llvm/test/Transforms/Attributor/allocator.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-attributes --check-globals --version 2
; RUN: opt -aa-pipeline=basic-aa -passes=attributor -attributor-manifest-internal -attributor-annotate-decl-cs  -S < %s | FileCheck %s --check-prefixes=CHECK,TUNIT
; RUN: opt -aa-pipeline=basic-aa -passes=attributor-cgscc -attributor-manifest-internal -attributor-annotate-decl-cs -S < %s | FileCheck %s --check-prefixes=CHECK,CGSCC

%struct.Foo = type { i32, i32, i8 }

@.str = private unnamed_addr constant [17 x i8] c"The value is %d\0A\00", align 1

;.
; CHECK: @.str = private unnamed_addr constant [17 x i8] c"The value is %d\0A\00", align 1
;.
define dso_local void @positive_alloca_1(i32 noundef %val) #0 {
; CHECK-LABEL: define dso_local void @positive_alloca_1
; CHECK-SAME: (i32 noundef [[VAL:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[VAL_ADDR1:%.*]] = alloca i8, i32 4, align 4
; CHECK-NEXT:    [[F2:%.*]] = alloca i8, i32 4, align 4
; CHECK-NEXT:    store i32 [[VAL]], ptr [[VAL_ADDR1]], align 4
; CHECK-NEXT:    store i32 10, ptr [[F2]], align 4
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[F2]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 1
; CHECK-NEXT:    store i32 [[ADD]], ptr [[F2]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[F2]], align 4
; CHECK-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP1]], [[VAL]]
; CHECK-NEXT:    [[CALL:%.*]] = call i32 (ptr, ...) @printf(ptr noundef nonnull dereferenceable(17) @.str, i32 noundef [[ADD3]])
; CHECK-NEXT:    ret void
;
entry:
  %val.addr = alloca i64, align 4
  %f = alloca %struct.Foo, align 4
  store i32 %val, ptr %val.addr, align 4
  %field1 = getelementptr inbounds %struct.Foo, ptr %f, i32 0, i32 0
  store i32 10, ptr %field1, align 4
  %field11 = getelementptr inbounds %struct.Foo, ptr %f, i32 0, i32 0
  %0 = load i32, ptr %field11, align 4
  %add = add nsw i32 %0, 1
  store i32 %add, ptr %field11, align 4
  %field12 = getelementptr inbounds %struct.Foo, ptr %f, i32 0, i32 0
  %1 = load i32, ptr %field12, align 4
  %2 = load i32, ptr %val.addr, align 4
  %add3 = add nsw i32 %1, %2
  %call = call i32 (ptr, ...) @printf(ptr noundef @.str, i32 noundef %add3)
  ret void
}

; TODO: change malloc like call
; Function Attrs: noinline nounwind uwtable
define dso_local void @positive_malloc_1(ptr noundef %val) #0 {
; CHECK-LABEL: define dso_local void @positive_malloc_1
; CHECK-SAME: (ptr nofree noundef readonly captures(none) [[VAL:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[VAL_ADDR:%.*]] = alloca ptr, align 8
; CHECK-NEXT:    [[F:%.*]] = alloca ptr, align 8
; CHECK-NEXT:    store ptr [[VAL]], ptr [[VAL_ADDR]], align 8
; CHECK-NEXT:    [[CALL:%.*]] = call noalias ptr @malloc(i64 noundef 12)
; CHECK-NEXT:    store ptr [[CALL]], ptr [[F]], align 8
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[VAL]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 10
; CHECK-NEXT:    store i32 [[ADD]], ptr [[CALL]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[CALL]], align 4
; CHECK-NEXT:    [[CALL2:%.*]] = call i32 (ptr, ...) @printf(ptr noundef nonnull dereferenceable(17) @.str, i32 noundef [[TMP1]])
; CHECK-NEXT:    ret void
;
entry:
  %val.addr = alloca ptr, align 8
  %f = alloca ptr, align 8
  store ptr %val, ptr %val.addr, align 8
  %call = call noalias ptr @malloc(i64 noundef 12) #3
  store ptr %call, ptr %f, align 8
  %0 = load ptr, ptr %val.addr, align 8
  %1 = load i32, ptr %0, align 4
  %add = add nsw i32 %1, 10
  %2 = load ptr, ptr %f, align 8
  %a = getelementptr inbounds %struct.Foo, ptr %2, i32 0, i32 0
  store i32 %add, ptr %a, align 4
  %3 = load ptr, ptr %f, align 8
  %a1 = getelementptr inbounds %struct.Foo, ptr %3, i32 0, i32 0
  %4 = load i32, ptr %a1, align 4
  %call2 = call i32 (ptr, ...) @printf(ptr noundef @.str, i32 noundef %4)
  ret void
}

