DefV));
+            // FIXME: The target might use more than one register for the type
+            // even in the scalar case.
+            RegUsage[ClassID] += 1;
+          }
+        }
+      } else {
+        for (auto *R : OpenIntervals) {
+          if (isa<VPVectorPointerRecipe, VPReverseVectorPointerRecipe>(R))
+            continue;
+          if (isa<VPCanonicalIVPHIRecipe, VPReplicateRecipe, VPDerivedIVRecipe,
+                  VPScalarIVStepsRecipe>(R) ||
+              (isa<VPInstruction>(R) &&
+               all_of(cast<VPSingleDefRecipe>(R)->users(), [&](VPUser *U) {
+                 return cast<VPRecipeBase>(U)->usesScalars(
+                     R->getVPSingleValue());
+               }))) {
+            unsigned ClassID = TTI.getRegisterClassForType(
+                false, TypeInfo.inferScalarType(R->getVPSingleValue()));
+            // FIXME: The target might use more than one register for the type
+            // even in the scalar case.
+            RegUsage[ClassID] += 1;
+          } else {
+            for (VPValue *DefV : R->definedValues()) {
+              Type *ScalarTy = TypeInfo.inferScalarType(DefV);
+              unsigned ClassID = TTI.getRegisterClassForType(true, ScalarTy);
+              RegUsage[ClassID] += GetRegUsage(ScalarTy, VFs[J]);
+            }
+          }
+        }
+      }
+
+      for (const auto &Pair : RegUsage) {
+        auto &Entry = MaxUsages[J][Pair.first];
+        Entry = std::max(Entry, Pair.second);
+      }
+    }
+
+    LLVM_DEBUG(dbgs() << "LV(REG): At #" << Idx << " Interval # "
+                      << OpenIntervals.size() << '\n');
+
+    // Add the current recipe to the list of open intervals.
+    OpenIntervals.insert(R);
+  }
+
+  for (unsigned Idx = 0, End = VFs.size(); Idx < End; ++Idx) {
+    // Note that elements in this SmallMapVector will be default constructed
+    // as 0. So we can use "Invariant[ClassID] += n" in the code below even if
+    // there is no previous entry for ClassID.
+    SmallMapVector<unsigned, unsigned, 4> Invariant;
+
+    for (auto *In : LoopInvariants) {
+      // FIXME: The target might use more than one register for the type
+      // even in the scalar case.
+      bool IsScalar = all_of(In->users(), [&](VPUser *U) {
+        return cast<VPRecipeBase>(U)->usesScalars(In);
+      });
+
+      ElementCount VF = IsScalar ? ElementCount::getFixed(1) : VFs[Idx];
+      unsigned ClassID = TTI.getRegisterClassForType(
+          VF.isVector(), TypeInfo.inferScalarType(In));
+      Invariant[ClassID] += GetRegUsage(TypeInfo.inferScalarType(In), VF);
+    }
+
+    LLVM_DEBUG({
+      dbgs() << "LV(REG): VF = " << VFs[Idx] << '\n';
+      dbgs() << "LV(REG): Found max usage: " << MaxUsages[Idx].size()
+             << " item\n";
+      for (const auto &pair : MaxUsages[Idx]) {
+        dbgs() << "LV(REG): RegisterClass: "
+               << TTI.getRegisterClassName(pair.first) << ", " << pair.second
+               << " registers\n";
+      }
+      dbgs() << "LV(REG): Found invariant usage: " << Invariant.size()
+             << " item\n";
+      for (const auto &pair : Invariant) {
+        dbgs() << "LV(REG): RegisterClass: "
+               << TTI.getRegisterClassName(pair.first) << ", " << pair.second
+               << " registers\n";
+      }
+    });
+
+    RU.LoopInvariantRegs = Invariant;
+    RU.MaxLocalUsers = MaxUsages[Idx];
+    RUs[Idx] = RU;
+  }
+
+  return RUs;
+}
+
 unsigned
-LoopVectorizationCostModel::selectInterleaveCount(ElementCount VF,
+LoopVectorizationCostModel::selectInterleaveCount(VPlan &Plan, ElementCount VF,
                                                   InstructionCost LoopCost) {
   // -- The interleave heuristics --
   // We interleave the loop in order to expose ILP and reduce the loop overhead.
@@ -4922,7 +5147,7 @@ LoopVectorizationCostModel::selectInterleaveCount(ElementCount VF,
       return 1;
   }
 
