; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -instcombine -simplifycfg -simplifycfg-require-and-preserve-domtree=1 -tail-predication=enabled < %s -S -o - | FileCheck %s

target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv8.1m.main-arm-none-eabi"

; Should not be vectorized
define i64 @add_i64_i64(i64* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i64_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[X:%.*]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[ADD]] = add nsw i64 [[TMP0]], [[R_07]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[ADD]], [[FOR_BODY]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i64 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i64, i64* %x, i32 %i.08
  %0 = load i64, i64* %arrayidx, align 8
  %add = add nsw i64 %0, %r.07
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i64 [ 0, %entry ], [ %add, %for.body ]
  ret i64 %r.0.lcssa
}

; 4x to use VADDLV
; FIXME: TailPredicate
define i64 @add_i32_i64(i32* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i32_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N]], -4
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4
; CHECK-NEXT:    [[TMP2:%.*]] = sext <4 x i32> [[WIDE_LOAD]] to <4 x i64>
; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[TMP2]])
; CHECK-NEXT:    [[TMP4]] = add i64 [[TMP3]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N_VEC]], [[N]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i64 [ [[TMP4]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[X]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[CONV:%.*]] = sext i32 [[TMP6]] to i64
; CHECK-NEXT:    [[ADD]] = add nsw i64 [[R_07]], [[CONV]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], [[LOOP2:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[ADD]], [[FOR_BODY]] ], [ [[TMP4]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i64 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %0 = load i32, i32* %arrayidx, align 4
  %conv = sext i32 %0 to i64
  %add = add nsw i64 %r.07, %conv
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i64 [ 0, %entry ], [ %add, %for.body ]
  ret i64 %r.0.lcssa
}

; 4x to use VADDLV
; FIXME: TailPredicate
define i64 @add_i16_i64(i16* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i16_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N]], -4
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[TMP0]] to <4 x i16>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i16>, <4 x i16>* [[TMP1]], align 2
; CHECK-NEXT:    [[TMP2:%.*]] = sext <4 x i16> [[WIDE_LOAD]] to <4 x i64>
; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[TMP2]])
; CHECK-NEXT:    [[TMP4]] = add i64 [[TMP3]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP4:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N_VEC]], [[N]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i64 [ [[TMP4]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, i16* [[X]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i16, i16* [[ARRAYIDX]], align 2
; CHECK-NEXT:    [[CONV:%.*]] = sext i16 [[TMP6]] to i64
; CHECK-NEXT:    [[ADD]] = add nsw i64 [[R_07]], [[CONV]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], [[LOOP5:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[ADD]], [[FOR_BODY]] ], [ [[TMP4]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i64 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i16, i16* %x, i32 %i.08
  %0 = load i16, i16* %arrayidx, align 2
  %conv = sext i16 %0 to i64
  %add = add nsw i64 %r.07, %conv
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i64 [ 0, %entry ], [ %add, %for.body ]
  ret i64 %r.0.lcssa
}

; 4x to use VADDLV
; FIXME: TailPredicate
define i64 @add_i8_i64(i8* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i8_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N]], -4
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x i8>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP1]], align 1
; CHECK-NEXT:    [[TMP2:%.*]] = zext <4 x i8> [[WIDE_LOAD]] to <4 x i64>
; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[TMP2]])
; CHECK-NEXT:    [[TMP4]] = add i64 [[TMP3]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP6:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N_VEC]], [[N]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i64 [ [[TMP4]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[X]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[CONV:%.*]] = zext i8 [[TMP6]] to i64
; CHECK-NEXT:    [[ADD]] = add nuw nsw i64 [[R_07]], [[CONV]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], [[LOOP7:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[ADD]], [[FOR_BODY]] ], [ [[TMP4]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i64 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i8, i8* %x, i32 %i.08
  %0 = load i8, i8* %arrayidx, align 1
  %conv = zext i8 %0 to i64
  %add = add nuw nsw i64 %r.07, %conv
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i64 [ 0, %entry ], [ %add, %for.body ]
  ret i64 %r.0.lcssa
}

; 4x to use VADDV.u32
define i32 @add_i32_i32(i32* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i32_i32(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 3
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -4
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP1]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> [[WIDE_MASKED_LOAD]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP2]])
; CHECK-NEXT:    [[TMP4]] = add i32 [[TMP3]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP8:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP4]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %0 = load i32, i32* %arrayidx, align 4
  %add = add nsw i32 %0, %r.07
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