; TODO: change malloc like call
; Function Attrs: noinline nounwind uwtable
define dso_local void @positive_malloc_2(ptr noundef %val) #0 {
; CHECK-LABEL: define dso_local void @positive_malloc_2
; CHECK-SAME: (ptr nofree noundef readonly captures(none) [[VAL:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[VAL_ADDR:%.*]] = alloca ptr, align 8
; CHECK-NEXT:    [[F:%.*]] = alloca ptr, align 8
; CHECK-NEXT:    store ptr [[VAL]], ptr [[VAL_ADDR]], align 8
; CHECK-NEXT:    [[CALL:%.*]] = call noalias ptr @malloc(i64 noundef 60)
; CHECK-NEXT:    store ptr [[CALL]], ptr [[F]], align 8
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[VAL]], align 4
; CHECK-NEXT:    store i32 [[TMP0]], ptr [[CALL]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[CALL]], align 4
; CHECK-NEXT:    [[CALL2:%.*]] = call i32 (ptr, ...) @printf(ptr noundef nonnull dereferenceable(17) @.str, i32 noundef [[TMP1]])
; CHECK-NEXT:    ret void
;
entry:
  %val.addr = alloca ptr, align 8
  %x = alloca i32, align 4
  %f = alloca ptr, align 8
  store ptr %val, ptr %val.addr, align 8
  store i32 15, ptr %x, align 4
  %0 = load i32, ptr %x, align 4
  %conv = sext i32 %0 to i64
  %mul = mul i64 4, %conv
  %call = call noalias ptr @malloc(i64 noundef %mul)
  store ptr %call, ptr %f, align 8
  %1 = load ptr, ptr %val.addr, align 8
  %2 = load i32, ptr %1, align 4
  %3 = load ptr, ptr %f, align 8
  %arrayidx = getelementptr inbounds i32, ptr %3, i64 0
  store i32 %2, ptr %arrayidx, align 4
  %4 = load ptr, ptr %f, align 8
  %arrayidx1 = getelementptr inbounds i32, ptr %4, i64 0
  %5 = load i32, ptr %arrayidx1, align 4
  %call2 = call i32 (ptr, ...) @printf(ptr noundef @.str, i32 noundef %5)
  ret void
}

; Function Attrs: noinline nounwind uwtable
define dso_local ptr @negative_test_escaping_pointer(i32 noundef %val) #0 {
; CHECK-LABEL: define dso_local ptr @negative_test_escaping_pointer
; CHECK-SAME: (i32 noundef [[VAL:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[VAL_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[F:%.*]] = alloca ptr, align 8
; CHECK-NEXT:    store i32 [[VAL]], ptr [[VAL_ADDR]], align 4
; CHECK-NEXT:    [[CALL:%.*]] = call noalias ptr @malloc(i64 noundef 16)
; CHECK-NEXT:    store ptr [[CALL]], ptr [[F]], align 8
; CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[F]], align 8
; CHECK-NEXT:    store i32 2, ptr [[TMP0]], align 8
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 10, [[VAL]]
; CHECK-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[F]], align 8
; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 8
; CHECK-NEXT:    [[ADD2:%.*]] = add nsw i32 [[TMP2]], [[ADD]]
; CHECK-NEXT:    store i32 [[ADD2]], ptr [[TMP1]], align 8
; CHECK-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[F]], align 8
; CHECK-NEXT:    ret ptr [[TMP3]]
;
entry:
  %val.addr = alloca i32, align 4
  %f = alloca ptr, align 8
  store i32 %val, ptr %val.addr, align 4
  %call = call noalias ptr @malloc(i64 noundef 16) #2
  store ptr %call, ptr %f, align 8
  %0 = load ptr, ptr %f, align 8
  %field1 = getelementptr inbounds %struct.Foo, ptr %0, i32 0, i32 0
  store i32 2, ptr %field1, align 8
  %1 = load i32, ptr %val.addr, align 4
  %add = add nsw i32 10, %1
  %2 = load ptr, ptr %f, align 8
  %field11 = getelementptr inbounds %struct.Foo, ptr %2, i32 0, i32 0
  %3 = load i32, ptr %field11, align 8
  %add2 = add nsw i32 %3, %add
  store i32 %add2, ptr %field11, align 8
  %4 = load ptr, ptr %f, align 8
  ret ptr %4
}


