[LoopVectorize] Simplify scalar cost calculation in getInstructionCost

This patch simplifies the calculation of certain costs in
getInstructionCost when isScalarAfterVectorization() returns a true value.
There are a few places where we multiply a cost by a number N, i.e.

  unsigned N = isScalarAfterVectorization(I, VF) ? VF.getKnownMinValue() : 1;
  return N * TTI.getArithmeticInstrCost(...

After some investigation it seems that there are only these cases that occur
in practice:

1. VF is a scalar, in which case N = 1.
2. VF is a vector. We can only get here if: a) the instruction is a
GEP/bitcast/PHI with scalar uses, or b) this is an update to an induction
variable that remains scalar.

I have changed the code so that N is assumed to always be 1. For GEPs
the cost is always 0, since this is calculated later on as part of the
load/store cost. PHI nodes are costed separately and were never previously
multiplied by VF. For all other cases I have added an assert that none of
the users needs scalarising, which didn't fire in any unit tests.

Only one test required fixing and I believe the original cost for the scalar
add instruction to have been wrong, since only one copy remains after
vectorisation.

I have also added a new test for the case when a pointer PHI feeds directly
into a store that will be scalarised as we were previously never testing it.

Differential Revision: https://reviews.llvm.org/D99718

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -7316,10 +7316,37 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
   Type *RetTy = I->getType();
   if (canTruncateToMinimalBitwidth(I, VF))
     RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
-  VectorTy = isScalarAfterVectorization(I, VF) ? RetTy : ToVectorTy(RetTy, VF);
   auto SE = PSE.getSE();
   TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
 
+  auto hasSingleCopyAfterVectorization = [this](Instruction *I,
+                                                ElementCount VF) -> bool {
+    if (VF.isScalar())
+      return true;
+
+    auto Scalarized = InstsToScalarize.find(VF);
+    assert(Scalarized != InstsToScalarize.end() &&
+           "VF not yet analyzed for scalarization profitability");
+    return !Scalarized->second.count(I) &&
+           llvm::all_of(I->users(), [&](User *U) {
+             auto *UI = cast<Instruction>(U);
+             return !Scalarized->second.count(UI);
+           });
+  };
+
+  if (isScalarAfterVectorization(I, VF)) {
+    // With the exception of GEPs and PHIs, after scalarization there should
+    // only be one copy of the instruction generated in the loop. This is
+    // because the VF is either 1, or any instructions that need scalarizing
+    // have already been dealt with by the the time we get here. As a result,
+    // it means we don't have to multiply the instruction cost by VF.
+    assert(I->getOpcode() == Instruction::GetElementPtr ||
+           I->getOpcode() == Instruction::PHI ||
+           hasSingleCopyAfterVectorization(I, VF));
+    VectorTy = RetTy;
+  } else
+    VectorTy = ToVectorTy(RetTy, VF);
+
   // TODO: We need to estimate the cost of intrinsic calls.
   switch (I->getOpcode()) {
   case Instruction::GetElementPtr:
@@ -7447,21 +7474,16 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
       Op2VK = TargetTransformInfo::OK_UniformValue;
 
     SmallVector<const Value *, 4> Operands(I->operand_values());
-    unsigned N = isScalarAfterVectorization(I, VF) ? VF.getKnownMinValue() : 1;
-    return N * TTI.getArithmeticInstrCost(
-                   I->getOpcode(), VectorTy, CostKind,
-                   TargetTransformInfo::OK_AnyValue,
-                   Op2VK, TargetTransformInfo::OP_None, Op2VP, Operands, I);
+    return TTI.getArithmeticInstrCost(
+        I->getOpcode(), VectorTy, CostKind, TargetTransformInfo::OK_AnyValue,
+        Op2VK, TargetTransformInfo::OP_None, Op2VP, Operands, I);
   }
   case Instruction::FNeg: {
     assert(!VF.isScalable() && "VF is assumed to be non scalable.");
-    unsigned N = isScalarAfterVectorization(I, VF) ? VF.getKnownMinValue() : 1;
-    return N * TTI.getArithmeticInstrCost(
-                   I->getOpcode(), VectorTy, CostKind,
-                   TargetTransformInfo::OK_AnyValue,
-                   TargetTransformInfo::OK_AnyValue,
-                   TargetTransformInfo::OP_None, TargetTransformInfo::OP_None,
-                   I->getOperand(0), I);
+    return TTI.getArithmeticInstrCost(
+        I->getOpcode(), VectorTy, CostKind, TargetTransformInfo::OK_AnyValue,
+        TargetTransformInfo::OK_AnyValue, TargetTransformInfo::OP_None,
+        TargetTransformInfo::OP_None, I->getOperand(0), I);
   }
   case Instruction::Select: {
     SelectInst *SI = cast<SelectInst>(I);
@@ -7605,14 +7627,7 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
       }
     }
 
