; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph:" --version 5
; RUN: opt -S -force-partial-aliasing-vectorization -force-target-supports-masked-memory-ops -tail-folding-policy=must-fold-tail -force-vector-width=4 -passes=loop-vectorize  %s | FileCheck %s

; Test taken from: scalable-first-order-recurrence.ll. Check we don't use
; an alias-mask with first-order recurrences, as we cannot handle the
; splice.right with the alias-mask/clamped VF yet.
define i32 @first_order_recurrence(ptr nocapture readonly %a, ptr nocapture %b, i32 %init_val, i32 %n) {
; CHECK-LABEL: define i32 @first_order_recurrence(
; CHECK-SAME: ptr readonly captures(none) [[A:%.*]], ptr captures(none) [[B:%.*]], i32 [[INIT_VAL:%.*]], i32 [[N:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[A2:%.*]] = ptrtoaddr ptr [[A]] to i64
; CHECK-NEXT:    [[B1:%.*]] = ptrtoaddr ptr [[B]] to i64
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[N]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
; CHECK-NEXT:    br label %[[VECTOR_MEMCHECK:.*]]
; CHECK:       [[VECTOR_MEMCHECK]]:
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[B1]], -4
; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 [[TMP3]], [[A2]]
; CHECK-NEXT:    [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP4]], 16
; CHECK-NEXT:    br i1 [[DIFF_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[TMP2]], 3
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[TMP2]], 1
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[VECTOR_RECUR_INIT:%.*]] = insertelement <4 x i32> poison, i32 [[INIT_VAL]], i32 3
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VECTOR_RECUR:%.*]] = phi <4 x i32> [ [[VECTOR_RECUR_INIT]], %[[VECTOR_PH]] ], [ [[WIDE_MASKED_LOAD:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IV:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP5:%.*]] = icmp ule <4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    [[TMP6:%.*]] = add nuw nsw i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP6]]
; CHECK-NEXT:    [[WIDE_MASKED_LOAD]] = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr align 4 [[TMP7]], <4 x i1> [[TMP5]], <4 x i32> poison)
; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <4 x i32> [[VECTOR_RECUR]], <4 x i32> [[WIDE_MASKED_LOAD]], <4 x i32> <i32 3, i32 4, i32 5, i32 6>
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP10:%.*]] = add <4 x i32> [[WIDE_MASKED_LOAD]], [[TMP8]]
; CHECK-NEXT:    call void @llvm.masked.store.v4i32.p0(<4 x i32> [[TMP10]], ptr align 4 [[TMP9]], <4 x i1> [[TMP5]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add nuw <4 x i64> [[VEC_IV]], splat (i64 4)
; CHECK-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP11]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[TMP12:%.*]] = xor <4 x i1> [[TMP5]], splat (i1 true)
; CHECK-NEXT:    [[FIRST_INACTIVE_LANE:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.v4i1(<4 x i1> [[TMP12]], i1 false)
; CHECK-NEXT:    [[LAST_ACTIVE_LANE:%.*]] = sub i64 [[FIRST_INACTIVE_LANE]], 1
; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <4 x i32> [[TMP8]], i64 [[LAST_ACTIVE_LANE]]
; CHECK-NEXT:    br [[FOR_EXIT:label %.*]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  br label %loop

loop:
  %0 = phi i32 [ %init_val, %entry ], [ %1, %loop ]
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %loop ]
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %arrayidx32 = getelementptr inbounds i32, ptr %a, i64 %indvars.iv.next
  %1 = load i32, ptr %arrayidx32
  %arrayidx34 = getelementptr inbounds i32, ptr %b, i64 %indvars.iv
  %add35 = add i32 %1, %0
  store i32 %add35, ptr %arrayidx34
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, %n
  br i1 %exitcond, label %for.exit, label %loop