;TODO: The allocation can be reduced here.
;However, the offsets (load/store etc.) Need to be changed.
; Function Attrs: noinline nounwind uwtable
define dso_local { i64, ptr } @positive_test_not_a_single_start_offset(i32 noundef %val) #0 {
; CHECK: Function Attrs: mustprogress nofree norecurse nosync nounwind willreturn memory(none)
; CHECK-LABEL: define dso_local { i64, ptr } @positive_test_not_a_single_start_offset
; CHECK-SAME: (i32 noundef [[VAL:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[RETVAL:%.*]] = alloca [[STRUCT_FOO:%.*]], align 8
; CHECK-NEXT:    [[VAL_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT:    store i32 [[VAL]], ptr [[VAL_ADDR]], align 4
; CHECK-NEXT:    store i32 2, ptr [[RETVAL]], align 8
; CHECK-NEXT:    [[FIELD3:%.*]] = getelementptr inbounds [[STRUCT_FOO]], ptr [[RETVAL]], i32 0, i32 2
; CHECK-NEXT:    store ptr [[VAL_ADDR]], ptr [[FIELD3]], align 8
; CHECK-NEXT:    [[TMP0:%.*]] = load { i64, ptr }, ptr [[RETVAL]], align 8
; CHECK-NEXT:    ret { i64, ptr } [[TMP0]]
;
entry:
  %retval = alloca %struct.Foo, align 8
  %val.addr = alloca i32, align 4
  store i32 %val, ptr %val.addr, align 4
  %field1 = getelementptr inbounds %struct.Foo, ptr %retval, i32 0, i32 0
  store i32 2, ptr %field1, align 8
  %field3 = getelementptr inbounds %struct.Foo, ptr %retval, i32 0, i32 2
  store ptr %val.addr, ptr %field3, align 8
  %0 = load { i64, ptr }, ptr %retval, align 8
  ret { i64, ptr } %0
}

; Function Attrs: noinline nounwind uwtable
define dso_local void @positive_test_reduce_array_allocation_1() {
; CHECK-LABEL: define dso_local void @positive_test_reduce_array_allocation_1() {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[ARRAY1:%.*]] = alloca i8, i32 4, align 8
; CHECK-NEXT:    store i32 0, ptr [[ARRAY1]], align 8
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[ARRAY1]], align 8
; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[TMP0]], 2
; CHECK-NEXT:    store i32 [[TMP1]], ptr [[ARRAY1]], align 8
; CHECK-NEXT:    [[TMP2:%.*]] = add i32 1, 2
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr [[ARRAY1]], align 8
; CHECK-NEXT:    [[TMP4:%.*]] = add i32 [[TMP2]], [[TMP3]]
; CHECK-NEXT:    store i32 [[TMP4]], ptr [[ARRAY1]], align 8
; CHECK-NEXT:    [[TMP5:%.*]] = load i32, ptr [[ARRAY1]], align 8
; CHECK-NEXT:    [[CALL:%.*]] = call i32 (ptr, ...) @printf(ptr noundef nonnull dereferenceable(17) @.str, i32 noundef [[TMP5]])
; CHECK-NEXT:    ret void
;
entry:
  %array = alloca ptr, i32 10
  store i32 0, ptr %array
  %0 = load i32, ptr %array
  %1 = add i32 %0, 2
  store i32 %1, ptr %array
  %2 = add i32 1, 2
  %3 = load i32, ptr %array
  %4 = add i32 %2, %3
  store i32 %4, ptr %array
  %5 = load i32, ptr %array
  %call = call i32 (ptr, ...) @printf(ptr noundef @.str, i32 noundef %5)
  ret void
}


