// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
// Test host codegen.
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK3
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK3

// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"

// Test target codegen - host bc file has to be created first.
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK9
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK9
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix=CHECK11
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK11

// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"

// Test host codegen.
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK3
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK3

// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"

// Test target codegen - host bc file has to be created first.
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK9
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK9
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix=CHECK11
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK11

// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"

// expected-no-diagnostics
#ifndef HEADER
#define HEADER


// We have 8 target regions, but only 6 that actually will generate offloading
// code and have mapped arguments, and only 4 have all-constant map sizes.


// Check target registration is registered as a Ctor.


template<typename tx, typename ty>
struct TT{
  tx X;
  ty Y;
};

int foo(int n) {
  int a = 0;
  short aa = 0;
  float b[10];
  float bn[n];
  double c[5][10];
  double cn[5][n];
  TT<long long, char> d;

  #pragma omp target parallel nowait
  {
  }

  #pragma omp target parallel if(target: 0)
  {
    a += 1;
  }


  #pragma omp target parallel if(target: 1)
  {
    aa += 1;
#pragma omp cancel parallel
  }


  #pragma omp target parallel if(target: n>10)
  {
    a += 1;
    aa += 1;
  }

  // We capture 3 VLA sizes in this target region


  // The names below are not necessarily consistent with the names used for the
  // addresses above as some are repeated.


  #pragma omp target parallel if(target: n>20)
  {
    a += 1;
    b[2] += 1.0;
    bn[3] += 1.0;
    c[1][2] += 1.0;
    cn[1][3] += 1.0;
    d.X += 1;
    d.Y += 1;
  }

  return a;
}

// Check that the offloading functions are emitted and that the arguments are
// correct and loaded correctly for the target regions in foo().


// Create stack storage and store argument in there.

// Create stack storage and store argument in there.

// Create stack storage and store argument in there.

// Create local storage for each capture.


// To reduce complexity, we're only going as far as validating the signature of the outlined parallel function.

template<typename tx>
tx ftemplate(int n) {
  tx a = 0;
  short aa = 0;
  tx b[10];

  #pragma omp target parallel if(target: n>40)
  {
    a += 1;
    aa += 1;
    b[2] += 1;
  }

  return a;
}

static
int fstatic(int n) {
  int a = 0;
  short aa = 0;
  char aaa = 0;
  int b[10];

  #pragma omp target parallel if(target: n>50)
  {
    a += 1;
    aa += 1;
    aaa += 1;
    b[2] += 1;
  }

  return a;
}

struct S1 {
  double a;

  int r1(int n){
    int b = n+1;
    short int c[2][n];

    #pragma omp target parallel if(target: n>60)
    {
      this->a = (double)b + 1.5;
      c[1][1] = ++a;
    }

    return c[1][1] + (int)b;
  }
};

int bar(int n){
  int a = 0;

  a += foo(n);

  S1 S;
  a += S.r1(n);

  a += fstatic(n);

  a += ftemplate<int>(n);

  return a;
}


// We capture 2 VLA sizes in this target region


// The names below are not necessarily consistent with the names used for the
// addresses above as some are repeated.


// Check that the offloading functions are emitted and that the arguments are
// correct and loaded correctly for the target regions of the callees of bar().

// Create local storage for each capture.
// Store captures in the context.


// To reduce complexity, we're only going as far as validating the signature of the outlined parallel function.


// Create local storage for each capture.
// Store captures in the context.


// To reduce complexity, we're only going as far as validating the signature of the outlined parallel function.

// Create local storage for each capture.
// Store captures in the context.


// To reduce complexity, we're only going as far as validating the signature of the outlined parallel function.


