; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S %s | FileCheck %s

; Make sure LV does not crash when creating runtime checks involving values from
; other loops.
define i16 @test(ptr %arg, i64 %N) {
; CHECK-LABEL: @test(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[OUTER:%.*]]
; CHECK:       outer:
; CHECK-NEXT:    [[L_1:%.*]] = load ptr, ptr [[ARG:%.*]], align 8
; CHECK-NEXT:    [[L_2:%.*]] = load ptr, ptr [[ARG]], align 8
; CHECK-NEXT:    [[C_1:%.*]] = call i1 @cond()
; CHECK-NEXT:    br i1 [[C_1]], label [[OUTER_BACKEDGE:%.*]], label [[INNER_PREHEADER:%.*]]
; CHECK:       outer.backedge:
; CHECK-NEXT:    br label [[OUTER]]
; CHECK:       inner.preheader:
; CHECK-NEXT:    br label [[INNER:%.*]]
; CHECK:       inner:
; CHECK-NEXT:    [[C_2:%.*]] = call i1 @cond()
; CHECK-NEXT:    br i1 [[C_2]], label [[OUTER_LATCH:%.*]], label [[INNER_BB:%.*]]
; CHECK:       inner.bb:
; CHECK-NEXT:    [[C_3:%.*]] = call i1 @cond()
; CHECK-NEXT:    br i1 [[C_3]], label [[LOOP_3_PREHEADER:%.*]], label [[INNER_LATCH:%.*]]
; CHECK:       loop.3.preheader:
; CHECK-NEXT:    [[L_1_LCSSA:%.*]] = phi ptr [ [[L_1]], [[INNER_BB]] ]
; CHECK-NEXT:    [[L_2_LCSSA:%.*]] = phi ptr [ [[L_2]], [[INNER_BB]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[N:%.*]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 2
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK:       vector.memcheck:
; CHECK-NEXT:    [[UGLYGEP:%.*]] = getelementptr i8, ptr [[L_2_LCSSA]], i64 2
; CHECK-NEXT:    [[UGLYGEP5:%.*]] = getelementptr i8, ptr [[L_1_LCSSA]], i64 2
; CHECK-NEXT:    [[TMP1:%.*]] = shl i64 [[N]], 1
; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[TMP1]], 4
; CHECK-NEXT:    [[UGLYGEP6:%.*]] = getelementptr i8, ptr [[L_1_LCSSA]], i64 [[TMP2]]
; CHECK-NEXT:    [[BOUND0:%.*]] = icmp ult ptr [[L_2_LCSSA]], [[UGLYGEP6]]
; CHECK-NEXT:    [[BOUND1:%.*]] = icmp ult ptr [[UGLYGEP5]], [[UGLYGEP]]
; CHECK-NEXT:    [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT:    br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 2
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT:    [[TMP4:%.*]] = add nuw nsw i64 [[TMP3]], 1
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i16, ptr [[L_1]], i64 [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i16, ptr [[TMP5]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i16>, ptr [[TMP6]], align 2, !alias.scope !0
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i16, ptr [[L_2]], i64 0
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x i16> [[WIDE_LOAD]], i32 1
; CHECK-NEXT:    store i16 [[TMP8]], ptr [[TMP7]], align 2, !alias.scope !3, !noalias !0
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[LOOP_3_PREHEADER]] ], [ 0, [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT:    br label [[LOOP_3:%.*]]
; CHECK:       inner.latch:
; CHECK-NEXT:    [[C_4:%.*]] = call i1 @cond()
; CHECK-NEXT:    br i1 [[C_4]], label [[EXIT_LOOPEXIT1:%.*]], label [[INNER]]
; CHECK:       outer.latch:
; CHECK-NEXT:    br label [[OUTER_BACKEDGE]]
; CHECK:       loop.3:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[LOOP_3]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[C_5:%.*]] = icmp ult i64 [[IV]], [[N]]
; CHECK-NEXT:    [[GEP_1:%.*]] = getelementptr inbounds i16, ptr [[L_1_LCSSA]], i64 [[IV_NEXT]]
; CHECK-NEXT:    [[LOOP_L_1:%.*]] = load i16, ptr [[GEP_1]], align 2
; CHECK-NEXT:    [[GEP_2:%.*]] = getelementptr inbounds i16, ptr [[L_2_LCSSA]], i64 0
; CHECK-NEXT:    store i16 [[LOOP_L_1]], ptr [[GEP_2]], align 2
; CHECK-NEXT:    br i1 [[C_5]], label [[LOOP_3]], label [[EXIT_LOOPEXIT]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       exit.loopexit:
; CHECK-NEXT:    br label [[EXIT:%.*]]
; CHECK:       exit.loopexit1:
; CHECK-NEXT:    [[L_1_LCSSA3:%.*]] = phi ptr [ [[L_1]], [[INNER_LATCH]] ]
; CHECK-NEXT:    br label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    [[L_14:%.*]] = phi ptr [ [[L_1_LCSSA3]], [[EXIT_LOOPEXIT1]] ], [ [[L_1_LCSSA]], [[EXIT_LOOPEXIT]] ]
; CHECK-NEXT:    [[L_3:%.*]] = load i16, ptr [[L_14]], align 2
; CHECK-NEXT:    ret i16 [[L_3]]
;
entry:
  br label %outer

