; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
; RUN: opt -passes=loop-vectorize -force-vector-width=4 -S %s | FileCheck %s

define void @minbw_cast(ptr %dst, i64 %n, i1 %bool1, i1 %bool2) {
; CHECK-LABEL: define void @minbw_cast(
; CHECK-SAME: ptr [[DST:%.*]], i64 [[N:%.*]], i1 [[BOOL1:%.*]], i1 [[BOOL2:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*]]:
; CHECK-NEXT:    [[BOOL1_EXT:%.*]] = zext i1 [[BOOL1]] to i32
; CHECK-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N]], i64 1)
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[UMAX]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[UMAX]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[UMAX]], [[N_MOD_VF]]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i1> poison, i1 [[BOOL2]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i1> [[BROADCAST_SPLATINSERT]], <4 x i1> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> poison, i32 [[BOOL1_EXT]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP0:%.*]] = trunc <4 x i32> [[BROADCAST_SPLAT2]] to <4 x i8>
; CHECK-NEXT:    [[TMP1:%.*]] = zext <4 x i1> [[BROADCAST_SPLAT]] to <4 x i8>
; CHECK-NEXT:    [[TMP2:%.*]] = xor <4 x i8> [[TMP0]], [[TMP1]]
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i8> [[TMP2]], i32 3
; CHECK-NEXT:    store i8 [[TMP3]], ptr [[DST]], align 1
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[UMAX]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT:    br label %[[LOOP:.*]]
; CHECK:       [[LOOP]]:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT:    [[BOOL2_EXT:%.*]] = zext i1 [[BOOL2]] to i32
; CHECK-NEXT:    [[XOR:%.*]] = xor i32 [[BOOL1_EXT]], [[BOOL2_EXT]]
; CHECK-NEXT:    [[XOR_TRUNC:%.*]] = trunc i32 [[XOR]] to i8
; CHECK-NEXT:    store i8 [[XOR_TRUNC]], ptr [[DST]], align 1
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[IV_NEXT]], [[N]]
; CHECK-NEXT:    br i1 [[CMP]], label %[[LOOP]], label %[[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       [[EXIT]]:
; CHECK-NEXT:    ret void
;
entry:
  %bool1.ext = zext i1 %bool1 to i32
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %bool2.ext = zext i1 %bool2 to i32
  %xor = xor i32 %bool1.ext, %bool2.ext
  %xor.trunc = trunc i32 %xor to i8
  store i8 %xor.trunc, ptr %dst, align 1
  %iv.next = add i64 %iv, 1
  %cmp = icmp ult i64 %iv.next, %n
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}