#endif
// CHECK1-LABEL: define {{[^@]+}}@_Z3fooi
// CHECK1-SAME: (i32 noundef signext [[N:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[AA:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[B:%.*]] = alloca [10 x float], align 4
// CHECK1-NEXT:    [[SAVED_STACK:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[C:%.*]] = alloca [5 x [10 x double]], align 8
// CHECK1-NEXT:    [[__VLA_EXPR1:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[D:%.*]] = alloca [[STRUCT_TT:%.*]], align 8
// CHECK1-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 1
// CHECK1-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [1 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_PTRS:%.*]] = alloca [1 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [1 x ptr], align 8
// CHECK1-NEXT:    [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK1-NEXT:    [[A_CASTED2:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_CASTED3:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_BASEPTRS4:%.*]] = alloca [2 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_PTRS5:%.*]] = alloca [2 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_MAPPERS6:%.*]] = alloca [2 x ptr], align 8
// CHECK1-NEXT:    [[KERNEL_ARGS7:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS]], align 8
// CHECK1-NEXT:    [[A_CASTED10:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_BASEPTRS13:%.*]] = alloca [9 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_PTRS14:%.*]] = alloca [9 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_MAPPERS15:%.*]] = alloca [9 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_SIZES:%.*]] = alloca [9 x i64], align 8
// CHECK1-NEXT:    [[KERNEL_ARGS16:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
// CHECK1-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    store i32 0, ptr [[A]], align 4
// CHECK1-NEXT:    store i16 0, ptr [[AA]], align 2
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP1]] to i64
// CHECK1-NEXT:    [[TMP3:%.*]] = call ptr @llvm.stacksave()
// CHECK1-NEXT:    store ptr [[TMP3]], ptr [[SAVED_STACK]], align 8
// CHECK1-NEXT:    [[VLA:%.*]] = alloca float, i64 [[TMP2]], align 4
// CHECK1-NEXT:    store i64 [[TMP2]], ptr [[__VLA_EXPR0]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK1-NEXT:    [[TMP6:%.*]] = mul nuw i64 5, [[TMP5]]
// CHECK1-NEXT:    [[VLA1:%.*]] = alloca double, i64 [[TMP6]], align 8
// CHECK1-NEXT:    store i64 [[TMP5]], ptr [[__VLA_EXPR1]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = call ptr @__kmpc_omp_target_task_alloc(ptr @[[GLOB1]], i32 [[TMP0]], i32 1, i64 40, i64 1, ptr @.omp_task_entry., i64 -1)
// CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], ptr [[TMP7]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP9:%.*]] = call i32 @__kmpc_omp_task(ptr @[[GLOB1]], i32 [[TMP0]], ptr [[TMP7]])
// CHECK1-NEXT:    [[TMP10:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    store i32 [[TMP10]], ptr [[A_CASTED]], align 4
// CHECK1-NEXT:    [[TMP11:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l104(i64 [[TMP11]]) #[[ATTR4:[0-9]+]]
// CHECK1-NEXT:    [[TMP12:%.*]] = load i16, ptr [[AA]], align 2
// CHECK1-NEXT:    store i16 [[TMP12]], ptr [[AA_CASTED]], align 2
// CHECK1-NEXT:    [[TMP13:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK1-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP13]], ptr [[TMP14]], align 8
// CHECK1-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP13]], ptr [[TMP15]], align 8
// CHECK1-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK1-NEXT:    store ptr null, ptr [[TMP16]], align 8
// CHECK1-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK1-NEXT:    store i32 2, ptr [[TMP19]], align 4
// CHECK1-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK1-NEXT:    store i32 1, ptr [[TMP20]], align 4
// CHECK1-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK1-NEXT:    store ptr [[TMP17]], ptr [[TMP21]], align 8
// CHECK1-NEXT:    [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[TMP18]], ptr [[TMP22]], align 8
// CHECK1-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK1-NEXT:    store ptr @.offload_sizes, ptr [[TMP23]], align 8
// CHECK1-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK1-NEXT:    store ptr @.offload_maptypes, ptr [[TMP24]], align 8
// CHECK1-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK1-NEXT:    store ptr null, ptr [[TMP25]], align 8
// CHECK1-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK1-NEXT:    store ptr null, ptr [[TMP26]], align 8
// CHECK1-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK1-NEXT:    store i64 0, ptr [[TMP27]], align 8
// CHECK1-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK1-NEXT:    store i64 0, ptr [[TMP28]], align 8
// CHECK1-NEXT:    [[TMP29:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK1-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP29]], align 4
// CHECK1-NEXT:    [[TMP30:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK1-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP30]], align 4
// CHECK1-NEXT:    [[TMP31:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK1-NEXT:    store i32 0, ptr [[TMP31]], align 4
// CHECK1-NEXT:    [[TMP32:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.region_id, ptr [[KERNEL_ARGS]])
// CHECK1-NEXT:    [[TMP33:%.*]] = icmp ne i32 [[TMP32]], 0
// CHECK1-NEXT:    br i1 [[TMP33]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK1:       omp_offload.failed:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110(i64 [[TMP13]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_OFFLOAD_CONT]]
// CHECK1:       omp_offload.cont:
// CHECK1-NEXT:    [[TMP34:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    store i32 [[TMP34]], ptr [[A_CASTED2]], align 4
// CHECK1-NEXT:    [[TMP35:%.*]] = load i64, ptr [[A_CASTED2]], align 8
// CHECK1-NEXT:    [[TMP36:%.*]] = load i16, ptr [[AA]], align 2
// CHECK1-NEXT:    store i16 [[TMP36]], ptr [[AA_CASTED3]], align 2
// CHECK1-NEXT:    [[TMP37:%.*]] = load i64, ptr [[AA_CASTED3]], align 8
// CHECK1-NEXT:    [[TMP38:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP38]], 10
// CHECK1-NEXT:    br i1 [[CMP]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_ELSE:%.*]]
// CHECK1:       omp_if.then:
// CHECK1-NEXT:    [[TMP39:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS4]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP35]], ptr [[TMP39]], align 8
// CHECK1-NEXT:    [[TMP40:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS5]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP35]], ptr [[TMP40]], align 8
// CHECK1-NEXT:    [[TMP41:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS6]], i64 0, i64 0
// CHECK1-NEXT:    store ptr null, ptr [[TMP41]], align 8
// CHECK1-NEXT:    [[TMP42:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS4]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP37]], ptr [[TMP42]], align 8
// CHECK1-NEXT:    [[TMP43:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS5]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP37]], ptr [[TMP43]], align 8
// CHECK1-NEXT:    [[TMP44:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS6]], i64 0, i64 1
// CHECK1-NEXT:    store ptr null, ptr [[TMP44]], align 8
// CHECK1-NEXT:    [[TMP45:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP46:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS5]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP47:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 0
// CHECK1-NEXT:    store i32 2, ptr [[TMP47]], align 4
// CHECK1-NEXT:    [[TMP48:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 1
// CHECK1-NEXT:    store i32 2, ptr [[TMP48]], align 4
// CHECK1-NEXT:    [[TMP49:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 2
// CHECK1-NEXT:    store ptr [[TMP45]], ptr [[TMP49]], align 8
// CHECK1-NEXT:    [[TMP50:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[TMP46]], ptr [[TMP50]], align 8
// CHECK1-NEXT:    [[TMP51:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 4
// CHECK1-NEXT:    store ptr @.offload_sizes.1, ptr [[TMP51]], align 8
// CHECK1-NEXT:    [[TMP52:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 5
// CHECK1-NEXT:    store ptr @.offload_maptypes.2, ptr [[TMP52]], align 8
// CHECK1-NEXT:    [[TMP53:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 6
// CHECK1-NEXT:    store ptr null, ptr [[TMP53]], align 8
// CHECK1-NEXT:    [[TMP54:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 7
// CHECK1-NEXT:    store ptr null, ptr [[TMP54]], align 8
// CHECK1-NEXT:    [[TMP55:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 8
// CHECK1-NEXT:    store i64 0, ptr [[TMP55]], align 8
// CHECK1-NEXT:    [[TMP56:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 9
// CHECK1-NEXT:    store i64 0, ptr [[TMP56]], align 8
// CHECK1-NEXT:    [[TMP57:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 10
// CHECK1-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP57]], align 4
// CHECK1-NEXT:    [[TMP58:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 11
// CHECK1-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP58]], align 4
// CHECK1-NEXT:    [[TMP59:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 12
// CHECK1-NEXT:    store i32 0, ptr [[TMP59]], align 4
// CHECK1-NEXT:    [[TMP60:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.region_id, ptr [[KERNEL_ARGS7]])
// CHECK1-NEXT:    [[TMP61:%.*]] = icmp ne i32 [[TMP60]], 0
// CHECK1-NEXT:    br i1 [[TMP61]], label [[OMP_OFFLOAD_FAILED8:%.*]], label [[OMP_OFFLOAD_CONT9:%.*]]
// CHECK1:       omp_offload.failed8:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119(i64 [[TMP35]], i64 [[TMP37]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_OFFLOAD_CONT9]]
// CHECK1:       omp_offload.cont9:
// CHECK1-NEXT:    br label [[OMP_IF_END:%.*]]
// CHECK1:       omp_if.else:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119(i64 [[TMP35]], i64 [[TMP37]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_IF_END]]
// CHECK1:       omp_if.end:
// CHECK1-NEXT:    [[TMP62:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    store i32 [[TMP62]], ptr [[A_CASTED10]], align 4
// CHECK1-NEXT:    [[TMP63:%.*]] = load i64, ptr [[A_CASTED10]], align 8
// CHECK1-NEXT:    [[TMP64:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[CMP11:%.*]] = icmp sgt i32 [[TMP64]], 20
// CHECK1-NEXT:    br i1 [[CMP11]], label [[OMP_IF_THEN12:%.*]], label [[OMP_IF_ELSE19:%.*]]
// CHECK1:       omp_if.then12:
// CHECK1-NEXT:    [[TMP65:%.*]] = mul nuw i64 [[TMP2]], 4
// CHECK1-NEXT:    [[TMP66:%.*]] = mul nuw i64 5, [[TMP5]]
// CHECK1-NEXT:    [[TMP67:%.*]] = mul nuw i64 [[TMP66]], 8
// CHECK1-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[DOTOFFLOAD_SIZES]], ptr align 8 @.offload_sizes.3, i64 72, i1 false)
// CHECK1-NEXT:    [[TMP68:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP63]], ptr [[TMP68]], align 8
// CHECK1-NEXT:    [[TMP69:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP63]], ptr [[TMP69]], align 8
// CHECK1-NEXT:    [[TMP70:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i64 0, i64 0
// CHECK1-NEXT:    store ptr null, ptr [[TMP70]], align 8
// CHECK1-NEXT:    [[TMP71:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 1
// CHECK1-NEXT:    store ptr [[B]], ptr [[TMP71]], align 8
// CHECK1-NEXT:    [[TMP72:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 1
// CHECK1-NEXT:    store ptr [[B]], ptr [[TMP72]], align 8
// CHECK1-NEXT:    [[TMP73:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i64 0, i64 1
// CHECK1-NEXT:    store ptr null, ptr [[TMP73]], align 8
// CHECK1-NEXT:    [[TMP74:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 2
// CHECK1-NEXT:    store i64 [[TMP2]], ptr [[TMP74]], align 8
// CHECK1-NEXT:    [[TMP75:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 2
// CHECK1-NEXT:    store i64 [[TMP2]], ptr [[TMP75]], align 8
// CHECK1-NEXT:    [[TMP76:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i64 0, i64 2
// CHECK1-NEXT:    store ptr null, ptr [[TMP76]], align 8
// CHECK1-NEXT:    [[TMP77:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[VLA]], ptr [[TMP77]], align 8
// CHECK1-NEXT:    [[TMP78:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[VLA]], ptr [[TMP78]], align 8
// CHECK1-NEXT:    [[TMP79:%.*]] = getelementptr inbounds [9 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 3
// CHECK1-NEXT:    store i64 [[TMP65]], ptr [[TMP79]], align 8
// CHECK1-NEXT:    [[TMP80:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i64 0, i64 3
// CHECK1-NEXT:    store ptr null, ptr [[TMP80]], align 8
// CHECK1-NEXT:    [[TMP81:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 4
// CHECK1-NEXT:    store ptr [[C]], ptr [[TMP81]], align 8
// CHECK1-NEXT:    [[TMP82:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 4
// CHECK1-NEXT:    store ptr [[C]], ptr [[TMP82]], align 8
// CHECK1-NEXT:    [[TMP83:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i64 0, i64 4
// CHECK1-NEXT:    store ptr null, ptr [[TMP83]], align 8
// CHECK1-NEXT:    [[TMP84:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 5
// CHECK1-NEXT:    store i64 5, ptr [[TMP84]], align 8
// CHECK1-NEXT:    [[TMP85:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 5
// CHECK1-NEXT:    store i64 5, ptr [[TMP85]], align 8
// CHECK1-NEXT:    [[TMP86:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i64 0, i64 5
// CHECK1-NEXT:    store ptr null, ptr [[TMP86]], align 8
// CHECK1-NEXT:    [[TMP87:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 6
// CHECK1-NEXT:    store i64 [[TMP5]], ptr [[TMP87]], align 8
// CHECK1-NEXT:    [[TMP88:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 6
// CHECK1-NEXT:    store i64 [[TMP5]], ptr [[TMP88]], align 8
// CHECK1-NEXT:    [[TMP89:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i64 0, i64 6
// CHECK1-NEXT:    store ptr null, ptr [[TMP89]], align 8
// CHECK1-NEXT:    [[TMP90:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 7
// CHECK1-NEXT:    store ptr [[VLA1]], ptr [[TMP90]], align 8
// CHECK1-NEXT:    [[TMP91:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 7
// CHECK1-NEXT:    store ptr [[VLA1]], ptr [[TMP91]], align 8
// CHECK1-NEXT:    [[TMP92:%.*]] = getelementptr inbounds [9 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 7
// CHECK1-NEXT:    store i64 [[TMP67]], ptr [[TMP92]], align 8
// CHECK1-NEXT:    [[TMP93:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i64 0, i64 7
// CHECK1-NEXT:    store ptr null, ptr [[TMP93]], align 8
// CHECK1-NEXT:    [[TMP94:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 8
// CHECK1-NEXT:    store ptr [[D]], ptr [[TMP94]], align 8
// CHECK1-NEXT:    [[TMP95:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 8
// CHECK1-NEXT:    store ptr [[D]], ptr [[TMP95]], align 8
// CHECK1-NEXT:    [[TMP96:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i64 0, i64 8
// CHECK1-NEXT:    store ptr null, ptr [[TMP96]], align 8
// CHECK1-NEXT:    [[TMP97:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP98:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP99:%.*]] = getelementptr inbounds [9 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP100:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 0
// CHECK1-NEXT:    store i32 2, ptr [[TMP100]], align 4
// CHECK1-NEXT:    [[TMP101:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 1
// CHECK1-NEXT:    store i32 9, ptr [[TMP101]], align 4
// CHECK1-NEXT:    [[TMP102:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 2
// CHECK1-NEXT:    store ptr [[TMP97]], ptr [[TMP102]], align 8
// CHECK1-NEXT:    [[TMP103:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[TMP98]], ptr [[TMP103]], align 8
// CHECK1-NEXT:    [[TMP104:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 4
// CHECK1-NEXT:    store ptr [[TMP99]], ptr [[TMP104]], align 8
// CHECK1-NEXT:    [[TMP105:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 5
// CHECK1-NEXT:    store ptr @.offload_maptypes.4, ptr [[TMP105]], align 8
// CHECK1-NEXT:    [[TMP106:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 6
// CHECK1-NEXT:    store ptr null, ptr [[TMP106]], align 8
// CHECK1-NEXT:    [[TMP107:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 7
// CHECK1-NEXT:    store ptr null, ptr [[TMP107]], align 8
// CHECK1-NEXT:    [[TMP108:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 8
// CHECK1-NEXT:    store i64 0, ptr [[TMP108]], align 8
// CHECK1-NEXT:    [[TMP109:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 9
// CHECK1-NEXT:    store i64 0, ptr [[TMP109]], align 8
// CHECK1-NEXT:    [[TMP110:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 10
// CHECK1-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP110]], align 4
// CHECK1-NEXT:    [[TMP111:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 11
// CHECK1-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP111]], align 4
// CHECK1-NEXT:    [[TMP112:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 12
// CHECK1-NEXT:    store i32 0, ptr [[TMP112]], align 4
// CHECK1-NEXT:    [[TMP113:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.region_id, ptr [[KERNEL_ARGS16]])
// CHECK1-NEXT:    [[TMP114:%.*]] = icmp ne i32 [[TMP113]], 0
// CHECK1-NEXT:    br i1 [[TMP114]], label [[OMP_OFFLOAD_FAILED17:%.*]], label [[OMP_OFFLOAD_CONT18:%.*]]
// CHECK1:       omp_offload.failed17:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144(i64 [[TMP63]], ptr [[B]], i64 [[TMP2]], ptr [[VLA]], ptr [[C]], i64 5, i64 [[TMP5]], ptr [[VLA1]], ptr [[D]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_OFFLOAD_CONT18]]
// CHECK1:       omp_offload.cont18:
// CHECK1-NEXT:    br label [[OMP_IF_END20:%.*]]
// CHECK1:       omp_if.else19:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144(i64 [[TMP63]], ptr [[B]], i64 [[TMP2]], ptr [[VLA]], ptr [[C]], i64 5, i64 [[TMP5]], ptr [[VLA1]], ptr [[D]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_IF_END20]]
// CHECK1:       omp_if.end20:
// CHECK1-NEXT:    [[TMP115:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    [[TMP116:%.*]] = load ptr, ptr [[SAVED_STACK]], align 8
// CHECK1-NEXT:    call void @llvm.stackrestore(ptr [[TMP116]])
// CHECK1-NEXT:    ret i32 [[TMP115]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100
// CHECK1-SAME: () #[[ATTR2:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 0, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.omp_outlined)
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry.
// CHECK1-SAME: (i32 noundef signext [[TMP0:%.*]], ptr noalias noundef [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[KERNEL_ARGS_I:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], ptr [[DOTADDR]], align 4
// CHECK1-NEXT:    store ptr [[TMP1]], ptr [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, ptr [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], ptr [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], ptr [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], ptr [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[TMP6]], align 8
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META12:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META15:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META17:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META19:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], ptr [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !21
// CHECK1-NEXT:    store ptr [[TMP5]], ptr [[DOTPART_ID__ADDR_I]], align 8, !noalias !21
// CHECK1-NEXT:    store ptr null, ptr [[DOTPRIVATES__ADDR_I]], align 8, !noalias !21
// CHECK1-NEXT:    store ptr null, ptr [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !21
// CHECK1-NEXT:    store ptr [[TMP3]], ptr [[DOTTASK_T__ADDR_I]], align 8, !noalias !21
// CHECK1-NEXT:    store ptr [[TMP7]], ptr [[__CONTEXT_ADDR_I]], align 8, !noalias !21
// CHECK1-NEXT:    [[TMP8:%.*]] = load ptr, ptr [[__CONTEXT_ADDR_I]], align 8, !noalias !21
// CHECK1-NEXT:    store i32 2, ptr [[KERNEL_ARGS_I]], align 4, !noalias !21
// CHECK1-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 1
// CHECK1-NEXT:    store i32 0, ptr [[TMP9]], align 4, !noalias !21
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 2
// CHECK1-NEXT:    store ptr null, ptr [[TMP10]], align 8, !noalias !21
