; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
; RUN: opt -passes=loop-vectorize -force-vector-width=4 -S %s | FileCheck %s

target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"

define void @test_versioned_with_sext_use(i32 %offset, ptr %dst) {
; CHECK-LABEL: define void @test_versioned_with_sext_use(
; CHECK-SAME: i32 [[OFFSET:%.*]], ptr [[DST:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[OFFSET_EXT:%.*]] = sext i32 [[OFFSET]] to i64
; CHECK-NEXT:    br label [[OUTER_HEADER:%.*]]
; CHECK:       outer.header.loopexit:
; CHECK-NEXT:    [[IV_2_NEXT_LCSSA:%.*]] = phi i64 [ [[IV_2_NEXT:%.*]], [[INNER_LOOP:%.*]] ]
; CHECK-NEXT:    br label [[OUTER_HEADER]]
; CHECK:       outer.header:
; CHECK-NEXT:    [[IV_1:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_2_NEXT_LCSSA]], [[OUTER_HEADER_LOOPEXIT:%.*]] ]
; CHECK-NEXT:    [[C:%.*]] = call i1 @cond()
; CHECK-NEXT:    br i1 [[C]], label [[INNER_LOOP_PREHEADER:%.*]], label [[EXIT:%.*]]
; CHECK:       inner.loop.preheader:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK:       vector.scevcheck:
; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i32 [[OFFSET]], 1
; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 200, [[OFFSET_EXT]]
; CHECK-NEXT:    [[IND_END:%.*]] = add i64 [[IV_1]], [[TMP0]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[INDEX]], [[OFFSET_EXT]]
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[IV_1]], [[TMP1]]
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i32, ptr [[DST]], i64 [[TMP3]]
; CHECK-NEXT:    store <4 x i32> zeroinitializer, ptr [[TMP4]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[IV_1]], [[INNER_LOOP_PREHEADER]] ], [ [[IV_1]], [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i32 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[INNER_LOOP_PREHEADER]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    br label [[INNER_LOOP]]
; CHECK:       inner.loop:
; CHECK-NEXT:    [[IV_2:%.*]] = phi i64 [ [[IV_2_NEXT]], [[INNER_LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[IV_3:%.*]] = phi i32 [ [[IV_3_NEXT:%.*]], [[INNER_LOOP]] ], [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[DST]], i64 [[IV_2]]
; CHECK-NEXT:    store i32 0, ptr [[GEP]], align 8
; CHECK-NEXT:    [[IV_2_NEXT]] = add i64 [[IV_2]], [[OFFSET_EXT]]
; CHECK-NEXT:    [[IV_3_NEXT]] = add i32 [[IV_3]], 1
; CHECK-NEXT:    [[EC:%.*]] = icmp eq i32 [[IV_3]], 200
; CHECK-NEXT:    br i1 [[EC]], label [[OUTER_HEADER_LOOPEXIT]], label [[INNER_LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  %offset.ext = sext i32 %offset to i64
  br label %outer.header

outer.header:
  %iv.1 = phi i64 [ 0, %entry ], [ %iv.2.next, %inner.loop ]
  %c = call i1 @cond()
  br i1 %c, label %inner.loop, label %exit

inner.loop:
  %iv.2 = phi i64 [ %iv.1, %outer.header ], [ %iv.2.next, %inner.loop ]
  %iv.3 = phi i32 [ 0, %outer.header ], [ %iv.3.next, %inner.loop ]
  %gep = getelementptr i32, ptr %dst, i64 %iv.2
  store i32 0, ptr %gep, align 8
  %iv.2.next = add i64 %iv.2, %offset.ext
  %iv.3.next = add i32 %iv.3, 1
  %ec = icmp eq i32 %iv.3, 200
  br i1 %ec, label %outer.header, label %inner.loop