; Function Attrs: noinline nounwind uwtable
; TODO: Here the array size is not known at compile time.
; However the array does not escape and is only partially used.
; Should the optimization reduce the allocation size regardless? Based on AAPointerInfo.
define dso_local void @baz(ptr noundef %val, i32 noundef %arrayLength) #0 {
; CHECK-LABEL: define dso_local void @baz
; CHECK-SAME: (ptr nofree noundef readonly captures(none) [[VAL:%.*]], i32 noundef [[ARRAYLENGTH:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[VAL_ADDR:%.*]] = alloca ptr, align 8
; CHECK-NEXT:    [[ARRAYLENGTH_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[F:%.*]] = alloca ptr, align 8
; CHECK-NEXT:    store ptr [[VAL]], ptr [[VAL_ADDR]], align 8
; CHECK-NEXT:    store i32 [[ARRAYLENGTH]], ptr [[ARRAYLENGTH_ADDR]], align 4
; CHECK-NEXT:    [[CONV:%.*]] = sext i32 [[ARRAYLENGTH]] to i64
; CHECK-NEXT:    [[MUL:%.*]] = mul i64 4, [[CONV]]
; CHECK-NEXT:    [[CALL:%.*]] = call noalias ptr @malloc(i64 noundef [[MUL]])
; CHECK-NEXT:    store ptr [[CALL]], ptr [[F]], align 8
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[VAL]], align 4
; CHECK-NEXT:    store i32 [[TMP0]], ptr [[CALL]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[CALL]], align 4
; CHECK-NEXT:    [[CALL2:%.*]] = call i32 (ptr, ...) @printf(ptr noundef nonnull dereferenceable(17) @.str, i32 noundef [[TMP1]])
; CHECK-NEXT:    ret void
;
entry:
  %val.addr = alloca ptr, align 8
  %arrayLength.addr = alloca i32, align 4
  %f = alloca ptr, align 8
  store ptr %val, ptr %val.addr, align 8
  store i32 %arrayLength, ptr %arrayLength.addr, align 4
  %0 = load i32, ptr %arrayLength.addr, align 4
  %conv = sext i32 %0 to i64
  %mul = mul i64 4, %conv
  %call = call noalias ptr @malloc(i64 noundef %mul) #3
  store ptr %call, ptr %f, align 8
  %1 = load ptr, ptr %val.addr, align 8
  %2 = load i32, ptr %1, align 4
  %3 = load ptr, ptr %f, align 8
  %arrayidx = getelementptr inbounds i32, ptr %3, i64 0
  store i32 %2, ptr %arrayidx, align 4
  %4 = load ptr, ptr %f, align 8
  %arrayidx1 = getelementptr inbounds i32, ptr %4, i64 0
  %5 = load i32, ptr %arrayidx1, align 4
  %call2 = call i32 (ptr, ...) @printf(ptr noundef @.str, i32 noundef %5)
  ret void
}