; 8x to use VADDV.u16
define i32 @add_i16_i32(i16* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i16_i32(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 7
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -8
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[TMP0]] to <8 x i16>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP1]], i32 2, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = sext <8 x i16> [[WIDE_MASKED_LOAD]] to <8 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i32> [[TMP2]], <8 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP4:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP3]])
; CHECK-NEXT:    [[TMP5]] = add i32 [[TMP4]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP9:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP5]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i16, i16* %x, i32 %i.08
  %0 = load i16, i16* %arrayidx, align 2
  %conv = sext i16 %0 to i32
  %add = add nsw i32 %r.07, %conv
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

; 16x to use VADDV.u16
define i32 @add_i8_i32(i8* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i8_i32(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 15
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -16
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP1]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = zext <16 x i8> [[WIDE_MASKED_LOAD]] to <16 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i32> [[TMP2]], <16 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP4:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP3]])
; CHECK-NEXT:    [[TMP5]] = add i32 [[TMP4]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP10:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP5]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i8, i8* %x, i32 %i.08
  %0 = load i8, i8* %arrayidx, align 1
  %conv = zext i8 %0 to i32
  %add = add nuw nsw i32 %r.07, %conv
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

; 8x to use VADDV.u16
define signext i16 @add_i16_i16(i16* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i16_i16(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP8:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP8]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 7
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -8
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i16 [ 0, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[TMP0]] to <8 x i16>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP1]], i32 2, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = select <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> [[WIDE_MASKED_LOAD]], <8 x i16> zeroinitializer
; CHECK-NEXT:    [[TMP3:%.*]] = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> [[TMP2]])
; CHECK-NEXT:    [[TMP4]] = add i16 [[TMP3]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP11:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[TMP4]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i16 [[R_0_LCSSA]]
;
entry:
  %cmp8 = icmp sgt i32 %n, 0
  br i1 %cmp8, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.010 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.09 = phi i16 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i16, i16* %x, i32 %i.010
  %0 = load i16, i16* %arrayidx, align 2
  %add = add i16 %0, %r.09
  %inc = add nuw nsw i32 %i.010, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i16 [ 0, %entry ], [ %add, %for.body ]
  ret i16 %r.0.lcssa
}

; 16x to use VADDV.u8
define signext i16 @add_i8_i16(i8* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i8_i16(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP8:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP8]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 15
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -16
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i16 [ 0, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP1]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = zext <16 x i8> [[WIDE_MASKED_LOAD]] to <16 x i16>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i16> [[TMP2]], <16 x i16> zeroinitializer
; CHECK-NEXT:    [[TMP4:%.*]] = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> [[TMP3]])
; CHECK-NEXT:    [[TMP5]] = add i16 [[TMP4]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP12:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[TMP5]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i16 [[R_0_LCSSA]]
;
entry:
  %cmp8 = icmp sgt i32 %n, 0
  br i1 %cmp8, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.010 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.09 = phi i16 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i8, i8* %x, i32 %i.010
  %0 = load i8, i8* %arrayidx, align 1
  %conv = zext i8 %0 to i16
  %add = add i16 %r.09, %conv
  %inc = add nuw nsw i32 %i.010, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i16 [ 0, %entry ], [ %add, %for.body ]
  ret i16 %r.0.lcssa
}

; 16x to use VADDV.u8
define zeroext i8 @add_i8_i8(i8* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i8_i8(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP7:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP7]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 15
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -16
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i8 [ 0, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP1]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> [[WIDE_MASKED_LOAD]], <16 x i8> zeroinitializer
; CHECK-NEXT:    [[TMP3:%.*]] = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> [[TMP2]])
; CHECK-NEXT:    [[TMP4]] = add i8 [[TMP3]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP13:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i8 [ 0, [[ENTRY:%.*]] ], [ [[TMP4]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i8 [[R_0_LCSSA]]
;
entry:
  %cmp7 = icmp sgt i32 %n, 0
  br i1 %cmp7, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.09 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.08 = phi i8 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i8, i8* %x, i32 %i.09
  %0 = load i8, i8* %arrayidx, align 1
  %add = add i8 %0, %r.08
  %inc = add nuw nsw i32 %i.09, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i8 [ 0, %entry ], [ %add, %for.body ]
  ret i8 %r.0.lcssa
}