-    unsigned N;
-    if (isScalarAfterVectorization(I, VF)) {
-      assert(!VF.isScalable() && "VF is assumed to be non scalable");
-      N = VF.getKnownMinValue();
-    } else
-      N = 1;
-    return N *
-           TTI.getCastInstrCost(Opcode, VectorTy, SrcVecTy, CCH, CostKind, I);
+    return TTI.getCastInstrCost(Opcode, VectorTy, SrcVecTy, CCH, CostKind, I);
   }
   case Instruction::Call: {
     bool NeedToScalarize;
@@ -7627,11 +7642,8 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
   case Instruction::ExtractValue:
     return TTI.getInstructionCost(I, TTI::TCK_RecipThroughput);
   default:
-    // The cost of executing VF copies of the scalar instruction. This opcode
-    // is unknown. Assume that it is the same as 'mul'.
-    return VF.getKnownMinValue() * TTI.getArithmeticInstrCost(
-                                       Instruction::Mul, VectorTy, CostKind) +
-           getScalarizationOverhead(I, VF);
+    // This opcode is unknown. Assume that it is the same as 'mul'.
+    return TTI.getArithmeticInstrCost(Instruction::Mul, VectorTy, CostKind);
   } // end of switch.
 }
 

llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll

@@ -6,7 +6,7 @@ target triple = "aarch64--linux-gnu"
 
 ; CHECK-LABEL: all_scalar
 ; CHECK:       LV: Found scalar instruction: %i.next = add nuw nsw i64 %i, 2
-; CHECK:       LV: Found an estimated cost of 2 for VF 2 For instruction: %i.next = add nuw nsw i64 %i, 2
+; CHECK:       LV: Found an estimated cost of 1 for VF 2 For instruction: %i.next = add nuw nsw i64 %i, 2
 ; CHECK:       LV: Not considering vector loop of width 2 because it will not generate any vector instructions
 ;
 define void @all_scalar(i64* %a, i64 %n) {

llvm/test/Transforms/LoopVectorize/AArch64/predication_costs.ll

@@ -86,6 +86,41 @@ for.end:
   ret void
 }
 
+; CHECK-LABEL: predicated_store_phi
+;
+; Same as predicate_store except we use a pointer PHI to maintain the address
+;
+; CHECK: Found new scalar instruction:   %addr = phi i32* [ %a, %entry ], [ %addr.next, %for.inc ]
+; CHECK: Found new scalar instruction:   %addr.next = getelementptr inbounds i32, i32* %addr, i64 1
+; CHECK: Scalarizing and predicating: store i32 %tmp2, i32* %addr, align 4
+; CHECK: Found an estimated cost of 0 for VF 2 For instruction:   %addr = phi i32* [ %a, %entry ], [ %addr.next, %for.inc ]
+; CHECK: Found an estimated cost of 3 for VF 2 For instruction: store i32 %tmp2, i32* %addr, align 4
+;
+define void @predicated_store_phi(i32* %a, i1 %c, i32 %x, i64 %n) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i64 [ 0, %entry ], [ %i.next, %for.inc ]
+  %addr = phi i32 * [ %a, %entry ], [ %addr.next, %for.inc ]
+  %tmp1 = load i32, i32* %addr, align 4
+  %tmp2 = add nsw i32 %tmp1, %x
+  br i1 %c, label %if.then, label %for.inc
+
+if.then:
+  store i32 %tmp2, i32* %addr, align 4
+  br label %for.inc
+
+for.inc:
+  %i.next = add nuw nsw i64 %i, 1
+  %cond = icmp slt i64 %i.next, %n
+  %addr.next = getelementptr inbounds i32, i32* %addr, i64 1
+  br i1 %cond, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
+
 ; CHECK-LABEL: predicated_udiv_scalarized_operand
 ;
 ; This test checks that we correctly compute the cost of the predicated udiv