; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -passes='loop-vectorize' -force-vector-width=4 -S < %s | FileCheck %s

; Test if the follow-up metadata for loops works fine. The original code is
; something like below. In this case, the unrolling metadata from the original
; loop should be applied to the vector loop as well.
;
; void f(float *a, float x) {
;   #pragma clang loop vectorize(enable) unroll_count(8)
;   for (int i = 0; i < 1024; i++) {
;     a[i] *= x;
;   }
; }
;
define void @scalar_loop_dead(ptr noundef captures(none) %a, float noundef %x) {
; CHECK-LABEL: define void @scalar_loop_dead(
; CHECK-SAME: ptr noundef captures(none) [[A:%.*]], float noundef [[X:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[X]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT]], <4 x float> 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:    [[TMP0:%.*]] = getelementptr inbounds nuw float, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = fmul <4 x float> [[BROADCAST_SPLAT]], [[WIDE_LOAD]]
; CHECK-NEXT:    store <4 x float> [[TMP1]], ptr [[TMP0]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
; CHECK-NEXT:    br i1 [[TMP2]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br label %[[EXIT:.*]]
; CHECK:       [[SCALAR_PH:.*]]:
; CHECK-NEXT:    br label %[[LOOP:.*]]
; CHECK:       [[LOOP]]:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds nuw float, ptr [[A]], i64 [[IV]]
; CHECK-NEXT:    [[LOAD:%.*]] = load float, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[MUL:%.*]] = fmul float [[X]], [[LOAD]]
; CHECK-NEXT:    store float [[MUL]], ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[COMP:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; CHECK-NEXT:    br i1 [[COMP]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       [[EXIT]]:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %arrayidx = getelementptr inbounds nuw float, ptr %a, i64 %iv
  %load = load float, ptr %arrayidx, align 4
  %mul = fmul float %x, %load
  store float %mul, ptr %arrayidx, align 4
  %iv.next = add nuw nsw i64 %iv, 1
  %comp = icmp eq i64 %iv.next, 1024
  br i1 %comp, label %exit, label %loop, !llvm.loop !0

exit:
  ret void
}

define void @scalar_loop_live(ptr noundef captures(none) %a, float noundef %x, i64 %n) {
; CHECK-LABEL: define void @scalar_loop_live(
; CHECK-SAME: ptr noundef captures(none) [[A:%.*]], float noundef [[X:%.*]], i64 [[N:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*]]:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[X]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT]], <4 x float> 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:    [[TMP0:%.*]] = getelementptr inbounds nuw float, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = fmul <4 x float> [[BROADCAST_SPLAT]], [[WIDE_LOAD]]
; CHECK-NEXT:    store <4 x float> [[TMP1]], ptr [[TMP0]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP2]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[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:    [[ARRAYIDX:%.*]] = getelementptr inbounds nuw float, ptr [[A]], i64 [[IV]]
; CHECK-NEXT:    [[LOAD:%.*]] = load float, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[MUL:%.*]] = fmul float [[X]], [[LOAD]]
; CHECK-NEXT:    store float [[MUL]], ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[COMP:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; CHECK-NEXT:    br i1 [[COMP]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       [[EXIT]]:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %arrayidx = getelementptr inbounds nuw float, ptr %a, i64 %iv
  %load = load float, ptr %arrayidx, align 4
  %mul = fmul float %x, %load
  store float %mul, ptr %arrayidx, align 4
  %iv.next = add nuw nsw i64 %iv, 1
  %comp = icmp eq i64 %iv.next, %n
  br i1 %comp, label %exit, label %loop, !llvm.loop !0

exit:
  ret void
}
!0 = distinct !{!0, !1, !2}
!1 = !{!"llvm.loop.vectorize.enable", i1 true}
!2 = !{!"llvm.loop.vectorize.followup_all", !3, !4}
!3 = !{!"llvm.loop.isvectorized"}
!4 = !{!"llvm.loop.unroll.count", i32 8}
;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]], [[META3:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized"}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.count", i32 8}
; CHECK: [[META3]] = !{!"llvm.loop.unroll.runtime.disable"}
; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META5:![0-9]+]], [[META6:![0-9]+]]}
; CHECK: [[META5]] = !{!"llvm.loop.vectorize.enable", i1 true}
; CHECK: [[META6]] = !{!"llvm.loop.vectorize.followup_all", [[META1]], [[META2]]}
; CHECK: [[LOOP7]] = distinct !{[[LOOP7]], [[META1]], [[META2]], [[META3]]}
; CHECK: [[LOOP8]] = distinct !{[[LOOP8]], [[META1]], [[META2]]}
;.