; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -instcombine -simplifycfg -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"

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
}

; FIXME: 4x
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:%.*]], 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 i32, i32* [[X:%.*]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[CONV:%.*]] = sext i32 [[TMP0]] 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]]
; 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 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
}

; FIXME: 4x ?
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:%.*]], 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 i16, i16* [[X:%.*]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i16, i16* [[ARRAYIDX]], align 2
; CHECK-NEXT:    [[CONV:%.*]] = sext i16 [[TMP0]] 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]]
; 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 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
}

; FIXME: 4x ?
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:%.*]], 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 i8, i8* [[X:%.*]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[CONV:%.*]] = zext i8 [[TMP0]] 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]]
; 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 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
}

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 <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP3:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX]], i32 [[N]])
; 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> undef)
; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> [[WIDE_MASKED_LOAD]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP3]] = add <4 x i32> [[VEC_PHI]], [[TMP2]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[TMP3]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP5]], [[MIDDLE_BLOCK]] ]
; 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
}

; FIXME: 8x
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]], 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 <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[TMP0]] to <4 x i16>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* [[TMP1]], i32 2, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i16> undef)
; CHECK-NEXT:    [[TMP2:%.*]] = sext <4 x i16> [[WIDE_MASKED_LOAD]] to <4 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> [[TMP2]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP4]] = add <4 x i32> [[VEC_PHI]], [[TMP3]]
; 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]], [[LOOP2:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP6:%.*]] = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[TMP4]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP6]], [[MIDDLE_BLOCK]] ]
; 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
}

; FIXME: 16x
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]], 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 <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* [[TMP1]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i8> undef)
; CHECK-NEXT:    [[TMP2:%.*]] = zext <4 x i8> [[WIDE_MASKED_LOAD]] to <4 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> [[TMP2]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP4]] = add <4 x i32> [[VEC_PHI]], [[TMP3]]
; 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]], [[LOOP3:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP6:%.*]] = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[TMP4]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP6]], [[MIDDLE_BLOCK]] ]
; 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
}

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 <8 x i16> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP3:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 [[INDEX]], i32 [[N]])
; 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> undef)
; CHECK-NEXT:    [[TMP2:%.*]] = select <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> [[WIDE_MASKED_LOAD]], <8 x i16> zeroinitializer
; CHECK-NEXT:    [[TMP3]] = add <8 x i16> [[VEC_PHI]], [[TMP2]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP4:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP5:%.*]] = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> [[TMP3]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[TMP5]], [[MIDDLE_BLOCK]] ]
; 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
}

; FIXME: 16x ?
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]], 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 <8 x i16> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* [[TMP1]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> undef)
; CHECK-NEXT:    [[TMP2:%.*]] = zext <8 x i8> [[WIDE_MASKED_LOAD]] to <8 x i16>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> [[TMP2]], <8 x i16> zeroinitializer
; CHECK-NEXT:    [[TMP4]] = add <8 x i16> [[VEC_PHI]], [[TMP3]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP5:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP6:%.*]] = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> [[TMP4]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[TMP6]], [[MIDDLE_BLOCK]] ]
; 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
}

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 <16 x i8> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP3:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 [[N]])
; 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> undef)
; CHECK-NEXT:    [[TMP2:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> [[WIDE_MASKED_LOAD]], <16 x i8> zeroinitializer
; CHECK-NEXT:    [[TMP3]] = add <16 x i8> [[VEC_PHI]], [[TMP2]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP6:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP5:%.*]] = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> [[TMP3]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i8 [ 0, [[ENTRY:%.*]] ], [ [[TMP5]], [[MIDDLE_BLOCK]] ]
; 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
}

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
}

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:%.*]], 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 i32, i32* [[X:%.*]], i32 [[I_010]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[Y:%.*]], i32 [[I_010]]
; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX1]], align 4
; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP1]], [[TMP0]]
; 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]]
; 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 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
}

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:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_012:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[R_011:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i16, i16* [[ARRAYIDX]], align 2
; CHECK-NEXT:    [[CONV:%.*]] = sext i16 [[TMP0]] to i32
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i16, i16* [[Y:%.*]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP1:%.*]] = load i16, i16* [[ARRAYIDX1]], align 2
; CHECK-NEXT:    [[CONV2:%.*]] = sext i16 [[TMP1]] 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]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[ADD]], [[FOR_BODY]] ]
; 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
}