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 3
// CHECK1-NEXT:    store ptr null, ptr [[TMP11]], align 8, !noalias !21
// CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 4
// CHECK1-NEXT:    store ptr null, ptr [[TMP12]], align 8, !noalias !21
// CHECK1-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 5
// CHECK1-NEXT:    store ptr null, ptr [[TMP13]], align 8, !noalias !21
// CHECK1-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 6
// CHECK1-NEXT:    store ptr null, ptr [[TMP14]], align 8, !noalias !21
// CHECK1-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 7
// CHECK1-NEXT:    store ptr null, ptr [[TMP15]], align 8, !noalias !21
// CHECK1-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 8
// CHECK1-NEXT:    store i64 0, ptr [[TMP16]], align 8, !noalias !21
// CHECK1-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 9
// CHECK1-NEXT:    store i64 1, ptr [[TMP17]], align 8, !noalias !21
// CHECK1-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 10
// CHECK1-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP18]], align 4, !noalias !21
// CHECK1-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 11
// CHECK1-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP19]], align 4, !noalias !21
// CHECK1-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 12
// CHECK1-NEXT:    store i32 0, ptr [[TMP20]], align 4, !noalias !21
// CHECK1-NEXT:    [[TMP21:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.region_id, ptr [[KERNEL_ARGS_I]])
// CHECK1-NEXT:    [[TMP22:%.*]] = icmp ne i32 [[TMP21]], 0
// CHECK1-NEXT:    br i1 [[TMP22]], label [[OMP_OFFLOAD_FAILED_I:%.*]], label [[DOTOMP_OUTLINED__EXIT:%.*]]
// CHECK1:       omp_offload.failed.i:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100() #[[ATTR4]]
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__EXIT]]
// CHECK1:       .omp_outlined..exit:
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l104
// CHECK1-SAME: (i64 noundef [[A:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK1-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l104.omp_outlined, i64 [[TMP1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l104.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[A:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 1
// CHECK1-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110
// CHECK1-SAME: (i64 noundef [[AA:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    store i16 [[TMP0]], ptr [[AA_CASTED]], align 2
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK1-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.omp_outlined, i64 [[TMP1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[AA:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    [[CONV:%.*]] = sext i16 [[TMP0]] to i32
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK1-NEXT:    [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK1-NEXT:    store i16 [[CONV1]], ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = call i32 @__kmpc_cancel(ptr @[[GLOB1]], i32 [[TMP2]], i32 1)
// CHECK1-NEXT:    [[TMP4:%.*]] = icmp ne i32 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[TMP4]], label [[DOTCANCEL_EXIT:%.*]], label [[DOTCANCEL_CONTINUE:%.*]]
// CHECK1:       .cancel.exit:
// CHECK1-NEXT:    [[TMP5:%.*]] = call i32 @__kmpc_cancel_barrier(ptr @[[GLOB2:[0-9]+]], i32 [[TMP2]])
// CHECK1-NEXT:    br label [[DOTCANCEL_CONTINUE]]
// CHECK1:       .cancel.continue:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119
// CHECK1-SAME: (i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    store i16 [[TMP2]], ptr [[AA_CASTED]], align 2
// CHECK1-NEXT:    [[TMP3:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK1-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 2, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.omp_outlined, i64 [[TMP1]], i64 [[TMP3]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 1
// CHECK1-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    [[TMP1:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK1-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK1-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK1-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144
// CHECK1-SAME: (i64 noundef [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[BN:%.*]], ptr noundef nonnull align 8 dereferenceable(400) [[C:%.*]], i64 noundef [[VLA1:%.*]], i64 noundef [[VLA3:%.*]], ptr noundef nonnull align 8 dereferenceable(8) [[CN:%.*]], ptr noundef nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[BN_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[VLA_ADDR2:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[VLA_ADDR4:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[CN_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[D_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[BN]], ptr [[BN_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA1]], ptr [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    store i64 [[VLA3]], ptr [[VLA_ADDR4]], align 8
// CHECK1-NEXT:    store ptr [[CN]], ptr [[CN_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[D]], ptr [[D_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[BN_ADDR]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load i64, ptr [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = load i64, ptr [[VLA_ADDR4]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[CN_ADDR]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[D_ADDR]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    store i32 [[TMP8]], ptr [[A_CASTED]], align 4
// CHECK1-NEXT:    [[TMP9:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK1-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 9, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.omp_outlined, i64 [[TMP9]], ptr [[TMP0]], i64 [[TMP1]], ptr [[TMP2]], ptr [[TMP3]], i64 [[TMP4]], i64 [[TMP5]], ptr [[TMP6]], ptr [[TMP7]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[BN:%.*]], ptr noundef nonnull align 8 dereferenceable(400) [[C:%.*]], i64 noundef [[VLA1:%.*]], i64 noundef [[VLA3:%.*]], ptr noundef nonnull align 8 dereferenceable(8) [[CN:%.*]], ptr noundef nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[BN_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[VLA_ADDR2:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[VLA_ADDR4:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[CN_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[D_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[BN]], ptr [[BN_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA1]], ptr [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    store i64 [[VLA3]], ptr [[VLA_ADDR4]], align 8
// CHECK1-NEXT:    store ptr [[CN]], ptr [[CN_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[D]], ptr [[D_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[BN_ADDR]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load i64, ptr [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = load i64, ptr [[VLA_ADDR4]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[CN_ADDR]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[D_ADDR]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP8]], 1
// CHECK1-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x float], ptr [[TMP0]], i64 0, i64 2
// CHECK1-NEXT:    [[TMP9:%.*]] = load float, ptr [[ARRAYIDX]], align 4
// CHECK1-NEXT:    [[CONV:%.*]] = fpext float [[TMP9]] to double
// CHECK1-NEXT:    [[ADD5:%.*]] = fadd double [[CONV]], 1.000000e+00
// CHECK1-NEXT:    [[CONV6:%.*]] = fptrunc double [[ADD5]] to float
// CHECK1-NEXT:    store float [[CONV6]], ptr [[ARRAYIDX]], align 4
// CHECK1-NEXT:    [[ARRAYIDX7:%.*]] = getelementptr inbounds float, ptr [[TMP2]], i64 3
// CHECK1-NEXT:    [[TMP10:%.*]] = load float, ptr [[ARRAYIDX7]], align 4
// CHECK1-NEXT:    [[CONV8:%.*]] = fpext float [[TMP10]] to double
// CHECK1-NEXT:    [[ADD9:%.*]] = fadd double [[CONV8]], 1.000000e+00
// CHECK1-NEXT:    [[CONV10:%.*]] = fptrunc double [[ADD9]] to float
// CHECK1-NEXT:    store float [[CONV10]], ptr [[ARRAYIDX7]], align 4
// CHECK1-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds [5 x [10 x double]], ptr [[TMP3]], i64 0, i64 1
// CHECK1-NEXT:    [[ARRAYIDX12:%.*]] = getelementptr inbounds [10 x double], ptr [[ARRAYIDX11]], i64 0, i64 2
// CHECK1-NEXT:    [[TMP11:%.*]] = load double, ptr [[ARRAYIDX12]], align 8
// CHECK1-NEXT:    [[ADD13:%.*]] = fadd double [[TMP11]], 1.000000e+00
// CHECK1-NEXT:    store double [[ADD13]], ptr [[ARRAYIDX12]], align 8
// CHECK1-NEXT:    [[TMP12:%.*]] = mul nsw i64 1, [[TMP5]]
// CHECK1-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds double, ptr [[TMP6]], i64 [[TMP12]]
// CHECK1-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr inbounds double, ptr [[ARRAYIDX14]], i64 3
// CHECK1-NEXT:    [[TMP13:%.*]] = load double, ptr [[ARRAYIDX15]], align 8
// CHECK1-NEXT:    [[ADD16:%.*]] = fadd double [[TMP13]], 1.000000e+00
// CHECK1-NEXT:    store double [[ADD16]], ptr [[ARRAYIDX15]], align 8
// CHECK1-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], ptr [[TMP7]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP14:%.*]] = load i64, ptr [[X]], align 8
// CHECK1-NEXT:    [[ADD17:%.*]] = add nsw i64 [[TMP14]], 1
// CHECK1-NEXT:    store i64 [[ADD17]], ptr [[X]], align 8
// CHECK1-NEXT:    [[Y:%.*]] = getelementptr inbounds [[STRUCT_TT]], ptr [[TMP7]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP15:%.*]] = load i8, ptr [[Y]], align 8
// CHECK1-NEXT:    [[CONV18:%.*]] = sext i8 [[TMP15]] to i32
// CHECK1-NEXT:    [[ADD19:%.*]] = add nsw i32 [[CONV18]], 1
// CHECK1-NEXT:    [[CONV20:%.*]] = trunc i32 [[ADD19]] to i8
// CHECK1-NEXT:    store i8 [[CONV20]], ptr [[Y]], align 8
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z3bari
// CHECK1-SAME: (i32 noundef signext [[N:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[S:%.*]] = alloca [[STRUCT_S1:%.*]], align 8
// CHECK1-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    store i32 0, ptr [[A]], align 4
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[CALL:%.*]] = call noundef signext i32 @_Z3fooi(i32 noundef signext [[TMP0]])
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], [[CALL]]
// CHECK1-NEXT:    store i32 [[ADD]], ptr [[A]], align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[CALL1:%.*]] = call noundef signext i32 @_ZN2S12r1Ei(ptr noundef nonnull align 8 dereferenceable(8) [[S]], i32 noundef signext [[TMP2]])
// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    [[ADD2:%.*]] = add nsw i32 [[TMP3]], [[CALL1]]
// CHECK1-NEXT:    store i32 [[ADD2]], ptr [[A]], align 4
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[CALL3:%.*]] = call noundef signext i32 @_ZL7fstatici(i32 noundef signext [[TMP4]])
// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    [[ADD4:%.*]] = add nsw i32 [[TMP5]], [[CALL3]]
// CHECK1-NEXT:    store i32 [[ADD4]], ptr [[A]], align 4
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[CALL5:%.*]] = call noundef signext i32 @_Z9ftemplateIiET_i(i32 noundef signext [[TMP6]])
// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP7]], [[CALL5]]
// CHECK1-NEXT:    store i32 [[ADD6]], ptr [[A]], align 4
// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    ret i32 [[TMP8]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2S12r1Ei
// CHECK1-SAME: (ptr noundef nonnull align 8 dereferenceable(8) [[THIS:%.*]], i32 noundef signext [[N:%.*]]) #[[ATTR0]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[B:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[SAVED_STACK:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[B_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [5 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_PTRS:%.*]] = alloca [5 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [5 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_SIZES:%.*]] = alloca [5 x i64], align 8
// CHECK1-NEXT:    [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 1
// CHECK1-NEXT:    store i32 [[ADD]], ptr [[B]], align 4
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP1]] to i64
// CHECK1-NEXT:    [[TMP3:%.*]] = call ptr @llvm.stacksave()
// CHECK1-NEXT:    store ptr [[TMP3]], ptr [[SAVED_STACK]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = mul nuw i64 2, [[TMP2]]
// CHECK1-NEXT:    [[VLA:%.*]] = alloca i16, i64 [[TMP4]], align 2
// CHECK1-NEXT:    store i64 [[TMP2]], ptr [[__VLA_EXPR0]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[B]], align 4
// CHECK1-NEXT:    store i32 [[TMP5]], ptr [[B_CASTED]], align 4
// CHECK1-NEXT:    [[TMP6:%.*]] = load i64, ptr [[B_CASTED]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP7]], 60
// CHECK1-NEXT:    br i1 [[CMP]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_ELSE:%.*]]
// CHECK1:       omp_if.then:
// CHECK1-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], ptr [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP8:%.*]] = mul nuw i64 2, [[TMP2]]
// CHECK1-NEXT:    [[TMP9:%.*]] = mul nuw i64 [[TMP8]], 2
// CHECK1-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[DOTOFFLOAD_SIZES]], ptr align 8 @.offload_sizes.5, i64 40, i1 false)
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT:    store ptr [[THIS1]], ptr [[TMP10]], align 8
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT:    store ptr [[A]], ptr [[TMP11]], align 8
// CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK1-NEXT:    store ptr null, ptr [[TMP12]], align 8
// CHECK1-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP6]], ptr [[TMP13]], align 8
// CHECK1-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP6]], ptr [[TMP14]], align 8
// CHECK1-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
// CHECK1-NEXT:    store ptr null, ptr [[TMP15]], align 8
// CHECK1-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK1-NEXT:    store i64 2, ptr [[TMP16]], align 8
// CHECK1-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK1-NEXT:    store i64 2, ptr [[TMP17]], align 8
// CHECK1-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 2
// CHECK1-NEXT:    store ptr null, ptr [[TMP18]], align 8
// CHECK1-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK1-NEXT:    store i64 [[TMP2]], ptr [[TMP19]], align 8
// CHECK1-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK1-NEXT:    store i64 [[TMP2]], ptr [[TMP20]], align 8
// CHECK1-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 3
// CHECK1-NEXT:    store ptr null, ptr [[TMP21]], align 8
// CHECK1-NEXT:    [[TMP22:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 4
// CHECK1-NEXT:    store ptr [[VLA]], ptr [[TMP22]], align 8
// CHECK1-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 4
// CHECK1-NEXT:    store ptr [[VLA]], ptr [[TMP23]], align 8
// CHECK1-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [5 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 4
// CHECK1-NEXT:    store i64 [[TMP9]], ptr [[TMP24]], align 8
// CHECK1-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 4
// CHECK1-NEXT:    store ptr null, ptr [[TMP25]], align 8
// CHECK1-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [5 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP29:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK1-NEXT:    store i32 2, ptr [[TMP29]], align 4
// CHECK1-NEXT:    [[TMP30:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK1-NEXT:    store i32 5, ptr [[TMP30]], align 4
// CHECK1-NEXT:    [[TMP31:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK1-NEXT:    store ptr [[TMP26]], ptr [[TMP31]], align 8
// CHECK1-NEXT:    [[TMP32:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[TMP27]], ptr [[TMP32]], align 8
// CHECK1-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK1-NEXT:    store ptr [[TMP28]], ptr [[TMP33]], align 8
// CHECK1-NEXT:    [[TMP34:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK1-NEXT:    store ptr @.offload_maptypes.6, ptr [[TMP34]], align 8
// CHECK1-NEXT:    [[TMP35:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK1-NEXT:    store ptr null, ptr [[TMP35]], align 8
// CHECK1-NEXT:    [[TMP36:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK1-NEXT:    store ptr null, ptr [[TMP36]], align 8
// CHECK1-NEXT:    [[TMP37:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK1-NEXT:    store i64 0, ptr [[TMP37]], align 8
// CHECK1-NEXT:    [[TMP38:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK1-NEXT:    store i64 0, ptr [[TMP38]], align 8
// CHECK1-NEXT:    [[TMP39:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK1-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP39]], align 4
// CHECK1-NEXT:    [[TMP40:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK1-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP40]], align 4
// CHECK1-NEXT:    [[TMP41:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK1-NEXT:    store i32 0, ptr [[TMP41]], align 4
// CHECK1-NEXT:    [[TMP42:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.region_id, ptr [[KERNEL_ARGS]])
// CHECK1-NEXT:    [[TMP43:%.*]] = icmp ne i32 [[TMP42]], 0
// CHECK1-NEXT:    br i1 [[TMP43]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK1:       omp_offload.failed:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216(ptr [[THIS1]], i64 [[TMP6]], i64 2, i64 [[TMP2]], ptr [[VLA]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_OFFLOAD_CONT]]
// CHECK1:       omp_offload.cont:
// CHECK1-NEXT:    br label [[OMP_IF_END:%.*]]
// CHECK1:       omp_if.else:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216(ptr [[THIS1]], i64 [[TMP6]], i64 2, i64 [[TMP2]], ptr [[VLA]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_IF_END]]
// CHECK1:       omp_if.end:
// CHECK1-NEXT:    [[TMP44:%.*]] = mul nsw i64 1, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[VLA]], i64 [[TMP44]]
// CHECK1-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i16, ptr [[ARRAYIDX]], i64 1
// CHECK1-NEXT:    [[TMP45:%.*]] = load i16, ptr [[ARRAYIDX2]], align 2
// CHECK1-NEXT:    [[CONV:%.*]] = sext i16 [[TMP45]] to i32
// CHECK1-NEXT:    [[TMP46:%.*]] = load i32, ptr [[B]], align 4
// CHECK1-NEXT:    [[ADD3:%.*]] = add nsw i32 [[CONV]], [[TMP46]]
// CHECK1-NEXT:    [[TMP47:%.*]] = load ptr, ptr [[SAVED_STACK]], align 8
// CHECK1-NEXT:    call void @llvm.stackrestore(ptr [[TMP47]])
// CHECK1-NEXT:    ret i32 [[ADD3]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZL7fstatici
// CHECK1-SAME: (i32 noundef signext [[N:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[AA:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[AAA:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    [[B:%.*]] = alloca [10 x i32], align 4
// CHECK1-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AAA_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [4 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_PTRS:%.*]] = alloca [4 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [4 x ptr], align 8
// CHECK1-NEXT:    [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK1-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    store i32 0, ptr [[A]], align 4
// CHECK1-NEXT:    store i16 0, ptr [[AA]], align 2
// CHECK1-NEXT:    store i8 0, ptr [[AAA]], align 1
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA]], align 2
// CHECK1-NEXT:    store i16 [[TMP2]], ptr [[AA_CASTED]], align 2
// CHECK1-NEXT:    [[TMP3:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load i8, ptr [[AAA]], align 1
// CHECK1-NEXT:    store i8 [[TMP4]], ptr [[AAA_CASTED]], align 1
// CHECK1-NEXT:    [[TMP5:%.*]] = load i64, ptr [[AAA_CASTED]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP6]], 50
// CHECK1-NEXT:    br i1 [[CMP]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_ELSE:%.*]]
// CHECK1:       omp_if.then:
// CHECK1-NEXT:    [[TMP7:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP1]], ptr [[TMP7]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP1]], ptr [[TMP8]], align 8
// CHECK1-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK1-NEXT:    store ptr null, ptr [[TMP9]], align 8
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP3]], ptr [[TMP10]], align 8
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP3]], ptr [[TMP11]], align 8
// CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
