; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
; RUN: opt -passes='default<O3>' -S %s | FileCheck %s

target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
target triple = "arm64-apple-macosx11.0.0"

define i32 @read_only_loop_with_runtime_check(ptr noundef %array, i32 noundef %count, i32 noundef %n) {
; CHECK-LABEL: define i32 @read_only_loop_with_runtime_check(
; CHECK-SAME: ptr nocapture noundef readonly [[ARRAY:%.*]], i32 noundef [[COUNT:%.*]], i32 noundef [[N:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6_NOT:%.*]] = icmp eq i32 [[N]], 0
; CHECK-NEXT:    br i1 [[CMP6_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[TMP0:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[N]], -1
; CHECK-NEXT:    [[DOTNOT_NOT:%.*]] = icmp ugt i32 [[COUNT]], [[TMP1]]
; CHECK-NEXT:    br i1 [[DOTNOT_NOT]], label [[FOR_BODY_PREHEADER10:%.*]], label [[IF_THEN:%.*]]
; CHECK:       for.body.preheader10:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 8
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[FOR_BODY_PREHEADER13:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       for.body.preheader13:
; CHECK-NEXT:    [[INDVARS_IV_PH:%.*]] = phi i64 [ 0, [[FOR_BODY_PREHEADER10]] ], [ [[N_VEC:%.*]], [[MIDDLE_BLOCK:%.*]] ]
; CHECK-NEXT:    [[SUM_07_PH:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER10]] ], [ [[TMP7:%.*]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC]] = and i64 [[TMP0]], 4294967288
; 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 i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI11:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[ARRAY]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, ptr [[TMP2]], i64 16
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP2]], align 4
; CHECK-NEXT:    [[WIDE_LOAD12:%.*]] = load <4 x i32>, ptr [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4]] = add <4 x i32> [[WIDE_LOAD]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP5]] = add <4 x i32> [[WIDE_LOAD12]], [[VEC_PHI11]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[BIN_RDX:%.*]] = add <4 x i32> [[TMP5]], [[TMP4]]
; CHECK-NEXT:    [[TMP7]] = tail call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[BIN_RDX]])
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N_VEC]], [[TMP0]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY_PREHEADER13]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    ret i32 [[SUM_0_LCSSA]]
; CHECK:       for.body:
; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ [[INDVARS_IV_PH]], [[FOR_BODY_PREHEADER13]] ]
; CHECK-NEXT:    [[SUM_07:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[SUM_07_PH]], [[FOR_BODY_PREHEADER13]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[ARRAY]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ADD]] = add nsw i32 [[TMP8]], [[SUM_07]]
; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[TMP0]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       if.then:
; CHECK-NEXT:    tail call void @llvm.trap()
; CHECK-NEXT:    unreachable
;
entry:
  %array.addr = alloca ptr, align 8
  %count.addr = alloca i32, align 4
  %n.addr = alloca i32, align 4
  %sum = alloca i32, align 4
  %i = alloca i32, align 4
  store ptr %array, ptr %array.addr, align 8
  store i32 %count, ptr %count.addr, align 4
  store i32 %n, ptr %n.addr, align 4
  call void @llvm.lifetime.start.p0(i64 4, ptr %sum) #3
  store i32 0, ptr %sum, align 4
  call void @llvm.lifetime.start.p0(i64 4, ptr %i) #3
  store i32 0, ptr %i, align 4
  br label %for.cond

for.cond:                                         ; preds = %for.inc, %entry
  %0 = load i32, ptr %i, align 4
  %1 = load i32, ptr %n.addr, align 4
  %cmp = icmp ult i32 %0, %1
  br i1 %cmp, label %for.body, label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %for.cond
  call void @llvm.lifetime.end.p0(i64 4, ptr %i) #3
  br label %for.end

for.body:                                         ; preds = %for.cond
  %2 = load i32, ptr %i, align 4
  %3 = load i32, ptr %count.addr, align 4
  %cmp1 = icmp uge i32 %2, %3
  br i1 %cmp1, label %if.then, label %if.end

if.then:                                          ; preds = %for.body
  call void @llvm.trap()
  br label %if.end

if.end:                                           ; preds = %if.then, %for.body
  %4 = load ptr, ptr %array.addr, align 8
  %5 = load i32, ptr %i, align 4
  %idxprom = zext i32 %5 to i64
  %arrayidx = getelementptr inbounds i32, ptr %4, i64 %idxprom
  %6 = load i32, ptr %arrayidx, align 4
  %7 = load i32, ptr %sum, align 4
  %add = add nsw i32 %7, %6
  store i32 %add, ptr %sum, align 4
  br label %for.inc

for.inc:                                          ; preds = %if.end
  %8 = load i32, ptr %i, align 4
  %inc = add i32 %8, 1
  store i32 %inc, ptr %i, align 4
  br label %for.cond

for.end:                                          ; preds = %for.cond.cleanup
  %9 = load i32, ptr %sum, align 4
  call void @llvm.lifetime.end.p0(i64 4, ptr %sum)
  ret i32 %9
}

%"class.std::__1::span" = type { ptr, i64 }
%"class.std::__1::__wrap_iter" = type { ptr }

define dso_local noundef i32 @sum_prefix_with_sum(ptr %s.coerce0, i64 %s.coerce1, i64 noundef %n) {
; CHECK-LABEL: define dso_local noundef i32 @sum_prefix_with_sum(
; CHECK-SAME: ptr nocapture readonly [[S_COERCE0:%.*]], i64 [[S_COERCE1:%.*]], i64 noundef [[N:%.*]]) local_unnamed_addr #[[ATTR0]] {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP5_NOT:%.*]] = icmp eq i64 [[N]], 0
; CHECK-NEXT:    br i1 [[CMP5_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[N]], -1
; CHECK-NEXT:    [[DOTNOT_NOT:%.*]] = icmp ugt i64 [[S_COERCE1]], [[TMP0]]
; CHECK-NEXT:    br i1 [[DOTNOT_NOT]], label [[FOR_BODY_PREHEADER8:%.*]], label [[COND_FALSE_I:%.*]], !prof [[PROF4:![0-9]+]]
; CHECK:       for.body.preheader8:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], 8
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[FOR_BODY_PREHEADER11:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       for.body.preheader11:
; CHECK-NEXT:    [[I_07_PH:%.*]] = phi i64 [ 0, [[FOR_BODY_PREHEADER8]] ], [ [[N_VEC:%.*]], [[SPAN_CHECKED_ACCESS_EXIT:%.*]] ]
; CHECK-NEXT:    [[RET_0_LCSSA:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER8]] ], [ [[ADD:%.*]], [[SPAN_CHECKED_ACCESS_EXIT]] ]
; CHECK-NEXT:    br label [[FOR_BODY1:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC]] = and i64 [[N]], -8
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP3:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI9:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP4:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[S_COERCE0]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i64 16
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP1]], align 4
; CHECK-NEXT:    [[WIDE_LOAD10:%.*]] = load <4 x i32>, ptr [[TMP2]], align 4
; CHECK-NEXT:    [[TMP3]] = add <4 x i32> [[WIDE_LOAD]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP4]] = add <4 x i32> [[WIDE_LOAD10]], [[VEC_PHI9]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[SPAN_CHECKED_ACCESS_EXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[BIN_RDX:%.*]] = add <4 x i32> [[TMP4]], [[TMP3]]
; CHECK-NEXT:    [[ADD]] = tail call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[BIN_RDX]])
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY_PREHEADER11]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[RET_0_LCSSA1:%.*]] = phi i32 [ 0, [[ENTRY1:%.*]] ], [ [[ADD]], [[SPAN_CHECKED_ACCESS_EXIT]] ], [ [[ADD1:%.*]], [[FOR_BODY1]] ]
; CHECK-NEXT:    ret i32 [[RET_0_LCSSA1]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_07:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_BODY1]] ], [ [[I_07_PH]], [[FOR_BODY_PREHEADER11]] ]
; CHECK-NEXT:    [[RET_06:%.*]] = phi i32 [ [[ADD1]], [[FOR_BODY1]] ], [ [[RET_0_LCSSA]], [[FOR_BODY_PREHEADER11]] ]
; CHECK-NEXT:    [[ARRAYIDX_I:%.*]] = getelementptr inbounds i32, ptr [[S_COERCE0]], i64 [[I_07]]
; CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr [[ARRAYIDX_I]], align 4
; CHECK-NEXT:    [[ADD1]] = add nsw i32 [[TMP7]], [[RET_06]]
; CHECK-NEXT:    [[INC]] = add nuw i64 [[I_07]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY1]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       cond.false.i:
; CHECK-NEXT:    tail call void @llvm.trap()
; CHECK-NEXT:    unreachable
;
entry:
  %s = alloca %"class.std::__1::span", align 8
  %n.addr = alloca i64, align 8
  %ret = alloca i32, align 4
  %i = alloca i64, align 8
  %0 = getelementptr inbounds { ptr, i64 }, ptr %s, i32 0, i32 0
  store ptr %s.coerce0, ptr %0, align 8
  %1 = getelementptr inbounds { ptr, i64 }, ptr %s, i32 0, i32 1
  store i64 %s.coerce1, ptr %1, align 8
  store i64 %n, ptr %n.addr, align 8
  call void @llvm.lifetime.start.p0(i64 4, ptr %ret) #7
  store i32 0, ptr %ret, align 4
  call void @llvm.lifetime.start.p0(i64 8, ptr %i) #7
  store i64 0, ptr %i, align 8
  br label %for.cond

for.cond:                                         ; preds = %for.inc, %entry
  %2 = load i64, ptr %i, align 8
  %3 = load i64, ptr %n.addr, align 8
  %cmp = icmp ult i64 %2, %3
  br i1 %cmp, label %for.body, label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %for.cond
  call void @llvm.lifetime.end.p0(i64 8, ptr %i) #7
  br label %for.end

