[Analysis][AArch64] Make fixed-width ordered reductions slightly more expensive

For tight loops like this:

  float r = 0;
  for (int i = 0; i < n; i++) {
    r += a[i];
  }

it's better not to vectorise at -O3 using fixed-width ordered reductions
on AArch64 targets. Although the resulting number of instructions in the
generated code ends up being comparable to not vectorising at all, there
may be additional costs on some CPUs, for example perhaps the scheduling
is worse. It makes sense to deter vectorisation in tight loops.

Differential Revision: https://reviews.llvm.org/D108292

Author: david-arm

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -1999,8 +1999,13 @@ AArch64TTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy,
                                            Optional<FastMathFlags> FMF,
                                            TTI::TargetCostKind CostKind) {
   if (TTI::requiresOrderedReduction(FMF)) {
-    if (!isa<ScalableVectorType>(ValTy))
-      return BaseT::getArithmeticReductionCost(Opcode, ValTy, FMF, CostKind);
+    if (auto *FixedVTy = dyn_cast<FixedVectorType>(ValTy)) {
+      InstructionCost BaseCost =
+          BaseT::getArithmeticReductionCost(Opcode, ValTy, FMF, CostKind);
+      // Add on extra cost to reflect the extra overhead on some CPUs. We still
+      // end up vectorizing for more computationally intensive loops.
+      return BaseCost + FixedVTy->getNumElements();
+    }
 
     if (Opcode != Instruction::FAdd)
       return InstructionCost::getInvalid();

llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll

@@ -2,10 +2,10 @@
 
 define void @strict_fp_reductions() {
 ; CHECK-LABEL: strict_fp_reductions
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef)
   %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.0, <4 x float> undef)
   %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.0, <8 x float> undef)
   %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.0, <2 x double> undef)

llvm/test/Transforms/LoopVectorize/AArch64/strict-fadd-cost.ll

@@ -6,8 +6,8 @@
 
 target triple="aarch64-unknown-linux-gnu"
 
-; CHECK-VF4: Found an estimated cost of 17 for VF 4 For instruction:   %add = fadd float %0, %sum.07
-; CHECK-VF8: Found an estimated cost of 34 for VF 8 For instruction:   %add = fadd float %0, %sum.07
+; CHECK-VF4: Found an estimated cost of 21 for VF 4 For instruction:   %add = fadd float %0, %sum.07
+; CHECK-VF8: Found an estimated cost of 42 for VF 8 For instruction:   %add = fadd float %0, %sum.07
 
 define float @fadd_strict32(float* noalias nocapture readonly %a, i64 %n) {
 entry:
@@ -28,8 +28,8 @@ for.end:
 }
 
 
-; CHECK-VF4: Found an estimated cost of 14 for VF 4 For instruction:   %add = fadd double %0, %sum.07
-; CHECK-VF8: Found an estimated cost of 28 for VF 8 For instruction:   %add = fadd double %0, %sum.07
+; CHECK-VF4: Found an estimated cost of 18 for VF 4 For instruction:   %add = fadd double %0, %sum.07
+; CHECK-VF8: Found an estimated cost of 36 for VF 8 For instruction:   %add = fadd double %0, %sum.07
 
 define double @fadd_strict64(double* noalias nocapture readonly %a, i64 %n) {
 entry: