[LoopVectorize][AArch64] Use get.active.lane.mask intrinsic when SVE is enabled

[david-arm]

Summary

When SVE is enabled for AArch64 targets it makes more sense to use the
get.active.lane.mask intrinsic, because SVE has an exact 1-1 mapping
from the intrinsic to the 'whilelo' instruction for legal vector types.
This instruction neatly takes overflow into account as well. This patch
fixes an issue in VPInstruction::generateInstruction that assumed we are
only dealing with fixed-width vectors.

[kmclaughlin]

This seems like a sensible change to me, LGTM!

[david-arm]

I landed this patch with dependencies open, because we don't have to improve the fixed-width code generation of get.active.lane.mask at this moment in time.

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

shouldConsiderAddressTypePromotion(const Instruction &I,
                                      bool &AllowPromotionWithoutCommonHeader);
 
   bool shouldExpandReduction(const IntrinsicInst *II) const { return false; }
 
   unsigned getGISelRematGlobalCost() const {
     return 2;
   }
 
+  bool emitGetActiveLaneMask() const {
+    return ST->hasSVE();
+  }
+
   bool supportsScalableVectors() const { return ST->hasSVE(); }
 
   bool enableScalableVectorization() const { return ST->hasSVE(); }
 
   bool isLegalToVectorizeReduction(const RecurrenceDescriptor &RdxDesc,
                                    ElementCount VF) const;
 
   InstructionCost getArithmeticReductionCost(unsigned Opcode, VectorType *Ty,

llvm/lib/Transforms/Vectorize/VPlan.cpp

void VPInstruction::generateInstruction(VPTransformState &State,
   }
   case VPInstruction::ActiveLaneMask: {
     // Get first lane of vector induction variable.
     Value *VIVElem0 = State.get(getOperand(0), VPIteration(Part, 0));
     // Get the original loop tripcount.
     Value *ScalarTC = State.get(getOperand(1), Part);
 
     auto *Int1Ty = Type::getInt1Ty(Builder.getContext());
-    auto *PredTy = FixedVectorType::get(Int1Ty, State.VF.getKnownMinValue());
+    auto *PredTy = VectorType::get(Int1Ty, State.VF);
     Instruction *Call = Builder.CreateIntrinsic(
         Intrinsic::get_active_lane_mask, {PredTy, ScalarTC->getType()},
         {VIVElem0, ScalarTC}, nullptr, "active.lane.mask");
     State.set(this, Call, Part);
     break;
   }
   case VPInstruction::FirstOrderRecurrenceSplice: {
     // Generate code to combine the previous and current values in vector v3.

llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[UMAX]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT6:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT5]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT2:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT4]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX1]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 [[UMAX]])
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i32, i32* [[PTR:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT6]], <vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[TMP9]])
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT6]], <vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP14]]
 ; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP15]], label %middle.block, label %vector.body
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label %while.end.loopexit, label %scalar.ph
 ;

llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[UMAX]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT6:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT5]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT2:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT4]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX1]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 [[UMAX]])
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i32, i32* [[PTR:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT6]], <vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[TMP9]])
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT6]], <vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP14]]
 ; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP15]], label %middle.block, label %vector.body
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label %while.end.loopexit, label %scalar.ph
 ;

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[UMAX]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT2:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT4]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX1]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 [[UMAX]])
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i32, i32* [[SRC:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr i32, i32* [[DST:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i32, i32* [[TMP13]], i32 0
 ; CHECK-NEXT:    [[TMP15:%.*]] = bitcast i32* [[TMP14]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32>* [[TMP15]], i32 4, <vscale x 4 x i1> [[TMP9]])
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32>* [[TMP15]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP17]]
 ; CHECK-NEXT:    [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP18]], label %middle.block, label %vector.body, !llvm.loop [[LOOP4:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label %while.end.loopexit, label %scalar.ph
 ;

 ; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = sub i64 [[TMP6]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[TMP2]], [[TMP7]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP4]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], 4
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[TMP2]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP9:%.*]] = add <vscale x 4 x i64> [[TMP8]], zeroinitializer
 ; CHECK-NEXT:    [[TMP10:%.*]] = mul <vscale x 4 x i64> [[TMP9]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 4, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP10]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP12:%.*]] = mul i64 [[TMP11]], 4
 ; CHECK-NEXT:    [[TMP13:%.*]] = mul i64 4, [[TMP12]]
 ; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP13]], i32 0
 ; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT2:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], %vector.ph ], [ [[VEC_IND_NEXT:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP14:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP15:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP14]]
 ; CHECK-NEXT:    [[VEC_IV:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT4]], [[TMP15]]
-; CHECK-NEXT:    [[TMP16:%.*]] = icmp ule <vscale x 4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <vscale x 4 x i64> [[VEC_IV]], i32 0
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP16]], i64 [[TMP2]])
 ; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr i32, i32* [[SRC:%.*]], <vscale x 4 x i64> [[VEC_IND]]
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[TMP17]], i32 4, <vscale x 4 x i1> [[TMP16]], <vscale x 4 x i32> undef)
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[TMP17]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> undef)
 ; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr i32, i32* [[DST:%.*]], <vscale x 4 x i64> [[VEC_IND]]
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x i32*> [[TMP18]], i32 4, <vscale x 4 x i1> [[TMP16]])
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x i32*> [[TMP18]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP19:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP20:%.*]] = mul i64 [[TMP19]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP20]]
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
 ; CHECK-NEXT:    [[TMP21:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP21]], label %middle.block, label %vector.body
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label %while.end.loopexit, label %scalar.ph

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[UMAX]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT2:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT4]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX1]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 [[UMAX]])
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i32, i32* [[IND:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr i32, i32* [[SRC:%.*]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD]]
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[TMP13]], i32 4, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i32> undef)
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> undef)
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i32, i32* [[DST:%.*]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD]]
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x i32*> [[TMP14]], i32 4, <vscale x 4 x i1> [[TMP9]])
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x i32*> [[TMP14]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP16]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP17]], label %middle.block, label %vector.body
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label %while.end.loopexit, label %scalar.ph
 ;

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N:%.*]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[N]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT1]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT2]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 %n)
 ; CHECK-NEXT:    [[TMP10:%.*]] = load i32, i32* [[SRC:%.*]], align 4
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[TMP10]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP11]], i32 0
 ; CHECK-NEXT:    [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT4]], <vscale x 4 x i32>* [[TMP13]], i32 4, <vscale x 4 x i1> [[TMP9]])
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT4]], <vscale x 4 x i32>* [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP14]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP15]]
 ; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP16]], label %middle.block, label %vector.body, !llvm.loop [[LOOP6:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label %for.end, label %scalar.ph
 ;

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N:%.*]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[N]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <vscale x 4 x i32*> poison, i32* [[SRC:%.*]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT6:%.*]] = shufflevector <vscale x 4 x i32*> [[BROADCAST_SPLATINSERT5]], <vscale x 4 x i32*> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT2:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT4]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX1]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 %n)
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[COND:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], zeroinitializer
 ; CHECK-NEXT:    [[TMP14:%.*]] = xor <vscale x 4 x i1> [[TMP13]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP15:%.*]] = select <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i1> [[TMP14]], <vscale x 4 x i1> zeroinitializer
+; CHECK-NEXT:    [[TMP15:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i1> [[TMP14]], <vscale x 4 x i1> zeroinitializer
 ; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[BROADCAST_SPLAT6]], i32 4, <vscale x 4 x i1> [[TMP15]], <vscale x 4 x i32> undef)
-; CHECK-NEXT:    [[TMP16:%.*]] = select <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i1> [[TMP13]], <vscale x 4 x i1> zeroinitializer
+; CHECK-NEXT:    [[TMP16:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i1> [[TMP13]], <vscale x 4 x i1> zeroinitializer
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <vscale x 4 x i1> [[TMP16]], <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> [[WIDE_MASKED_GATHER]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP18:%.*]] = or <vscale x 4 x i1> [[TMP15]], [[TMP16]]
 ; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds i32, i32* [[TMP17]], i32 0
 ; CHECK-NEXT:    [[TMP20:%.*]] = bitcast i32* [[TMP19]] to <vscale x 4 x i32>*
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[PREDPHI]], <vscale x 4 x i32>* [[TMP20]], i32 4, <vscale x 4 x i1> [[TMP18]])
 ; CHECK-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 4

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N:%.*]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[N]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i32*> poison, i32* [[DST:%.*]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i32*> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i32*> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT1]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT2]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 %n)
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i32> poison)
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32*> [[BROADCAST_SPLAT4]], i32 4, <vscale x 4 x i1> [[TMP9]])
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32*> [[BROADCAST_SPLAT4]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP14]]
 ; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP15]], label %middle.block, label %vector.body
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label %for.end, label %scalar.ph
 ;

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[UMAX]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT2:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT4]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX1]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 [[UMAX]])
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr float, float* [[SRC:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr float, float* [[DST:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr float, float* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP13:%.*]] = bitcast float* [[TMP12]] to <vscale x 4 x float>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP13]], i32 4, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x float> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> poison)
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr float, float* [[TMP11]], i32 0
 ; CHECK-NEXT:    [[TMP15:%.*]] = bitcast float* [[TMP14]] to <vscale x 4 x float>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD5:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP15]], i32 4, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x float> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD5:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP15]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> poison)
 ; CHECK-NEXT:    [[TMP16:%.*]] = fdiv <vscale x 4 x float> [[WIDE_MASKED_LOAD]], [[WIDE_MASKED_LOAD5]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = bitcast float* [[TMP14]] to <vscale x 4 x float>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4f32.p0nxv4f32(<vscale x 4 x float> [[TMP16]], <vscale x 4 x float>* [[TMP17]], i32 4, <vscale x 4 x i1> [[TMP9]])
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4f32.p0nxv4f32(<vscale x 4 x float> [[TMP16]], <vscale x 4 x float>* [[TMP17]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP18:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP19:%.*]] = mul i64 [[TMP18]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP19]]
 ; CHECK-NEXT:    [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP20]], label %middle.block, label %vector.body, !llvm.loop [[LOOP18:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label %while.end.loopexit, label %scalar.ph
 ;

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[UMAX]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT2:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ insertelement (<vscale x 4 x i32> zeroinitializer, i32 0, i32 0), %vector.ph ], [ [[TMP16:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT4]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX1]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 [[UMAX]])
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i32, i32* [[PTR:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP13]] = add <vscale x 4 x i32> [[VEC_PHI]], [[WIDE_MASKED_LOAD]]
-; CHECK-NEXT:    [[TMP16:%.*]] = select <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i32> [[TMP13]], <vscale x 4 x i32> [[VEC_PHI]]
+; CHECK-NEXT:    [[TMP16:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> [[TMP13]], <vscale x 4 x i32> [[VEC_PHI]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP14]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP15]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP17]], label %middle.block, label %vector.body, !llvm.loop [[LOOP20:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[TMP18:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP16]])
 ; CHECK-NEXT:    br i1 true, label %while.end.loopexit, label %scalar.ph