// CHECK1-NEXT:    store ptr null, ptr [[TMP12]], align 8
// CHECK1-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK1-NEXT:    store i64 [[TMP5]], ptr [[TMP13]], align 8
// CHECK1-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK1-NEXT:    store i64 [[TMP5]], ptr [[TMP14]], align 8
// CHECK1-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 2
// CHECK1-NEXT:    store ptr null, ptr [[TMP15]], align 8
// CHECK1-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[B]], ptr [[TMP16]], align 8
// CHECK1-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[B]], ptr [[TMP17]], align 8
// CHECK1-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 3
// CHECK1-NEXT:    store ptr null, ptr [[TMP18]], align 8
// CHECK1-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK1-NEXT:    store i32 2, ptr [[TMP21]], align 4
// CHECK1-NEXT:    [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK1-NEXT:    store i32 4, ptr [[TMP22]], align 4
// CHECK1-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK1-NEXT:    store ptr [[TMP19]], ptr [[TMP23]], align 8
// CHECK1-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[TMP20]], ptr [[TMP24]], align 8
// CHECK1-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK1-NEXT:    store ptr @.offload_sizes.7, ptr [[TMP25]], align 8
// CHECK1-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK1-NEXT:    store ptr @.offload_maptypes.8, ptr [[TMP26]], align 8
// CHECK1-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK1-NEXT:    store ptr null, ptr [[TMP27]], align 8
// CHECK1-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK1-NEXT:    store ptr null, ptr [[TMP28]], align 8
// CHECK1-NEXT:    [[TMP29:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK1-NEXT:    store i64 0, ptr [[TMP29]], align 8
// CHECK1-NEXT:    [[TMP30:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK1-NEXT:    store i64 0, ptr [[TMP30]], align 8
// CHECK1-NEXT:    [[TMP31:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK1-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP31]], align 4
// CHECK1-NEXT:    [[TMP32:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK1-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP32]], align 4
// CHECK1-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK1-NEXT:    store i32 0, ptr [[TMP33]], align 4
// CHECK1-NEXT:    [[TMP34:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.region_id, ptr [[KERNEL_ARGS]])
// CHECK1-NEXT:    [[TMP35:%.*]] = icmp ne i32 [[TMP34]], 0
// CHECK1-NEXT:    br i1 [[TMP35]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK1:       omp_offload.failed:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198(i64 [[TMP1]], i64 [[TMP3]], i64 [[TMP5]], ptr [[B]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_OFFLOAD_CONT]]
// CHECK1:       omp_offload.cont:
// CHECK1-NEXT:    br label [[OMP_IF_END:%.*]]
// CHECK1:       omp_if.else:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198(i64 [[TMP1]], i64 [[TMP3]], i64 [[TMP5]], ptr [[B]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_IF_END]]
// CHECK1:       omp_if.end:
// CHECK1-NEXT:    [[TMP36:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    ret i32 [[TMP36]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z9ftemplateIiET_i
// CHECK1-SAME: (i32 noundef signext [[N:%.*]]) #[[ATTR0]] comdat {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[AA:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[B:%.*]] = alloca [10 x i32], align 4
// CHECK1-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [3 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_PTRS:%.*]] = alloca [3 x ptr], align 8
// CHECK1-NEXT:    [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [3 x ptr], align 8
// CHECK1-NEXT:    [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK1-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    store i32 0, ptr [[A]], align 4
// CHECK1-NEXT:    store i16 0, ptr [[AA]], align 2
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA]], align 2
// CHECK1-NEXT:    store i16 [[TMP2]], ptr [[AA_CASTED]], align 2
// CHECK1-NEXT:    [[TMP3:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK1-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP4]], 40
// CHECK1-NEXT:    br i1 [[CMP]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_ELSE:%.*]]
// CHECK1:       omp_if.then:
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP1]], ptr [[TMP5]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT:    store i64 [[TMP1]], ptr [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK1-NEXT:    store ptr null, ptr [[TMP7]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP3]], ptr [[TMP8]], align 8
// CHECK1-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP3]], ptr [[TMP9]], align 8
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
// CHECK1-NEXT:    store ptr null, ptr [[TMP10]], align 8
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK1-NEXT:    store ptr [[B]], ptr [[TMP11]], align 8
// CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK1-NEXT:    store ptr [[B]], ptr [[TMP12]], align 8
// CHECK1-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 2
// CHECK1-NEXT:    store ptr null, ptr [[TMP13]], align 8
// CHECK1-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK1-NEXT:    store i32 2, ptr [[TMP16]], align 4
// CHECK1-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK1-NEXT:    store i32 3, ptr [[TMP17]], align 4
// CHECK1-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK1-NEXT:    store ptr [[TMP14]], ptr [[TMP18]], align 8
// CHECK1-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK1-NEXT:    store ptr [[TMP15]], ptr [[TMP19]], align 8
// CHECK1-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK1-NEXT:    store ptr @.offload_sizes.9, ptr [[TMP20]], align 8
// CHECK1-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK1-NEXT:    store ptr @.offload_maptypes.10, ptr [[TMP21]], align 8
// CHECK1-NEXT:    [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK1-NEXT:    store ptr null, ptr [[TMP22]], align 8
// CHECK1-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK1-NEXT:    store ptr null, ptr [[TMP23]], align 8
// CHECK1-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK1-NEXT:    store i64 0, ptr [[TMP24]], align 8
// CHECK1-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK1-NEXT:    store i64 0, ptr [[TMP25]], align 8
// CHECK1-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK1-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP26]], align 4
// CHECK1-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK1-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP27]], align 4
// CHECK1-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK1-NEXT:    store i32 0, ptr [[TMP28]], align 4
// CHECK1-NEXT:    [[TMP29:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.region_id, ptr [[KERNEL_ARGS]])
// CHECK1-NEXT:    [[TMP30:%.*]] = icmp ne i32 [[TMP29]], 0
// CHECK1-NEXT:    br i1 [[TMP30]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK1:       omp_offload.failed:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181(i64 [[TMP1]], i64 [[TMP3]], ptr [[B]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_OFFLOAD_CONT]]
// CHECK1:       omp_offload.cont:
// CHECK1-NEXT:    br label [[OMP_IF_END:%.*]]
// CHECK1:       omp_if.else:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181(i64 [[TMP1]], i64 [[TMP3]], ptr [[B]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_IF_END]]
// CHECK1:       omp_if.end:
// CHECK1-NEXT:    [[TMP31:%.*]] = load i32, ptr [[A]], align 4
// CHECK1-NEXT:    ret i32 [[TMP31]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216
// CHECK1-SAME: (ptr noundef [[THIS:%.*]], i64 noundef [[B:%.*]], i64 noundef [[VLA:%.*]], i64 noundef [[VLA1:%.*]], ptr noundef nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[VLA_ADDR2:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[B_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[B]], ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA1]], ptr [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i64, ptr [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[B_CASTED]], align 4
// CHECK1-NEXT:    [[TMP5:%.*]] = load i64, ptr [[B_CASTED]], align 8
// CHECK1-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 5, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.omp_outlined, ptr [[TMP0]], i64 [[TMP5]], i64 [[TMP1]], i64 [[TMP2]], ptr [[TMP3]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], ptr noundef [[THIS:%.*]], i64 noundef [[B:%.*]], i64 noundef [[VLA:%.*]], i64 noundef [[VLA1:%.*]], ptr noundef nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[VLA_ADDR2:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[B]], ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA1]], ptr [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i64, ptr [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK1-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP4]] to double
// CHECK1-NEXT:    [[ADD:%.*]] = fadd double [[CONV]], 1.500000e+00
// CHECK1-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], ptr [[TMP0]], i32 0, i32 0
// CHECK1-NEXT:    store double [[ADD]], ptr [[A]], align 8
// CHECK1-NEXT:    [[A3:%.*]] = getelementptr inbounds [[STRUCT_S1]], ptr [[TMP0]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = load double, ptr [[A3]], align 8
// CHECK1-NEXT:    [[INC:%.*]] = fadd double [[TMP5]], 1.000000e+00
// CHECK1-NEXT:    store double [[INC]], ptr [[A3]], align 8
// CHECK1-NEXT:    [[CONV4:%.*]] = fptosi double [[INC]] to i16
// CHECK1-NEXT:    [[TMP6:%.*]] = mul nsw i64 1, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[TMP3]], i64 [[TMP6]]
// CHECK1-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i16, ptr [[ARRAYIDX]], i64 1
// CHECK1-NEXT:    store i16 [[CONV4]], ptr [[ARRAYIDX5]], align 2
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198
// CHECK1-SAME: (i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]], i64 noundef [[AAA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AAA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AAA_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AAA]], ptr [[AAA_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[A_CASTED]], align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    store i16 [[TMP3]], ptr [[AA_CASTED]], align 2
// CHECK1-NEXT:    [[TMP4:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = load i8, ptr [[AAA_ADDR]], align 1
// CHECK1-NEXT:    store i8 [[TMP5]], ptr [[AAA_CASTED]], align 1
// CHECK1-NEXT:    [[TMP6:%.*]] = load i64, ptr [[AAA_CASTED]], align 8
// CHECK1-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 4, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.omp_outlined, i64 [[TMP2]], i64 [[TMP4]], i64 [[TMP6]], ptr [[TMP0]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]], i64 noundef [[AAA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AAA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AAA]], ptr [[AAA_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], 1
// CHECK1-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    [[CONV:%.*]] = sext i16 [[TMP2]] to i32
// CHECK1-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK1-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK1-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    [[TMP3:%.*]] = load i8, ptr [[AAA_ADDR]], align 1
// CHECK1-NEXT:    [[CONV3:%.*]] = sext i8 [[TMP3]] to i32
// CHECK1-NEXT:    [[ADD4:%.*]] = add nsw i32 [[CONV3]], 1
// CHECK1-NEXT:    [[CONV5:%.*]] = trunc i32 [[ADD4]] to i8
// CHECK1-NEXT:    store i8 [[CONV5]], ptr [[AAA_ADDR]], align 1
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], ptr [[TMP0]], i64 0, i64 2
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK1-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP4]], 1
// CHECK1-NEXT:    store i32 [[ADD6]], ptr [[ARRAYIDX]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181
// CHECK1-SAME: (i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[A_CASTED]], align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    store i16 [[TMP3]], ptr [[AA_CASTED]], align 2
// CHECK1-NEXT:    [[TMP4:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK1-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 3, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.omp_outlined, i64 [[TMP2]], i64 [[TMP4]], ptr [[TMP0]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK1-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], 1
// CHECK1-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    [[CONV:%.*]] = sext i16 [[TMP2]] to i32
// CHECK1-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK1-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK1-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], ptr [[TMP0]], i64 0, i64 2
// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK1-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK1-NEXT:    store i32 [[ADD3]], ptr [[ARRAYIDX]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
// CHECK1-SAME: () #[[ATTR8:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    call void @__tgt_register_requires(i64 1)
// CHECK1-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z3fooi
// CHECK3-SAME: (i32 noundef [[N:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA:%.*]] = alloca i16, align 2
// CHECK3-NEXT:    [[B:%.*]] = alloca [10 x float], align 4
// CHECK3-NEXT:    [[SAVED_STACK:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[__VLA_EXPR0:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[C:%.*]] = alloca [5 x [10 x double]], align 8
// CHECK3-NEXT:    [[__VLA_EXPR1:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[D:%.*]] = alloca [[STRUCT_TT:%.*]], align 4
// CHECK3-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 1
// CHECK3-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [1 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_PTRS:%.*]] = alloca [1 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [1 x ptr], align 4
// CHECK3-NEXT:    [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK3-NEXT:    [[A_CASTED2:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_CASTED3:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_BASEPTRS4:%.*]] = alloca [2 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_PTRS5:%.*]] = alloca [2 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_MAPPERS6:%.*]] = alloca [2 x ptr], align 4
// CHECK3-NEXT:    [[KERNEL_ARGS7:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS]], align 8
// CHECK3-NEXT:    [[A_CASTED10:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_BASEPTRS13:%.*]] = alloca [9 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_PTRS14:%.*]] = alloca [9 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_MAPPERS15:%.*]] = alloca [9 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_SIZES:%.*]] = alloca [9 x i64], align 4
// CHECK3-NEXT:    [[KERNEL_ARGS16:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS]], align 8
// CHECK3-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
// CHECK3-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    store i32 0, ptr [[A]], align 4
// CHECK3-NEXT:    store i16 0, ptr [[AA]], align 2
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = call ptr @llvm.stacksave()
// CHECK3-NEXT:    store ptr [[TMP2]], ptr [[SAVED_STACK]], align 4
// CHECK3-NEXT:    [[VLA:%.*]] = alloca float, i32 [[TMP1]], align 4
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[__VLA_EXPR0]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = mul nuw i32 5, [[TMP3]]
// CHECK3-NEXT:    [[VLA1:%.*]] = alloca double, i32 [[TMP4]], align 8
// CHECK3-NEXT:    store i32 [[TMP3]], ptr [[__VLA_EXPR1]], align 4
// CHECK3-NEXT:    [[TMP5:%.*]] = call ptr @__kmpc_omp_target_task_alloc(ptr @[[GLOB1]], i32 [[TMP0]], i32 1, i32 20, i32 1, ptr @.omp_task_entry., i64 -1)
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], ptr [[TMP5]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = call i32 @__kmpc_omp_task(ptr @[[GLOB1]], i32 [[TMP0]], ptr [[TMP5]])
// CHECK3-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    store i32 [[TMP8]], ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP9:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l104(i32 [[TMP9]]) #[[ATTR4:[0-9]+]]
// CHECK3-NEXT:    [[TMP10:%.*]] = load i16, ptr [[AA]], align 2
// CHECK3-NEXT:    store i16 [[TMP10]], ptr [[AA_CASTED]], align 2
// CHECK3-NEXT:    [[TMP11:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK3-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP11]], ptr [[TMP12]], align 4
// CHECK3-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP11]], ptr [[TMP13]], align 4
// CHECK3-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
// CHECK3-NEXT:    store ptr null, ptr [[TMP14]], align 4
// CHECK3-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 2, ptr [[TMP17]], align 4
// CHECK3-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 1, ptr [[TMP18]], align 4
// CHECK3-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK3-NEXT:    store ptr [[TMP15]], ptr [[TMP19]], align 4
// CHECK3-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[TMP16]], ptr [[TMP20]], align 4
// CHECK3-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK3-NEXT:    store ptr @.offload_sizes, ptr [[TMP21]], align 4
// CHECK3-NEXT:    [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK3-NEXT:    store ptr @.offload_maptypes, ptr [[TMP22]], align 4
// CHECK3-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK3-NEXT:    store ptr null, ptr [[TMP23]], align 4
// CHECK3-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK3-NEXT:    store ptr null, ptr [[TMP24]], align 4
// CHECK3-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK3-NEXT:    store i64 0, ptr [[TMP25]], align 8
// CHECK3-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK3-NEXT:    store i64 0, ptr [[TMP26]], align 8
// CHECK3-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK3-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP27]], align 4
// CHECK3-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK3-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP28]], align 4
// CHECK3-NEXT:    [[TMP29:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK3-NEXT:    store i32 0, ptr [[TMP29]], align 4
// CHECK3-NEXT:    [[TMP30:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.region_id, ptr [[KERNEL_ARGS]])
// CHECK3-NEXT:    [[TMP31:%.*]] = icmp ne i32 [[TMP30]], 0
// CHECK3-NEXT:    br i1 [[TMP31]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK3:       omp_offload.failed:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110(i32 [[TMP11]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_OFFLOAD_CONT]]
// CHECK3:       omp_offload.cont:
// CHECK3-NEXT:    [[TMP32:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    store i32 [[TMP32]], ptr [[A_CASTED2]], align 4
// CHECK3-NEXT:    [[TMP33:%.*]] = load i32, ptr [[A_CASTED2]], align 4
// CHECK3-NEXT:    [[TMP34:%.*]] = load i16, ptr [[AA]], align 2
// CHECK3-NEXT:    store i16 [[TMP34]], ptr [[AA_CASTED3]], align 2
// CHECK3-NEXT:    [[TMP35:%.*]] = load i32, ptr [[AA_CASTED3]], align 4
// CHECK3-NEXT:    [[TMP36:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP36]], 10
// CHECK3-NEXT:    br i1 [[CMP]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_ELSE:%.*]]
// CHECK3:       omp_if.then:
// CHECK3-NEXT:    [[TMP37:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS4]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP33]], ptr [[TMP37]], align 4
// CHECK3-NEXT:    [[TMP38:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS5]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP33]], ptr [[TMP38]], align 4
// CHECK3-NEXT:    [[TMP39:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS6]], i32 0, i32 0
// CHECK3-NEXT:    store ptr null, ptr [[TMP39]], align 4
// CHECK3-NEXT:    [[TMP40:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS4]], i32 0, i32 1
// CHECK3-NEXT:    store i32 [[TMP35]], ptr [[TMP40]], align 4
// CHECK3-NEXT:    [[TMP41:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS5]], i32 0, i32 1
// CHECK3-NEXT:    store i32 [[TMP35]], ptr [[TMP41]], align 4
// CHECK3-NEXT:    [[TMP42:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS6]], i32 0, i32 1