;TODO: Here since only even indexes of the array are part of the output
;We can reduce the allocation by half and make an array that's accessed contiguously
; Function Attrs: noinline nounwind uwtable
define dso_local void @positive_test_reduce_array_allocation_2() #0 {
; CHECK-LABEL: define dso_local void @positive_test_reduce_array_allocation_2() {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[ARRAY:%.*]] = alloca ptr, align 8
; CHECK-NEXT:    [[I:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[CALL:%.*]] = call noalias ptr @malloc(i64 noundef 40000)
; CHECK-NEXT:    store ptr [[CALL]], ptr [[ARRAY]], align 8
; CHECK-NEXT:    store i32 0, ptr [[I]], align 4
; CHECK-NEXT:    br label [[FOR_COND:%.*]]
; CHECK:       for.cond:
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[TMP0]], 10000
; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[IDXPROM:%.*]] = sext i32 [[TMP2]] to i64
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[CALL]], i64 [[IDXPROM]]
; CHECK-NEXT:    store i32 [[TMP1]], ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    br label [[FOR_INC:%.*]]
; CHECK:       for.inc:
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP3]], 2
; CHECK-NEXT:    store i32 [[ADD]], ptr [[I]], align 4
; CHECK-NEXT:    br label [[FOR_COND]]
; CHECK:       for.end:
; CHECK-NEXT:    store i32 0, ptr [[I]], align 4
; CHECK-NEXT:    br label [[FOR_COND1:%.*]]
; CHECK:       for.cond1:
; CHECK-NEXT:    [[TMP4:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[CMP2:%.*]] = icmp slt i32 [[TMP4]], 10000
; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_BODY3:%.*]], label [[FOR_END9:%.*]]
; CHECK:       for.body3:
; CHECK-NEXT:    [[TMP5:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[IDXPROM4:%.*]] = sext i32 [[TMP5]] to i64
; CHECK-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, ptr [[CALL]], i64 [[IDXPROM4]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr [[ARRAYIDX5]], align 4
; CHECK-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP6]], 1
; CHECK-NEXT:    store i32 [[ADD6]], ptr [[ARRAYIDX5]], align 4
; CHECK-NEXT:    br label [[FOR_INC7:%.*]]
; CHECK:       for.inc7:
; CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[ADD8:%.*]] = add nsw i32 [[TMP7]], 2
; CHECK-NEXT:    store i32 [[ADD8]], ptr [[I]], align 4
; CHECK-NEXT:    br label [[FOR_COND1]]
; CHECK:       for.end9:
; CHECK-NEXT:    store i32 0, ptr [[I]], align 4
; CHECK-NEXT:    br label [[FOR_COND10:%.*]]
; CHECK:       for.cond10:
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[CMP11:%.*]] = icmp slt i32 [[TMP8]], 10000
; CHECK-NEXT:    br i1 [[CMP11]], label [[FOR_BODY12:%.*]], label [[FOR_END18:%.*]]
; CHECK:       for.body12:
; CHECK-NEXT:    [[TMP9:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[IDXPROM13:%.*]] = sext i32 [[TMP9]] to i64
; CHECK-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds i32, ptr [[CALL]], i64 [[IDXPROM13]]
; CHECK-NEXT:    [[TMP10:%.*]] = load i32, ptr [[ARRAYIDX14]], align 4
; CHECK-NEXT:    [[CALL15:%.*]] = call i32 (ptr, ...) @printf(ptr noundef nonnull dereferenceable(17) @.str, i32 noundef [[TMP10]])
; CHECK-NEXT:    br label [[FOR_INC16:%.*]]
; CHECK:       for.inc16:
; CHECK-NEXT:    [[TMP11:%.*]] = load i32, ptr [[I]], align 4
; CHECK-NEXT:    [[ADD17:%.*]] = add nsw i32 [[TMP11]], 2
; CHECK-NEXT:    store i32 [[ADD17]], ptr [[I]], align 4
; CHECK-NEXT:    br label [[FOR_COND10]]
; CHECK:       for.end18:
; CHECK-NEXT:    ret void
;
entry:
  %array = alloca ptr, align 8
  %i = alloca i32, align 4
  %call = call noalias ptr @malloc(i64 noundef 40000) #3
  store ptr %call, ptr %array, align 8
  store i32 0, ptr %i, align 4
  br label %for.cond

for.cond:
  %0 = load i32, ptr %i, align 4
  %cmp = icmp slt i32 %0, 10000
  br i1 %cmp, label %for.body, label %for.end

for.body:
  %1 = load i32, ptr %i, align 4
  %2 = load ptr, ptr %array, align 8
  %3 = load i32, ptr %i, align 4
  %idxprom = sext i32 %3 to i64
  %arrayidx = getelementptr inbounds i32, ptr %2, i64 %idxprom
  store i32 %1, ptr %arrayidx, align 4
  br label %for.inc

for.inc:
  %4 = load i32, ptr %i, align 4
  %add = add nsw i32 %4, 2
  store i32 %add, ptr %i, align 4
  br label %for.cond

for.end:
  store i32 0, ptr %i, align 4
  br label %for.cond1

for.cond1:
  %5 = load i32, ptr %i, align 4
  %cmp2 = icmp slt i32 %5, 10000
  br i1 %cmp2, label %for.body3, label %for.end9

for.body3:
  %6 = load ptr, ptr %array, align 8
  %7 = load i32, ptr %i, align 4
  %idxprom4 = sext i32 %7 to i64
  %arrayidx5 = getelementptr inbounds i32, ptr %6, i64 %idxprom4
  %8 = load i32, ptr %arrayidx5, align 4
  %add6 = add nsw i32 %8, 1
  store i32 %add6, ptr %arrayidx5, align 4
  br label %for.inc7

