// 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 target codegen - host bc file has to be created first.
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK2
// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK3
// expected-no-diagnostics

#ifndef HEADER
#define HEADER

__thread int id;

int baz(int f, double &a);

template <typename tx, typename ty>
struct TT {
  tx X;
  ty Y;
  tx &operator[](int i) { return X; }
};

void targetBar(int *Ptr1, int *Ptr2) {
#pragma omp target map(Ptr1[:0], Ptr2)
#pragma omp parallel num_threads(2)
  *Ptr1 = *Ptr2;
}

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
  {
  }

#pragma omp target if (0)
  {
  }

#pragma omp target if (1)
  {
    aa += 1;
    aa += 2;
  }

#pragma omp target if (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;
    d[0] += 1;
  }

  return a;
}

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

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

int baz(int f, double &a) {
#pragma omp parallel
  f = 2 + a;
  return f;
}

extern void assert(int) throw() __attribute__((__noreturn__));
void unreachable_call() {
#pragma omp target
    assert(0);
}

#endif
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9targetBarPiS__l25
// CHECK1-SAME: (i32* [[PTR1:%.*]], i32** nonnull align 8 dereferenceable(8) [[PTR2:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[PTR1_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[PTR2_ADDR:%.*]] = alloca i32**, align 8
// CHECK1-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [2 x i8*], align 8
// CHECK1-NEXT:    store i32* [[PTR1]], i32** [[PTR1_ADDR]], align 8
// CHECK1-NEXT:    store i32** [[PTR2]], i32*** [[PTR2_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32**, i32*** [[PTR2_ADDR]], align 8
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK1-NEXT:    call void @__kmpc_data_sharing_init_stack_spmd()
// CHECK1-NEXT:    br label [[DOTEXECUTE:%.*]]
// CHECK1:       .execute:
// CHECK1-NEXT:    [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK1-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP3:%.*]] = bitcast i32** [[PTR1_ADDR]] to i8*
// CHECK1-NEXT:    store i8* [[TMP3]], i8** [[TMP2]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 1
// CHECK1-NEXT:    [[TMP5:%.*]] = bitcast i32** [[TMP0]] to i8*
// CHECK1-NEXT:    store i8* [[TMP5]], i8** [[TMP4]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = bitcast [2 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK1-NEXT:    call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32**, i32**)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP6]], i64 2)
// CHECK1-NEXT:    br label [[DOTOMP_DEINIT:%.*]]
// CHECK1:       .omp.deinit:
// CHECK1-NEXT:    call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK1-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32** nonnull align 8 dereferenceable(8) [[PTR1:%.*]], i32** nonnull align 8 dereferenceable(8) [[PTR2:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[PTR1_ADDR:%.*]] = alloca i32**, align 8
// CHECK1-NEXT:    [[PTR2_ADDR:%.*]] = alloca i32**, align 8
// CHECK1-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store i32** [[PTR1]], i32*** [[PTR1_ADDR]], align 8
// CHECK1-NEXT:    store i32** [[PTR2]], i32*** [[PTR2_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32**, i32*** [[PTR1_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32**, i32*** [[PTR2_ADDR]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32*, i32** [[TMP1]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32*, i32** [[TMP0]], align 8
// CHECK1-NEXT:    store i32 [[TMP3]], i32* [[TMP4]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39_worker
// CHECK1-SAME: () #[[ATTR3:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    store i8* null, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK1:       .await.work:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK1-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK1-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK1-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK1:       .select.workers:
// CHECK1-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK1:       .execute.parallel:
// CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2:[0-9]+]])
// CHECK1-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK1-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK1-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK1:       .terminate.parallel:
// CHECK1-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK1-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK1:       .barrier.parallel:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39
// CHECK1-SAME: () #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK1-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK1-NEXT:    br i1 [[TMP0]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK1:       .worker:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39_worker() #[[ATTR2:[0-9]+]]
// CHECK1-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK1:       .mastercheck:
// CHECK1-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[TMP1:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK1-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK1-NEXT:    [[TMP3:%.*]] = xor i32 [[TMP1]], -1
// CHECK1-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP2]], [[TMP3]]
