[SVE] Add support for scalable vectorization of loops with int/fast FP reductions

This patch enables scalable vectorization of loops with integer/fast reductions, e.g:

```
unsigned sum = 0;
for (int i = 0; i < n; ++i) {
  sum += a[i];
}
```

A new TTI interface, isLegalToVectorizeReduction, has been added to prevent
reductions which are not supported for scalable types from vectorizing.
If the reduction is not supported for a given scalable VF,
computeFeasibleMaxVF will fall back to using fixed-width vectorization.

Reviewed By: david-arm, fhahn, dmgreen

Differential Revision: https://reviews.llvm.org/D95245

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -21,6 +21,7 @@
 #ifndef LLVM_ANALYSIS_TARGETTRANSFORMINFO_H
 #define LLVM_ANALYSIS_TARGETTRANSFORMINFO_H
 
+#include "llvm/Analysis/IVDescriptors.h"
 #include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/IR/PassManager.h"
@@ -1308,6 +1309,10 @@ public:
   bool isLegalToVectorizeStoreChain(unsigned ChainSizeInBytes, Align Alignment,
                                     unsigned AddrSpace) const;
 
+  /// \returns True if it is legal to vectorize the given reduction kind.
+  bool isLegalToVectorizeReduction(RecurrenceDescriptor RdxDesc,
+                                   ElementCount VF) const;
+
   /// \returns The new vector factor value if the target doesn't support \p
   /// SizeInBytes loads or has a better vector factor.
   unsigned getLoadVectorFactor(unsigned VF, unsigned LoadSize,
@@ -1643,6 +1648,8 @@ public:
   virtual bool isLegalToVectorizeStoreChain(unsigned ChainSizeInBytes,
                                             Align Alignment,
                                             unsigned AddrSpace) const = 0;
+  virtual bool isLegalToVectorizeReduction(RecurrenceDescriptor RdxDesc,
+                                           ElementCount VF) const = 0;
   virtual unsigned getLoadVectorFactor(unsigned VF, unsigned LoadSize,
                                        unsigned ChainSizeInBytes,
                                        VectorType *VecTy) const = 0;
@@ -2169,6 +2176,10 @@ public:
     return Impl.isLegalToVectorizeStoreChain(ChainSizeInBytes, Alignment,
                                              AddrSpace);
   }
+  bool isLegalToVectorizeReduction(RecurrenceDescriptor RdxDesc,
+                                   ElementCount VF) const override {
+    return Impl.isLegalToVectorizeReduction(RdxDesc, VF);
+  }
   unsigned getLoadVectorFactor(unsigned VF, unsigned LoadSize,
                                unsigned ChainSizeInBytes,
                                VectorType *VecTy) const override {

llvm/include/llvm/Analysis/TargetTransformInfoImpl.h

@@ -689,6 +689,11 @@ public:
     return true;
   }
 
+  bool isLegalToVectorizeReduction(RecurrenceDescriptor RdxDesc,
+                                   ElementCount VF) const {
+    return true;
+  }
+
   unsigned getLoadVectorFactor(unsigned VF, unsigned LoadSize,
                                unsigned ChainSizeInBytes,
                                VectorType *VecTy) const {

llvm/lib/Analysis/TargetTransformInfo.cpp

@@ -1033,6 +1033,11 @@ bool TargetTransformInfo::isLegalToVectorizeStoreChain(
                                                AddrSpace);
 }
 
+bool TargetTransformInfo::isLegalToVectorizeReduction(
+    RecurrenceDescriptor RdxDesc, ElementCount VF) const {
+  return TTIImpl->isLegalToVectorizeReduction(RdxDesc, VF);
+}
+
 unsigned TargetTransformInfo::getLoadVectorFactor(unsigned VF,
                                                   unsigned LoadSize,
                                                   unsigned ChainSizeInBytes,