for.inc7:
  %9 = load i32, ptr %i, align 4
  %add8 = add nsw i32 %9, 2
  store i32 %add8, ptr %i, align 4
  br label %for.cond1

for.end9:
  store i32 0, ptr %i, align 4
  br label %for.cond10

for.cond10:
  %10 = load i32, ptr %i, align 4
  %cmp11 = icmp slt i32 %10, 10000
  br i1 %cmp11, label %for.body12, label %for.end18

for.body12:
  %11 = load ptr, ptr %array, align 8
  %12 = load i32, ptr %i, align 4
  %idxprom13 = sext i32 %12 to i64
  %arrayidx14 = getelementptr inbounds i32, ptr %11, i64 %idxprom13
  %13 = load i32, ptr %arrayidx14, align 4
  %call15 = call i32 (ptr, ...) @printf(ptr noundef @.str, i32 noundef %13)
  br label %for.inc16

for.inc16:
  %14 = load i32, ptr %i, align 4
  %add17 = add nsw i32 %14, 2
  store i32 %add17, ptr %i, align 4
  br label %for.cond10

for.end18:
  ret void
}


define dso_local void @pthread_test(){
; TUNIT-LABEL: define dso_local void @pthread_test() {
; TUNIT-NEXT:    [[ARG1:%.*]] = alloca i8, align 8
; TUNIT-NEXT:    [[THREAD:%.*]] = alloca i64, align 8
; TUNIT-NEXT:    [[CALL1:%.*]] = call i32 @pthread_create(ptr noundef nonnull align 8 dereferenceable(8) [[THREAD]], ptr noundef null, ptr noundef nonnull @pthread_allocation_should_remain_same, ptr noundef nonnull align 8 dereferenceable(1) [[ARG1]])
; TUNIT-NEXT:    [[F1:%.*]] = alloca i8, i32 4, align 4
; TUNIT-NEXT:    [[CALL2:%.*]] = call i32 @pthread_create(ptr noundef nonnull align 8 dereferenceable(8) [[THREAD]], ptr noundef null, ptr noundef nonnull @pthread_allocation_should_be_reduced, ptr noalias nofree nonnull readnone align 4 captures(none) undef)
; TUNIT-NEXT:    [[F2:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
; TUNIT-NEXT:    [[CALL3:%.*]] = call i32 @pthread_create(ptr noundef nonnull align 8 dereferenceable(8) [[THREAD]], ptr noundef null, ptr noundef nonnull @pthread_check_captured_pointer, ptr noundef nonnull align 4 dereferenceable(12) [[F2]])
; TUNIT-NEXT:    ret void
;
; CGSCC-LABEL: define dso_local void @pthread_test() {
; CGSCC-NEXT:    [[ARG1:%.*]] = alloca i8, align 8
; CGSCC-NEXT:    [[THREAD:%.*]] = alloca i64, align 8
; CGSCC-NEXT:    [[CALL1:%.*]] = call i32 @pthread_create(ptr noundef nonnull align 8 dereferenceable(8) [[THREAD]], ptr noundef null, ptr noundef nonnull @pthread_allocation_should_remain_same, ptr noundef nonnull align 8 dereferenceable(1) [[ARG1]])
; CGSCC-NEXT:    [[F:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
; CGSCC-NEXT:    [[CALL2:%.*]] = call i32 @pthread_create(ptr noundef nonnull align 8 dereferenceable(8) [[THREAD]], ptr noundef null, ptr noundef nonnull @pthread_allocation_should_be_reduced, ptr noalias nofree noundef nonnull readonly align 4 captures(none) dereferenceable(12) [[F]])
; CGSCC-NEXT:    [[F2:%.*]] = alloca [[STRUCT_FOO]], align 4
; CGSCC-NEXT:    [[CALL3:%.*]] = call i32 @pthread_create(ptr noundef nonnull align 8 dereferenceable(8) [[THREAD]], ptr noundef null, ptr noundef nonnull @pthread_check_captured_pointer, ptr noundef nonnull align 4 dereferenceable(12) [[F2]])
; CGSCC-NEXT:    ret void
;
  %arg1 = alloca i8, align 8
  %thread = alloca i64, align 8
  %call1 = call i32 @pthread_create(ptr nonnull %thread, ptr null, ptr nonnull @pthread_allocation_should_remain_same, ptr %arg1)
  %f = alloca %struct.Foo, align 4
  %call2 = call i32 @pthread_create(ptr nonnull %thread, ptr null, ptr nonnull @pthread_allocation_should_be_reduced, ptr %f)
  %f2 = alloca %struct.Foo, align 4
  %call3 = call i32 @pthread_create(ptr nonnull %thread, ptr null, ptr nonnull @pthread_check_captured_pointer, ptr %f2)
  ret void
}