exit:
  ret void
}

define void @test_versioned_with_zext_use(i32 %offset, ptr %dst) {
; CHECK-LABEL: define void @test_versioned_with_zext_use(
; CHECK-SAME: i32 [[OFFSET:%.*]], ptr [[DST:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[OFFSET_EXT:%.*]] = zext i32 [[OFFSET]] to i64
; CHECK-NEXT:    br label [[OUTER_HEADER:%.*]]
; CHECK:       outer.header.loopexit:
; CHECK-NEXT:    [[IV_2_NEXT_LCSSA:%.*]] = phi i64 [ [[IV_2_NEXT:%.*]], [[INNER_LOOP:%.*]] ]
; CHECK-NEXT:    br label [[OUTER_HEADER]]
; CHECK:       outer.header:
; CHECK-NEXT:    [[IV_1:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_2_NEXT_LCSSA]], [[OUTER_HEADER_LOOPEXIT:%.*]] ]
; CHECK-NEXT:    [[C:%.*]] = call i1 @cond()
; CHECK-NEXT:    br i1 [[C]], label [[INNER_LOOP_PREHEADER:%.*]], label [[EXIT:%.*]]
; CHECK:       inner.loop.preheader:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK:       vector.scevcheck:
; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i32 [[OFFSET]], 1
; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 200, [[OFFSET_EXT]]
; CHECK-NEXT:    [[IND_END:%.*]] = add i64 [[IV_1]], [[TMP0]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[INDEX]], [[OFFSET_EXT]]
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[IV_1]], [[TMP1]]
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i32, ptr [[DST]], i64 [[TMP3]]
; CHECK-NEXT:    store <4 x i32> zeroinitializer, ptr [[TMP4]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[IV_1]], [[INNER_LOOP_PREHEADER]] ], [ [[IV_1]], [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i32 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[INNER_LOOP_PREHEADER]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    br label [[INNER_LOOP]]
; CHECK:       inner.loop:
; CHECK-NEXT:    [[IV_2:%.*]] = phi i64 [ [[IV_2_NEXT]], [[INNER_LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[IV_3:%.*]] = phi i32 [ [[IV_3_NEXT:%.*]], [[INNER_LOOP]] ], [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[DST]], i64 [[IV_2]]
; CHECK-NEXT:    store i32 0, ptr [[GEP]], align 8
; CHECK-NEXT:    [[IV_2_NEXT]] = add i64 [[IV_2]], [[OFFSET_EXT]]
; CHECK-NEXT:    [[IV_3_NEXT]] = add i32 [[IV_3]], 1
; CHECK-NEXT:    [[EC:%.*]] = icmp eq i32 [[IV_3]], 200
; CHECK-NEXT:    br i1 [[EC]], label [[OUTER_HEADER_LOOPEXIT]], label [[INNER_LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  %offset.ext = zext i32 %offset to i64
  br label %outer.header

outer.header:
  %iv.1 = phi i64 [ 0, %entry ], [ %iv.2.next, %inner.loop ]
  %c = call i1 @cond()
  br i1 %c, label %inner.loop, label %exit

inner.loop:
  %iv.2 = phi i64 [ %iv.1, %outer.header ], [ %iv.2.next, %inner.loop ]
  %iv.3 = phi i32 [ 0, %outer.header ], [ %iv.3.next, %inner.loop ]
  %gep = getelementptr i32, ptr %dst, i64 %iv.2
  store i32 0, ptr %gep, align 8
  %iv.2.next = add i64 %iv.2, %offset.ext
  %iv.3.next = add i32 %iv.3, 1
  %ec = icmp eq i32 %iv.3, 200
  br i1 %ec, label %outer.header, label %inner.loop