; Not vectorized
define i64 @mla_i64_i64(i64* nocapture readonly %x, i64* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i64_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP8:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP8]], label [[FOR_BODY:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_010:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[R_09:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[X:%.*]], i32 [[I_010]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[Y:%.*]], i32 [[I_010]]
; CHECK-NEXT:    [[TMP1:%.*]] = load i64, i64* [[ARRAYIDX1]], align 8
; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i64 [[TMP1]], [[TMP0]]
; CHECK-NEXT:    [[ADD]] = add nsw i64 [[MUL]], [[R_09]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_010]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[ADD]], [[FOR_BODY]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  %cmp8 = icmp sgt i32 %n, 0
  br i1 %cmp8, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.010 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.09 = phi i64 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i64, i64* %x, i32 %i.010
  %0 = load i64, i64* %arrayidx, align 8
  %arrayidx1 = getelementptr inbounds i64, i64* %y, i32 %i.010
  %1 = load i64, i64* %arrayidx1, align 8
  %mul = mul nsw i64 %1, %0
  %add = add nsw i64 %mul, %r.09
  %inc = add nuw nsw i32 %i.010, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i64 [ 0, %entry ], [ %add, %for.body ]
  ret i64 %r.0.lcssa
}

; 4x to use VMLAL.u32
; FIXME: TailPredicate
define i64 @mla_i32_i64(i32* nocapture readonly %x, i32* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i32_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP8:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP8]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N]], -4
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP7:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = mul nsw <4 x i32> [[WIDE_LOAD1]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP5:%.*]] = sext <4 x i32> [[TMP4]] to <4 x i64>
; CHECK-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[TMP5]])
; CHECK-NEXT:    [[TMP7]] = add i64 [[TMP6]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP14:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N_VEC]], [[N]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i64 [ [[TMP7]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_010:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_09:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[X]], i32 [[I_010]]
; CHECK-NEXT:    [[TMP9:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[Y]], i32 [[I_010]]
; CHECK-NEXT:    [[TMP10:%.*]] = load i32, i32* [[ARRAYIDX1]], align 4
; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP10]], [[TMP9]]
; CHECK-NEXT:    [[CONV:%.*]] = sext i32 [[MUL]] to i64
; CHECK-NEXT:    [[ADD]] = add nsw i64 [[R_09]], [[CONV]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_010]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], [[LOOP15:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[ADD]], [[FOR_BODY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  %cmp8 = icmp sgt i32 %n, 0
  br i1 %cmp8, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.010 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.09 = phi i64 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.010
  %0 = load i32, i32* %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds i32, i32* %y, i32 %i.010
  %1 = load i32, i32* %arrayidx1, align 4
  %mul = mul nsw i32 %1, %0
  %conv = sext i32 %mul to i64
  %add = add nsw i64 %r.09, %conv
  %inc = add nuw nsw i32 %i.010, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i64 [ 0, %entry ], [ %add, %for.body ]
  ret i64 %r.0.lcssa
}