// CHECK3-NEXT:    store ptr null, ptr [[TMP42]], align 4
// CHECK3-NEXT:    [[TMP43:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP44:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS5]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP45:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 0
// CHECK3-NEXT:    store i32 2, ptr [[TMP45]], align 4
// CHECK3-NEXT:    [[TMP46:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 1
// CHECK3-NEXT:    store i32 2, ptr [[TMP46]], align 4
// CHECK3-NEXT:    [[TMP47:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 2
// CHECK3-NEXT:    store ptr [[TMP43]], ptr [[TMP47]], align 4
// CHECK3-NEXT:    [[TMP48:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[TMP44]], ptr [[TMP48]], align 4
// CHECK3-NEXT:    [[TMP49:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 4
// CHECK3-NEXT:    store ptr @.offload_sizes.1, ptr [[TMP49]], align 4
// CHECK3-NEXT:    [[TMP50:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 5
// CHECK3-NEXT:    store ptr @.offload_maptypes.2, ptr [[TMP50]], align 4
// CHECK3-NEXT:    [[TMP51:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 6
// CHECK3-NEXT:    store ptr null, ptr [[TMP51]], align 4
// CHECK3-NEXT:    [[TMP52:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 7
// CHECK3-NEXT:    store ptr null, ptr [[TMP52]], align 4
// CHECK3-NEXT:    [[TMP53:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 8
// CHECK3-NEXT:    store i64 0, ptr [[TMP53]], align 8
// CHECK3-NEXT:    [[TMP54:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 9
// CHECK3-NEXT:    store i64 0, ptr [[TMP54]], align 8
// CHECK3-NEXT:    [[TMP55:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 10
// CHECK3-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP55]], align 4
// CHECK3-NEXT:    [[TMP56:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 11
// CHECK3-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP56]], align 4
// CHECK3-NEXT:    [[TMP57:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS7]], i32 0, i32 12
// CHECK3-NEXT:    store i32 0, ptr [[TMP57]], align 4
// CHECK3-NEXT:    [[TMP58:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.region_id, ptr [[KERNEL_ARGS7]])
// CHECK3-NEXT:    [[TMP59:%.*]] = icmp ne i32 [[TMP58]], 0
// CHECK3-NEXT:    br i1 [[TMP59]], label [[OMP_OFFLOAD_FAILED8:%.*]], label [[OMP_OFFLOAD_CONT9:%.*]]
// CHECK3:       omp_offload.failed8:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119(i32 [[TMP33]], i32 [[TMP35]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_OFFLOAD_CONT9]]
// CHECK3:       omp_offload.cont9:
// CHECK3-NEXT:    br label [[OMP_IF_END:%.*]]
// CHECK3:       omp_if.else:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119(i32 [[TMP33]], i32 [[TMP35]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_IF_END]]
// CHECK3:       omp_if.end:
// CHECK3-NEXT:    [[TMP60:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    store i32 [[TMP60]], ptr [[A_CASTED10]], align 4
// CHECK3-NEXT:    [[TMP61:%.*]] = load i32, ptr [[A_CASTED10]], align 4
// CHECK3-NEXT:    [[TMP62:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[CMP11:%.*]] = icmp sgt i32 [[TMP62]], 20
// CHECK3-NEXT:    br i1 [[CMP11]], label [[OMP_IF_THEN12:%.*]], label [[OMP_IF_ELSE19:%.*]]
// CHECK3:       omp_if.then12:
// CHECK3-NEXT:    [[TMP63:%.*]] = mul nuw i32 [[TMP1]], 4
// CHECK3-NEXT:    [[TMP64:%.*]] = sext i32 [[TMP63]] to i64
// CHECK3-NEXT:    [[TMP65:%.*]] = mul nuw i32 5, [[TMP3]]
// CHECK3-NEXT:    [[TMP66:%.*]] = mul nuw i32 [[TMP65]], 8
// CHECK3-NEXT:    [[TMP67:%.*]] = sext i32 [[TMP66]] to i64
// CHECK3-NEXT:    call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[DOTOFFLOAD_SIZES]], ptr align 4 @.offload_sizes.3, i32 72, i1 false)
// CHECK3-NEXT:    [[TMP68:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP61]], ptr [[TMP68]], align 4
// CHECK3-NEXT:    [[TMP69:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP61]], ptr [[TMP69]], align 4
// CHECK3-NEXT:    [[TMP70:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i32 0, i32 0
// CHECK3-NEXT:    store ptr null, ptr [[TMP70]], align 4
// CHECK3-NEXT:    [[TMP71:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 1
// CHECK3-NEXT:    store ptr [[B]], ptr [[TMP71]], align 4
// CHECK3-NEXT:    [[TMP72:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 1
// CHECK3-NEXT:    store ptr [[B]], ptr [[TMP72]], align 4
// CHECK3-NEXT:    [[TMP73:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i32 0, i32 1
// CHECK3-NEXT:    store ptr null, ptr [[TMP73]], align 4
// CHECK3-NEXT:    [[TMP74:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 2
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[TMP74]], align 4
// CHECK3-NEXT:    [[TMP75:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 2
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[TMP75]], align 4
// CHECK3-NEXT:    [[TMP76:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i32 0, i32 2
// CHECK3-NEXT:    store ptr null, ptr [[TMP76]], align 4
// CHECK3-NEXT:    [[TMP77:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[VLA]], ptr [[TMP77]], align 4
// CHECK3-NEXT:    [[TMP78:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[VLA]], ptr [[TMP78]], align 4
// CHECK3-NEXT:    [[TMP79:%.*]] = getelementptr inbounds [9 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 3
// CHECK3-NEXT:    store i64 [[TMP64]], ptr [[TMP79]], align 4
// CHECK3-NEXT:    [[TMP80:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i32 0, i32 3
// CHECK3-NEXT:    store ptr null, ptr [[TMP80]], align 4
// CHECK3-NEXT:    [[TMP81:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 4
// CHECK3-NEXT:    store ptr [[C]], ptr [[TMP81]], align 4
// CHECK3-NEXT:    [[TMP82:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 4
// CHECK3-NEXT:    store ptr [[C]], ptr [[TMP82]], align 4
// CHECK3-NEXT:    [[TMP83:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i32 0, i32 4
// CHECK3-NEXT:    store ptr null, ptr [[TMP83]], align 4
// CHECK3-NEXT:    [[TMP84:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 5
// CHECK3-NEXT:    store i32 5, ptr [[TMP84]], align 4
// CHECK3-NEXT:    [[TMP85:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 5
// CHECK3-NEXT:    store i32 5, ptr [[TMP85]], align 4
// CHECK3-NEXT:    [[TMP86:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i32 0, i32 5
// CHECK3-NEXT:    store ptr null, ptr [[TMP86]], align 4
// CHECK3-NEXT:    [[TMP87:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 6
// CHECK3-NEXT:    store i32 [[TMP3]], ptr [[TMP87]], align 4
// CHECK3-NEXT:    [[TMP88:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 6
// CHECK3-NEXT:    store i32 [[TMP3]], ptr [[TMP88]], align 4
// CHECK3-NEXT:    [[TMP89:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i32 0, i32 6
// CHECK3-NEXT:    store ptr null, ptr [[TMP89]], align 4
// CHECK3-NEXT:    [[TMP90:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 7
// CHECK3-NEXT:    store ptr [[VLA1]], ptr [[TMP90]], align 4
// CHECK3-NEXT:    [[TMP91:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 7
// CHECK3-NEXT:    store ptr [[VLA1]], ptr [[TMP91]], align 4
// CHECK3-NEXT:    [[TMP92:%.*]] = getelementptr inbounds [9 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 7
// CHECK3-NEXT:    store i64 [[TMP67]], ptr [[TMP92]], align 4
// CHECK3-NEXT:    [[TMP93:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i32 0, i32 7
// CHECK3-NEXT:    store ptr null, ptr [[TMP93]], align 4
// CHECK3-NEXT:    [[TMP94:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 8
// CHECK3-NEXT:    store ptr [[D]], ptr [[TMP94]], align 4
// CHECK3-NEXT:    [[TMP95:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 8
// CHECK3-NEXT:    store ptr [[D]], ptr [[TMP95]], align 4
// CHECK3-NEXT:    [[TMP96:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_MAPPERS15]], i32 0, i32 8
// CHECK3-NEXT:    store ptr null, ptr [[TMP96]], align 4
// CHECK3-NEXT:    [[TMP97:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_BASEPTRS13]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP98:%.*]] = getelementptr inbounds [9 x ptr], ptr [[DOTOFFLOAD_PTRS14]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP99:%.*]] = getelementptr inbounds [9 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP100:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 0
// CHECK3-NEXT:    store i32 2, ptr [[TMP100]], align 4
// CHECK3-NEXT:    [[TMP101:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 1
// CHECK3-NEXT:    store i32 9, ptr [[TMP101]], align 4
// CHECK3-NEXT:    [[TMP102:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 2
// CHECK3-NEXT:    store ptr [[TMP97]], ptr [[TMP102]], align 4
// CHECK3-NEXT:    [[TMP103:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[TMP98]], ptr [[TMP103]], align 4
// CHECK3-NEXT:    [[TMP104:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 4
// CHECK3-NEXT:    store ptr [[TMP99]], ptr [[TMP104]], align 4
// CHECK3-NEXT:    [[TMP105:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 5
// CHECK3-NEXT:    store ptr @.offload_maptypes.4, ptr [[TMP105]], align 4
// CHECK3-NEXT:    [[TMP106:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 6
// CHECK3-NEXT:    store ptr null, ptr [[TMP106]], align 4
// CHECK3-NEXT:    [[TMP107:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 7
// CHECK3-NEXT:    store ptr null, ptr [[TMP107]], align 4
// CHECK3-NEXT:    [[TMP108:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 8
// CHECK3-NEXT:    store i64 0, ptr [[TMP108]], align 8
// CHECK3-NEXT:    [[TMP109:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 9
// CHECK3-NEXT:    store i64 0, ptr [[TMP109]], align 8
// CHECK3-NEXT:    [[TMP110:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 10
// CHECK3-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP110]], align 4
// CHECK3-NEXT:    [[TMP111:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 11
// CHECK3-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP111]], align 4
// CHECK3-NEXT:    [[TMP112:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS16]], i32 0, i32 12
// CHECK3-NEXT:    store i32 0, ptr [[TMP112]], align 4
// CHECK3-NEXT:    [[TMP113:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.region_id, ptr [[KERNEL_ARGS16]])
// CHECK3-NEXT:    [[TMP114:%.*]] = icmp ne i32 [[TMP113]], 0
// CHECK3-NEXT:    br i1 [[TMP114]], label [[OMP_OFFLOAD_FAILED17:%.*]], label [[OMP_OFFLOAD_CONT18:%.*]]
// CHECK3:       omp_offload.failed17:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144(i32 [[TMP61]], ptr [[B]], i32 [[TMP1]], ptr [[VLA]], ptr [[C]], i32 5, i32 [[TMP3]], ptr [[VLA1]], ptr [[D]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_OFFLOAD_CONT18]]
// CHECK3:       omp_offload.cont18:
// CHECK3-NEXT:    br label [[OMP_IF_END20:%.*]]
// CHECK3:       omp_if.else19:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144(i32 [[TMP61]], ptr [[B]], i32 [[TMP1]], ptr [[VLA]], ptr [[C]], i32 5, i32 [[TMP3]], ptr [[VLA1]], ptr [[D]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_IF_END20]]
// CHECK3:       omp_if.end20:
// CHECK3-NEXT:    [[TMP115:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    [[TMP116:%.*]] = load ptr, ptr [[SAVED_STACK]], align 4
// CHECK3-NEXT:    call void @llvm.stackrestore(ptr [[TMP116]])
// CHECK3-NEXT:    ret i32 [[TMP115]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100
// CHECK3-SAME: () #[[ATTR2:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 0, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.omp_outlined)
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.omp_outlined
// CHECK3-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry.
// CHECK3-SAME: (i32 noundef [[TMP0:%.*]], ptr noalias noundef [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[KERNEL_ARGS_I:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    store i32 [[TMP0]], ptr [[DOTADDR]], align 4
// CHECK3-NEXT:    store ptr [[TMP1]], ptr [[DOTADDR1]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, ptr [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[DOTADDR1]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], ptr [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], ptr [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], ptr [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[TMP6]], align 4
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META13:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META16:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META18:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META20:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], ptr [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !22
// CHECK3-NEXT:    store ptr [[TMP5]], ptr [[DOTPART_ID__ADDR_I]], align 4, !noalias !22
// CHECK3-NEXT:    store ptr null, ptr [[DOTPRIVATES__ADDR_I]], align 4, !noalias !22
// CHECK3-NEXT:    store ptr null, ptr [[DOTCOPY_FN__ADDR_I]], align 4, !noalias !22
// CHECK3-NEXT:    store ptr [[TMP3]], ptr [[DOTTASK_T__ADDR_I]], align 4, !noalias !22
// CHECK3-NEXT:    store ptr [[TMP7]], ptr [[__CONTEXT_ADDR_I]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP8:%.*]] = load ptr, ptr [[__CONTEXT_ADDR_I]], align 4, !noalias !22
// CHECK3-NEXT:    store i32 2, ptr [[KERNEL_ARGS_I]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 1
// CHECK3-NEXT:    store i32 0, ptr [[TMP9]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 2
// CHECK3-NEXT:    store ptr null, ptr [[TMP10]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 3
// CHECK3-NEXT:    store ptr null, ptr [[TMP11]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 4
// CHECK3-NEXT:    store ptr null, ptr [[TMP12]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 5
// CHECK3-NEXT:    store ptr null, ptr [[TMP13]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 6
// CHECK3-NEXT:    store ptr null, ptr [[TMP14]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 7
// CHECK3-NEXT:    store ptr null, ptr [[TMP15]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 8
// CHECK3-NEXT:    store i64 0, ptr [[TMP16]], align 8, !noalias !22
// CHECK3-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 9
// CHECK3-NEXT:    store i64 1, ptr [[TMP17]], align 8, !noalias !22
// CHECK3-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 10
// CHECK3-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP18]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 11
// CHECK3-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP19]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS_I]], i32 0, i32 12
// CHECK3-NEXT:    store i32 0, ptr [[TMP20]], align 4, !noalias !22
// CHECK3-NEXT:    [[TMP21:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.region_id, ptr [[KERNEL_ARGS_I]])
// CHECK3-NEXT:    [[TMP22:%.*]] = icmp ne i32 [[TMP21]], 0
// CHECK3-NEXT:    br i1 [[TMP22]], label [[OMP_OFFLOAD_FAILED_I:%.*]], label [[DOTOMP_OUTLINED__EXIT:%.*]]
// CHECK3:       omp_offload.failed.i:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100() #[[ATTR4]]
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__EXIT]]
// CHECK3:       .omp_outlined..exit:
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l104
// CHECK3-SAME: (i32 noundef [[A:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l104.omp_outlined, i32 [[TMP1]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l104.omp_outlined
// CHECK3-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[A:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 1
// CHECK3-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110
// CHECK3-SAME: (i32 noundef [[AA:%.*]]) #[[ATTR2]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    store i16 [[TMP0]], ptr [[AA_CASTED]], align 2
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK3-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.omp_outlined, i32 [[TMP1]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.omp_outlined
// CHECK3-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[AA:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    [[CONV:%.*]] = sext i16 [[TMP0]] to i32
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK3-NEXT:    [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK3-NEXT:    store i16 [[CONV1]], ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = call i32 @__kmpc_cancel(ptr @[[GLOB1]], i32 [[TMP2]], i32 1)
// CHECK3-NEXT:    [[TMP4:%.*]] = icmp ne i32 [[TMP3]], 0
// CHECK3-NEXT:    br i1 [[TMP4]], label [[DOTCANCEL_EXIT:%.*]], label [[DOTCANCEL_CONTINUE:%.*]]
// CHECK3:       .cancel.exit:
// CHECK3-NEXT:    [[TMP5:%.*]] = call i32 @__kmpc_cancel_barrier(ptr @[[GLOB2:[0-9]+]], i32 [[TMP2]])
// CHECK3-NEXT:    br label [[DOTCANCEL_CONTINUE]]
// CHECK3:       .cancel.continue:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119
// CHECK3-SAME: (i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]]) #[[ATTR2]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    store i16 [[TMP2]], ptr [[AA_CASTED]], align 2
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK3-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 2, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.omp_outlined, i32 [[TMP1]], i32 [[TMP3]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.omp_outlined
// CHECK3-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 1
// CHECK3-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK3-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK3-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK3-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144
// CHECK3-SAME: (i32 noundef [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]], i32 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[BN:%.*]], ptr noundef nonnull align 4 dereferenceable(400) [[C:%.*]], i32 noundef [[VLA1:%.*]], i32 noundef [[VLA3:%.*]], ptr noundef nonnull align 4 dereferenceable(8) [[CN:%.*]], ptr noundef nonnull align 4 dereferenceable(12) [[D:%.*]]) #[[ATTR2]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[BN_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[VLA_ADDR4:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[CN_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[D_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA]], ptr [[VLA_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[BN]], ptr [[BN_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA1]], ptr [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    store i32 [[VLA3]], ptr [[VLA_ADDR4]], align 4
// CHECK3-NEXT:    store ptr [[CN]], ptr [[CN_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[D]], ptr [[D_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[VLA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[BN_ADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    [[TMP5:%.*]] = load i32, ptr [[VLA_ADDR4]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[CN_ADDR]], align 4
// CHECK3-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[D_ADDR]], align 4
// CHECK3-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[TMP8]], ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP9:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 9, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.omp_outlined, i32 [[TMP9]], ptr [[TMP0]], i32 [[TMP1]], ptr [[TMP2]], ptr [[TMP3]], i32 [[TMP4]], i32 [[TMP5]], ptr [[TMP6]], ptr [[TMP7]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.omp_outlined
// CHECK3-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]], i32 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[BN:%.*]], ptr noundef nonnull align 4 dereferenceable(400) [[C:%.*]], i32 noundef [[VLA1:%.*]], i32 noundef [[VLA3:%.*]], ptr noundef nonnull align 4 dereferenceable(8) [[CN:%.*]], ptr noundef nonnull align 4 dereferenceable(12) [[D:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[BN_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[VLA_ADDR4:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[CN_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[D_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA]], ptr [[VLA_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[BN]], ptr [[BN_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA1]], ptr [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    store i32 [[VLA3]], ptr [[VLA_ADDR4]], align 4
// CHECK3-NEXT:    store ptr [[CN]], ptr [[CN_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[D]], ptr [[D_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[VLA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[BN_ADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    [[TMP5:%.*]] = load i32, ptr [[VLA_ADDR4]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[CN_ADDR]], align 4
// CHECK3-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[D_ADDR]], align 4
// CHECK3-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP8]], 1
// CHECK3-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x float], ptr [[TMP0]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP9:%.*]] = load float, ptr [[ARRAYIDX]], align 4
// CHECK3-NEXT:    [[CONV:%.*]] = fpext float [[TMP9]] to double
// CHECK3-NEXT:    [[ADD5:%.*]] = fadd double [[CONV]], 1.000000e+00
// CHECK3-NEXT:    [[CONV6:%.*]] = fptrunc double [[ADD5]] to float
// CHECK3-NEXT:    store float [[CONV6]], ptr [[ARRAYIDX]], align 4
// CHECK3-NEXT:    [[ARRAYIDX7:%.*]] = getelementptr inbounds float, ptr [[TMP2]], i32 3
// CHECK3-NEXT:    [[TMP10:%.*]] = load float, ptr [[ARRAYIDX7]], align 4
// CHECK3-NEXT:    [[CONV8:%.*]] = fpext float [[TMP10]] to double
// CHECK3-NEXT:    [[ADD9:%.*]] = fadd double [[CONV8]], 1.000000e+00
// CHECK3-NEXT:    [[CONV10:%.*]] = fptrunc double [[ADD9]] to float
// CHECK3-NEXT:    store float [[CONV10]], ptr [[ARRAYIDX7]], align 4
// CHECK3-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds [5 x [10 x double]], ptr [[TMP3]], i32 0, i32 1
// CHECK3-NEXT:    [[ARRAYIDX12:%.*]] = getelementptr inbounds [10 x double], ptr [[ARRAYIDX11]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP11:%.*]] = load double, ptr [[ARRAYIDX12]], align 8
// CHECK3-NEXT:    [[ADD13:%.*]] = fadd double [[TMP11]], 1.000000e+00
// CHECK3-NEXT:    store double [[ADD13]], ptr [[ARRAYIDX12]], align 8
// CHECK3-NEXT:    [[TMP12:%.*]] = mul nsw i32 1, [[TMP5]]
// CHECK3-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds double, ptr [[TMP6]], i32 [[TMP12]]
// CHECK3-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr inbounds double, ptr [[ARRAYIDX14]], i32 3
// CHECK3-NEXT:    [[TMP13:%.*]] = load double, ptr [[ARRAYIDX15]], align 8
// CHECK3-NEXT:    [[ADD16:%.*]] = fadd double [[TMP13]], 1.000000e+00
// CHECK3-NEXT:    store double [[ADD16]], ptr [[ARRAYIDX15]], align 8
// CHECK3-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], ptr [[TMP7]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP14:%.*]] = load i64, ptr [[X]], align 4
// CHECK3-NEXT:    [[ADD17:%.*]] = add nsw i64 [[TMP14]], 1
// CHECK3-NEXT:    store i64 [[ADD17]], ptr [[X]], align 4
// CHECK3-NEXT:    [[Y:%.*]] = getelementptr inbounds [[STRUCT_TT]], ptr [[TMP7]], i32 0, i32 1
// CHECK3-NEXT:    [[TMP15:%.*]] = load i8, ptr [[Y]], align 4
// CHECK3-NEXT:    [[CONV18:%.*]] = sext i8 [[TMP15]] to i32
// CHECK3-NEXT:    [[ADD19:%.*]] = add nsw i32 [[CONV18]], 1
// CHECK3-NEXT:    [[CONV20:%.*]] = trunc i32 [[ADD19]] to i8
// CHECK3-NEXT:    store i8 [[CONV20]], ptr [[Y]], align 4
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z3bari
// CHECK3-SAME: (i32 noundef [[N:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[S:%.*]] = alloca [[STRUCT_S1:%.*]], align 4
// CHECK3-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    store i32 0, ptr [[A]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[CALL:%.*]] = call noundef i32 @_Z3fooi(i32 noundef [[TMP0]])
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], [[CALL]]
// CHECK3-NEXT:    store i32 [[ADD]], ptr [[A]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[CALL1:%.*]] = call noundef i32 @_ZN2S12r1Ei(ptr noundef nonnull align 4 dereferenceable(8) [[S]], i32 noundef [[TMP2]])
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    [[ADD2:%.*]] = add nsw i32 [[TMP3]], [[CALL1]]
// CHECK3-NEXT:    store i32 [[ADD2]], ptr [[A]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[CALL3:%.*]] = call noundef i32 @_ZL7fstatici(i32 noundef [[TMP4]])
// CHECK3-NEXT:    [[TMP5:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    [[ADD4:%.*]] = add nsw i32 [[TMP5]], [[CALL3]]
// CHECK3-NEXT:    store i32 [[ADD4]], ptr [[A]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[CALL5:%.*]] = call noundef i32 @_Z9ftemplateIiET_i(i32 noundef [[TMP6]])
// CHECK3-NEXT:    [[TMP7:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP7]], [[CALL5]]
// CHECK3-NEXT:    store i32 [[ADD6]], ptr [[A]], align 4
// CHECK3-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    ret i32 [[TMP8]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2S12r1Ei
// CHECK3-SAME: (ptr noundef nonnull align 4 dereferenceable(8) [[THIS:%.*]], i32 noundef [[N:%.*]]) #[[ATTR0]] comdat align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[SAVED_STACK:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[__VLA_EXPR0:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [5 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_PTRS:%.*]] = alloca [5 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [5 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_SIZES:%.*]] = alloca [5 x i64], align 4
// CHECK3-NEXT:    [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK3-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 1
// CHECK3-NEXT:    store i32 [[ADD]], ptr [[B]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = call ptr @llvm.stacksave()
// CHECK3-NEXT:    store ptr [[TMP2]], ptr [[SAVED_STACK]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = mul nuw i32 2, [[TMP1]]
// CHECK3-NEXT:    [[VLA:%.*]] = alloca i16, i32 [[TMP3]], align 2
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[__VLA_EXPR0]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[B]], align 4
// CHECK3-NEXT:    store i32 [[TMP4]], ptr [[B_CASTED]], align 4
// CHECK3-NEXT:    [[TMP5:%.*]] = load i32, ptr [[B_CASTED]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP6]], 60
// CHECK3-NEXT:    br i1 [[CMP]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_ELSE:%.*]]
// CHECK3:       omp_if.then:
// CHECK3-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], ptr [[THIS1]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = mul nuw i32 2, [[TMP1]]
// CHECK3-NEXT:    [[TMP8:%.*]] = mul nuw i32 [[TMP7]], 2
// CHECK3-NEXT:    [[TMP9:%.*]] = sext i32 [[TMP8]] to i64
// CHECK3-NEXT:    call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[DOTOFFLOAD_SIZES]], ptr align 4 @.offload_sizes.5, i32 40, i1 false)
// CHECK3-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT:    store ptr [[THIS1]], ptr [[TMP10]], align 4
// CHECK3-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT:    store ptr [[A]], ptr [[TMP11]], align 4
// CHECK3-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
// CHECK3-NEXT:    store ptr null, ptr [[TMP12]], align 4
// CHECK3-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 [[TMP5]], ptr [[TMP13]], align 4
// CHECK3-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 [[TMP5]], ptr [[TMP14]], align 4
// CHECK3-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 1
// CHECK3-NEXT:    store ptr null, ptr [[TMP15]], align 4
// CHECK3-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK3-NEXT:    store i32 2, ptr [[TMP16]], align 4
// CHECK3-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK3-NEXT:    store i32 2, ptr [[TMP17]], align 4
// CHECK3-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 2
// CHECK3-NEXT:    store ptr null, ptr [[TMP18]], align 4
// CHECK3-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[TMP19]], align 4
// CHECK3-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[TMP20]], align 4
// CHECK3-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 3
// CHECK3-NEXT:    store ptr null, ptr [[TMP21]], align 4
// CHECK3-NEXT:    [[TMP22:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 4
// CHECK3-NEXT:    store ptr [[VLA]], ptr [[TMP22]], align 4
// CHECK3-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 4
// CHECK3-NEXT:    store ptr [[VLA]], ptr [[TMP23]], align 4
// CHECK3-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [5 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 4
// CHECK3-NEXT:    store i64 [[TMP9]], ptr [[TMP24]], align 4
// CHECK3-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 4
// CHECK3-NEXT:    store ptr null, ptr [[TMP25]], align 4
// CHECK3-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [5 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [5 x i64], ptr [[DOTOFFLOAD_SIZES]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP29:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 2, ptr [[TMP29]], align 4
// CHECK3-NEXT:    [[TMP30:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 5, ptr [[TMP30]], align 4
// CHECK3-NEXT:    [[TMP31:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK3-NEXT:    store ptr [[TMP26]], ptr [[TMP31]], align 4
// CHECK3-NEXT:    [[TMP32:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[TMP27]], ptr [[TMP32]], align 4
// CHECK3-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK3-NEXT:    store ptr [[TMP28]], ptr [[TMP33]], align 4
// CHECK3-NEXT:    [[TMP34:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK3-NEXT:    store ptr @.offload_maptypes.6, ptr [[TMP34]], align 4
// CHECK3-NEXT:    [[TMP35:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK3-NEXT:    store ptr null, ptr [[TMP35]], align 4
// CHECK3-NEXT:    [[TMP36:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK3-NEXT:    store ptr null, ptr [[TMP36]], align 4
// CHECK3-NEXT:    [[TMP37:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK3-NEXT:    store i64 0, ptr [[TMP37]], align 8
// CHECK3-NEXT:    [[TMP38:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK3-NEXT:    store i64 0, ptr [[TMP38]], align 8
// CHECK3-NEXT:    [[TMP39:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK3-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP39]], align 4
// CHECK3-NEXT:    [[TMP40:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK3-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP40]], align 4
// CHECK3-NEXT:    [[TMP41:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK3-NEXT:    store i32 0, ptr [[TMP41]], align 4
// CHECK3-NEXT:    [[TMP42:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.region_id, ptr [[KERNEL_ARGS]])
// CHECK3-NEXT:    [[TMP43:%.*]] = icmp ne i32 [[TMP42]], 0
// CHECK3-NEXT:    br i1 [[TMP43]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK3:       omp_offload.failed:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216(ptr [[THIS1]], i32 [[TMP5]], i32 2, i32 [[TMP1]], ptr [[VLA]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_OFFLOAD_CONT]]
// CHECK3:       omp_offload.cont:
// CHECK3-NEXT:    br label [[OMP_IF_END:%.*]]
// CHECK3:       omp_if.else:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216(ptr [[THIS1]], i32 [[TMP5]], i32 2, i32 [[TMP1]], ptr [[VLA]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_IF_END]]
// CHECK3:       omp_if.end:
// CHECK3-NEXT:    [[TMP44:%.*]] = mul nsw i32 1, [[TMP1]]
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[VLA]], i32 [[TMP44]]
// CHECK3-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i16, ptr [[ARRAYIDX]], i32 1
// CHECK3-NEXT:    [[TMP45:%.*]] = load i16, ptr [[ARRAYIDX2]], align 2
// CHECK3-NEXT:    [[CONV:%.*]] = sext i16 [[TMP45]] to i32
// CHECK3-NEXT:    [[TMP46:%.*]] = load i32, ptr [[B]], align 4
// CHECK3-NEXT:    [[ADD3:%.*]] = add nsw i32 [[CONV]], [[TMP46]]
// CHECK3-NEXT:    [[TMP47:%.*]] = load ptr, ptr [[SAVED_STACK]], align 4
// CHECK3-NEXT:    call void @llvm.stackrestore(ptr [[TMP47]])
// CHECK3-NEXT:    ret i32 [[ADD3]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZL7fstatici
// CHECK3-SAME: (i32 noundef [[N:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA:%.*]] = alloca i16, align 2
// CHECK3-NEXT:    [[AAA:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    [[B:%.*]] = alloca [10 x i32], align 4
// CHECK3-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AAA_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [4 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_PTRS:%.*]] = alloca [4 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [4 x ptr], align 4
// CHECK3-NEXT:    [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK3-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    store i32 0, ptr [[A]], align 4
// CHECK3-NEXT:    store i16 0, ptr [[AA]], align 2
// CHECK3-NEXT:    store i8 0, ptr [[AAA]], align 1
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA]], align 2
// CHECK3-NEXT:    store i16 [[TMP2]], ptr [[AA_CASTED]], align 2
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i8, ptr [[AAA]], align 1
// CHECK3-NEXT:    store i8 [[TMP4]], ptr [[AAA_CASTED]], align 1
// CHECK3-NEXT:    [[TMP5:%.*]] = load i32, ptr [[AAA_CASTED]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP6]], 50
// CHECK3-NEXT:    br i1 [[CMP]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_ELSE:%.*]]
// CHECK3:       omp_if.then:
// CHECK3-NEXT:    [[TMP7:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[TMP7]], align 4
// CHECK3-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[TMP8]], align 4
// CHECK3-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
// CHECK3-NEXT:    store ptr null, ptr [[TMP9]], align 4
// CHECK3-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 [[TMP3]], ptr [[TMP10]], align 4
// CHECK3-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 [[TMP3]], ptr [[TMP11]], align 4
// CHECK3-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 1
// CHECK3-NEXT:    store ptr null, ptr [[TMP12]], align 4
// CHECK3-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK3-NEXT:    store i32 [[TMP5]], ptr [[TMP13]], align 4
// CHECK3-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK3-NEXT:    store i32 [[TMP5]], ptr [[TMP14]], align 4
// CHECK3-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 2
// CHECK3-NEXT:    store ptr null, ptr [[TMP15]], align 4
// CHECK3-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[B]], ptr [[TMP16]], align 4
// CHECK3-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[B]], ptr [[TMP17]], align 4
// CHECK3-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 3
// CHECK3-NEXT:    store ptr null, ptr [[TMP18]], align 4
// CHECK3-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 2, ptr [[TMP21]], align 4
// CHECK3-NEXT:    [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 4, ptr [[TMP22]], align 4
// CHECK3-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK3-NEXT:    store ptr [[TMP19]], ptr [[TMP23]], align 4
// CHECK3-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[TMP20]], ptr [[TMP24]], align 4
// CHECK3-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK3-NEXT:    store ptr @.offload_sizes.7, ptr [[TMP25]], align 4
// CHECK3-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK3-NEXT:    store ptr @.offload_maptypes.8, ptr [[TMP26]], align 4
// CHECK3-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK3-NEXT:    store ptr null, ptr [[TMP27]], align 4
// CHECK3-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK3-NEXT:    store ptr null, ptr [[TMP28]], align 4
// CHECK3-NEXT:    [[TMP29:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK3-NEXT:    store i64 0, ptr [[TMP29]], align 8
// CHECK3-NEXT:    [[TMP30:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK3-NEXT:    store i64 0, ptr [[TMP30]], align 8
// CHECK3-NEXT:    [[TMP31:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK3-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP31]], align 4
// CHECK3-NEXT:    [[TMP32:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK3-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP32]], align 4
// CHECK3-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK3-NEXT:    store i32 0, ptr [[TMP33]], align 4
// CHECK3-NEXT:    [[TMP34:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.region_id, ptr [[KERNEL_ARGS]])
// CHECK3-NEXT:    [[TMP35:%.*]] = icmp ne i32 [[TMP34]], 0
// CHECK3-NEXT:    br i1 [[TMP35]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK3:       omp_offload.failed:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198(i32 [[TMP1]], i32 [[TMP3]], i32 [[TMP5]], ptr [[B]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_OFFLOAD_CONT]]
// CHECK3:       omp_offload.cont:
// CHECK3-NEXT:    br label [[OMP_IF_END:%.*]]
// CHECK3:       omp_if.else:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198(i32 [[TMP1]], i32 [[TMP3]], i32 [[TMP5]], ptr [[B]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_IF_END]]
// CHECK3:       omp_if.end:
// CHECK3-NEXT:    [[TMP36:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    ret i32 [[TMP36]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z9ftemplateIiET_i
// CHECK3-SAME: (i32 noundef [[N:%.*]]) #[[ATTR0]] comdat {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[N_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA:%.*]] = alloca i16, align 2
// CHECK3-NEXT:    [[B:%.*]] = alloca [10 x i32], align 4
// CHECK3-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [3 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_PTRS:%.*]] = alloca [3 x ptr], align 4
// CHECK3-NEXT:    [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [3 x ptr], align 4
// CHECK3-NEXT:    [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK3-NEXT:    store i32 [[N]], ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    store i32 0, ptr [[A]], align 4
// CHECK3-NEXT:    store i16 0, ptr [[AA]], align 2
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA]], align 2
// CHECK3-NEXT:    store i16 [[TMP2]], ptr [[AA_CASTED]], align 2
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[N_ADDR]], align 4
// CHECK3-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP4]], 40
// CHECK3-NEXT:    br i1 [[CMP]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_ELSE:%.*]]
// CHECK3:       omp_if.then:
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[TMP5]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[TMP6]], align 4
// CHECK3-NEXT:    [[TMP7:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
// CHECK3-NEXT:    store ptr null, ptr [[TMP7]], align 4
// CHECK3-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 [[TMP3]], ptr [[TMP8]], align 4
// CHECK3-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 [[TMP3]], ptr [[TMP9]], align 4
// CHECK3-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 1
// CHECK3-NEXT:    store ptr null, ptr [[TMP10]], align 4
// CHECK3-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK3-NEXT:    store ptr [[B]], ptr [[TMP11]], align 4
// CHECK3-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK3-NEXT:    store ptr [[B]], ptr [[TMP12]], align 4
// CHECK3-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i32 0, i32 2
// CHECK3-NEXT:    store ptr null, ptr [[TMP13]], align 4
// CHECK3-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [3 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK3-NEXT:    store i32 2, ptr [[TMP16]], align 4
// CHECK3-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK3-NEXT:    store i32 3, ptr [[TMP17]], align 4
// CHECK3-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK3-NEXT:    store ptr [[TMP14]], ptr [[TMP18]], align 4
// CHECK3-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK3-NEXT:    store ptr [[TMP15]], ptr [[TMP19]], align 4
// CHECK3-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK3-NEXT:    store ptr @.offload_sizes.9, ptr [[TMP20]], align 4
// CHECK3-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK3-NEXT:    store ptr @.offload_maptypes.10, ptr [[TMP21]], align 4
// CHECK3-NEXT:    [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK3-NEXT:    store ptr null, ptr [[TMP22]], align 4
// CHECK3-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK3-NEXT:    store ptr null, ptr [[TMP23]], align 4
// CHECK3-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK3-NEXT:    store i64 0, ptr [[TMP24]], align 8
// CHECK3-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK3-NEXT:    store i64 0, ptr [[TMP25]], align 8