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -1089,6 +1089,33 @@ bool AArch64TTIImpl::shouldConsiderAddressTypePromotion(
   return Considerable;
 }
 
+bool AArch64TTIImpl::isLegalToVectorizeReduction(RecurrenceDescriptor RdxDesc,
+                                                 ElementCount VF) const {
+  if (!VF.isScalable())
+    return true;
+
+  Type *Ty = RdxDesc.getRecurrenceType();
+  if (Ty->isBFloatTy() || !isLegalElementTypeForSVE(Ty))
+    return false;
+
+  switch (RdxDesc.getRecurrenceKind()) {
+  case RecurKind::Add:
+  case RecurKind::FAdd:
+  case RecurKind::And:
+  case RecurKind::Or:
+  case RecurKind::Xor:
+  case RecurKind::SMin:
+  case RecurKind::SMax:
+  case RecurKind::UMin:
+  case RecurKind::UMax:
+  case RecurKind::FMin:
+  case RecurKind::FMax:
+    return true;
+  default:
+    return false;
+  }
+}
+
 int AArch64TTIImpl::getMinMaxReductionCost(VectorType *Ty, VectorType *CondTy,
                                            bool IsPairwise, bool IsUnsigned,
                                            TTI::TargetCostKind CostKind) {

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

@@ -186,12 +186,14 @@ public:
 
   bool getTgtMemIntrinsic(IntrinsicInst *Inst, MemIntrinsicInfo &Info);
 
-  bool isLegalScalarTypeForSVEMaskedMemOp(Type *Ty) const {
+  bool isLegalElementTypeForSVE(Type *Ty) const {
     if (Ty->isPointerTy())
       return true;
 
-    if (Ty->isBFloatTy() || Ty->isHalfTy() ||
-        Ty->isFloatTy() || Ty->isDoubleTy())
+    if (Ty->isBFloatTy() && ST->hasBF16())
+      return true;
+
+    if (Ty->isHalfTy() || Ty->isFloatTy() || Ty->isDoubleTy())
       return true;
 
     if (Ty->isIntegerTy(8) || Ty->isIntegerTy(16) ||
@@ -205,7 +207,7 @@ public:
     if (isa<FixedVectorType>(DataType) || !ST->hasSVE())
       return false;
 
-    return isLegalScalarTypeForSVEMaskedMemOp(DataType->getScalarType());
+    return isLegalElementTypeForSVE(DataType->getScalarType());
   }
 
   bool isLegalMaskedLoad(Type *DataType, Align Alignment) {
@@ -220,7 +222,7 @@ public:
     if (isa<FixedVectorType>(DataType) || !ST->hasSVE())
       return false;
 
-    return isLegalScalarTypeForSVEMaskedMemOp(DataType->getScalarType());
+    return isLegalElementTypeForSVE(DataType->getScalarType());
   }
 
   bool isLegalMaskedGather(Type *DataType, Align Alignment) const {
@@ -266,6 +268,9 @@ public:
 
   bool supportsScalableVectors() const { return ST->hasSVE(); }
 
+  bool isLegalToVectorizeReduction(RecurrenceDescriptor RdxDesc,
+                                   ElementCount VF) const;
+
   int getArithmeticReductionCost(unsigned Opcode, VectorType *Ty,
                                  bool IsPairwiseForm,
                                  TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput);

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -1525,6 +1525,15 @@ public:
            (SI && isLegalMaskedScatter(Ty, Align));
   }
 
+  /// Returns true if the target machine supports all of the reduction
+  /// variables found for the given VF.
+  bool canVectorizeReductions(ElementCount VF) {
+    return (all_of(Legal->getReductionVars(), [&](auto &Reduction) -> bool {
+      RecurrenceDescriptor RdxDesc = Reduction.second;
+      return TTI.isLegalToVectorizeReduction(RdxDesc, VF);
+    }));
+  }
+
   /// Returns true if \p I is an instruction that will be scalarized with
   /// predication. Such instructions include conditional stores and
   /// instructions that may divide by zero.
@@ -4626,7 +4635,6 @@ void InnerLoopVectorizer::widenPHIInstruction(Instruction *PN,
                                               RecurrenceDescriptor *RdxDesc,
                                               Value *StartV, VPValue *Def,
                                               VPTransformState &State) {
-  assert(!State.VF.isScalable() && "scalable vectors not yet supported.");
   PHINode *P = cast<PHINode>(PN);
   if (EnableVPlanNativePath) {
     // Currently we enter here in the VPlan-native path for non-induction
@@ -5688,9 +5696,22 @@ LoopVectorizationCostModel::computeFeasibleMaxVF(unsigned ConstTripCount,
   // then a suitable VF is chosen. If UserVF is specified and there are
   // dependencies, check if it's legal. However, if a UserVF is specified and
   // there are no dependencies, then there's nothing to do.
-  if (UserVF.isNonZero() && !IgnoreScalableUserVF &&
-      Legal->isSafeForAnyVectorWidth())
-    return UserVF;
+  if (UserVF.isNonZero() && !IgnoreScalableUserVF) {
+    if (!canVectorizeReductions(UserVF)) {
+      reportVectorizationFailure(
+          "LV: Scalable vectorization not supported for the reduction "
+          "operations found in this loop. Using fixed-width "
+          "vectorization instead.",
+          "Scalable vectorization not supported for the reduction operations "
+          "found in this loop. Using fixed-width vectorization instead.",
+          "ScalableVFUnfeasible", ORE, TheLoop);
+      return computeFeasibleMaxVF(
+          ConstTripCount, ElementCount::getFixed(UserVF.getKnownMinValue()));
+    }
+
+    if (Legal->isSafeForAnyVectorWidth())
+      return UserVF;
+  }
 
   MinBWs = computeMinimumValueSizes(TheLoop->getBlocks(), *DB, &TTI);
   unsigned SmallestType, WidestType;

llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll

@@ -0,0 +1,400 @@
+; RUN: opt < %s -loop-vectorize -pass-remarks=loop-vectorize -pass-remarks-analysis=loop-vectorize -pass-remarks-missed=loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -S 2>%t | FileCheck %s -check-prefix=CHECK
+; RUN: cat %t | FileCheck %s -check-prefix=CHECK-REMARK
+
+; Reduction can be vectorized
+
+; ADD
+
+; CHECK-REMARK: vectorized loop (vectorization width: vscale x 8, interleaved count: 2)
+define i32 @add(i32* nocapture %a, i32* nocapture readonly %b, i64 %n) {
+; CHECK-LABEL: @add
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[LOAD2:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[ADD1:.*]] = add <vscale x 8 x i32> %[[LOAD1]]
+; CHECK: %[[ADD2:.*]] = add <vscale x 8 x i32> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[ADD:.*]] = add <vscale x 8 x i32> %[[ADD2]], %[[ADD1]]
+; CHECK-NEXT: call i32 @llvm.vector.reduce.add.nxv8i32(<vscale x 8 x i32> %[[ADD]])
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.07 = phi i32 [ 2, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %sum.07
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:                                 ; preds = %for.body, %entry
+  ret i32 %add
+}
+
+; OR
+
+; CHECK-REMARK: vectorized loop (vectorization width: vscale x 8, interleaved count: 2)
+define i32 @or(i32* nocapture %a, i32* nocapture readonly %b, i64 %n) {
+; CHECK-LABEL: @or
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[LOAD2:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[OR1:.*]] = or <vscale x 8 x i32> %[[LOAD1]]
+; CHECK: %[[OR2:.*]] = or <vscale x 8 x i32> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[OR:.*]] = or <vscale x 8 x i32> %[[OR2]], %[[OR1]]
+; CHECK-NEXT: call i32 @llvm.vector.reduce.or.nxv8i32(<vscale x 8 x i32> %[[OR]])
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.07 = phi i32 [ 2, %entry ], [ %or, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %or = or i32 %0, %sum.07
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:                                 ; preds = %for.body, %entry
+  ret i32 %or
+}
+
+; AND
+
+; CHECK-REMARK: vectorized loop (vectorization width: vscale x 8, interleaved count: 2)
+define i32 @and(i32* nocapture %a, i32* nocapture readonly %b, i64 %n) {
+; CHECK-LABEL: @and
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[LOAD2:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[AND1:.*]] = and <vscale x 8 x i32> %[[LOAD1]]
+; CHECK: %[[AND2:.*]] = and <vscale x 8 x i32> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[ABD:.*]] = and <vscale x 8 x i32> %[[ADD2]], %[[AND1]]
+; CHECK-NEXT: call i32 @llvm.vector.reduce.and.nxv8i32(<vscale x 8 x i32> %[[ADD]])
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.07 = phi i32 [ 2, %entry ], [ %and, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %and = and i32 %0, %sum.07
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:                                 ; preds = %for.body, %entry
+  ret i32 %and
+}
+
+; XOR
+
+; CHECK-REMARK: vectorized loop (vectorization width: vscale x 8, interleaved count: 2)
+define i32 @xor(i32* nocapture %a, i32* nocapture readonly %b, i64 %n) {
+; CHECK-LABEL: @xor
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[LOAD2:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[XOR1:.*]] = xor <vscale x 8 x i32> %[[LOAD1]]
+; CHECK: %[[XOR2:.*]] = xor <vscale x 8 x i32> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[XOR:.*]] = xor <vscale x 8 x i32> %[[XOR2]], %[[XOR1]]
+; CHECK-NEXT: call i32 @llvm.vector.reduce.xor.nxv8i32(<vscale x 8 x i32> %[[XOR]])
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.07 = phi i32 [ 2, %entry ], [ %xor, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %xor = xor i32 %0, %sum.07
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:                                 ; preds = %for.body, %entry
+  ret i32 %xor
+}
+
+; CHECK-REMARK: vectorized loop (vectorization width: vscale x 8, interleaved count: 2)
+; SMIN
+
+define i32 @smin(i32* nocapture %a, i32* nocapture readonly %b, i64 %n) {
+; CHECK-LABEL: @smin
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[LOAD2:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[ICMP1:.*]] = icmp slt <vscale x 8 x i32> %[[LOAD1]]
+; CHECK: %[[ICMP2:.*]] = icmp slt <vscale x 8 x i32> %[[LOAD2]]
+; CHECK: %[[SEL1:.*]] = select <vscale x 8 x i1> %[[ICMP1]], <vscale x 8 x i32> %[[LOAD1]]
+; CHECK: %[[SEL2:.*]] = select <vscale x 8 x i1> %[[ICMP2]], <vscale x 8 x i32> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[ICMP:.*]] = icmp slt <vscale x 8 x i32> %[[SEL1]], %[[SEL2]]
+; CHECK-NEXT: %[[SEL:.*]] = select <vscale x 8 x i1> %[[ICMP]], <vscale x 8 x i32> %[[SEL1]], <vscale x 8 x i32> %[[SEL2]]
+; CHECK-NEXT: call i32 @llvm.vector.reduce.smin.nxv8i32(<vscale x 8 x i32>  %[[SEL]])
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.010 = phi i32 [ 2, %entry ], [ %.sroa.speculated, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %cmp.i = icmp slt i32 %0, %sum.010
+  %.sroa.speculated = select i1 %cmp.i, i32 %0, i32 %sum.010
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:
+  ret i32 %.sroa.speculated
+}
+
+; CHECK-REMARK: vectorized loop (vectorization width: vscale x 8, interleaved count: 2)
+; UMAX
+
+define i32 @umax(i32* nocapture %a, i32* nocapture readonly %b, i64 %n) {
+; CHECK-LABEL: @umax
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[LOAD2:.*]] = load <vscale x 8 x i32>
+; CHECK: %[[ICMP1:.*]] = icmp ugt <vscale x 8 x i32> %[[LOAD1]]
+; CHECK: %[[ICMP2:.*]] = icmp ugt <vscale x 8 x i32> %[[LOAD2]]
+; CHECK: %[[SEL1:.*]] = select <vscale x 8 x i1> %[[ICMP1]], <vscale x 8 x i32> %[[LOAD1]]
+; CHECK: %[[SEL2:.*]] = select <vscale x 8 x i1> %[[ICMP2]], <vscale x 8 x i32> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[ICMP:.*]] = icmp ugt <vscale x 8 x i32> %[[SEL1]], %[[SEL2]]
+; CHECK-NEXT: %[[SEL:.*]] = select <vscale x 8 x i1> %[[ICMP]], <vscale x 8 x i32> %[[SEL1]], <vscale x 8 x i32> %[[SEL2]]
+; CHECK-NEXT: call i32 @llvm.vector.reduce.umax.nxv8i32(<vscale x 8 x i32>  %[[SEL]])
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.010 = phi i32 [ 2, %entry ], [ %.sroa.speculated, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %cmp.i = icmp ugt i32 %0, %sum.010
+  %.sroa.speculated = select i1 %cmp.i, i32 %0, i32 %sum.010
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:
+  ret i32 %.sroa.speculated
+}
+
+; CHECK-REMARK: vectorized loop (vectorization width: vscale x 8, interleaved count: 2)
+; FADD (FAST)
+
+define float @fadd_fast(float* noalias nocapture readonly %a, i64 %n) {
+; CHECK-LABEL: @fadd_fast
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <vscale x 8 x float>
+; CHECK: %[[LOAD2:.*]] = load <vscale x 8 x float>
+; CHECK: %[[ADD1:.*]] = fadd fast <vscale x 8 x float> %[[LOAD1]]
+; CHECK: %[[ADD2:.*]] = fadd fast <vscale x 8 x float> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[ADD:.*]] = fadd fast <vscale x 8 x float> %[[ADD2]], %[[ADD1]]
+; CHECK-NEXT: call fast float @llvm.vector.reduce.fadd.nxv8f32(float -0.000000e+00, <vscale x 8 x float> %[[ADD]])
+entry:
+  br label %for.body
+
+for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.07 = phi float [ 0.000000e+00, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds float, float* %a, i64 %iv
+  %0 = load float, float* %arrayidx, align 4
+  %add = fadd fast float %0, %sum.07
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:
+  ret float %add
+}
+
+; CHECK-REMARK: Scalable vectorization not supported for the reduction operations found in this loop. Using fixed-width vectorization instead.
+; CHECK-REMARK: vectorized loop (vectorization width: 8, interleaved count: 2)
+define bfloat @fadd_fast_bfloat(bfloat* noalias nocapture readonly %a, i64 %n) {
+; CHECK-LABEL: @fadd_fast_bfloat
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <8 x bfloat>
+; CHECK: %[[LOAD2:.*]] = load <8 x bfloat>
+; CHECK: %[[FADD1:.*]] = fadd fast <8 x bfloat> %[[LOAD1]]
+; CHECK: %[[FADD2:.*]] = fadd fast <8 x bfloat> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[RDX:.*]] = fadd fast <8 x bfloat> %[[FADD2]], %[[FADD1]]
+; CHECK: call fast bfloat @llvm.vector.reduce.fadd.v8bf16(bfloat 0xR8000, <8 x bfloat> %[[RDX]])
+entry:
+  br label %for.body
+
+for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.07 = phi bfloat [ 0.000000e+00, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds bfloat, bfloat* %a, i64 %iv
+  %0 = load bfloat, bfloat* %arrayidx, align 4
+  %add = fadd fast bfloat %0, %sum.07
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:
+  ret bfloat %add
+}
+
+; FMIN (FAST)
+
+; CHECK-REMARK: vectorized loop (vectorization width: vscale x 8, interleaved count: 2)
+define float @fmin_fast(float* noalias nocapture readonly %a, i64 %n) #0 {
+; CHECK-LABEL: @fmin_fast
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <vscale x 8 x float>
+; CHECK: %[[LOAD2:.*]] = load <vscale x 8 x float>
+; CHECK: %[[FCMP1:.*]] = fcmp olt <vscale x 8 x float> %[[LOAD1]]
+; CHECK: %[[FCMP2:.*]] = fcmp olt <vscale x 8 x float> %[[LOAD2]]
+; CHECK: %[[SEL1:.*]] = select <vscale x 8 x i1> %[[FCMP1]], <vscale x 8 x float> %[[LOAD1]]
+; CHECK: %[[SEL2:.*]] = select <vscale x 8 x i1> %[[FCMP2]], <vscale x 8 x float> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[FCMP:.*]] = fcmp olt <vscale x 8 x float> %[[SEL1]], %[[SEL2]]
+; CHECK-NEXT: %[[SEL:.*]] = select <vscale x 8 x i1> %[[FCMP]], <vscale x 8 x float> %[[SEL1]], <vscale x 8 x float> %[[SEL2]]
+; CHECK-NEXT: call float @llvm.vector.reduce.fmin.nxv8f32(<vscale x 8 x float> %[[SEL]])
+entry:
+  br label %for.body
+
+for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.07 = phi float [ 0.000000e+00, %entry ], [ %.sroa.speculated, %for.body ]
+  %arrayidx = getelementptr inbounds float, float* %a, i64 %iv
+  %0 = load float, float* %arrayidx, align 4
+  %cmp.i = fcmp olt float %0, %sum.07
+  %.sroa.speculated = select i1 %cmp.i, float %0, float %sum.07
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:
+  ret float %.sroa.speculated
+}
+
+; FMAX (FAST)
+
+; CHECK-REMARK: vectorized loop (vectorization width: vscale x 8, interleaved count: 2)
+define float @fmax_fast(float* noalias nocapture readonly %a, i64 %n) #0 {
+; CHECK-LABEL: @fmax_fast
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <vscale x 8 x float>
+; CHECK: %[[LOAD2:.*]] = load <vscale x 8 x float>
+; CHECK: %[[FCMP1:.*]] = fcmp fast ogt <vscale x 8 x float> %[[LOAD1]]
+; CHECK: %[[FCMP2:.*]] = fcmp fast ogt <vscale x 8 x float> %[[LOAD2]]
+; CHECK: %[[SEL1:.*]] = select <vscale x 8 x i1> %[[FCMP1]], <vscale x 8 x float> %[[LOAD1]]
+; CHECK: %[[SEL2:.*]] = select <vscale x 8 x i1> %[[FCMP2]], <vscale x 8 x float> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[FCMP:.*]] = fcmp fast ogt <vscale x 8 x float> %[[SEL1]], %[[SEL2]]
+; CHECK-NEXT: %[[SEL:.*]] = select fast <vscale x 8 x i1> %[[FCMP]], <vscale x 8 x float> %[[SEL1]], <vscale x 8 x float> %[[SEL2]]
+; CHECK-NEXT: call fast float @llvm.vector.reduce.fmax.nxv8f32(<vscale x 8 x float> %[[SEL]])
+entry:
+  br label %for.body
+
+for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.07 = phi float [ 0.000000e+00, %entry ], [ %.sroa.speculated, %for.body ]
+  %arrayidx = getelementptr inbounds float, float* %a, i64 %iv
+  %0 = load float, float* %arrayidx, align 4
+  %cmp.i = fcmp fast ogt float %0, %sum.07
+  %.sroa.speculated = select i1 %cmp.i, float %0, float %sum.07
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:
+  ret float %.sroa.speculated
+}
+
+; Reduction cannot be vectorized
+
+; MUL
+
+; CHECK-REMARK: Scalable vectorization not supported for the reduction operations found in this loop. Using fixed-width vectorization instead.
+; CHECK-REMARK: vectorized loop (vectorization width: 8, interleaved count: 2)
+define i32 @mul(i32* nocapture %a, i32* nocapture readonly %b, i64 %n) {
+; CHECK-LABEL: @mul
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <8 x i32>
+; CHECK: %[[LOAD2:.*]] = load <8 x i32>
+; CHECK: %[[MUL1:.*]] = mul <8 x i32> %[[LOAD1]]
+; CHECK: %[[MUL2:.*]] = mul <8 x i32> %[[LOAD2]]
+; CHECK: middle.block:
+; CHECK: %[[RDX:.*]] = mul <8 x i32> %[[MUL2]], %[[MUL1]]
+; CHECK: call i32 @llvm.vector.reduce.mul.v8i32(<8 x i32> %[[RDX]])
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %sum.07 = phi i32 [ 2, %entry ], [ %mul, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %mul = mul nsw i32 %0, %sum.07
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:                                 ; preds = %for.body, %entry
+  ret i32 %mul
+}
+
+; Note: This test was added to ensure we always check the legality of reductions (end emit a warning if necessary) before checking for memory dependencies
+; CHECK-REMARK: Scalable vectorization not supported for the reduction operations found in this loop. Using fixed-width vectorization instead.
+; CHECK-REMARK: vectorized loop (vectorization width: 8, interleaved count: 2)
+define i32 @memory_dependence(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i64 %n) {
+; CHECK-LABEL: @memory_dependence
+; CHECK: vector.body:
+; CHECK: %[[LOAD1:.*]] = load <8 x i32>
+; CHECK: %[[LOAD2:.*]] = load <8 x i32>
+; CHECK: %[[LOAD3:.*]] = load <8 x i32>
+; CHECK: %[[LOAD4:.*]] = load <8 x i32>
+; CHECK: %[[ADD1:.*]] = add nsw <8 x i32> %[[LOAD3]], %[[LOAD1]]
+; CHECK: %[[ADD2:.*]] = add nsw <8 x i32> %[[LOAD4]], %[[LOAD2]]
+; CHECK: %[[MUL1:.*]] = mul <8 x i32> %[[LOAD3]]
+; CHECK: %[[MUL2:.*]] = mul <8 x i32> %[[LOAD4]]
+; CHECK: middle.block:
+; CHECK: %[[RDX:.*]] = mul <8 x i32> %[[MUL2]], %[[MUL1]]
+; CHECK: call i32 @llvm.vector.reduce.mul.v8i32(<8 x i32> %[[RDX]])
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %sum = phi i32 [ %mul, %for.body ], [ 2, %entry ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %i
+  %0 = load i32, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32, i32* %b, i64 %i
+  %1 = load i32, i32* %arrayidx1, align 4
+  %add = add nsw i32 %1, %0
+  %add2 = add nuw nsw i64 %i, 32
+  %arrayidx3 = getelementptr inbounds i32, i32* %a, i64 %add2
+  store i32 %add, i32* %arrayidx3, align 4
+  %mul = mul nsw i32 %1, %sum
+  %inc = add nuw nsw i64 %i, 1
+  %exitcond.not = icmp eq i64 %inc, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:
+  ret i32 %mul
+}
+
+attributes #0 = { "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" }
+
+!0 = distinct !{!0, !1, !2, !3, !4}
+!1 = !{!"llvm.loop.vectorize.width", i32 8}
+!2 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
+!3 = !{!"llvm.loop.interleave.count", i32 2}
+!4 = !{!"llvm.loop.vectorize.enable", i1 true}