// CHECK1-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK1-NEXT:    br i1 [[TMP4]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK1:       .master:
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK1-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK1-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK1-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK1:       .termination.notifier:
// CHECK1-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTEXIT]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47_worker
// CHECK1-SAME: () #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    store i8* null, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK1:       .await.work:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK1-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK1-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK1-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK1:       .select.workers:
// CHECK1-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK1:       .execute.parallel:
// CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK1-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK1-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK1-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK1:       .terminate.parallel:
// CHECK1-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK1-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK1:       .barrier.parallel:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47
// CHECK1-SAME: (i64 [[AA:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    store i64 [[AA]], i64* [[AA_ADDR]], align 8
// CHECK1-NEXT:    [[CONV:%.*]] = bitcast i64* [[AA_ADDR]] to i16*
// CHECK1-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK1-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK1-NEXT:    br i1 [[TMP0]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK1:       .worker:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47_worker() #[[ATTR2]]
// CHECK1-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK1:       .mastercheck:
// CHECK1-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[TMP1:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK1-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK1-NEXT:    [[TMP3:%.*]] = xor i32 [[TMP1]], -1
// CHECK1-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP2]], [[TMP3]]
// CHECK1-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK1-NEXT:    br i1 [[TMP4]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK1:       .master:
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK1-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK1-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK1-NEXT:    [[TMP5:%.*]] = load i16, i16* [[CONV]], align 8
// CHECK1-NEXT:    [[CONV7:%.*]] = sext i16 [[TMP5]] to i32
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[CONV7]], 1
// CHECK1-NEXT:    [[CONV8:%.*]] = trunc i32 [[ADD]] to i16
// CHECK1-NEXT:    store i16 [[CONV8]], i16* [[CONV]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = load i16, i16* [[CONV]], align 8
// CHECK1-NEXT:    [[CONV9:%.*]] = sext i16 [[TMP6]] to i32
// CHECK1-NEXT:    [[ADD10:%.*]] = add nsw i32 [[CONV9]], 2
// CHECK1-NEXT:    [[CONV11:%.*]] = trunc i32 [[ADD10]] to i16
// CHECK1-NEXT:    store i16 [[CONV11]], i16* [[CONV]], align 8
// CHECK1-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK1:       .termination.notifier:
// CHECK1-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTEXIT]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53_worker
// CHECK1-SAME: () #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    store i8* null, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK1:       .await.work:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK1-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK1-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK1-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK1:       .select.workers:
// CHECK1-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK1:       .execute.parallel:
// CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK1-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK1-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK1-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK1:       .terminate.parallel:
// CHECK1-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK1-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK1:       .barrier.parallel:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53
// CHECK1-SAME: (i64 [[A:%.*]], [10 x float]* nonnull align 4 dereferenceable(40) [[B:%.*]], i64 [[VLA:%.*]], float* nonnull align 4 dereferenceable(4) [[BN:%.*]], [5 x [10 x double]]* nonnull align 8 dereferenceable(400) [[C:%.*]], i64 [[VLA1:%.*]], i64 [[VLA3:%.*]], double* nonnull align 8 dereferenceable(8) [[CN:%.*]], %struct.TT* nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca [10 x float]*, align 8
// CHECK1-NEXT:    [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[BN_ADDR:%.*]] = alloca float*, align 8
// CHECK1-NEXT:    [[C_ADDR:%.*]] = alloca [5 x [10 x double]]*, align 8
// CHECK1-NEXT:    [[VLA_ADDR2:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[VLA_ADDR4:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[CN_ADDR:%.*]] = alloca double*, align 8
// CHECK1-NEXT:    [[D_ADDR:%.*]] = alloca %struct.TT*, align 8
// CHECK1-NEXT:    store i64 [[A]], i64* [[A_ADDR]], align 8
