; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-vectorize,dce,instcombine -scalable-vectorization=on -force-target-instruction-cost=1 -force-target-supports-scalable-vectors < %s -S | FileCheck %s

; Test that we can add on the induction variable
;   for (long long i = 0; i < n; i++) {
;     a[i] = b[i] + i;
;   }
; with an unroll factor (interleave count) of 2.

define void @add_ind64_unrolled(ptr noalias nocapture %a, ptr noalias nocapture readonly %b, i64 %n) {
; CHECK-LABEL: @add_ind64_unrolled(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 2
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP8:%.*]] = shl nuw i64 [[TMP4]], 1
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP8]], i64 0
; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP5:%.*]] = shl i64 [[TMP4]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP5]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[TMP6]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[STEP_ADD:%.*]] = add <vscale x 2 x i64> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[DOTIDX:%.*]] = shl i64 [[TMP10]], 4
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[TMP9]], i64 [[DOTIDX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP9]], align 8
; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <vscale x 2 x i64>, ptr [[TMP11]], align 8
; CHECK-NEXT:    [[TMP12:%.*]] = add nsw <vscale x 2 x i64> [[WIDE_LOAD]], [[VEC_IND]]
; CHECK-NEXT:    [[TMP13:%.*]] = add nsw <vscale x 2 x i64> [[WIDE_LOAD2]], [[STEP_ADD]]
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[DOTIDX3:%.*]] = shl i64 [[TMP15]], 4
; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[TMP14]], i64 [[DOTIDX3]]
; CHECK-NEXT:    store <vscale x 2 x i64> [[TMP12]], ptr [[TMP14]], align 8
; CHECK-NEXT:    store <vscale x 2 x i64> [[TMP13]], ptr [[TMP16]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[STEP_ADD]], [[DOTSPLAT]]
; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP18:%.*]] = load i64, ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i64 [[TMP18]], [[I_08]]
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[I_08]]
; CHECK-NEXT:    store i64 [[ADD]], ptr [[ARRAYIDX1]], align 8
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[EXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i64, ptr %b, i64 %i.08
  %0 = load i64, ptr %arrayidx, align 8
  %add = add nsw i64 %0, %i.08
  %arrayidx1 = getelementptr inbounds i64, ptr %a, i64 %i.08
  store i64 %add, ptr %arrayidx1, align 8
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, %n
  br i1 %exitcond.not, label %exit, label %for.body, !llvm.loop !0

exit:                                 ; preds = %for.body
  ret void
}


; Same as above, except we test with a vectorisation factor of (1, scalable)

define void @add_ind64_unrolled_nxv1i64(ptr noalias nocapture %a, ptr noalias nocapture readonly %b, i64 %n) {
; CHECK-LABEL: @add_ind64_unrolled_nxv1i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP2]], i64 0
; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 1 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP3:%.*]] = shl i64 [[TMP2]], 1
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    [[TMP6:%.*]] = call <vscale x 1 x i64> @llvm.stepvector.nxv1i64()
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 1 x i64> [ [[TMP6]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[STEP_ADD:%.*]] = add <vscale x 1 x i64> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i64 [[TMP9]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 1 x i64>, ptr [[TMP8]], align 8
; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <vscale x 1 x i64>, ptr [[TMP10]], align 8
; CHECK-NEXT:    [[TMP11:%.*]] = add nsw <vscale x 1 x i64> [[WIDE_LOAD]], [[VEC_IND]]
; CHECK-NEXT:    [[TMP12:%.*]] = add nsw <vscale x 1 x i64> [[WIDE_LOAD2]], [[STEP_ADD]]
; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i64, ptr [[TMP13]], i64 [[TMP14]]
; CHECK-NEXT:    store <vscale x 1 x i64> [[TMP11]], ptr [[TMP13]], align 8
; CHECK-NEXT:    store <vscale x 1 x i64> [[TMP12]], ptr [[TMP15]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]]
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 1 x i64> [[STEP_ADD]], [[DOTSPLAT]]
; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP17:%.*]] = load i64, ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i64 [[TMP17]], [[I_08]]
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[I_08]]
; CHECK-NEXT:    store i64 [[ADD]], ptr [[ARRAYIDX1]], align 8
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[EXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i64, ptr %b, i64 %i.08
  %0 = load i64, ptr %arrayidx, align 8
  %add = add nsw i64 %0, %i.08
  %arrayidx1 = getelementptr inbounds i64, ptr %a, i64 %i.08
  store i64 %add, ptr %arrayidx1, align 8
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, %n
  br i1 %exitcond.not, label %exit, label %for.body, !llvm.loop !9

exit:                                 ; preds = %for.body
  ret void
}


; Test that we can vectorize a separate induction variable (not used for the branch)
;   int r = 0;
;   for (long long i = 0; i < n; i++) {
;     a[i] = r;
;     r += 2;
;   }
; with an unroll factor (interleave count) of 1.