exit:
  ret void
}

define void @versioned_sext_use_in_gep(i32 %scale, ptr %dst, i64 %scale.2) {
; CHECK-LABEL: define void @versioned_sext_use_in_gep(
; CHECK-SAME: i32 [[SCALE:%.*]], ptr [[DST:%.*]], i64 [[SCALE_2:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[SCALE_EXT:%.*]] = sext i32 [[SCALE]] to i64
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK:       vector.scevcheck:
; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i32 [[SCALE]], 1
; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP83:%.*]] = getelementptr i8, ptr [[DST]], i64 [[SCALE_2]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP14:%.*]] = add i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP16:%.*]] = add i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP10]]
; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP12]]
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP14]]
; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP16]]
; CHECK-NEXT:    store ptr [[TMP83]], ptr [[TMP11]], align 8
; CHECK-NEXT:    store ptr [[TMP83]], ptr [[TMP13]], align 8
; CHECK-NEXT:    store ptr [[TMP83]], ptr [[TMP15]], align 8
; CHECK-NEXT:    store ptr [[TMP83]], ptr [[TMP17]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[EXIT:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[IV_MUL:%.*]] = mul i64 [[IV]], [[SCALE_EXT]]
; CHECK-NEXT:    [[GEP_1:%.*]] = getelementptr i8, ptr [[DST]], i64 [[IV_MUL]]
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[SCALE_MUL:%.*]] = mul i64 [[SCALE_EXT]], [[SCALE_2]]
; CHECK-NEXT:    [[GEP_2:%.*]] = getelementptr i8, ptr [[DST]], i64 [[SCALE_MUL]]
; CHECK-NEXT:    store ptr [[GEP_2]], ptr [[GEP_1]], align 8
; CHECK-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV_NEXT]], 256
; CHECK-NEXT:    br i1 [[EC]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  %scale.ext = sext i32 %scale to i64
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %iv.mul  = mul i64 %iv, %scale.ext
  %gep.1 = getelementptr i8, ptr %dst, i64 %iv.mul
  %iv.next = add i64 %iv, 1
  %scale.mul = mul i64 %scale.ext, %scale.2
  %gep.2 = getelementptr i8, ptr %dst, i64 %scale.mul
  store ptr %gep.2, ptr %gep.1, align 8
  %ec = icmp eq i64 %iv.next, 256
  br i1 %ec, label %exit, label %loop

exit:
  ret void
}

declare i1 @cond()

define void @test_versioned_with_different_uses(i32 %offset, ptr noalias %dst.1, ptr %dst.2) {
; CHECK-LABEL: define void @test_versioned_with_different_uses(
; CHECK-SAME: i32 [[OFFSET:%.*]], ptr noalias [[DST_1:%.*]], ptr [[DST_2:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[OFFSET_EXT:%.*]] = zext i32 [[OFFSET]] to i64
; CHECK-NEXT:    br label [[OUTER_HEADER:%.*]]
; CHECK:       outer.header.loopexit:
; CHECK-NEXT:    [[IV_2_NEXT_LCSSA:%.*]] = phi i64 [ [[IV_2_NEXT:%.*]], [[INNER_LOOP:%.*]] ]
; CHECK-NEXT:    br label [[OUTER_HEADER]]
; CHECK:       outer.header:
; CHECK-NEXT:    [[IV_1:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_2_NEXT_LCSSA]], [[OUTER_HEADER_LOOPEXIT:%.*]] ]
; CHECK-NEXT:    [[C:%.*]] = call i1 @cond()
; CHECK-NEXT:    br i1 [[C]], label [[INNER_LOOP_PREHEADER:%.*]], label [[EXIT:%.*]]
; CHECK:       inner.loop.preheader:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK:       vector.scevcheck:
; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i32 [[OFFSET]], 1
; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 200, [[OFFSET_EXT]]
; CHECK-NEXT:    [[IND_END:%.*]] = add i64 [[IV_1]], [[TMP0]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[INDEX]], [[OFFSET_EXT]]
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[IV_1]], [[TMP1]]
; CHECK-NEXT:    [[OFFSET_IDX2:%.*]] = trunc i64 [[INDEX]] to i32
; CHECK-NEXT:    [[TMP4:%.*]] = add i32 [[OFFSET_IDX2]], 0
; CHECK-NEXT:    [[TMP5:%.*]] = add i32 [[OFFSET_IDX2]], 1
; CHECK-NEXT:    [[TMP6:%.*]] = add i32 [[OFFSET_IDX2]], 2
; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[OFFSET_IDX2]], 3
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[TMP4]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[TMP5]]
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[TMP6]]
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[TMP7]]
; CHECK-NEXT:    store i32 0, ptr [[TMP8]], align 8
; CHECK-NEXT:    store i32 0, ptr [[TMP9]], align 8
; CHECK-NEXT:    store i32 0, ptr [[TMP10]], align 8
; CHECK-NEXT:    store i32 0, ptr [[TMP11]], align 8
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[DST_2]], i64 [[TMP3]]
; CHECK-NEXT:    store <4 x i32> zeroinitializer, ptr [[TMP12]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
; CHECK-NEXT:    br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[IV_1]], [[INNER_LOOP_PREHEADER]] ], [ [[IV_1]], [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i32 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[INNER_LOOP_PREHEADER]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    br label [[INNER_LOOP]]
; CHECK:       inner.loop:
; CHECK-NEXT:    [[IV_2:%.*]] = phi i64 [ [[IV_2_NEXT]], [[INNER_LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[IV_3:%.*]] = phi i32 [ [[IV_3_NEXT:%.*]], [[INNER_LOOP]] ], [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[IV_MUL:%.*]] = mul i32 [[IV_3]], [[OFFSET]]
; CHECK-NEXT:    [[GEP_MUL:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[IV_MUL]]
; CHECK-NEXT:    store i32 0, ptr [[GEP_MUL]], align 8
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[DST_2]], i64 [[IV_2]]
; CHECK-NEXT:    store i32 0, ptr [[GEP]], align 8
; CHECK-NEXT:    [[IV_2_NEXT]] = add i64 [[IV_2]], [[OFFSET_EXT]]
; CHECK-NEXT:    [[IV_3_NEXT]] = add i32 [[IV_3]], 1
; CHECK-NEXT:    [[EC:%.*]] = icmp eq i32 [[IV_3]], 200
; CHECK-NEXT:    br i1 [[EC]], label [[OUTER_HEADER_LOOPEXIT]], label [[INNER_LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  %offset.ext = zext i32 %offset to i64
  br label %outer.header