define internal ptr @pthread_allocation_should_remain_same(ptr %arg) {
; CHECK-LABEL: define internal noundef nonnull align 8 dereferenceable(1) ptr @pthread_allocation_should_remain_same
; CHECK-SAME: (ptr noundef nonnull returned align 8 dereferenceable(1) [[ARG:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CALL:%.*]] = call i32 (ptr, ...) @printf(ptr noundef nonnull dereferenceable(17) @.str, ptr noundef nonnull align 8 dereferenceable(1) [[ARG]])
; CHECK-NEXT:    ret ptr [[ARG]]
;
entry:
  %call = call i32 (ptr, ...) @printf(ptr noundef @.str, ptr noundef %arg)
  ret ptr %arg
}

define internal void @pthread_allocation_should_be_reduced(ptr %arg) {
;
; TUNIT-LABEL: define internal void @pthread_allocation_should_be_reduced
; TUNIT-SAME: (ptr noalias nofree nonnull readnone align 4 captures(none) dereferenceable(12) [[ARG:%.*]]) {
; TUNIT-NEXT:  entry:
; TUNIT-NEXT:    [[CALL:%.*]] = call i32 (ptr, ...) @printf(ptr noundef nonnull dereferenceable(17) @.str, i32 undef)
; TUNIT-NEXT:    ret void
;
; CGSCC-LABEL: define internal void @pthread_allocation_should_be_reduced
; CGSCC-SAME: (ptr noalias nofree noundef nonnull readonly align 4 captures(none) dereferenceable(12) [[ARG:%.*]]) {
; CGSCC-NEXT:  entry:
; CGSCC-NEXT:    [[TMP0:%.*]] = load i32, ptr [[ARG]], align 4
; CGSCC-NEXT:    [[CALL:%.*]] = call i32 (ptr, ...) @printf(ptr noundef nonnull dereferenceable(17) @.str, i32 noundef [[TMP0]])
; CGSCC-NEXT:    ret void
;
entry:
  %field1 = getelementptr inbounds %struct.Foo, ptr %arg, i32 0, i32 0
  %0 = load i32, ptr %field1, align 4
  %call = call i32 (ptr, ...) @printf(ptr noundef @.str, i32 noundef %0)
  ret void
}

define internal void @pthread_check_captured_pointer(ptr %arg){
; CHECK-LABEL: define internal void @pthread_check_captured_pointer
; CHECK-SAME: (ptr noundef nonnull align 4 dereferenceable(12) [[ARG:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    call void @external_call(ptr noundef nonnull align 4 dereferenceable(12) [[ARG]])
; CHECK-NEXT:    ret void
;
entry:
  %field1 = getelementptr inbounds %struct.Foo, ptr %arg, i32 0, i32 0
  call void @external_call(ptr %field1)
  ret void
}


declare external void @external_call(ptr)

declare !callback !0 dso_local i32 @pthread_create(ptr, ptr, ptr, ptr)
!1 = !{i64 2, i64 3, i1 false}
!0 = !{!1}

declare i32 @printf(ptr noundef, ...) #1

; Function Attrs: nounwind allocsize(0)
declare noalias ptr @malloc(i64 noundef) #1
;.
; TUNIT: attributes #[[ATTR0]] = { mustprogress nofree norecurse nosync nounwind willreturn memory(none) }
;.
; CGSCC: attributes #[[ATTR0]] = { mustprogress nofree norecurse nosync nounwind willreturn memory(none) }
;.
; TUNIT: [[META0:![0-9]+]] = !{[[META1:![0-9]+]]}
; TUNIT: [[META1]] = !{i64 2, i64 3, i1 false}
;.
; CGSCC: [[META0:![0-9]+]] = !{[[META1:![0-9]+]]}
; CGSCC: [[META1]] = !{i64 2, i64 3, i1 false}
;.