// CHECK3-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK3-NEXT:    store [3 x i32] [i32 1, i32 0, i32 0], ptr [[TMP26]], align 4
// CHECK3-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK3-NEXT:    store [3 x i32] zeroinitializer, ptr [[TMP27]], align 4
// CHECK3-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK3-NEXT:    store i32 0, ptr [[TMP28]], align 4
// CHECK3-NEXT:    [[TMP29:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.region_id, ptr [[KERNEL_ARGS]])
// CHECK3-NEXT:    [[TMP30:%.*]] = icmp ne i32 [[TMP29]], 0
// CHECK3-NEXT:    br i1 [[TMP30]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK3:       omp_offload.failed:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181(i32 [[TMP1]], i32 [[TMP3]], ptr [[B]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_OFFLOAD_CONT]]
// CHECK3:       omp_offload.cont:
// CHECK3-NEXT:    br label [[OMP_IF_END:%.*]]
// CHECK3:       omp_if.else:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181(i32 [[TMP1]], i32 [[TMP3]], ptr [[B]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[OMP_IF_END]]
// CHECK3:       omp_if.end:
// CHECK3-NEXT:    [[TMP31:%.*]] = load i32, ptr [[A]], align 4
// CHECK3-NEXT:    ret i32 [[TMP31]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216
// CHECK3-SAME: (ptr noundef [[THIS:%.*]], i32 noundef [[B:%.*]], i32 noundef [[VLA:%.*]], i32 noundef [[VLA1:%.*]], ptr noundef nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR2]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[B_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[B]], ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA]], ptr [[VLA_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA1]], ptr [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[THIS_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[VLA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, ptr [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[TMP4]], ptr [[B_CASTED]], align 4
// CHECK3-NEXT:    [[TMP5:%.*]] = load i32, ptr [[B_CASTED]], align 4
// CHECK3-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 5, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.omp_outlined, ptr [[TMP0]], i32 [[TMP5]], i32 [[TMP1]], i32 [[TMP2]], ptr [[TMP3]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.omp_outlined
// CHECK3-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], ptr noundef [[THIS:%.*]], i32 noundef [[B:%.*]], i32 noundef [[VLA:%.*]], i32 noundef [[VLA1:%.*]], ptr noundef nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[B]], ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA]], ptr [[VLA_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA1]], ptr [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[THIS_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[VLA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, ptr [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP4]] to double
// CHECK3-NEXT:    [[ADD:%.*]] = fadd double [[CONV]], 1.500000e+00
// CHECK3-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], ptr [[TMP0]], i32 0, i32 0
// CHECK3-NEXT:    store double [[ADD]], ptr [[A]], align 4
// CHECK3-NEXT:    [[A3:%.*]] = getelementptr inbounds [[STRUCT_S1]], ptr [[TMP0]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = load double, ptr [[A3]], align 4
// CHECK3-NEXT:    [[INC:%.*]] = fadd double [[TMP5]], 1.000000e+00
// CHECK3-NEXT:    store double [[INC]], ptr [[A3]], align 4
// CHECK3-NEXT:    [[CONV4:%.*]] = fptosi double [[INC]] to i16
// CHECK3-NEXT:    [[TMP6:%.*]] = mul nsw i32 1, [[TMP2]]
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[TMP3]], i32 [[TMP6]]
// CHECK3-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i16, ptr [[ARRAYIDX]], i32 1
// CHECK3-NEXT:    store i16 [[CONV4]], ptr [[ARRAYIDX5]], align 2
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198
// CHECK3-SAME: (i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]], i32 noundef [[AAA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR2]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AAA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AAA_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AAA]], ptr [[AAA_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    store i16 [[TMP3]], ptr [[AA_CASTED]], align 2
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK3-NEXT:    [[TMP5:%.*]] = load i8, ptr [[AAA_ADDR]], align 1
// CHECK3-NEXT:    store i8 [[TMP5]], ptr [[AAA_CASTED]], align 1
// CHECK3-NEXT:    [[TMP6:%.*]] = load i32, ptr [[AAA_CASTED]], align 4
// CHECK3-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 4, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.omp_outlined, i32 [[TMP2]], i32 [[TMP4]], i32 [[TMP6]], ptr [[TMP0]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.omp_outlined
// CHECK3-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]], i32 noundef [[AAA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AAA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AAA]], ptr [[AAA_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], 1
// CHECK3-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    [[CONV:%.*]] = sext i16 [[TMP2]] to i32
// CHECK3-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK3-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK3-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    [[TMP3:%.*]] = load i8, ptr [[AAA_ADDR]], align 1
// CHECK3-NEXT:    [[CONV3:%.*]] = sext i8 [[TMP3]] to i32
// CHECK3-NEXT:    [[ADD4:%.*]] = add nsw i32 [[CONV3]], 1
// CHECK3-NEXT:    [[CONV5:%.*]] = trunc i32 [[ADD4]] to i8
// CHECK3-NEXT:    store i8 [[CONV5]], ptr [[AAA_ADDR]], align 1
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], ptr [[TMP0]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK3-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP4]], 1
// CHECK3-NEXT:    store i32 [[ADD6]], ptr [[ARRAYIDX]], align 4
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181
// CHECK3-SAME: (i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR2]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[TMP1]], ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    store i16 [[TMP3]], ptr [[AA_CASTED]], align 2
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK3-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 3, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.omp_outlined, i32 [[TMP2]], i32 [[TMP4]], ptr [[TMP0]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.omp_outlined
// CHECK3-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK3-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK3-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], 1
// CHECK3-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    [[CONV:%.*]] = sext i16 [[TMP2]] to i32
// CHECK3-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK3-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK3-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], ptr [[TMP0]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK3-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK3-NEXT:    store i32 [[ADD3]], ptr [[ARRAYIDX]], align 4
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
// CHECK3-SAME: () #[[ATTR8:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    call void @__tgt_register_requires(i64 1)
// CHECK3-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100
// CHECK9-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1:[0-9]+]], i32 0, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.omp_outlined)
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.omp_outlined
// CHECK9-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110
// CHECK9-SAME: (i64 noundef [[AA:%.*]]) #[[ATTR0]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    store i16 [[TMP0]], ptr [[AA_CASTED]], align 2
// CHECK9-NEXT:    [[TMP1:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK9-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.omp_outlined, i64 [[TMP1]])
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.omp_outlined
// CHECK9-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[AA:%.*]]) #[[ATTR1]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK9-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    [[CONV:%.*]] = sext i16 [[TMP0]] to i32
// CHECK9-NEXT:    [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK9-NEXT:    [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK9-NEXT:    store i16 [[CONV1]], ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT:    [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4
// CHECK9-NEXT:    [[TMP3:%.*]] = call i32 @__kmpc_cancel(ptr @[[GLOB1]], i32 [[TMP2]], i32 1)
// CHECK9-NEXT:    [[TMP4:%.*]] = icmp ne i32 [[TMP3]], 0
// CHECK9-NEXT:    br i1 [[TMP4]], label [[DOTCANCEL_EXIT:%.*]], label [[DOTCANCEL_CONTINUE:%.*]]
// CHECK9:       .cancel.exit:
// CHECK9-NEXT:    [[TMP5:%.*]] = call i32 @__kmpc_cancel_barrier(ptr @[[GLOB2:[0-9]+]], i32 [[TMP2]])
// CHECK9-NEXT:    br label [[DOTCANCEL_CONTINUE]]
// CHECK9:       .cancel.continue:
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119
// CHECK9-SAME: (i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]]) #[[ATTR0]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK9-NEXT:    [[TMP1:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK9-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    store i16 [[TMP2]], ptr [[AA_CASTED]], align 2
// CHECK9-NEXT:    [[TMP3:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK9-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 2, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.omp_outlined, i64 [[TMP1]], i64 [[TMP3]])
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.omp_outlined
// CHECK9-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]]) #[[ATTR1]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK9-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 1
// CHECK9-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    [[TMP1:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK9-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK9-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK9-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144
// CHECK9-SAME: (i64 noundef [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[BN:%.*]], ptr noundef nonnull align 8 dereferenceable(400) [[C:%.*]], i64 noundef [[VLA1:%.*]], i64 noundef [[VLA3:%.*]], ptr noundef nonnull align 8 dereferenceable(8) [[CN:%.*]], ptr noundef nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR0]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[BN_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[VLA_ADDR2:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[VLA_ADDR4:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[CN_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[D_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[BN]], ptr [[BN_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[VLA1]], ptr [[VLA_ADDR2]], align 8
// CHECK9-NEXT:    store i64 [[VLA3]], ptr [[VLA_ADDR4]], align 8
// CHECK9-NEXT:    store ptr [[CN]], ptr [[CN_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[D]], ptr [[D_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK9-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[BN_ADDR]], align 8
// CHECK9-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 8
// CHECK9-NEXT:    [[TMP4:%.*]] = load i64, ptr [[VLA_ADDR2]], align 8
// CHECK9-NEXT:    [[TMP5:%.*]] = load i64, ptr [[VLA_ADDR4]], align 8
// CHECK9-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[CN_ADDR]], align 8
// CHECK9-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[D_ADDR]], align 8
// CHECK9-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    store i32 [[TMP8]], ptr [[A_CASTED]], align 4
// CHECK9-NEXT:    [[TMP9:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK9-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 9, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.omp_outlined, i64 [[TMP9]], ptr [[TMP0]], i64 [[TMP1]], ptr [[TMP2]], ptr [[TMP3]], i64 [[TMP4]], i64 [[TMP5]], ptr [[TMP6]], ptr [[TMP7]])
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.omp_outlined
// CHECK9-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[BN:%.*]], ptr noundef nonnull align 8 dereferenceable(400) [[C:%.*]], i64 noundef [[VLA1:%.*]], i64 noundef [[VLA3:%.*]], ptr noundef nonnull align 8 dereferenceable(8) [[CN:%.*]], ptr noundef nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR1]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[BN_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[VLA_ADDR2:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[VLA_ADDR4:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[CN_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[D_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK9-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[BN]], ptr [[BN_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[VLA1]], ptr [[VLA_ADDR2]], align 8
// CHECK9-NEXT:    store i64 [[VLA3]], ptr [[VLA_ADDR4]], align 8
// CHECK9-NEXT:    store ptr [[CN]], ptr [[CN_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[D]], ptr [[D_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK9-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[BN_ADDR]], align 8
// CHECK9-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 8
// CHECK9-NEXT:    [[TMP4:%.*]] = load i64, ptr [[VLA_ADDR2]], align 8
// CHECK9-NEXT:    [[TMP5:%.*]] = load i64, ptr [[VLA_ADDR4]], align 8
// CHECK9-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[CN_ADDR]], align 8
// CHECK9-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[D_ADDR]], align 8
// CHECK9-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP8]], 1
// CHECK9-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x float], ptr [[TMP0]], i64 0, i64 2
// CHECK9-NEXT:    [[TMP9:%.*]] = load float, ptr [[ARRAYIDX]], align 4
// CHECK9-NEXT:    [[CONV:%.*]] = fpext float [[TMP9]] to double
// CHECK9-NEXT:    [[ADD5:%.*]] = fadd double [[CONV]], 1.000000e+00
// CHECK9-NEXT:    [[CONV6:%.*]] = fptrunc double [[ADD5]] to float
// CHECK9-NEXT:    store float [[CONV6]], ptr [[ARRAYIDX]], align 4
// CHECK9-NEXT:    [[ARRAYIDX7:%.*]] = getelementptr inbounds float, ptr [[TMP2]], i64 3
// CHECK9-NEXT:    [[TMP10:%.*]] = load float, ptr [[ARRAYIDX7]], align 4
// CHECK9-NEXT:    [[CONV8:%.*]] = fpext float [[TMP10]] to double
// CHECK9-NEXT:    [[ADD9:%.*]] = fadd double [[CONV8]], 1.000000e+00
// CHECK9-NEXT:    [[CONV10:%.*]] = fptrunc double [[ADD9]] to float
// CHECK9-NEXT:    store float [[CONV10]], ptr [[ARRAYIDX7]], align 4
// CHECK9-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds [5 x [10 x double]], ptr [[TMP3]], i64 0, i64 1
// CHECK9-NEXT:    [[ARRAYIDX12:%.*]] = getelementptr inbounds [10 x double], ptr [[ARRAYIDX11]], i64 0, i64 2
// CHECK9-NEXT:    [[TMP11:%.*]] = load double, ptr [[ARRAYIDX12]], align 8
// CHECK9-NEXT:    [[ADD13:%.*]] = fadd double [[TMP11]], 1.000000e+00
// CHECK9-NEXT:    store double [[ADD13]], ptr [[ARRAYIDX12]], align 8
// CHECK9-NEXT:    [[TMP12:%.*]] = mul nsw i64 1, [[TMP5]]
// CHECK9-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds double, ptr [[TMP6]], i64 [[TMP12]]
// CHECK9-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr inbounds double, ptr [[ARRAYIDX14]], i64 3
// CHECK9-NEXT:    [[TMP13:%.*]] = load double, ptr [[ARRAYIDX15]], align 8
// CHECK9-NEXT:    [[ADD16:%.*]] = fadd double [[TMP13]], 1.000000e+00
// CHECK9-NEXT:    store double [[ADD16]], ptr [[ARRAYIDX15]], align 8
// CHECK9-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], ptr [[TMP7]], i32 0, i32 0
// CHECK9-NEXT:    [[TMP14:%.*]] = load i64, ptr [[X]], align 8
// CHECK9-NEXT:    [[ADD17:%.*]] = add nsw i64 [[TMP14]], 1
// CHECK9-NEXT:    store i64 [[ADD17]], ptr [[X]], align 8
// CHECK9-NEXT:    [[Y:%.*]] = getelementptr inbounds [[STRUCT_TT]], ptr [[TMP7]], i32 0, i32 1
// CHECK9-NEXT:    [[TMP15:%.*]] = load i8, ptr [[Y]], align 8
// CHECK9-NEXT:    [[CONV18:%.*]] = sext i8 [[TMP15]] to i32
// CHECK9-NEXT:    [[ADD19:%.*]] = add nsw i32 [[CONV18]], 1
// CHECK9-NEXT:    [[CONV20:%.*]] = trunc i32 [[ADD19]] to i8
// CHECK9-NEXT:    store i8 [[CONV20]], ptr [[Y]], align 8
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198
// CHECK9-SAME: (i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]], i64 noundef [[AAA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AAA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AAA_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[AAA]], ptr [[AAA_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    store i32 [[TMP1]], ptr [[A_CASTED]], align 4
// CHECK9-NEXT:    [[TMP2:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK9-NEXT:    [[TMP3:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    store i16 [[TMP3]], ptr [[AA_CASTED]], align 2
// CHECK9-NEXT:    [[TMP4:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK9-NEXT:    [[TMP5:%.*]] = load i8, ptr [[AAA_ADDR]], align 1
// CHECK9-NEXT:    store i8 [[TMP5]], ptr [[AAA_CASTED]], align 1
// CHECK9-NEXT:    [[TMP6:%.*]] = load i64, ptr [[AAA_CASTED]], align 8
// CHECK9-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 4, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.omp_outlined, i64 [[TMP2]], i64 [[TMP4]], i64 [[TMP6]], ptr [[TMP0]])
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.omp_outlined
// CHECK9-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]], i64 noundef [[AAA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR1]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AAA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK9-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[AAA]], ptr [[AAA_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], 1
// CHECK9-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    [[CONV:%.*]] = sext i16 [[TMP2]] to i32
// CHECK9-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK9-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK9-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    [[TMP3:%.*]] = load i8, ptr [[AAA_ADDR]], align 1
// CHECK9-NEXT:    [[CONV3:%.*]] = sext i8 [[TMP3]] to i32
// CHECK9-NEXT:    [[ADD4:%.*]] = add nsw i32 [[CONV3]], 1
// CHECK9-NEXT:    [[CONV5:%.*]] = trunc i32 [[ADD4]] to i8
// CHECK9-NEXT:    store i8 [[CONV5]], ptr [[AAA_ADDR]], align 1
// CHECK9-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], ptr [[TMP0]], i64 0, i64 2
// CHECK9-NEXT:    [[TMP4:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK9-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP4]], 1
// CHECK9-NEXT:    store i32 [[ADD6]], ptr [[ARRAYIDX]], align 4
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216
// CHECK9-SAME: (ptr noundef [[THIS:%.*]], i64 noundef [[B:%.*]], i64 noundef [[VLA:%.*]], i64 noundef [[VLA1:%.*]], ptr noundef nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR0]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[B_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[VLA_ADDR2:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[B_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[B]], ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[VLA1]], ptr [[VLA_ADDR2]], align 8
// CHECK9-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK9-NEXT:    [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK9-NEXT:    [[TMP2:%.*]] = load i64, ptr [[VLA_ADDR2]], align 8
// CHECK9-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 8
// CHECK9-NEXT:    [[TMP4:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK9-NEXT:    store i32 [[TMP4]], ptr [[B_CASTED]], align 4
// CHECK9-NEXT:    [[TMP5:%.*]] = load i64, ptr [[B_CASTED]], align 8
// CHECK9-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 5, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.omp_outlined, ptr [[TMP0]], i64 [[TMP5]], i64 [[TMP1]], i64 [[TMP2]], ptr [[TMP3]])
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.omp_outlined