outer.header:
  %iv.1 = phi i64 [ 0, %entry ], [ %iv.2.next, %inner.loop ]
  %c = call i1 @cond()
  br i1 %c, label %inner.loop, label %exit

inner.loop:
  %iv.2 = phi i64 [ %iv.1, %outer.header ], [ %iv.2.next, %inner.loop ]
  %iv.3 = phi i32 [ 0, %outer.header ], [ %iv.3.next, %inner.loop ]
  %iv.mul  = mul i32 %iv.3, %offset
  %gep.mul = getelementptr i8, ptr %dst.1, i32 %iv.mul
  store i32 0, ptr %gep.mul, align 8
  %gep = getelementptr i32, ptr %dst.2, i64 %iv.2
  store i32 0, ptr %gep, align 8
  %iv.2.next = add i64 %iv.2, %offset.ext
  %iv.3.next = add i32 %iv.3, 1
  %ec = icmp eq i32 %iv.3, 200
  br i1 %ec, label %outer.header, label %inner.loop

exit:
  ret void
}

define void @test_versioned_with_non_ex_use(i32 %offset, ptr noalias %dst.1, ptr %dst.2) {
; CHECK-LABEL: define void @test_versioned_with_non_ex_use(
; CHECK-SAME: i32 [[OFFSET:%.*]], ptr noalias [[DST_1:%.*]], ptr [[DST_2:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[OFFSET_EXT:%.*]] = zext i32 [[OFFSET]] to i64
; CHECK-NEXT:    [[ADD:%.*]] = add i32 [[OFFSET]], 3
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK:       vector.scevcheck:
; CHECK-NEXT:    [[TMP0:%.*]] = sub i32 -3, [[OFFSET]]
; CHECK-NEXT:    [[TMP1:%.*]] = icmp slt i32 [[ADD]], 0
; CHECK-NEXT:    [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[TMP0]], i32 [[ADD]]
; CHECK-NEXT:    [[MUL:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 [[TMP2]], i32 200)
; CHECK-NEXT:    [[MUL_RESULT:%.*]] = extractvalue { i32, i1 } [[MUL]], 0
; CHECK-NEXT:    [[MUL_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[MUL]], 1
; CHECK-NEXT:    [[TMP3:%.*]] = sub i32 0, [[MUL_RESULT]]
; CHECK-NEXT:    [[TMP4:%.*]] = icmp slt i32 [[MUL_RESULT]], 0
; CHECK-NEXT:    [[TMP5:%.*]] = icmp sgt i32 [[TMP3]], 0
; CHECK-NEXT:    [[TMP6:%.*]] = select i1 [[TMP1]], i1 [[TMP5]], i1 [[TMP4]]
; CHECK-NEXT:    [[TMP7:%.*]] = or i1 [[TMP6]], [[MUL_OVERFLOW]]
; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i32 [[OFFSET]], 1
; CHECK-NEXT:    [[TMP8:%.*]] = or i1 [[TMP7]], [[IDENT_CHECK]]
; CHECK-NEXT:    br i1 [[TMP8]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[ADD]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = mul <4 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <4 x i32> [[TMP10]], i32 0
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <4 x i32> [[TMP10]], i32 1
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[TMP13]]
; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <4 x i32> [[TMP10]], i32 2
; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[TMP15]]
; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <4 x i32> [[TMP10]], i32 3
; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[TMP17]]
; CHECK-NEXT:    store i32 0, ptr [[TMP12]], align 8
; CHECK-NEXT:    store i32 0, ptr [[TMP14]], align 8
; CHECK-NEXT:    store i32 0, ptr [[TMP16]], align 8
; CHECK-NEXT:    store i32 0, ptr [[TMP18]], align 8
; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr i32, ptr [[DST_2]], i64 [[INDEX]]
; CHECK-NEXT:    store <4 x i32> zeroinitializer, ptr [[TMP20]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], splat (i32 4)
; CHECK-NEXT:    [[TMP22:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
; CHECK-NEXT:    br i1 [[TMP22]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i32 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV_2:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_2_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[IV_3:%.*]] = phi i32 [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[IV_3_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[IV_MUL:%.*]] = mul i32 [[IV_3]], [[ADD]]
; CHECK-NEXT:    [[GEP_MUL:%.*]] = getelementptr i8, ptr [[DST_1]], i32 [[IV_MUL]]
; CHECK-NEXT:    store i32 0, ptr [[GEP_MUL]], align 8
; CHECK-NEXT:    [[IV_2_MUL:%.*]] = mul i64 [[IV_2]], [[OFFSET_EXT]]
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[DST_2]], i64 [[IV_2_MUL]]
; CHECK-NEXT:    store i32 0, ptr [[GEP]], align 8
; CHECK-NEXT:    [[IV_2_NEXT]] = add i64 [[IV_2]], 1
; CHECK-NEXT:    [[IV_3_NEXT]] = add i32 [[IV_3]], 1
; CHECK-NEXT:    [[EC:%.*]] = icmp eq i32 [[IV_3]], 200
; CHECK-NEXT:    br i1 [[EC]], label [[EXIT:%.*]], label [[LOOP]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  %offset.ext = zext i32 %offset to i64
  %add = add i32 %offset, 3
  br label %loop

loop:
  %iv.2 = phi i64 [ 0, %entry ], [ %iv.2.next, %loop ]
  %iv.3 = phi i32 [ 0, %entry ], [ %iv.3.next, %loop ]
  %iv.mul  = mul i32 %iv.3, %add
  %gep.mul = getelementptr i8, ptr %dst.1, i32 %iv.mul
  store i32 0, ptr %gep.mul, align 8
  %iv.2.mul  = mul i64 %iv.2, %offset.ext
  %gep = getelementptr i32, ptr %dst.2, i64 %iv.2.mul
  store i32 0, ptr %gep, align 8
  %iv.2.next = add i64 %iv.2, 1
  %iv.3.next = add i32 %iv.3, 1
  %ec = icmp eq i32 %iv.3, 200
  br i1 %ec, label %exit, label %loop

