; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph" --version 6
; RUN: opt -S -passes=loop-vectorize -enable-vplan-native-path -verify-loop-info -verify-dom-info < %s | FileCheck %s

; extern int arr[8][8];
; extern int arr2[8];
;
; void foo(int n)
; {
;   int i1, i2;
;
; #pragma clang loop vectorize(enable) vectorize_width(4)
;   for (i1 = 0; i1 < 8; i1++) {
;     arr2[i1] = i1;
;     for (i2 = 0; i2 < 8; i2++)
;       arr[i2][i1] = i1 + n;
;   }
; }
;

@arr2 = external global [8 x i32], align 16
@arr = external global [8 x [8 x i32]], align 16

define void @foo(i32 %n) {
; CHECK-LABEL: define void @foo(
; CHECK-SAME: i32 [[N:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[N]], 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_LATCH:.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_LATCH]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [8 x i32], ptr @arr2, i64 0, <4 x i64> [[VEC_IND]]
; CHECK-NEXT:    [[TMP1:%.*]] = trunc <4 x i64> [[VEC_IND]] to <4 x i32>
; CHECK-NEXT:    call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> [[TMP1]], <4 x ptr> align 4 [[TMP0]], <4 x i1> splat (i1 true))
; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <4 x i32> [[TMP1]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    br label %[[FOR_BODY31:.*]]
; CHECK:       [[FOR_BODY31]]:
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i64> [ zeroinitializer, %[[VECTOR_BODY]] ], [ [[TMP4:%.*]], %[[FOR_BODY31]] ]
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [8 x [8 x i32]], ptr @arr, i64 0, <4 x i64> [[VEC_PHI]], <4 x i64> [[VEC_IND]]
; CHECK-NEXT:    call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> [[TMP2]], <4 x ptr> align 4 [[TMP3]], <4 x i1> splat (i1 true))
; CHECK-NEXT:    [[TMP4]] = add nuw nsw <4 x i64> [[VEC_PHI]], splat (i64 1)
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq <4 x i64> [[TMP4]], splat (i64 8)
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    br i1 [[TMP6]], label %[[VECTOR_LATCH]], label %[[FOR_BODY31]]
; CHECK:       [[VECTOR_LATCH]]:
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add nuw nsw <4 x i64> [[VEC_IND]], splat (i64 4)
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 8
; 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:    ret void
;
entry:
  br label %outer.header

outer.header:
  %iv.outer = phi i64 [ 0, %entry ], [ %iv.outer.next, %outer.latch ]
  %gep.arr2 = getelementptr inbounds [8 x i32], ptr @arr2, i64 0, i64 %iv.outer
  %i.trunc = trunc i64 %iv.outer to i32
  store i32 %i.trunc, ptr %gep.arr2, align 4
  %i.trunc2 = trunc i64 %iv.outer to i32
  %add = add nsw i32 %i.trunc2, %n
  br label %inner

inner:
  %iv.inner = phi i64 [ 0, %outer.header ], [ %iv.inner.next, %inner ]
  %gep.arr = getelementptr inbounds [8 x [8 x i32]], ptr @arr, i64 0, i64 %iv.inner, i64 %iv.outer
  store i32 %add, ptr %gep.arr, align 4
  %iv.inner.next = add nuw nsw i64 %iv.inner, 1
  %inner.ec = icmp eq i64 %iv.inner.next, 8
  br i1 %inner.ec, label %outer.latch, label %inner

outer.latch:
  %iv.outer.next = add nuw nsw i64 %iv.outer, 1
  %outer.ec = icmp eq i64 %iv.outer.next, 8
  br i1 %outer.ec, label %exit, label %outer.header, !llvm.loop !1

exit:
  ret void
}

!1 = distinct !{!1, !2, !3}
!2 = !{!"llvm.loop.vectorize.width", i32 4}
!3 = !{!"llvm.loop.vectorize.enable", i1 true}