// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// Check that the CHECK lines are generated for clang-generated functions
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -fopenmp %s -emit-llvm -o - | FileCheck --check-prefix=OMP %s
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu %s -emit-llvm -o - | FileCheck --check-prefix=NOOMP %s

const int size = 1024 * 1024 * 32;

double A[size];

void foo(void);

// OMP-LABEL: @main(
// OMP-NEXT:  entry:
// OMP-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// OMP-NEXT:    [[I:%.*]] = alloca i32, align 4
// OMP-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// OMP-NEXT:    store i32 0, i32* [[I]], align 4
// OMP-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined..1 to void (i32*, i32*, ...)*))
// OMP-NEXT:    call void @foo()
// OMP-NEXT:    ret i32 0
//
// NOOMP-LABEL: @main(
// NOOMP-NEXT:  entry:
// NOOMP-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// NOOMP-NEXT:    [[I:%.*]] = alloca i32, align 4
// NOOMP-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// NOOMP-NEXT:    store i32 0, i32* [[I]], align 4
// NOOMP-NEXT:    store i32 0, i32* [[I]], align 4
// NOOMP-NEXT:    br label [[FOR_COND:%.*]]
// NOOMP:       for.cond:
// NOOMP-NEXT:    [[TMP0:%.*]] = load i32, i32* [[I]], align 4
// NOOMP-NEXT:    [[CMP:%.*]] = icmp slt i32 [[TMP0]], 33554432
// NOOMP-NEXT:    br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
// NOOMP:       for.body:
// NOOMP-NEXT:    [[TMP1:%.*]] = load i32, i32* [[I]], align 4
// NOOMP-NEXT:    [[IDXPROM:%.*]] = sext i32 [[TMP1]] to i64
// NOOMP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [33554432 x double], [33554432 x double]* @A, i64 0, i64 [[IDXPROM]]
// NOOMP-NEXT:    store double 0.000000e+00, double* [[ARRAYIDX]], align 8
// NOOMP-NEXT:    br label [[FOR_INC:%.*]]
// NOOMP:       for.inc:
// NOOMP-NEXT:    [[TMP2:%.*]] = load i32, i32* [[I]], align 4
// NOOMP-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP2]], 1
// NOOMP-NEXT:    store i32 [[INC]], i32* [[I]], align 4
// NOOMP-NEXT:    br label [[FOR_COND]], !llvm.loop [[LOOP2:![0-9]+]]
// NOOMP:       for.end:
// NOOMP-NEXT:    call void @foo()
// NOOMP-NEXT:    ret i32 0
//
int main() {
  int i = 0;

#pragma omp parallel for
  for (i = 0; i < size; ++i) {
    A[i] = 0.0;
  }

  foo();

  return 0;
}

// OMP-LABEL: @foo(
// OMP-NEXT:  entry:
// OMP-NEXT:    [[I:%.*]] = alloca i32, align 4
// OMP-NEXT:    store i32 0, i32* [[I]], align 4
// OMP-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined. to void (i32*, i32*, ...)*))
// OMP-NEXT:    ret void
//
// NOOMP-LABEL: @foo(
// NOOMP-NEXT:  entry:
// NOOMP-NEXT:    [[I:%.*]] = alloca i32, align 4
// NOOMP-NEXT:    store i32 0, i32* [[I]], align 4
// NOOMP-NEXT:    store i32 0, i32* [[I]], align 4
// NOOMP-NEXT:    br label [[FOR_COND:%.*]]
// NOOMP:       for.cond:
// NOOMP-NEXT:    [[TMP0:%.*]] = load i32, i32* [[I]], align 4
// NOOMP-NEXT:    [[CMP:%.*]] = icmp slt i32 [[TMP0]], 33554432
// NOOMP-NEXT:    br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
// NOOMP:       for.body:
// NOOMP-NEXT:    [[TMP1:%.*]] = load i32, i32* [[I]], align 4
// NOOMP-NEXT:    [[IDXPROM:%.*]] = sext i32 [[TMP1]] to i64
// NOOMP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [33554432 x double], [33554432 x double]* @A, i64 0, i64 [[IDXPROM]]
// NOOMP-NEXT:    store double 1.000000e+00, double* [[ARRAYIDX]], align 8
// NOOMP-NEXT:    br label [[FOR_INC:%.*]]
// NOOMP:       for.inc:
// NOOMP-NEXT:    [[TMP2:%.*]] = load i32, i32* [[I]], align 4
// NOOMP-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP2]], 1
// NOOMP-NEXT:    store i32 [[INC]], i32* [[I]], align 4
// NOOMP-NEXT:    br label [[FOR_COND]], !llvm.loop [[LOOP4:![0-9]+]]
// NOOMP:       for.end:
// NOOMP-NEXT:    ret void
//
void foo(void) {
  int i = 0;

#pragma omp parallel for
  for (i = 0; i < size; ++i) {
    A[i] = 1.0;
  }
}