// CHECK9-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], ptr noundef [[THIS:%.*]], i64 noundef [[B:%.*]], i64 noundef [[VLA:%.*]], i64 noundef [[VLA1:%.*]], ptr noundef nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR1]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[B_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[VLA_ADDR2:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK9-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[B]], ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[VLA1]], ptr [[VLA_ADDR2]], align 8
// CHECK9-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK9-NEXT:    [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK9-NEXT:    [[TMP2:%.*]] = load i64, ptr [[VLA_ADDR2]], align 8
// CHECK9-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 8
// CHECK9-NEXT:    [[TMP4:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK9-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP4]] to double
// CHECK9-NEXT:    [[ADD:%.*]] = fadd double [[CONV]], 1.500000e+00
// CHECK9-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], ptr [[TMP0]], i32 0, i32 0
// CHECK9-NEXT:    store double [[ADD]], ptr [[A]], align 8
// CHECK9-NEXT:    [[A3:%.*]] = getelementptr inbounds [[STRUCT_S1]], ptr [[TMP0]], i32 0, i32 0
// CHECK9-NEXT:    [[TMP5:%.*]] = load double, ptr [[A3]], align 8
// CHECK9-NEXT:    [[INC:%.*]] = fadd double [[TMP5]], 1.000000e+00
// CHECK9-NEXT:    store double [[INC]], ptr [[A3]], align 8
// CHECK9-NEXT:    [[CONV4:%.*]] = fptosi double [[INC]] to i16
// CHECK9-NEXT:    [[TMP6:%.*]] = mul nsw i64 1, [[TMP2]]
// CHECK9-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[TMP3]], i64 [[TMP6]]
// CHECK9-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i16, ptr [[ARRAYIDX]], i64 1
// CHECK9-NEXT:    store i16 [[CONV4]], ptr [[ARRAYIDX5]], align 2
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181
// CHECK9-SAME: (i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    store i32 [[TMP1]], ptr [[A_CASTED]], align 4
// CHECK9-NEXT:    [[TMP2:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK9-NEXT:    [[TMP3:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    store i16 [[TMP3]], ptr [[AA_CASTED]], align 2
// CHECK9-NEXT:    [[TMP4:%.*]] = load i64, ptr [[AA_CASTED]], align 8
// CHECK9-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 3, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.omp_outlined, i64 [[TMP2]], i64 [[TMP4]], ptr [[TMP0]])
// CHECK9-NEXT:    ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.omp_outlined
// CHECK9-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[A:%.*]], i64 noundef [[AA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR1]] {
// CHECK9-NEXT:  entry:
// CHECK9-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK9-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK9-NEXT:    store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK9-NEXT:    store i64 [[AA]], ptr [[AA_ADDR]], align 8
// CHECK9-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK9-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], 1
// CHECK9-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK9-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    [[CONV:%.*]] = sext i16 [[TMP2]] to i32
// CHECK9-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK9-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK9-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK9-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], ptr [[TMP0]], i64 0, i64 2
// CHECK9-NEXT:    [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK9-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK9-NEXT:    store i32 [[ADD3]], ptr [[ARRAYIDX]], align 4
// CHECK9-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100
// CHECK11-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1:[0-9]+]], i32 0, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.omp_outlined)
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l100.omp_outlined
// CHECK11-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110
// CHECK11-SAME: (i32 noundef [[AA:%.*]]) #[[ATTR0]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    store i16 [[TMP0]], ptr [[AA_CASTED]], align 2
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK11-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.omp_outlined, i32 [[TMP1]])
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l110.omp_outlined
// CHECK11-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[AA:%.*]]) #[[ATTR1]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK11-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    [[CONV:%.*]] = sext i16 [[TMP0]] to i32
// CHECK11-NEXT:    [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK11-NEXT:    [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK11-NEXT:    store i16 [[CONV1]], ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4
// CHECK11-NEXT:    [[TMP3:%.*]] = call i32 @__kmpc_cancel(ptr @[[GLOB1]], i32 [[TMP2]], i32 1)
// CHECK11-NEXT:    [[TMP4:%.*]] = icmp ne i32 [[TMP3]], 0
// CHECK11-NEXT:    br i1 [[TMP4]], label [[DOTCANCEL_EXIT:%.*]], label [[DOTCANCEL_CONTINUE:%.*]]
// CHECK11:       .cancel.exit:
// CHECK11-NEXT:    [[TMP5:%.*]] = call i32 @__kmpc_cancel_barrier(ptr @[[GLOB2:[0-9]+]], i32 [[TMP2]])
// CHECK11-NEXT:    br label [[DOTCANCEL_CONTINUE]]
// CHECK11:       .cancel.continue:
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119
// CHECK11-SAME: (i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]]) #[[ATTR0]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[TMP0]], ptr [[A_CASTED]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    store i16 [[TMP2]], ptr [[AA_CASTED]], align 2
// CHECK11-NEXT:    [[TMP3:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK11-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 2, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.omp_outlined, i32 [[TMP1]], i32 [[TMP3]])
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l119.omp_outlined
// CHECK11-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]]) #[[ATTR1]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK11-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], 1
// CHECK11-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK11-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK11-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK11-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144
// CHECK11-SAME: (i32 noundef [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]], i32 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[BN:%.*]], ptr noundef nonnull align 4 dereferenceable(400) [[C:%.*]], i32 noundef [[VLA1:%.*]], i32 noundef [[VLA3:%.*]], ptr noundef nonnull align 4 dereferenceable(8) [[CN:%.*]], ptr noundef nonnull align 4 dereferenceable(12) [[D:%.*]]) #[[ATTR0]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[BN_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[VLA_ADDR4:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[CN_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[D_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[VLA]], ptr [[VLA_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[BN]], ptr [[BN_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[VLA1]], ptr [[VLA_ADDR2]], align 4
// CHECK11-NEXT:    store i32 [[VLA3]], ptr [[VLA_ADDR4]], align 4
// CHECK11-NEXT:    store ptr [[CN]], ptr [[CN_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[D]], ptr [[D_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[VLA_ADDR]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[BN_ADDR]], align 4
// CHECK11-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 4
// CHECK11-NEXT:    [[TMP4:%.*]] = load i32, ptr [[VLA_ADDR2]], align 4
// CHECK11-NEXT:    [[TMP5:%.*]] = load i32, ptr [[VLA_ADDR4]], align 4
// CHECK11-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[CN_ADDR]], align 4
// CHECK11-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[D_ADDR]], align 4
// CHECK11-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[TMP8]], ptr [[A_CASTED]], align 4
// CHECK11-NEXT:    [[TMP9:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK11-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 9, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.omp_outlined, i32 [[TMP9]], ptr [[TMP0]], i32 [[TMP1]], ptr [[TMP2]], ptr [[TMP3]], i32 [[TMP4]], i32 [[TMP5]], ptr [[TMP6]], ptr [[TMP7]])
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l144.omp_outlined
// CHECK11-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]], i32 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[BN:%.*]], ptr noundef nonnull align 4 dereferenceable(400) [[C:%.*]], i32 noundef [[VLA1:%.*]], i32 noundef [[VLA3:%.*]], ptr noundef nonnull align 4 dereferenceable(8) [[CN:%.*]], ptr noundef nonnull align 4 dereferenceable(12) [[D:%.*]]) #[[ATTR1]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[BN_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[VLA_ADDR4:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[CN_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[D_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK11-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[VLA]], ptr [[VLA_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[BN]], ptr [[BN_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[VLA1]], ptr [[VLA_ADDR2]], align 4
// CHECK11-NEXT:    store i32 [[VLA3]], ptr [[VLA_ADDR4]], align 4
// CHECK11-NEXT:    store ptr [[CN]], ptr [[CN_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[D]], ptr [[D_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[VLA_ADDR]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[BN_ADDR]], align 4
// CHECK11-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 4
// CHECK11-NEXT:    [[TMP4:%.*]] = load i32, ptr [[VLA_ADDR2]], align 4
// CHECK11-NEXT:    [[TMP5:%.*]] = load i32, ptr [[VLA_ADDR4]], align 4
// CHECK11-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[CN_ADDR]], align 4
// CHECK11-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[D_ADDR]], align 4
// CHECK11-NEXT:    [[TMP8:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP8]], 1
// CHECK11-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x float], ptr [[TMP0]], i32 0, i32 2
// CHECK11-NEXT:    [[TMP9:%.*]] = load float, ptr [[ARRAYIDX]], align 4
// CHECK11-NEXT:    [[CONV:%.*]] = fpext float [[TMP9]] to double
// CHECK11-NEXT:    [[ADD5:%.*]] = fadd double [[CONV]], 1.000000e+00
// CHECK11-NEXT:    [[CONV6:%.*]] = fptrunc double [[ADD5]] to float
// CHECK11-NEXT:    store float [[CONV6]], ptr [[ARRAYIDX]], align 4
// CHECK11-NEXT:    [[ARRAYIDX7:%.*]] = getelementptr inbounds float, ptr [[TMP2]], i32 3
// CHECK11-NEXT:    [[TMP10:%.*]] = load float, ptr [[ARRAYIDX7]], align 4
// CHECK11-NEXT:    [[CONV8:%.*]] = fpext float [[TMP10]] to double
// CHECK11-NEXT:    [[ADD9:%.*]] = fadd double [[CONV8]], 1.000000e+00
// CHECK11-NEXT:    [[CONV10:%.*]] = fptrunc double [[ADD9]] to float
// CHECK11-NEXT:    store float [[CONV10]], ptr [[ARRAYIDX7]], align 4
// CHECK11-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds [5 x [10 x double]], ptr [[TMP3]], i32 0, i32 1
// CHECK11-NEXT:    [[ARRAYIDX12:%.*]] = getelementptr inbounds [10 x double], ptr [[ARRAYIDX11]], i32 0, i32 2
// CHECK11-NEXT:    [[TMP11:%.*]] = load double, ptr [[ARRAYIDX12]], align 8
// CHECK11-NEXT:    [[ADD13:%.*]] = fadd double [[TMP11]], 1.000000e+00
// CHECK11-NEXT:    store double [[ADD13]], ptr [[ARRAYIDX12]], align 8
// CHECK11-NEXT:    [[TMP12:%.*]] = mul nsw i32 1, [[TMP5]]
// CHECK11-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds double, ptr [[TMP6]], i32 [[TMP12]]
// CHECK11-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr inbounds double, ptr [[ARRAYIDX14]], i32 3
// CHECK11-NEXT:    [[TMP13:%.*]] = load double, ptr [[ARRAYIDX15]], align 8
// CHECK11-NEXT:    [[ADD16:%.*]] = fadd double [[TMP13]], 1.000000e+00
// CHECK11-NEXT:    store double [[ADD16]], ptr [[ARRAYIDX15]], align 8
// CHECK11-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], ptr [[TMP7]], i32 0, i32 0
// CHECK11-NEXT:    [[TMP14:%.*]] = load i64, ptr [[X]], align 4
// CHECK11-NEXT:    [[ADD17:%.*]] = add nsw i64 [[TMP14]], 1
// CHECK11-NEXT:    store i64 [[ADD17]], ptr [[X]], align 4
// CHECK11-NEXT:    [[Y:%.*]] = getelementptr inbounds [[STRUCT_TT]], ptr [[TMP7]], i32 0, i32 1
// CHECK11-NEXT:    [[TMP15:%.*]] = load i8, ptr [[Y]], align 4
// CHECK11-NEXT:    [[CONV18:%.*]] = sext i8 [[TMP15]] to i32
// CHECK11-NEXT:    [[ADD19:%.*]] = add nsw i32 [[CONV18]], 1
// CHECK11-NEXT:    [[CONV20:%.*]] = trunc i32 [[ADD19]] to i8
// CHECK11-NEXT:    store i8 [[CONV20]], ptr [[Y]], align 4
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198
// CHECK11-SAME: (i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]], i32 noundef [[AAA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AAA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AAA_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[AAA]], ptr [[AAA_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[TMP1]], ptr [[A_CASTED]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK11-NEXT:    [[TMP3:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    store i16 [[TMP3]], ptr [[AA_CASTED]], align 2
// CHECK11-NEXT:    [[TMP4:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK11-NEXT:    [[TMP5:%.*]] = load i8, ptr [[AAA_ADDR]], align 1
// CHECK11-NEXT:    store i8 [[TMP5]], ptr [[AAA_CASTED]], align 1
// CHECK11-NEXT:    [[TMP6:%.*]] = load i32, ptr [[AAA_CASTED]], align 4
// CHECK11-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 4, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.omp_outlined, i32 [[TMP2]], i32 [[TMP4]], i32 [[TMP6]], ptr [[TMP0]])
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l198.omp_outlined
// CHECK11-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]], i32 noundef [[AAA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR1]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AAA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK11-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[AAA]], ptr [[AAA_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], 1
// CHECK11-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    [[CONV:%.*]] = sext i16 [[TMP2]] to i32
// CHECK11-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK11-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK11-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    [[TMP3:%.*]] = load i8, ptr [[AAA_ADDR]], align 1
// CHECK11-NEXT:    [[CONV3:%.*]] = sext i8 [[TMP3]] to i32
// CHECK11-NEXT:    [[ADD4:%.*]] = add nsw i32 [[CONV3]], 1
// CHECK11-NEXT:    [[CONV5:%.*]] = trunc i32 [[ADD4]] to i8
// CHECK11-NEXT:    store i8 [[CONV5]], ptr [[AAA_ADDR]], align 1
// CHECK11-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], ptr [[TMP0]], i32 0, i32 2
// CHECK11-NEXT:    [[TMP4:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK11-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP4]], 1
// CHECK11-NEXT:    store i32 [[ADD6]], ptr [[ARRAYIDX]], align 4
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216
// CHECK11-SAME: (ptr noundef [[THIS:%.*]], i32 noundef [[B:%.*]], i32 noundef [[VLA:%.*]], i32 noundef [[VLA1:%.*]], ptr noundef nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR0]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[B_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[B]], ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[VLA]], ptr [[VLA_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[VLA1]], ptr [[VLA_ADDR2]], align 4
// CHECK11-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[THIS_ADDR]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[VLA_ADDR]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load i32, ptr [[VLA_ADDR2]], align 4
// CHECK11-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 4
// CHECK11-NEXT:    [[TMP4:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[TMP4]], ptr [[B_CASTED]], align 4
// CHECK11-NEXT:    [[TMP5:%.*]] = load i32, ptr [[B_CASTED]], align 4
// CHECK11-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 5, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.omp_outlined, ptr [[TMP0]], i32 [[TMP5]], i32 [[TMP1]], i32 [[TMP2]], ptr [[TMP3]])
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l216.omp_outlined
// CHECK11-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], ptr noundef [[THIS:%.*]], i32 noundef [[B:%.*]], i32 noundef [[VLA:%.*]], i32 noundef [[VLA1:%.*]], ptr noundef nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR1]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[C_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK11-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[B]], ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[VLA]], ptr [[VLA_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[VLA1]], ptr [[VLA_ADDR2]], align 4
// CHECK11-NEXT:    store ptr [[C]], ptr [[C_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[THIS_ADDR]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[VLA_ADDR]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load i32, ptr [[VLA_ADDR2]], align 4
// CHECK11-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[C_ADDR]], align 4
// CHECK11-NEXT:    [[TMP4:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP4]] to double
// CHECK11-NEXT:    [[ADD:%.*]] = fadd double [[CONV]], 1.500000e+00
// CHECK11-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], ptr [[TMP0]], i32 0, i32 0
// CHECK11-NEXT:    store double [[ADD]], ptr [[A]], align 4
// CHECK11-NEXT:    [[A3:%.*]] = getelementptr inbounds [[STRUCT_S1]], ptr [[TMP0]], i32 0, i32 0
// CHECK11-NEXT:    [[TMP5:%.*]] = load double, ptr [[A3]], align 4
// CHECK11-NEXT:    [[INC:%.*]] = fadd double [[TMP5]], 1.000000e+00
// CHECK11-NEXT:    store double [[INC]], ptr [[A3]], align 4
// CHECK11-NEXT:    [[CONV4:%.*]] = fptosi double [[INC]] to i16
// CHECK11-NEXT:    [[TMP6:%.*]] = mul nsw i32 1, [[TMP2]]
// CHECK11-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[TMP3]], i32 [[TMP6]]
// CHECK11-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i16, ptr [[ARRAYIDX]], i32 1
// CHECK11-NEXT:    store i16 [[CONV4]], ptr [[ARRAYIDX5]], align 2
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181
// CHECK11-SAME: (i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[A_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_CASTED:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[TMP1]], ptr [[A_CASTED]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load i32, ptr [[A_CASTED]], align 4
// CHECK11-NEXT:    [[TMP3:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    store i16 [[TMP3]], ptr [[AA_CASTED]], align 2
// CHECK11-NEXT:    [[TMP4:%.*]] = load i32, ptr [[AA_CASTED]], align 4
// CHECK11-NEXT:    call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 3, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.omp_outlined, i32 [[TMP2]], i32 [[TMP4]], ptr [[TMP0]])
// CHECK11-NEXT:    ret void
//
//
// CHECK11-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l181.omp_outlined
// CHECK11-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[A:%.*]], i32 noundef [[AA:%.*]], ptr noundef nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR1]] {
// CHECK11-NEXT:  entry:
// CHECK11-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK11-NEXT:    [[B_ADDR:%.*]] = alloca ptr, align 4
// CHECK11-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 4
// CHECK11-NEXT:    store i32 [[A]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    store i32 [[AA]], ptr [[AA_ADDR]], align 4
// CHECK11-NEXT:    store ptr [[B]], ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 4
// CHECK11-NEXT:    [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], 1
// CHECK11-NEXT:    store i32 [[ADD]], ptr [[A_ADDR]], align 4
// CHECK11-NEXT:    [[TMP2:%.*]] = load i16, ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    [[CONV:%.*]] = sext i16 [[TMP2]] to i32
// CHECK11-NEXT:    [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK11-NEXT:    [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK11-NEXT:    store i16 [[CONV2]], ptr [[AA_ADDR]], align 2
// CHECK11-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], ptr [[TMP0]], i32 0, i32 2
// CHECK11-NEXT:    [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK11-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK11-NEXT:    store i32 [[ADD3]], ptr [[ARRAYIDX]], align 4
// CHECK11-NEXT:    ret void
//