-  RegisterUsage R = calculateRegisterUsage({VF})[0];
+  RegisterUsage R = ::calculateRegisterUsage(Plan, {VF}, TTI)[0];
   // We divide by these constants so assume that we have at least one
   // instruction that uses at least one register.
   for (auto &Pair : R.MaxLocalUsers) {
@@ -10760,7 +10985,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
                            AddBranchWeights, CM.CostKind);
   if (LVP.hasPlanWithVF(VF.Width)) {
     // Select the interleave count.
-    IC = CM.selectInterleaveCount(VF.Width, VF.Cost);
+    IC = CM.selectInterleaveCount(LVP.getPlanFor(VF.Width), VF.Width, VF.Cost);
 
     unsigned SelectedIC = std::max(IC, UserIC);
     //  Optimistically generate runtime checks if they are needed. Drop them if

llvm/test/Transforms/LoopVectorize/AArch64/i1-reg-usage.ll

@@ -8,8 +8,8 @@ target triple = "aarch64"
 ; CHECK-LABEL: LV: Checking a loop in 'or_reduction_neon' from <stdin>
 ; CHECK: LV(REG): VF = 32
 ; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
 ; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 72 registers
-; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 1 registers
 
 define i1 @or_reduction_neon(i32 %arg, ptr %ptr) {
 entry:
@@ -31,8 +31,8 @@ loop:
 ; CHECK-LABEL: LV: Checking a loop in 'or_reduction_sve'
 ; CHECK: LV(REG): VF = 64
 ; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
 ; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 136 registers
-; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 1 registers
 
 define i1 @or_reduction_sve(i32 %arg, ptr %ptr) vscale_range(2,2) "target-features"="+sve" {
 entry:

llvm/test/Transforms/LoopVectorize/AArch64/reg-usage.ll

@@ -16,11 +16,10 @@ define void @get_invariant_reg_usage(ptr %z) {
 ; CHECK-LABEL: LV: Checking a loop in 'get_invariant_reg_usage'
 ; CHECK: LV(REG): VF = vscale x 16
 ; CHECK-NEXT: LV(REG): Found max usage: 2 item
-; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 3 registers
-; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 1 registers 
-; CHECK-NEXT: LV(REG): Found invariant usage: 2 item
 ; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
-; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 8 registers
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 1 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 1 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 3 registers
 
 L.entry:
   %0 = load i128, ptr %z, align 16

llvm/test/Transforms/LoopVectorize/LoongArch/reg-usage.ll

@@ -9,17 +9,18 @@
 define void @bar(ptr %A, i32 signext %n) {
 ; CHECK-LABEL: bar
 ; CHECK-SCALAR:      LV(REG): Found max usage: 2 item
-; CHECK-SCALAR-NEXT: LV(REG): RegisterClass: LoongArch::GPRRC, 2 registers
+; CHECK-SCALAR-NEXT: LV(REG): RegisterClass: LoongArch::GPRRC, 3 registers
 ; CHECK-SCALAR-NEXT: LV(REG): RegisterClass: LoongArch::FPRRC, 1 registers
 ; CHECK-SCALAR-NEXT: LV(REG): Found invariant usage: 1 item
 ; CHECK-SCALAR-NEXT: LV(REG): RegisterClass: LoongArch::GPRRC, 1 registers
 ; CHECK-SCALAR-NEXT: LV: The target has 30 registers of LoongArch::GPRRC register class
 ; CHECK-SCALAR-NEXT: LV: The target has 32 registers of LoongArch::FPRRC register class
 ; CHECK-VECTOR:      LV(REG): Found max usage: 2 item
-; CHECK-VECTOR-NEXT: LV(REG): RegisterClass: LoongArch::VRRC, 3 registers
-; CHECK-VECTOR-NEXT: LV(REG): RegisterClass: LoongArch::GPRRC, 1 registers
+; CHECK-VECTOR-NEXT: LV(REG): RegisterClass: LoongArch::GPRRC, 2 registers
+; CHECK-VECTOR-NEXT: LV(REG): RegisterClass: LoongArch::VRRC, 2 registers
 ; CHECK-VECTOR-NEXT: LV(REG): Found invariant usage: 1 item
 ; CHECK-VECTOR-NEXT: LV(REG): RegisterClass: LoongArch::GPRRC, 1 registers
+; CHECK-VECTOR-NEXT: LV: The target has 30 registers of LoongArch::GPRRC register class
 ; CHECK-VECTOR-NEXT: LV: The target has 32 registers of LoongArch::VRRC register class
 
 entry: