[VPlan] Expand WidenInt inductions with nuw/nsw (#163538)

While at it, record VPIRFlags in VPWidenInductionRecipe.

Author: artagnon

flang/test/Integration/unroll-loops.f90

@@ -25,7 +25,7 @@ subroutine unroll(a)
     ! NO-UNROLL-NEXT: %[[GEP:.*]] = getelementptr i64, ptr %[[ARG0]], i64 %[[IND]]
     ! NO-UNROLL-NEXT: store <2 x i64> %[[VIND]], ptr %[[GEP]]
     ! NO-UNROLL-NEXT: %[[NIV:.*]] = add nuw i64 %{{.*}}, 2
-    ! NO-UNROLL-NEXT: %[[NVIND]] = add <2 x i64> %[[VIND]], splat (i64 2)
+    ! NO-UNROLL-NEXT: %[[NVIND]] = add nuw nsw <2 x i64> %[[VIND]], splat (i64 2)
     !
     ! UNROLL-NEXT: %[[VIND1:.*]] = add <2 x i64> %[[VIND]], splat (i64 2)
     ! UNROLL-NEXT: %[[GEP0:.*]] = getelementptr i64, ptr %[[ARG0]], i64 %[[IND]]

flang/test/Lower/HLFIR/unroll-loops.fir

@@ -27,7 +27,7 @@ func.func @unroll(%arg0: !fir.ref<!fir.array<1000 x index>> {fir.bindc_name = "a
     // NO-UNROLL-NEXT: %[[GEP:.*]] = getelementptr i64, ptr %[[ARG0]], i64 %[[IND]]
     // NO-UNROLL-NEXT: store <2 x i64> %[[VIND]], ptr %[[GEP]]
     // NO-UNROLL-NEXT: %[[NIV:.*]] = add nuw i64 %{{.*}}, 2
-    // NO-UNROLL-NEXT: %[[NVIND]] = add <2 x i64> %[[VIND]], splat (i64 2)
+    // NO-UNROLL-NEXT: %[[NVIND]] = add nuw nsw <2 x i64> %[[VIND]], splat (i64 2)
 
     // UNROLL-NEXT: %[[VIND1:.*]] = add <2 x i64> %[[VIND]], splat (i64 2)
     // UNROLL-NEXT: %[[GEP0:.*]] = getelementptr i64, ptr %[[ARG0]], i64 %[[IND]]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -7639,6 +7639,10 @@ createWidenInductionRecipes(VPInstruction *PhiR,
   assert(Plan.getLiveIn(IndDesc.getStartValue()) == Start &&
          "Start VPValue must match IndDesc's start value");
 
+  // It is always safe to copy over the NoWrap and FastMath flags. In
+  // particular, when folding tail by masking, the masked-off lanes are never
+  // used, so it is safe.
+  VPIRFlags Flags = vputils::getFlagsFromIndDesc(IndDesc);
   VPValue *Step =
       vputils::getOrCreateVPValueForSCEVExpr(Plan, IndDesc.getStep());
 
@@ -7651,7 +7655,7 @@ createWidenInductionRecipes(VPInstruction *PhiR,
 
   PHINode *Phi = cast<PHINode>(PhiR->getUnderlyingInstr());
   return new VPWidenIntOrFpInductionRecipe(Phi, Start, Step, &Plan.getVF(),
-                                           IndDesc, PhiR->getDebugLoc());
+                                           IndDesc, Flags, PhiR->getDebugLoc());
 }
 
 VPHeaderPHIRecipe *
@@ -7705,10 +7709,15 @@ VPRecipeBuilder::tryToOptimizeInductionTruncate(VPInstruction *VPI,
   PHINode *Phi = WidenIV->getPHINode();
   VPValue *Start = WidenIV->getStartValue();
   const InductionDescriptor &IndDesc = WidenIV->getInductionDescriptor();
+
+  // It is always safe to copy over the NoWrap and FastMath flags. In
+  // particular, when folding tail by masking, the masked-off lanes are never
+  // used, so it is safe.
+  VPIRFlags Flags = vputils::getFlagsFromIndDesc(IndDesc);
   VPValue *Step =
       vputils::getOrCreateVPValueForSCEVExpr(Plan, IndDesc.getStep());
-  return new VPWidenIntOrFpInductionRecipe(Phi, Start, Step, &Plan.getVF(),
-                                           IndDesc, I, VPI->getDebugLoc());
+  return new VPWidenIntOrFpInductionRecipe(
+      Phi, Start, Step, &Plan.getVF(), IndDesc, I, Flags, VPI->getDebugLoc());
 }
 
 VPSingleDefRecipe *VPRecipeBuilder::tryToWidenCall(VPInstruction *VPI,

llvm/lib/Transforms/Vectorize/VPlan.h

@@ -2124,7 +2124,8 @@ class VPWidenInductionRecipe : public VPHeaderPHIRecipe {
 /// A recipe for handling phi nodes of integer and floating-point inductions,
 /// producing their vector values. This is an abstract recipe and must be
 /// converted to concrete recipes before executing.
-class VPWidenIntOrFpInductionRecipe : public VPWidenInductionRecipe {
+class VPWidenIntOrFpInductionRecipe : public VPWidenInductionRecipe,
+                                      public VPIRFlags {
   TruncInst *Trunc;
 
   // If this recipe is unrolled it will have 2 additional operands.
@@ -2133,19 +2134,20 @@ class VPWidenIntOrFpInductionRecipe : public VPWidenInductionRecipe {
 public:
   VPWidenIntOrFpInductionRecipe(PHINode *IV, VPValue *Start, VPValue *Step,
                                 VPValue *VF, const InductionDescriptor &IndDesc,
-                                DebugLoc DL)
+                                const VPIRFlags &Flags, DebugLoc DL)
       : VPWidenInductionRecipe(VPDef::VPWidenIntOrFpInductionSC, IV, Start,
                                Step, IndDesc, DL),
-        Trunc(nullptr) {
+        VPIRFlags(Flags), Trunc(nullptr) {
     addOperand(VF);
   }
 
   VPWidenIntOrFpInductionRecipe(PHINode *IV, VPValue *Start, VPValue *Step,
                                 VPValue *VF, const InductionDescriptor &IndDesc,
-                                TruncInst *Trunc, DebugLoc DL)
+                                TruncInst *Trunc, const VPIRFlags &Flags,
+                                DebugLoc DL)
       : VPWidenInductionRecipe(VPDef::VPWidenIntOrFpInductionSC, IV, Start,
                                Step, IndDesc, DL),
-        Trunc(Trunc) {
+        VPIRFlags(Flags), Trunc(Trunc) {
     addOperand(VF);
     SmallVector<std::pair<unsigned, MDNode *>> Metadata;
     (void)Metadata;
@@ -2159,7 +2161,7 @@ class VPWidenIntOrFpInductionRecipe : public VPWidenInductionRecipe {
   VPWidenIntOrFpInductionRecipe *clone() override {
     return new VPWidenIntOrFpInductionRecipe(
         getPHINode(), getStartValue(), getStepValue(), getVFValue(),
-        getInductionDescriptor(), Trunc, getDebugLoc());
+        getInductionDescriptor(), Trunc, *this, getDebugLoc());
   }
 
   VP_CLASSOF_IMPL(VPDef::VPWidenIntOrFpInductionSC)

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -2376,7 +2376,9 @@ void VPWidenIntOrFpInductionRecipe::print(raw_ostream &O, const Twine &Indent,
                                           VPSlotTracker &SlotTracker) const {
   O << Indent;
   printAsOperand(O, SlotTracker);
-  O << " = WIDEN-INDUCTION  ";
+  O << " = WIDEN-INDUCTION";
+  printFlags(O);
+  O << " ";
   printOperands(O, SlotTracker);
 
   if (auto *TI = getTruncInst())

llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp

@@ -76,8 +76,13 @@ bool VPlanTransforms::tryToConvertVPInstructionsToVPRecipes(
           VPValue *Start = Plan.getOrAddLiveIn(II->getStartValue());
           VPValue *Step =
               vputils::getOrCreateVPValueForSCEVExpr(Plan, II->getStep());
+          // It is always safe to copy over the NoWrap and FastMath flags. In
+          // particular, when folding tail by masking, the masked-off lanes are
+          // never used, so it is safe.
+          VPIRFlags Flags = vputils::getFlagsFromIndDesc(*II);
           NewRecipe = new VPWidenIntOrFpInductionRecipe(
-              Phi, Start, Step, &Plan.getVF(), *II, Ingredient.getDebugLoc());
+              Phi, Start, Step, &Plan.getVF(), *II, Flags,
+              Ingredient.getDebugLoc());
         }
       } else {
         assert(isa<VPInstruction>(&Ingredient) &&
@@ -542,6 +547,11 @@ static void removeRedundantCanonicalIVs(VPlan &Plan) {
     // only.
     if (!vputils::onlyScalarValuesUsed(WidenOriginalIV) ||
         vputils::onlyFirstLaneUsed(WidenNewIV)) {
+      // We are replacing a wide canonical iv with a suitable wide induction.
+      // This is used to compute header mask, hence all lanes will be used and
+      // we need to drop wrap flags only applying to lanes guranteed to execute
+      // in the original scalar loop.
+      WidenOriginalIV->dropPoisonGeneratingFlags();
       WidenNewIV->replaceAllUsesWith(WidenOriginalIV);
       WidenNewIV->eraseFromParent();
       return;
@@ -3290,16 +3300,13 @@ expandVPWidenIntOrFpInduction(VPWidenIntOrFpInductionRecipe *WidenIVR,
   const InductionDescriptor &ID = WidenIVR->getInductionDescriptor();
   Instruction::BinaryOps AddOp;
   Instruction::BinaryOps MulOp;
-  // FIXME: The newly created binary instructions should contain nsw/nuw
-  // flags, which can be found from the original scalar operations.
-  VPIRFlags Flags;
+  VPIRFlags Flags = *WidenIVR;
   if (ID.getKind() == InductionDescriptor::IK_IntInduction) {
     AddOp = Instruction::Add;
     MulOp = Instruction::Mul;
   } else {
     AddOp = ID.getInductionOpcode();
     MulOp = Instruction::FMul;
-    Flags = ID.getInductionBinOp()->getFastMathFlags();
   }
 
   // If the phi is truncated, truncate the start and step values.

llvm/lib/Transforms/Vectorize/VPlanUtils.h

@@ -73,6 +73,19 @@ std::optional<VPValue *>
 getRecipesForUncountableExit(VPlan &Plan,
                              SmallVectorImpl<VPRecipeBase *> &Recipes,
                              SmallVectorImpl<VPRecipeBase *> &GEPs);
+
+/// Extracts and returns NoWrap and FastMath flags from the induction binop in
+/// \p ID.
+inline VPIRFlags getFlagsFromIndDesc(const InductionDescriptor &ID) {
+  if (ID.getKind() == InductionDescriptor::IK_FpInduction)
+    return ID.getInductionBinOp()->getFastMathFlags();
+
+  if (auto *OBO = dyn_cast_if_present<OverflowingBinaryOperator>(
+          ID.getInductionBinOp()))
+    return VPIRFlags::WrapFlagsTy(OBO->hasNoUnsignedWrap(),
+                                  OBO->hasNoSignedWrap());
+  return {};
+}
 } // namespace vputils
 
 //===----------------------------------------------------------------------===//

llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll

@@ -14,8 +14,8 @@ define void @clamped_tc_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range(1,1
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[VAL]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 8 x i64> @llvm.stepvector.nxv8i64()
-; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 8 x i64> [[TMP8]], splat (i64 1)
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP7]]
+; CHECK-NEXT:    [[TMP3:%.*]] = mul <vscale x 8 x i64> [[TMP8]], splat (i64 1)
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP3]]
 ; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP1]], i64 0
 ; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[DOTSPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
@@ -76,8 +76,8 @@ define void @clamped_tc_max_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[VAL]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 8 x i64> @llvm.stepvector.nxv8i64()
-; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 8 x i64> [[TMP8]], splat (i64 1)
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP7]]
+; CHECK-NEXT:    [[TMP3:%.*]] = mul <vscale x 8 x i64> [[TMP8]], splat (i64 1)
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP3]]
 ; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP1]], i64 0
 ; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[DOTSPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]

llvm/test/Transforms/LoopVectorize/AArch64/conditional-branches-cost.ll

@@ -1052,7 +1052,7 @@ define void @redundant_branch_and_tail_folding(ptr %dst, i1 %c) {
 ; DEFAULT-NEXT:    [[TMP2:%.*]] = extractelement <4 x i32> [[TMP1]], i32 3
 ; DEFAULT-NEXT:    store i32 [[TMP2]], ptr [[DST]], align 4
 ; DEFAULT-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; DEFAULT-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[STEP_ADD]], splat (i64 4)
+; DEFAULT-NEXT:    [[VEC_IND_NEXT]] = add nuw nsw <4 x i64> [[STEP_ADD]], splat (i64 4)
 ; DEFAULT-NEXT:    [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
 ; DEFAULT-NEXT:    br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP27:![0-9]+]]
 ; DEFAULT:       [[MIDDLE_BLOCK]]:

llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll

@@ -35,7 +35,7 @@ define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) {
 ; CHECK-NEXT:    [[TMP10]] = select <16 x i1> [[TMP17]], <16 x i8> [[VEC_IND]], <16 x i8> [[VEC_PHI]]
 ; CHECK-NEXT:    [[TMP11]] = select <16 x i1> [[TMP23]], <16 x i8> [[STEP_ADD]], <16 x i8> [[VEC_PHI2]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 32
-; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <16 x i8> [[STEP_ADD]], splat (i8 16)
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add nuw nsw <16 x i8> [[STEP_ADD]], splat (i8 16)
 ; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       [[MIDDLE_BLOCK]]:
@@ -48,7 +48,7 @@ define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) {
 ; CHECK:       [[VEC_EPILOG_ITER_CHECK]]:
 ; CHECK-NEXT:    [[IND_END:%.*]] = trunc i32 [[N_VEC]] to i8
 ; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i32 [[N_MOD_VF]], 8
-; CHECK-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]]
+; CHECK-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]], !prof [[PROF3:![0-9]+]]
 ; CHECK:       [[VEC_EPILOG_PH]]:
 ; CHECK-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
@@ -62,21 +62,21 @@ define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) {
 ; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <8 x i8> [[DOTSPLATINSERT]], <8 x i8> poison, <8 x i32> zeroinitializer
 ; CHECK-NEXT:    [[DOTSPLATINSERT10:%.*]] = insertelement <8 x i8> poison, i8 [[BC_RESUME_VAL]], i64 0
 ; CHECK-NEXT:    [[DOTSPLAT11:%.*]] = shufflevector <8 x i8> [[DOTSPLATINSERT10]], <8 x i8> poison, <8 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <8 x i8> [[DOTSPLAT11]], <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7>
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add nuw nsw <8 x i8> [[DOTSPLAT11]], <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7>
 ; CHECK-NEXT:    br label %[[VEC_EPILOG_VECTOR_BODY:.*]]
 ; CHECK:       [[VEC_EPILOG_VECTOR_BODY]]:
 ; CHECK-NEXT:    [[INDEX6:%.*]] = phi i32 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT13:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ]
-; CHECK-NEXT:    [[VEC_IND7:%.*]] = phi <8 x i8> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT8:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_IND7:%.*]] = phi <8 x i8> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT13:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI9:%.*]] = phi <8 x i8> [ [[DOTSPLAT]], %[[VEC_EPILOG_PH]] ], [ [[TMP20:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[IV:%.*]] = trunc i32 [[INDEX6]] to i8
 ; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV]]
 ; CHECK-NEXT:    [[WIDE_LOAD12:%.*]] = load <8 x i8>, ptr [[GEP]], align 8
 ; CHECK-NEXT:    [[TMP19:%.*]] = icmp eq <8 x i8> [[WIDE_LOAD12]], splat (i8 3)
 ; CHECK-NEXT:    [[TMP20]] = select <8 x i1> [[TMP19]], <8 x i8> [[VEC_IND7]], <8 x i8> [[VEC_PHI9]]
 ; CHECK-NEXT:    [[INDEX_NEXT13]] = add nuw i32 [[INDEX6]], 8
-; CHECK-NEXT:    [[VEC_IND_NEXT8]] = add <8 x i8> [[VEC_IND7]], splat (i8 8)
+; CHECK-NEXT:    [[VEC_IND_NEXT13]] = add nuw nsw <8 x i8> [[VEC_IND7]], splat (i8 8)
 ; CHECK-NEXT:    [[TMP21:%.*]] = icmp eq i32 [[INDEX_NEXT13]], [[N_VEC5]]
-; CHECK-NEXT:    br i1 [[TMP21]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP21]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
 ; CHECK:       [[VEC_EPILOG_MIDDLE_BLOCK]]:
 ; CHECK-NEXT:    [[TMP22:%.*]] = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> [[TMP20]])
 ; CHECK-NEXT:    [[RDX_SELECT_CMP14:%.*]] = icmp ne i8 [[TMP22]], -128
@@ -96,7 +96,7 @@ define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) {
 ; CHECK-NEXT:    [[SEL]] = select i1 [[C]], i8 [[IV1]], i8 [[RDX]]
 ; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i8 [[IV1]], 1
 ; CHECK-NEXT:    [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]]
-; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       [[EXIT]]:
 ; CHECK-NEXT:    [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT15]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    ret i8 [[SEL_LCSSA]]
@@ -158,7 +158,7 @@ define i32 @select_icmp_var_start_iv_trunc(i32 %N, i32 %start) #0 {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[STEP_ADD_3]], splat (i32 4)
 ; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
 ; CHECK:       [[MIDDLE_BLOCK]]:
 ; CHECK-NEXT:    [[RDX_MINMAX:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[TMP3]], <4 x i32> [[TMP4]])
 ; CHECK-NEXT:    [[RDX_MINMAX5:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[RDX_MINMAX]], <4 x i32> [[TMP5]])
@@ -170,7 +170,7 @@ define i32 @select_icmp_var_start_iv_trunc(i32 %N, i32 %start) #0 {
 ; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]]
 ; CHECK:       [[VEC_EPILOG_ITER_CHECK]]:
 ; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_MOD_VF]], 4
-; CHECK-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]]
+; CHECK-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]], !prof [[PROF7:![0-9]+]]
 ; CHECK:       [[VEC_EPILOG_PH]]:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
 ; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[FR]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
@@ -197,7 +197,7 @@ define i32 @select_icmp_var_start_iv_trunc(i32 %N, i32 %start) #0 {
 ; CHECK-NEXT:    [[INDEX_NEXT17]] = add nuw i64 [[INDEX11]], 4
 ; CHECK-NEXT:    [[VEC_IND_NEXT16]] = add <4 x i32> [[VEC_IND15]], splat (i32 4)
 ; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT17]], [[N_VEC8]]
-; CHECK-NEXT:    br i1 [[TMP15]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP15]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; CHECK:       [[VEC_EPILOG_MIDDLE_BLOCK]]:
 ; CHECK-NEXT:    [[TMP16:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[TMP14]])
 ; CHECK-NEXT:    [[RDX_SELECT_CMP18:%.*]] = icmp ne i32 [[TMP16]], -2147483648
@@ -216,7 +216,7 @@ define i32 @select_icmp_var_start_iv_trunc(i32 %N, i32 %start) #0 {
 ; CHECK-NEXT:    [[RED_NEXT]] = select i1 [[C]], i32 [[IV_TRUNC]], i32 [[RED]]
 ; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
 ; CHECK-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV]], [[N_EXT]]
-; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
 ; CHECK:       [[EXIT]]:
 ; CHECK-NEXT:    [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT19]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    ret i32 [[RED_NEXT_LCSSA]]