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:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_012:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[R_011:%.*]] = phi i64 [ [[ADD:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[CONV:%.*]] = zext i8 [[TMP0]] to i32
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[Y:%.*]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP1:%.*]] = load i8, i8* [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[CONV2:%.*]] = zext i8 [[TMP1]] 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]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[ADD]], [[FOR_BODY]] ]
; 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
}

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 <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP6:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX]], i32 [[N]])
; 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> undef)
; 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> undef)
; 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]] = add <4 x i32> [[VEC_PHI]], [[TMP5]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP7:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP8:%.*]] = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[TMP6]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP8]], [[MIDDLE_BLOCK]] ]
; 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
}

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]], 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 <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP8:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[TMP0]] to <4 x i16>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* [[TMP1]], i32 2, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i16> undef)
; CHECK-NEXT:    [[TMP2:%.*]] = sext <4 x i16> [[WIDE_MASKED_LOAD]] to <4 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i16, i16* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i16* [[TMP3]] to <4 x i16>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* [[TMP4]], i32 2, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i16> undef)
; CHECK-NEXT:    [[TMP5:%.*]] = sext <4 x i16> [[WIDE_MASKED_LOAD1]] to <4 x i32>
; CHECK-NEXT:    [[TMP6:%.*]] = mul nsw <4 x i32> [[TMP5]], [[TMP2]]
; CHECK-NEXT:    [[TMP7:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> [[TMP6]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP8]] = add <4 x i32> [[VEC_PHI]], [[TMP7]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP8:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP10:%.*]] = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[TMP8]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP10]], [[MIDDLE_BLOCK]] ]
; 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
}

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]], 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 <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP8:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* [[TMP1]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i8> undef)
; CHECK-NEXT:    [[TMP2:%.*]] = zext <4 x i8> [[WIDE_MASKED_LOAD]] to <4 x i32>
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <4 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* [[TMP4]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i8> undef)
; CHECK-NEXT:    [[TMP5:%.*]] = zext <4 x i8> [[WIDE_MASKED_LOAD1]] to <4 x i32>
; CHECK-NEXT:    [[TMP6:%.*]] = mul nuw nsw <4 x i32> [[TMP5]], [[TMP2]]
; CHECK-NEXT:    [[TMP7:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> [[TMP6]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP8]] = add <4 x i32> [[VEC_PHI]], [[TMP7]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP9:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP10:%.*]] = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[TMP8]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP10]], [[MIDDLE_BLOCK]] ]
; 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
}

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 <8 x i16> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP6:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i16, i16* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 [[INDEX]], i32 [[N]])
; 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> undef)
; 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> undef)
; 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]] = add <8 x i16> [[VEC_PHI]], [[TMP5]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP10:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP8:%.*]] = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> [[TMP6]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[TMP8]], [[MIDDLE_BLOCK]] ]
; 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
}

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]], 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 <8 x i16> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP8:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 [[INDEX]], i32 [[N]])
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* [[TMP1]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> undef)
; CHECK-NEXT:    [[TMP2:%.*]] = zext <8 x i8> [[WIDE_MASKED_LOAD]] to <8 x i16>
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <8 x i8>*
; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* [[TMP4]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> undef)
; CHECK-NEXT:    [[TMP5:%.*]] = zext <8 x i8> [[WIDE_MASKED_LOAD1]] to <8 x i16>
; CHECK-NEXT:    [[TMP6:%.*]] = mul nuw <8 x i16> [[TMP5]], [[TMP2]]
; CHECK-NEXT:    [[TMP7:%.*]] = select <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i16> [[TMP6]], <8 x i16> zeroinitializer
; CHECK-NEXT:    [[TMP8]] = add <8 x i16> [[VEC_PHI]], [[TMP7]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP11:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP10:%.*]] = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> [[TMP8]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[TMP10]], [[MIDDLE_BLOCK]] ]
; 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
}

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 <16 x i8> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP6:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 [[N]])
; 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> undef)
; 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> undef)
; 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]] = add <16 x i8> [[VEC_PHI]], [[TMP5]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP12:!llvm.loop !.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP8:%.*]] = call i8 @llvm.experimental.vector.reduce.add.v16i8(<16 x i8> [[TMP6]])
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i8 [ 0, [[ENTRY:%.*]] ], [ [[TMP8]], [[MIDDLE_BLOCK]] ]
; 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
}

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