; 8x to use VMLAL.u16
; FIXME: TailPredicate
define i64 @mla_i16_i64(i16* nocapture readonly %x, i16* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i16_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP10:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP10]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 8
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N]], -8
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[TMP0]] to <8 x i16>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x i16>, <8 x i16>* [[TMP1]], align 2
; CHECK-NEXT:    [[TMP2:%.*]] = sext <8 x i16> [[WIDE_LOAD]] to <8 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i16, i16* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i16* [[TMP3]] to <8 x i16>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <8 x i16>, <8 x i16>* [[TMP4]], align 2
; CHECK-NEXT:    [[TMP5:%.*]] = sext <8 x i16> [[WIDE_LOAD1]] to <8 x i32>
; CHECK-NEXT:    [[TMP6:%.*]] = mul nsw <8 x i32> [[TMP5]], [[TMP2]]
; CHECK-NEXT:    [[TMP7:%.*]] = sext <8 x i32> [[TMP6]] to <8 x i64>
; CHECK-NEXT:    [[TMP8:%.*]] = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> [[TMP7]])
; CHECK-NEXT:    [[TMP9]] = add i64 [[TMP8]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP16:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N_VEC]], [[N]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i64 [ [[TMP9]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_012:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_011:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, i16* [[X]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP11:%.*]] = load i16, i16* [[ARRAYIDX]], align 2
; CHECK-NEXT:    [[CONV:%.*]] = sext i16 [[TMP11]] to i32
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i16, i16* [[Y]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP12:%.*]] = load i16, i16* [[ARRAYIDX1]], align 2
; CHECK-NEXT:    [[CONV2:%.*]] = sext i16 [[TMP12]] to i32
; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[CONV2]], [[CONV]]
; CHECK-NEXT:    [[CONV3:%.*]] = sext i32 [[MUL]] to i64
; CHECK-NEXT:    [[ADD]] = add nsw i64 [[R_011]], [[CONV3]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_012]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], [[LOOP17:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[ADD]], [[FOR_BODY]] ], [ [[TMP9]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  %cmp10 = icmp sgt i32 %n, 0
  br i1 %cmp10, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.012 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.011 = phi i64 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i16, i16* %x, i32 %i.012
  %0 = load i16, i16* %arrayidx, align 2
  %conv = sext i16 %0 to i32
  %arrayidx1 = getelementptr inbounds i16, i16* %y, i32 %i.012
  %1 = load i16, i16* %arrayidx1, align 2
  %conv2 = sext i16 %1 to i32
  %mul = mul nsw i32 %conv2, %conv
  %conv3 = sext i32 %mul to i64
  %add = add nsw i64 %r.011, %conv3
  %inc = add nuw nsw i32 %i.012, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i64 [ 0, %entry ], [ %add, %for.body ]
  ret i64 %r.0.lcssa
}

; 8x to use VMLAL.u16
; FIXME: 8x, TailPredicate, double-extended
define i64 @mla_i8_i64(i8* nocapture readonly %x, i8* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i8_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP10:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP10]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 16
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N]], -16
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, <16 x i8>* [[TMP1]], align 1
; CHECK-NEXT:    [[TMP2:%.*]] = zext <16 x i8> [[WIDE_LOAD]] to <16 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP4]], align 1
; CHECK-NEXT:    [[TMP5:%.*]] = zext <16 x i8> [[WIDE_LOAD1]] to <16 x i32>
; CHECK-NEXT:    [[TMP6:%.*]] = mul nuw nsw <16 x i32> [[TMP5]], [[TMP2]]
; CHECK-NEXT:    [[TMP7:%.*]] = zext <16 x i32> [[TMP6]] to <16 x i64>
; CHECK-NEXT:    [[TMP8:%.*]] = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> [[TMP7]])
; CHECK-NEXT:    [[TMP9]] = add i64 [[TMP8]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP18:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N_VEC]], [[N]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i64 [ [[TMP9]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_012:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_011:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[X]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP11:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[CONV:%.*]] = zext i8 [[TMP11]] to i32
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[Y]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP12:%.*]] = load i8, i8* [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[CONV2:%.*]] = zext i8 [[TMP12]] to i32
; CHECK-NEXT:    [[MUL:%.*]] = mul nuw nsw i32 [[CONV2]], [[CONV]]
; CHECK-NEXT:    [[CONV3:%.*]] = zext i32 [[MUL]] to i64
; CHECK-NEXT:    [[ADD]] = add nuw nsw i64 [[R_011]], [[CONV3]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_012]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], [[LOOP19:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[ADD]], [[FOR_BODY]] ], [ [[TMP9]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  %cmp10 = icmp sgt i32 %n, 0
  br i1 %cmp10, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.012 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.011 = phi i64 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i8, i8* %x, i32 %i.012
  %0 = load i8, i8* %arrayidx, align 1
  %conv = zext i8 %0 to i32
  %arrayidx1 = getelementptr inbounds i8, i8* %y, i32 %i.012
  %1 = load i8, i8* %arrayidx1, align 1
  %conv2 = zext i8 %1 to i32
  %mul = mul nuw nsw i32 %conv2, %conv
  %conv3 = zext i32 %mul to i64
  %add = add nuw nsw i64 %r.011, %conv3
  %inc = add nuw nsw i32 %i.012, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i64 [ 0, %entry ], [ %add, %for.body ]
  ret i64 %r.0.lcssa
}

