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

define void @trunc_minimal_bitwidth(i8* %bptr, i16* noalias %hptr, i32 %val, i64 %N) {
; CHECK-LABEL: @trunc_minimal_bitwidth(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i32 0
; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP4:%.*]] = trunc <vscale x 4 x i32> [[BROADCAST_SPLAT2]] to <vscale x 4 x i16>
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i16, i16* [[HPTR:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i16* [[TMP5]] to <vscale x 4 x i16>*
; CHECK-NEXT:    store <vscale x 4 x i16> [[TMP4]], <vscale x 4 x i16>* [[TMP6]], align 2
; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP8]]
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[CONV21:%.*]] = trunc i32 [[VAL]] to i16
; CHECK-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds i16, i16* [[HPTR]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    store i16 [[CONV21]], i16* [[ARRAYIDX23]], align 2
; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_EXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
; CHECK:       for.exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %0 = load i8, i8* %bptr, align 1
  %conv = zext i8 %0 to i32
  %conv21 = trunc i32 %val to i16
  %arrayidx23 = getelementptr inbounds i16, i16* %hptr, i64 %indvars.iv
  store i16 %conv21, i16* %arrayidx23, align 2
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond.not = icmp eq i64 %indvars.iv.next, %N
  br i1 %exitcond.not, label %for.exit, label %for.body, !llvm.loop !0

for.exit:
  ret void
}

define void @trunc_minimal_bitwidths_shufflevector (i8* %p, i32 %arg1, i64 %len) {
; CHECK-LABEL: @trunc_minimal_bitwidths_shufflevector(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[LEN:%.*]], [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[LEN]], [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[LEN]], [[N_MOD_VF]]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[ARG1:%.*]], i32 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[P:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP4]] to <vscale x 4 x i8>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i8>, <vscale x 4 x i8>* [[TMP5]], align 1
; CHECK-NEXT:    [[TMP6:%.*]] = trunc <vscale x 4 x i32> [[BROADCAST_SPLAT]] to <vscale x 4 x i8>
; CHECK-NEXT:    [[TMP7:%.*]] = xor <vscale x 4 x i8> [[WIDE_LOAD]], [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = mul <vscale x 4 x i8> [[TMP7]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP9:%.*]] = bitcast i8* [[TMP4]] to <vscale x 4 x i8>*
; CHECK-NEXT:    store <vscale x 4 x i8> [[TMP8]], <vscale x 4 x i8>* [[TMP9]], align 1
; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
entry:
  br label %for.body

for.body:                                         ; preds = %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %arrayidx = getelementptr inbounds i8, i8* %p, i64 %indvars.iv
  %0 = load i8, i8* %arrayidx
  %conv = zext i8 %0 to i32
  %conv17 = xor i32 %conv, %arg1
  %mul18 = mul nuw nsw i32 %conv17, %conv
  %conv19 = trunc i32 %mul18 to i8
  store i8 %conv19, i8* %arrayidx
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, %len
  br i1 %exitcond, label %for.exit, label %for.body, !llvm.loop !0

for.exit:                                 ; preds = %for.body
  ret void
}
!0 = !{!0, !1, !2}
!1 = !{!"llvm.loop.vectorize.width", i32 4}
!2 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}