for.body:                                         ; preds = %for.cond
  %4 = load i64, ptr %i, align 8
  %call = call noundef nonnull align 4 dereferenceable(4) ptr @span_checked_access(ptr noundef nonnull align 8 dereferenceable(16) %s, i64 noundef %4) #7
  %5 = load i32, ptr %call, align 4
  %6 = load i32, ptr %ret, align 4
  %add = add nsw i32 %6, %5
  store i32 %add, ptr %ret, align 4
  br label %for.inc

for.inc:                                          ; preds = %for.body
  %7 = load i64, ptr %i, align 8
  %inc = add i64 %7, 1
  store i64 %inc, ptr %i, align 8
  br label %for.cond

for.end:                                          ; preds = %for.cond.cleanup
  %8 = load i32, ptr %ret, align 4
  call void @llvm.lifetime.end.p0(i64 4, ptr %ret)
  ret i32 %8
}

define hidden noundef nonnull align 4 dereferenceable(4) ptr @span_checked_access(ptr noundef nonnull align 8 dereferenceable(16) %this, i64 noundef %__idx) {
; CHECK-LABEL: define hidden noundef nonnull align 4 dereferenceable(4) ptr @span_checked_access(
; CHECK-SAME: ptr nocapture noundef nonnull readonly align 8 dereferenceable(16) [[THIS:%.*]], i64 noundef [[__IDX:%.*]]) local_unnamed_addr #[[ATTR0]] {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[__SIZE__I:%.*]] = getelementptr inbounds i8, ptr [[THIS]], i64 8
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr [[__SIZE__I]], align 8
; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[__IDX]], [[TMP0]]
; CHECK-NEXT:    br i1 [[CMP]], label [[COND_END:%.*]], label [[COND_FALSE:%.*]], !prof [[PROF4]]
; CHECK:       cond.false:
; CHECK-NEXT:    tail call void @llvm.trap()
; CHECK-NEXT:    unreachable
; CHECK:       cond.end:
; CHECK-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[THIS]], align 8
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 [[__IDX]]
; CHECK-NEXT:    ret ptr [[ARRAYIDX]]
;
entry:
  %this.addr = alloca ptr, align 8
  %__idx.addr = alloca i64, align 8
  store ptr %this, ptr %this.addr, align 8
  store i64 %__idx, ptr %__idx.addr, align 8
  %this1 = load ptr, ptr %this.addr, align 8
  %0 = load i64, ptr %__idx.addr, align 8
  %call = call noundef i64 @span_access(ptr noundef nonnull align 8 dereferenceable(16) %this1)
  %cmp = icmp ult i64 %0, %call
  %conv = zext i1 %cmp to i64
  %expval = call i64 @llvm.expect.i64(i64 %conv, i64 1)
  %tobool = icmp ne i64 %expval, 0
  br i1 %tobool, label %cond.true, label %cond.false

cond.true:                                        ; preds = %entry
  br label %cond.end

cond.false:                                       ; preds = %entry
  call void @llvm.trap()
  br label %cond.end

cond.end:                                         ; preds = %cond.false, %cond.true
  %__data_ = getelementptr inbounds %"class.std::__1::span", ptr %this1, i32 0, i32 0
  %1 = load ptr, ptr %__data_, align 8
  %2 = load i64, ptr %__idx.addr, align 8
  %arrayidx = getelementptr inbounds i32, ptr %1, i64 %2
  ret ptr %arrayidx
}

define hidden noundef i64 @span_access(ptr noundef nonnull align 8 dereferenceable(16) %this) {
; CHECK-LABEL: define hidden noundef i64 @span_access(
; CHECK-SAME: ptr nocapture noundef nonnull readonly align 8 dereferenceable(16) [[THIS:%.*]]) local_unnamed_addr #[[ATTR1:[0-9]+]] {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[__SIZE_:%.*]] = getelementptr inbounds i8, ptr [[THIS]], i64 8
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, ptr [[__SIZE_]], align 8
; CHECK-NEXT:    ret i64 [[TMP0]]
;
entry:
  %this.addr = alloca ptr, align 8
  store ptr %this, ptr %this.addr, align 8
  %this1 = load ptr, ptr %this.addr, align 8
  %__size_ = getelementptr inbounds %"class.std::__1::span", ptr %this1, i32 0, i32 1
  %0 = load i64, ptr %__size_, align 8
  ret i64 %0
}

declare void @llvm.lifetime.start.p0(i64 immarg, ptr nocapture)

declare void @llvm.trap()

declare void @llvm.lifetime.end.p0(i64 immarg, ptr nocapture)
;.
; 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]], [[META2]], [[META1]]}
; CHECK: [[PROF4]] = !{!"branch_weights", !"expected", i32 2000, i32 1}
; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META1]], [[META2]]}
; CHECK: [[LOOP6]] = distinct !{[[LOOP6]], [[META2]], [[META1]]}
;.