; 4x to use VMLA.u32
define i32 @mla_i32_i32(i32* nocapture readonly %x, i32* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i32_i32(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP8:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP8]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 3
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -4
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP7:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP1]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP3]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> poison)
; CHECK-NEXT:    [[TMP4:%.*]] = mul nsw <4 x i32> [[WIDE_MASKED_LOAD1]], [[WIDE_MASKED_LOAD]]
; CHECK-NEXT:    [[TMP5:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> [[TMP4]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP6:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP5]])
; CHECK-NEXT:    [[TMP7]] = add i32 [[TMP6]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP8]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP20:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP7]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp8 = icmp sgt i32 %n, 0
  br i1 %cmp8, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.010 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.09 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.010
  %0 = load i32, i32* %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds i32, i32* %y, i32 %i.010
  %1 = load i32, i32* %arrayidx1, align 4
  %mul = mul nsw i32 %1, %0
  %add = add nsw i32 %mul, %r.09
  %inc = add nuw nsw i32 %i.010, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

; 8x to use VMLA.u16
define i32 @mla_i16_i32(i16* nocapture readonly %x, i16* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i16_i32(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP9:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP9]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 7
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -8
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[TMP0]] to <8 x i16>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP1]], i32 2, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = sext <8 x i16> [[WIDE_MASKED_LOAD]] to <8 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i16, i16* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i16* [[TMP3]] to <8 x i16>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP4]], i32 2, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> poison)
; CHECK-NEXT:    [[TMP5:%.*]] = sext <8 x i16> [[WIDE_MASKED_LOAD1]] to <8 x i32>
; CHECK-NEXT:    [[TMP6:%.*]] = mul nsw <8 x i32> [[TMP5]], [[TMP2]]
; CHECK-NEXT:    [[TMP7:%.*]] = select <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i32> [[TMP6]], <8 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP8:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP7]])
; CHECK-NEXT:    [[TMP9]] = add i32 [[TMP8]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP10]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP21:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP9]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp9 = icmp sgt i32 %n, 0
  br i1 %cmp9, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.011 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.010 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i16, i16* %x, i32 %i.011
  %0 = load i16, i16* %arrayidx, align 2
  %conv = sext i16 %0 to i32
  %arrayidx1 = getelementptr inbounds i16, i16* %y, i32 %i.011
  %1 = load i16, i16* %arrayidx1, align 2
  %conv2 = sext i16 %1 to i32
  %mul = mul nsw i32 %conv2, %conv
  %add = add nsw i32 %mul, %r.010
  %inc = add nuw nsw i32 %i.011, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

; 16x to use VMLA.u8
define i32 @mla_i8_i32(i8* nocapture readonly %x, i8* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i8_i32(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP9:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP9]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 15
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -16
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP1]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = zext <16 x i8> [[WIDE_MASKED_LOAD]] to <16 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP4]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
; CHECK-NEXT:    [[TMP5:%.*]] = zext <16 x i8> [[WIDE_MASKED_LOAD1]] to <16 x i32>
; CHECK-NEXT:    [[TMP6:%.*]] = mul nuw nsw <16 x i32> [[TMP5]], [[TMP2]]
; CHECK-NEXT:    [[TMP7:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i32> [[TMP6]], <16 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP8:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP7]])
; CHECK-NEXT:    [[TMP9]] = add i32 [[TMP8]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP10]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP22:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP9]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp9 = icmp sgt i32 %n, 0
  br i1 %cmp9, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.011 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.010 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i8, i8* %x, i32 %i.011
  %0 = load i8, i8* %arrayidx, align 1
  %conv = zext i8 %0 to i32
  %arrayidx1 = getelementptr inbounds i8, i8* %y, i32 %i.011
  %1 = load i8, i8* %arrayidx1, align 1
  %conv2 = zext i8 %1 to i32
  %mul = mul nuw nsw i32 %conv2, %conv
  %add = add nuw nsw i32 %mul, %r.010
  %inc = add nuw nsw i32 %i.011, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