outer:
  %l.1 = load ptr, ptr %arg, align 8
  %l.2 = load ptr, ptr %arg, align 8
  %c.1 = call i1 @cond()
  br i1 %c.1, label %outer, label %inner

inner:
  %c.2 = call i1 @cond()
  br i1 %c.2, label %outer.latch, label %inner.bb

inner.bb:
  %c.3 = call i1 @cond()
  br i1 %c.3, label %loop.3, label %inner.latch

inner.latch:
  %c.4 = call i1 @cond()
  br i1 %c.4, label %exit, label %inner

outer.latch:
  br label %outer

loop.3:
  %iv = phi i64 [ %iv.next, %loop.3 ], [ 0, %inner.bb ]
  %iv.next = add nsw nuw i64 %iv, 1
  %c.5  = icmp ult i64 %iv, %N
  %gep.1 = getelementptr inbounds i16, ptr %l.1, i64 %iv.next
  %loop.l.1 = load i16, ptr %gep.1, align 2
  %gep.2 = getelementptr inbounds i16, ptr %l.2, i64 0
  store i16 %loop.l.1, ptr %gep.2 , align 2
  br i1 %c.5, label %loop.3, label %exit

exit:
  %l.3 = load i16, ptr %l.1, align 2
  ret i16 %l.3
}

define void @test2(ptr %dst) {
; CHECK-LABEL: @test2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP_1_HEADER:%.*]]
; CHECK:       loop.1.header:
; CHECK-NEXT:    br label [[LOOP_2:%.*]]
; CHECK:       loop.2:
; CHECK-NEXT:    [[INDVAR:%.*]] = phi i32 [ [[INDVAR_NEXT:%.*]], [[LOOP_2]] ], [ 0, [[LOOP_1_HEADER]] ]
; CHECK-NEXT:    [[IV_1:%.*]] = phi i64 [ 1000, [[LOOP_1_HEADER]] ], [ [[IV_1_NEXT:%.*]], [[LOOP_2]] ]
; CHECK-NEXT:    [[IV_1_NEXT]] = add i64 [[IV_1]], -1
; CHECK-NEXT:    [[C_1:%.*]] = call i1 @cond()
; CHECK-NEXT:    [[INDVAR_NEXT]] = add i32 [[INDVAR]], 1
; CHECK-NEXT:    br i1 [[C_1]], label [[LOOP_2]], label [[LOOP_3_PH:%.*]]
; CHECK:       loop.3.ph:
; CHECK-NEXT:    [[INDVAR_LCSSA1:%.*]] = phi i32 [ [[INDVAR]], [[LOOP_2]] ]
; CHECK-NEXT:    [[INDVAR_LCSSA:%.*]] = phi i32 [ [[INDVAR]], [[LOOP_2]] ]
; CHECK-NEXT:    [[IV_1_LCSSA:%.*]] = phi i64 [ [[IV_1]], [[LOOP_2]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = and i64 [[IV_1_LCSSA]], 4294967295
; CHECK-NEXT:    [[TMP1:%.*]] = mul i32 [[INDVAR_LCSSA1]], -1
; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[TMP1]], 1000
; CHECK-NEXT:    [[SMIN2:%.*]] = call i32 @llvm.smin.i32(i32 [[TMP2]], i32 1)
; CHECK-NEXT:    [[TMP3:%.*]] = sub i32 [[TMP2]], [[SMIN2]]
; CHECK-NEXT:    [[TMP4:%.*]] = zext i32 [[TMP3]] to i64
; CHECK-NEXT:    [[TMP5:%.*]] = add nuw nsw i64 [[TMP4]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP5]], 2
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK:       vector.scevcheck:
; CHECK-NEXT:    [[TMP6:%.*]] = mul i32 [[INDVAR_LCSSA]], -1
; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[TMP6]], 1000
; CHECK-NEXT:    [[SMIN:%.*]] = call i32 @llvm.smin.i32(i32 [[TMP7]], i32 1)
; CHECK-NEXT:    [[TMP8:%.*]] = sub i32 [[TMP7]], [[SMIN]]
; CHECK-NEXT:    [[TMP9:%.*]] = add i32 [[TMP6]], 999
; CHECK-NEXT:    [[MUL:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 1, i32 [[TMP8]])
; CHECK-NEXT:    [[MUL_RESULT:%.*]] = extractvalue { i32, i1 } [[MUL]], 0
; CHECK-NEXT:    [[MUL_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[MUL]], 1