 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], 1
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP4]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[UMAX]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %vector.body
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT2:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi float [ 0.000000e+00, %vector.ph ], [ [[TMP14:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = add <vscale x 4 x i64> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul <vscale x 4 x i64> [[TMP6]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT4]], [[TMP7]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX1]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP8]], i64 [[UMAX]])
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr float, float* [[PTR:%.*]], i64 [[TMP8]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr float, float* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast float* [[TMP11]] to <vscale x 4 x float>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP12]], i32 4, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x float> poison)
-; CHECK-NEXT:    [[TMP13:%.*]] = select <vscale x 4 x i1> [[TMP9]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float -0.000000e+00, i32 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> poison)
+; CHECK-NEXT:    [[TMP13:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float -0.000000e+00, i32 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP14]] = call float @llvm.vector.reduce.fadd.nxv4f32(float [[VEC_PHI]], <vscale x 4 x float> [[TMP13]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP16]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP17]], label %middle.block, label %vector.body, !llvm.loop [[LOOP22:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label %while.end.loopexit, label %scalar.ph

llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll

 define void @uniform_load(i32* noalias %dst, i32* noalias readonly %src, i64 %n) #0 {
 ; CHECK-LABEL: @uniform_load(
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[IDX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[IDX_NEXT:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i64> poison, i64 [[IDX]], i32 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[TMP2]], <i64 0, i64 1, i64 2, i64 3>
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[IDX]], 0
-; CHECK-NEXT:    [[LOOP_PRED:%.*]] = icmp ule <4 x i64> [[INDUCTION]]
+; CHECK-NEXT:    [[LOOP_PRED:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[TMP3]], i64 %n)
 ; CHECK-NEXT:    [[LOAD_VAL:%.*]] = load i32, i32* %src, align 4
 ; CHECK-NOT:     load i32, i32* %src, align 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[LOAD_VAL]], i32 0
 ; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* %dst, i64 [[TMP3]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i32 0
 ; CHECK-NEXT:    [[STORE_PTR:%.*]] = bitcast i32* [[TMP7]] to <4 x i32>*
 ; CHECK-NEXT:    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> [[TMP5]], <4 x i32>* [[STORE_PTR]], i32 4, <4 x i1> [[LOOP_PRED]])

 ; CHECK:       vector.ph:
 ; CHECK:         [[TMP1:%.*]] = insertelement <4 x i32*> poison, i32* %src, i32 0
 ; CHECK-NEXT:    [[SRC_SPLAT:%.*]] = shufflevector <4 x i32*> [[TMP1]], <4 x i32*> poison, <4 x i32> zeroinitializer
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[IDX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[IDX_NEXT:%.*]], %vector.body ]
 ; CHECK:         [[TMP1:%.*]] = insertelement <4 x i64> poison, i64 [[IDX]], i32 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[TMP2]], <i64 0, i64 1, i64 2, i64 3>
-; CHECK:         [[LOOP_PRED:%.*]] = icmp ule <4 x i64> [[INDUCTION]]
+; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[IDX]], 0
+; CHECK-NEXT:    [[LOOP_PRED:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[TMP3]], i64 %n)
 ; CHECK:         [[COND_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* {{%.*}}, i32 4, <4 x i1> [[LOOP_PRED]], <4 x i32> poison)
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq <4 x i32> [[COND_LOAD]], zeroinitializer
-; CHECK-NEXT:    [[TMP4:%.*]] = xor <4 x i1> [[TMP3]], <i1 true, i1 true, i1 true, i1 true>
-; CHECK-NEXT:    [[MASK:%.*]] = select <4 x i1> [[LOOP_PRED]], <4 x i1> [[TMP4]], <4 x i1> zeroinitializer
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <4 x i32> [[COND_LOAD]], zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = xor <4 x i1> [[TMP4]], <i1 true, i1 true, i1 true, i1 true>
+; CHECK-NEXT:    [[MASK:%.*]] = select <4 x i1> [[LOOP_PRED]], <4 x i1> [[TMP5]], <4 x i1> zeroinitializer
 ; CHECK-NEXT:    call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> [[SRC_SPLAT]], i32 4, <4 x i1> [[MASK]], <4 x i32> undef)
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %entry, %if.end
   %index = phi i64 [ %index.next, %if.end ], [ 0, %entry ]
   %arrayidx = getelementptr inbounds i32, i32* %cond, i64 %index
   %0 = load i32, i32* %arrayidx, align 4