; 8x to use VMLA.u16
define signext i16 @mla_i16_i16(i16* nocapture readonly %x, i16* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i16_i16(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP11]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 7
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -8
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i16 [ 0, [[VECTOR_PH]] ], [ [[TMP7:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[TMP0]] to <8 x i16>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP1]], i32 2, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i16, i16* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i16* [[TMP2]] to <8 x i16>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP3]], i32 2, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> poison)
; CHECK-NEXT:    [[TMP4:%.*]] = mul <8 x i16> [[WIDE_MASKED_LOAD1]], [[WIDE_MASKED_LOAD]]
; CHECK-NEXT:    [[TMP5:%.*]] = select <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> [[TMP4]], <8 x i16> zeroinitializer
; CHECK-NEXT:    [[TMP6:%.*]] = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> [[TMP5]])
; CHECK-NEXT:    [[TMP7]] = add i16 [[TMP6]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP8]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP23:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[TMP7]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i16 [[R_0_LCSSA]]
;
entry:
  %cmp11 = icmp sgt i32 %n, 0
  br i1 %cmp11, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.013 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.012 = phi i16 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i16, i16* %x, i32 %i.013
  %0 = load i16, i16* %arrayidx, align 2
  %arrayidx1 = getelementptr inbounds i16, i16* %y, i32 %i.013
  %1 = load i16, i16* %arrayidx1, align 2
  %mul = mul i16 %1, %0
  %add = add i16 %mul, %r.012
  %inc = add nuw nsw i32 %i.013, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i16 [ 0, %entry ], [ %add, %for.body ]
  ret i16 %r.0.lcssa
}

; 16x to use VMLA.u8
define signext i16 @mla_i8_i16(i8* nocapture readonly %x, i8* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i8_i16(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP11]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 15
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -16
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i16 [ 0, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP1]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = zext <16 x i8> [[WIDE_MASKED_LOAD]] to <16 x i16>
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP4]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
; CHECK-NEXT:    [[TMP5:%.*]] = zext <16 x i8> [[WIDE_MASKED_LOAD1]] to <16 x i16>
; CHECK-NEXT:    [[TMP6:%.*]] = mul nuw <16 x i16> [[TMP5]], [[TMP2]]
; CHECK-NEXT:    [[TMP7:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i16> [[TMP6]], <16 x i16> zeroinitializer
; CHECK-NEXT:    [[TMP8:%.*]] = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> [[TMP7]])
; CHECK-NEXT:    [[TMP9]] = add i16 [[TMP8]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP10]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP24:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[TMP9]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i16 [[R_0_LCSSA]]
;
entry:
  %cmp11 = icmp sgt i32 %n, 0
  br i1 %cmp11, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.013 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.012 = phi i16 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i8, i8* %x, i32 %i.013
  %0 = load i8, i8* %arrayidx, align 1
  %conv = zext i8 %0 to i16
  %arrayidx1 = getelementptr inbounds i8, i8* %y, i32 %i.013
  %1 = load i8, i8* %arrayidx1, align 1
  %conv2 = zext i8 %1 to i16
  %mul = mul nuw i16 %conv2, %conv
  %add = add i16 %mul, %r.012
  %inc = add nuw nsw i32 %i.013, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i16 [ 0, %entry ], [ %add, %for.body ]
  ret i16 %r.0.lcssa
}

; 16x to use VMLA.u8
define zeroext i8 @mla_i8_i8(i8* nocapture readonly %x, i8* nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i8_i8(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP10:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP10]], label [[VECTOR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 15
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -16
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i8 [ 0, [[VECTOR_PH]] ], [ [[TMP7:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP1]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP3]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
; CHECK-NEXT:    [[TMP4:%.*]] = mul <16 x i8> [[WIDE_MASKED_LOAD1]], [[WIDE_MASKED_LOAD]]
; CHECK-NEXT:    [[TMP5:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> [[TMP4]], <16 x i8> zeroinitializer
; CHECK-NEXT:    [[TMP6:%.*]] = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> [[TMP5]])
; CHECK-NEXT:    [[TMP7]] = add i8 [[TMP6]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP8]], label [[FOR_COND_CLEANUP]], label [[VECTOR_BODY]], [[LOOP25:!llvm.loop !.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i8 [ 0, [[ENTRY:%.*]] ], [ [[TMP7]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    ret i8 [[R_0_LCSSA]]
;
entry:
  %cmp10 = icmp sgt i32 %n, 0
  br i1 %cmp10, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.012 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.011 = phi i8 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i8, i8* %x, i32 %i.012
  %0 = load i8, i8* %arrayidx, align 1
  %arrayidx1 = getelementptr inbounds i8, i8* %y, i32 %i.012
  %1 = load i8, i8* %arrayidx1, align 1
  %mul = mul i8 %1, %0
  %add = add i8 %mul, %r.011
  %inc = add nuw nsw i32 %i.012, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i8 [ 0, %entry ], [ %add, %for.body ]
  ret i8 %r.0.lcssa
}