; CHECK-NEXT:    [[TMP10:%.*]] = sub i32 [[TMP9]], [[MUL_RESULT]]
; CHECK-NEXT:    [[TMP11:%.*]] = icmp ugt i32 [[TMP10]], [[TMP9]]
; CHECK-NEXT:    [[TMP12:%.*]] = or i1 [[TMP11]], [[MUL_OVERFLOW]]
; CHECK-NEXT:    br i1 [[TMP12]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP5]], 2
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP5]], [[N_MOD_VF]]
; CHECK-NEXT:    [[IND_END:%.*]] = sub i64 [[TMP0]], [[N_VEC]]
; 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:%.*]] = sub i64 [[TMP0]], [[INDEX]]
; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[OFFSET_IDX]], 0
; CHECK-NEXT:    [[TMP14:%.*]] = add nsw i64 [[TMP13]], -1
; CHECK-NEXT:    [[TMP15:%.*]] = and i64 [[TMP14]], 4294967295
; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i64 [[TMP15]]
; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds i32, ptr [[TMP17]], i32 -1
; CHECK-NEXT:    store <2 x i32> zeroinitializer, ptr [[TMP18]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP5]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[LOOP_1_LATCH:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[TMP0]], [[LOOP_3_PH]] ], [ [[TMP0]], [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT:    br label [[LOOP_3:%.*]]
; CHECK:       loop.3:
; CHECK-NEXT:    [[IV_2:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_2_NEXT:%.*]], [[LOOP_3]] ]
; CHECK-NEXT:    [[IV_2_NEXT]] = add nsw i64 [[IV_2]], -1
; CHECK-NEXT:    [[AND_IV:%.*]] = and i64 [[IV_2_NEXT]], 4294967295
; CHECK-NEXT:    [[GEP_DST:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[AND_IV]]
; CHECK-NEXT:    store i32 0, ptr [[GEP_DST]], align 4
; CHECK-NEXT:    [[IV_2_TRUNC:%.*]] = trunc i64 [[IV_2]] to i32
; CHECK-NEXT:    [[EC:%.*]] = icmp sgt i32 [[IV_2_TRUNC]], 1
; CHECK-NEXT:    br i1 [[EC]], label [[LOOP_3]], label [[LOOP_1_LATCH]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       loop.1.latch:
; CHECK-NEXT:    [[C_2:%.*]] = call i1 @cond()
; CHECK-NEXT:    br i1 [[C_2]], label [[EXIT:%.*]], label [[LOOP_1_HEADER]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop.1.header

loop.1.header:
  br label %loop.2

loop.2:
  %iv.1 = phi i64 [ 1000, %loop.1.header ], [ %iv.1.next, %loop.2 ]
  %iv.1.next = add i64 %iv.1, -1
  %c.1 = call i1 @cond()
  br i1 %c.1, label %loop.2, label %loop.3.ph

loop.3.ph:
  %iv.1.lcssa = phi i64 [ %iv.1, %loop.2 ]
  %0 = and i64 %iv.1.lcssa, 4294967295
  br label %loop.3

loop.3:
  %iv.2 = phi i64 [ %0, %loop.3.ph ], [ %iv.2.next, %loop.3 ]
  %iv.2.next = add nsw i64 %iv.2, -1
  %and.iv = and i64 %iv.2.next, 4294967295
  %gep.dst = getelementptr inbounds i32, ptr %dst, i64 %and.iv
  store i32 0, ptr %gep.dst, align 4
  %iv.2.trunc = trunc i64 %iv.2 to i32
  %ec = icmp sgt i32 %iv.2.trunc, 1
  br i1 %ec, label %loop.3, label %loop.1.latch

loop.1.latch:
  %c.2 = call i1 @cond()
  br i1 %c.2, label %exit, label %loop.1.header

exit:
  ret void
}

declare i1 @cond()