exit:
  ret void
}

; Test case to make sure that uses of versioned strides of type i1 are properly
; extended. From https://github.com/llvm/llvm-project/issues/91369.
; TODO: Better check (udiv i64 15, %g.64) after checking if %g == 1.
define void @zext_of_i1_stride(i1 %g, ptr %dst) mustprogress {
; CHECK-LABEL: define void @zext_of_i1_stride(
; CHECK-SAME: i1 [[G:%.*]], ptr [[DST:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[G_16:%.*]] = zext i1 [[G]] to i16
; CHECK-NEXT:    [[G_64:%.*]] = zext i1 [[G]] to i64
; CHECK-NEXT:    [[TMP0:%.*]] = udiv i64 15, [[G_64]]
; CHECK-NEXT:    [[TMP1:%.*]] = add nuw nsw i64 [[TMP0]], 1
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK:       vector.scevcheck:
; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i1 [[G]], true
; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
; CHECK-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], [[G_64]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], [[G_64]]
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i16, ptr [[DST]], i64 [[OFFSET_IDX]]
; CHECK-NEXT:    store <4 x i16> splat (i16 1), ptr [[TMP4]], align 2
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP1]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i16, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT:    store i16 [[G_16]], ptr [[GEP]], align 2
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], [[G_64]]
; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[IV_NEXT]], 16
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP13:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  %g.16 = zext i1 %g to i16
  %g.64 = zext i1 %g to i64
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %gep = getelementptr inbounds i16, ptr %dst, i64 %iv
  store i16 %g.16, ptr %gep, align 2
  %iv.next = add nuw nsw i64 %iv, %g.64
  %cmp = icmp ult i64 %iv.next, 16
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}

; Test case to make sure that uses of versioned strides of type i1 are properly
; extended.
define void @sext_of_i1_stride(i1 %g, ptr %dst) mustprogress {
; CHECK-LABEL: define void @sext_of_i1_stride(
; CHECK-SAME: i1 [[G:%.*]], ptr [[DST:%.*]]) #[[ATTR0]] {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[G_16:%.*]] = sext i1 [[G]] to i16
; CHECK-NEXT:    [[G_64:%.*]] = sext i1 [[G]] to i64
; CHECK-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[G_64]], i64 16)
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[UMAX]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = udiv i64 [[TMP0]], [[G_64]]
; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
; CHECK-NEXT:    br i1 true, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK:       vector.scevcheck:
; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i1 [[G]], true
; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
; CHECK-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], [[G_64]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i16, ptr [[DST]], i32 0
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i16, ptr [[TMP6]], i32 -3
; CHECK-NEXT:    store <4 x i16> splat (i16 -1), ptr [[TMP7]], align 2
; CHECK-NEXT:    br label [[MIDDLE_BLOCK:%.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP2]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i16, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT:    store i16 [[G_16]], ptr [[GEP]], align 2
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], [[G_64]]
; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[IV_NEXT]], 16
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP14:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  %g.16 = sext i1 %g to i16
  %g.64 = sext i1 %g to i64
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %gep = getelementptr inbounds i16, ptr %dst, i64 %iv
  store i16 %g.16, ptr %gep, align 2
  %iv.next = add nuw nsw i64 %iv, %g.64
  %cmp = icmp ult i64 %iv.next, 16
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}


;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META1]]}
; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META1]]}
; CHECK: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META2]]}
; CHECK: [[LOOP7]] = distinct !{[[LOOP7]], [[META1]]}
; CHECK: [[LOOP8]] = distinct !{[[LOOP8]], [[META1]], [[META2]]}
; CHECK: [[LOOP9]] = distinct !{[[LOOP9]], [[META1]]}
; CHECK: [[LOOP10]] = distinct !{[[LOOP10]], [[META1]], [[META2]]}
; CHECK: [[LOOP11]] = distinct !{[[LOOP11]], [[META1]]}
; CHECK: [[LOOP12]] = distinct !{[[LOOP12]], [[META1]], [[META2]]}
; CHECK: [[LOOP13]] = distinct !{[[LOOP13]], [[META1]]}
; CHECK: [[LOOP14]] = distinct !{[[LOOP14]], [[META1]]}
;.