; Make sure interleave group members feeding in-loop reductions can be handled.
define i32 @reduction_interleave_group(i32 %n, i32* %arr) #0 {
; CHECK-LABEL: @reduction_interleave_group(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[GUARD:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[GUARD]], label [[FOR_BODY_PREHEADER:%.*]], label [[EXIT:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[N]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = lshr i32 [[TMP0]], 1
; CHECK-NEXT:    [[TMP2:%.*]] = add nuw i32 [[TMP1]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP0]], 6
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[TMP2]], -4
; CHECK-NEXT:    [[IND_END:%.*]] = shl i32 [[N_VEC]], 1
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP10:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = shl i32 [[INDEX]], 1
; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[OFFSET_IDX]], 1
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[ARR:%.*]], i32 -1
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 [[TMP3]]
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <8 x i32>*
; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <8 x i32>, <8 x i32>* [[TMP6]], align 4
; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <8 x i32> [[WIDE_VEC]], <8 x i32> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <8 x i32> [[WIDE_VEC]], <8 x i32> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[STRIDED_VEC1]])
; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[TMP7]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP9:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[STRIDED_VEC]])
; CHECK-NEXT:    [[TMP10]] = add i32 [[TMP9]], [[TMP8]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP11:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP26:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP10]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[IV_NEXT:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[RED_PHI:%.*]] = phi i32 [ [[RED_2:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ADD:%.*]] = or i32 [[IV]], 1
; CHECK-NEXT:    [[GEP_0:%.*]] = getelementptr inbounds i32, i32* [[ARR]], i32 [[ADD]]
; CHECK-NEXT:    [[L_0:%.*]] = load i32, i32* [[GEP_0]], align 4
; CHECK-NEXT:    [[GEP_1:%.*]] = getelementptr inbounds i32, i32* [[ARR]], i32 [[IV]]
; CHECK-NEXT:    [[L_1:%.*]] = load i32, i32* [[GEP_1]], align 4
; CHECK-NEXT:    [[RED_1:%.*]] = add i32 [[L_0]], [[RED_PHI]]
; CHECK-NEXT:    [[RED_2]] = add i32 [[RED_1]], [[L_1]]
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 2
; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[IV_NEXT]], [[N]]
; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[EXIT]], [[LOOP27:!llvm.loop !.*]]
; CHECK:       exit:
; CHECK-NEXT:    [[RET_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[RED_2]], [[FOR_BODY]] ], [ [[TMP10]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[RET_LCSSA]]
;
entry:
  %guard = icmp sgt i32 %n, 0
  br i1 %guard , label %for.body, label %exit

for.body:                                         ; preds = %for.body.preheader, %for.body
  %iv = phi i32 [ %iv.next, %for.body ], [ 0, %entry ]
  %red.phi = phi i32 [ %red.2, %for.body ], [ 0, %entry ]
  %add = or i32 %iv, 1
  %gep.0 = getelementptr inbounds i32, i32* %arr, i32 %add
  %l.0 = load i32, i32* %gep.0, align 4
  %gep.1 = getelementptr inbounds i32, i32* %arr, i32 %iv
  %l.1 = load i32, i32* %gep.1, align 4
  %red.1 = add i32 %l.0, %red.phi
  %red.2 = add i32 %red.1, %l.1
  %iv.next = add nuw nsw i32 %iv, 2
  %cmp = icmp slt i32 %iv.next, %n
  br i1 %cmp, label %for.body, label %exit

exit:
  %ret.lcssa = phi i32 [ 0, %entry ], [ %red.2, %for.body ]
  ret i32 %ret.lcssa
}

attributes #0 = { "target-features"="+mve" }