define void @add_unique_ind32(ptr noalias nocapture %a, i64 %n) {
; CHECK-LABEL: @add_unique_ind32(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 2
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    [[DOTCAST:%.*]] = trunc i64 [[N_VEC]] to i32
; CHECK-NEXT:    [[IND_END:%.*]] = shl i32 [[DOTCAST]], 1
; CHECK-NEXT:    [[TMP6:%.*]] = call <vscale x 4 x i32> @llvm.stepvector.nxv4i32()
; CHECK-NEXT:    [[TMP7:%.*]] = shl <vscale x 4 x i32> [[TMP6]], splat (i32 1)
; CHECK-NEXT:    [[TMP8:%.*]] = trunc i64 [[TMP3]] to i32
; CHECK-NEXT:    [[TMP9:%.*]] = shl i32 [[TMP8]], 1
; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[TMP9]], i64 0
; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <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:    [[VEC_IND:%.*]] = phi <vscale x 4 x i32> [ [[TMP7]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    store <vscale x 4 x i32> [[VEC_IND]], ptr [[TMP10]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]]
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i32> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i32 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[I_08]]
; CHECK-NEXT:    store i32 [[R_07]], ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ADD]] = add nuw nsw i32 [[R_07]], 2
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[EXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i32, ptr %a, i64 %i.08
  store i32 %r.07, ptr %arrayidx, align 4
  %add = add nuw nsw i32 %r.07, 2
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, %n
  br i1 %exitcond.not, label %exit, label %for.body, !llvm.loop !6

exit:                                 ; preds = %for.body
  ret void
}


; Test that we can vectorize a separate FP induction variable (not used for the branch)
;   float r = 0;
;   for (long long i = 0; i < n; i++) {
;     a[i] = r;
;     r += 2;
;   }
; with an unroll factor (interleave count) of 1.

define void @add_unique_indf32(ptr noalias nocapture %a, i64 %n) {
; CHECK-LABEL: @add_unique_indf32(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 2
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    [[DOTCAST:%.*]] = sitofp i64 [[N_VEC]] to float
; CHECK-NEXT:    [[TMP4:%.*]] = fmul float [[DOTCAST]], 2.000000e+00
; CHECK-NEXT:    [[IND_END:%.*]] = fadd float [[TMP4]], 0.000000e+00
; CHECK-NEXT:    [[TMP7:%.*]] = call <vscale x 4 x i32> @llvm.stepvector.nxv4i32()
; CHECK-NEXT:    [[TMP8:%.*]] = uitofp <vscale x 4 x i32> [[TMP7]] to <vscale x 4 x float>
; CHECK-NEXT:    [[TMP9:%.*]] = fmul <vscale x 4 x float> [[TMP8]], splat (float 2.000000e+00)
; CHECK-NEXT:    [[INDUCTION:%.*]] = fadd <vscale x 4 x float> [[TMP9]], zeroinitializer
; CHECK-NEXT:    [[TMP12:%.*]] = uitofp i64 [[TMP3]] to float
; CHECK-NEXT:    [[TMP13:%.*]] = fmul float [[TMP12]], 2.000000e+00
; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[TMP13]], i64 0
; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> 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:    [[VEC_IND:%.*]] = phi <vscale x 4 x float> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    store <vscale x 4 x float> [[VEC_IND]], ptr [[TMP14]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]]
; CHECK-NEXT:    [[VEC_IND_NEXT]] = fadd <vscale x 4 x float> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi float [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0.000000e+00, [[ENTRY]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi float [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[I_08]]
; CHECK-NEXT:    store float [[R_07]], ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ADD]] = fadd float [[R_07]], 2.000000e+00
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[EXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi float [ %add, %for.body ], [ 0.000000e+00, %entry ]
  %arrayidx = getelementptr inbounds float, ptr %a, i64 %i.08
  store float %r.07, ptr %arrayidx, align 4
  %add = fadd float %r.07, 2.000000e+00
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, %n
  br i1 %exitcond.not, label %exit, label %for.body, !llvm.loop !6

exit:                                 ; preds = %for.body
  ret void
}

!0 = distinct !{!0, !1, !2, !3, !4, !5}
!1 = !{!"llvm.loop.mustprogress"}
!2 = !{!"llvm.loop.vectorize.width", i32 2}
!3 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
!4 = !{!"llvm.loop.interleave.count", i32 2}
!5 = !{!"llvm.loop.vectorize.enable", i1 true}
!6 = distinct !{!6, !1, !7, !3, !8, !5}
!7 = !{!"llvm.loop.vectorize.width", i32 4}
!8 = !{!"llvm.loop.interleave.count", i32 1}
!9 = distinct !{!9, !1, !10, !3, !4, !5}
!10 = !{!"llvm.loop.vectorize.width", i32 1}