for.exit:
  ret i32 %0
}

; This loop uses bounds checks (not diff checks), so can't use an alias mask.
define void @uses_bounds_checks(ptr noalias %a, ptr %b, ptr %c, i64 %n) {
; CHECK-LABEL: define void @uses_bounds_checks(
; CHECK-SAME: ptr noalias [[A:%.*]], ptr [[B:%.*]], ptr [[C:%.*]], i64 [[N:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    br label %[[VECTOR_MEMCHECK:.*]]
; CHECK:       [[VECTOR_MEMCHECK]]:
; CHECK-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[C]], i64 [[N]]
; CHECK-NEXT:    [[TMP0:%.*]] = shl i64 [[N]], 2
; CHECK-NEXT:    [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[B]], i64 [[TMP0]]
; CHECK-NEXT:    [[BOUND0:%.*]] = icmp ult ptr [[C]], [[SCEVGEP1]]
; CHECK-NEXT:    [[BOUND1:%.*]] = icmp ult ptr [[B]], [[SCEVGEP]]
; 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_RND_UP:%.*]] = add i64 [[N]], 3
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[N]], 1
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> 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_IV:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule <4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds nuw i8, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0(ptr align 1 [[TMP2]], <4 x i1> [[TMP1]], <4 x i8> poison)
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds nuw i32, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_MASKED_LOAD4:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr align 4 [[TMP3]], <4 x i1> [[TMP1]], <4 x i32> poison), !alias.scope [[META4:![0-9]+]]
; CHECK-NEXT:    [[TMP4:%.*]] = trunc <4 x i32> [[WIDE_MASKED_LOAD4]] to <4 x i8>
; CHECK-NEXT:    [[TMP5:%.*]] = add <4 x i8> [[TMP4]], [[WIDE_MASKED_LOAD]]
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds nuw i8, ptr [[C]], i64 [[INDEX]]
; CHECK-NEXT:    call void @llvm.masked.store.v4i8.p0(<4 x i8> [[TMP5]], ptr align 1 [[TMP6]], <4 x i1> [[TMP1]]), !alias.scope [[META7:![0-9]+]], !noalias [[META4]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add nuw <4 x i64> [[VEC_IV]], splat (i64 4)
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br [[EXIT:label %.*]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %ptr.a = getelementptr inbounds nuw i8, ptr %a, i64 %iv
  %load.a = load i8, ptr %ptr.a, align 1
  %ptr.b = getelementptr inbounds nuw i32, ptr %b, i64 %iv
  %load.b = load i32, ptr %ptr.b, align 4
  %b.trunc = trunc i32 %load.b to i8
  %add = add i8 %b.trunc, %load.a
  %ptr.c = getelementptr inbounds nuw i8, ptr %c, i64 %iv
  store i8 %add, ptr %ptr.c, align 1
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, %n
  br i1 %exitcond.not, label %exit, label %for.body

exit:
  ret void
}

; TODO: Handle the horizontal reduction outside the loop with an alias-mask.
; We need to set values outside the alias-mask to the identity value before
; the reduction.
define i8 @add_reduction(ptr %a, ptr %b, i64 %n) {
; CHECK-LABEL: define i8 @add_reduction(
; CHECK-SAME: ptr [[A:%.*]], ptr [[B:%.*]], i64 [[N:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[A2:%.*]] = ptrtoaddr ptr [[A]] to i64
; CHECK-NEXT:    [[B1:%.*]] = ptrtoaddr ptr [[B]] to i64
; CHECK-NEXT:    br label %[[VECTOR_MEMCHECK:.*]]
; CHECK:       [[VECTOR_MEMCHECK]]:
; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 [[B1]], [[A2]]
; CHECK-NEXT:    [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP0]], 4
; CHECK-NEXT:    br i1 [[DIFF_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N]], 3
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[N]], 1
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> 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_PHI:%.*]] = phi <4 x i8> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP3:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 0, i8 1, i8 2, i8 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND3:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT4:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule <4 x i64> [[VEC_IND3]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0(ptr align 1 [[TMP2]], <4 x i1> [[TMP1]], <4 x i8> poison)
; CHECK-NEXT:    [[TMP3]] = add <4 x i8> [[VEC_PHI]], [[WIDE_MASKED_LOAD]]
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT:    call void @llvm.masked.store.v4i8.p0(<4 x i8> [[VEC_IND]], ptr align 1 [[TMP4]], <4 x i1> [[TMP1]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i8> [[VEC_IND]], splat (i8 4)
; CHECK-NEXT:    [[VEC_IND_NEXT4]] = add nuw <4 x i64> [[VEC_IND3]], splat (i64 4)
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[TMP6:%.*]] = select <4 x i1> [[TMP1]], <4 x i8> [[TMP3]], <4 x i8> [[VEC_PHI]]
; CHECK-NEXT:    [[TMP7:%.*]] = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> [[TMP6]])
; CHECK-NEXT:    br [[EXIT:label %.*]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %sum.0 = phi i8 [ 0, %entry ], [ %sum.1, %for.body ]
  %gep.a = getelementptr inbounds i8, ptr %a, i64 %iv
  %load.a = load i8, ptr %gep.a, align 1
  %sum.1 = add i8 %sum.0, %load.a
  %gep.b = getelementptr inbounds i8, ptr %b, i64 %iv
  %trunc = trunc i64 %iv to i8
  store i8 %trunc, ptr %gep.b, align 1
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, %n
  br i1 %exitcond.not, label %exit, label %for.body

exit:
  ret i8 %sum.1
}