// CHECK1-NEXT:    store [10 x float]* [[B]], [10 x float]** [[B_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA]], i64* [[VLA_ADDR]], align 8
// CHECK1-NEXT:    store float* [[BN]], float** [[BN_ADDR]], align 8
// CHECK1-NEXT:    store [5 x [10 x double]]* [[C]], [5 x [10 x double]]** [[C_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA1]], i64* [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    store i64 [[VLA3]], i64* [[VLA_ADDR4]], align 8
// CHECK1-NEXT:    store double* [[CN]], double** [[CN_ADDR]], align 8
// CHECK1-NEXT:    store %struct.TT* [[D]], %struct.TT** [[D_ADDR]], align 8
// CHECK1-NEXT:    [[CONV:%.*]] = bitcast i64* [[A_ADDR]] to i32*
// CHECK1-NEXT:    [[TMP0:%.*]] = load [10 x float]*, [10 x float]** [[B_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, i64* [[VLA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load float*, float** [[BN_ADDR]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load [5 x [10 x double]]*, [5 x [10 x double]]** [[C_ADDR]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load i64, i64* [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = load i64, i64* [[VLA_ADDR4]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = load double*, double** [[CN_ADDR]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = load %struct.TT*, %struct.TT** [[D_ADDR]], align 8
// CHECK1-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK1-NEXT:    [[TMP8:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK1-NEXT:    br i1 [[TMP8]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK1:       .worker:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53_worker() #[[ATTR2]]
// CHECK1-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK1:       .mastercheck:
// CHECK1-NEXT:    [[NVPTX_TID5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE7:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[TMP9:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE7]], 1
// CHECK1-NEXT:    [[TMP10:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS6]], 1
// CHECK1-NEXT:    [[TMP11:%.*]] = xor i32 [[TMP9]], -1
// CHECK1-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP10]], [[TMP11]]
// CHECK1-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[NVPTX_TID5]], [[MASTER_TID]]
// CHECK1-NEXT:    br i1 [[TMP12]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK1:       .master:
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS8:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE9:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT10:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS8]], [[NVPTX_WARP_SIZE9]]
// CHECK1-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT10]], i16 1)
// CHECK1-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP13]], 1
// CHECK1-NEXT:    store i32 [[ADD]], i32* [[CONV]], align 8
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x float], [10 x float]* [[TMP0]], i64 0, i64 2
// CHECK1-NEXT:    [[TMP14:%.*]] = load float, float* [[ARRAYIDX]], align 4
// CHECK1-NEXT:    [[CONV11:%.*]] = fpext float [[TMP14]] to double
// CHECK1-NEXT:    [[ADD12:%.*]] = fadd double [[CONV11]], 1.000000e+00
// CHECK1-NEXT:    [[CONV13:%.*]] = fptrunc double [[ADD12]] to float
// CHECK1-NEXT:    store float [[CONV13]], float* [[ARRAYIDX]], align 4
// CHECK1-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds float, float* [[TMP2]], i64 3
// CHECK1-NEXT:    [[TMP15:%.*]] = load float, float* [[ARRAYIDX14]], align 4
// CHECK1-NEXT:    [[CONV15:%.*]] = fpext float [[TMP15]] to double
// CHECK1-NEXT:    [[ADD16:%.*]] = fadd double [[CONV15]], 1.000000e+00
// CHECK1-NEXT:    [[CONV17:%.*]] = fptrunc double [[ADD16]] to float
// CHECK1-NEXT:    store float [[CONV17]], float* [[ARRAYIDX14]], align 4
// CHECK1-NEXT:    [[ARRAYIDX18:%.*]] = getelementptr inbounds [5 x [10 x double]], [5 x [10 x double]]* [[TMP3]], i64 0, i64 1
// CHECK1-NEXT:    [[ARRAYIDX19:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYIDX18]], i64 0, i64 2
// CHECK1-NEXT:    [[TMP16:%.*]] = load double, double* [[ARRAYIDX19]], align 8
// CHECK1-NEXT:    [[ADD20:%.*]] = fadd double [[TMP16]], 1.000000e+00
// CHECK1-NEXT:    store double [[ADD20]], double* [[ARRAYIDX19]], align 8
// CHECK1-NEXT:    [[TMP17:%.*]] = mul nsw i64 1, [[TMP5]]
// CHECK1-NEXT:    [[ARRAYIDX21:%.*]] = getelementptr inbounds double, double* [[TMP6]], i64 [[TMP17]]
// CHECK1-NEXT:    [[ARRAYIDX22:%.*]] = getelementptr inbounds double, double* [[ARRAYIDX21]], i64 3
// CHECK1-NEXT:    [[TMP18:%.*]] = load double, double* [[ARRAYIDX22]], align 8
// CHECK1-NEXT:    [[ADD23:%.*]] = fadd double [[TMP18]], 1.000000e+00
// CHECK1-NEXT:    store double [[ADD23]], double* [[ARRAYIDX22]], align 8
// CHECK1-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], %struct.TT* [[TMP7]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP19:%.*]] = load i64, i64* [[X]], align 8
// CHECK1-NEXT:    [[ADD24:%.*]] = add nsw i64 [[TMP19]], 1
// CHECK1-NEXT:    store i64 [[ADD24]], i64* [[X]], align 8
// CHECK1-NEXT:    [[Y:%.*]] = getelementptr inbounds [[STRUCT_TT]], %struct.TT* [[TMP7]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP20:%.*]] = load i8, i8* [[Y]], align 8
// CHECK1-NEXT:    [[CONV25:%.*]] = sext i8 [[TMP20]] to i32
// CHECK1-NEXT:    [[ADD26:%.*]] = add nsw i32 [[CONV25]], 1
// CHECK1-NEXT:    [[CONV27:%.*]] = trunc i32 [[ADD26]] to i8
// CHECK1-NEXT:    store i8 [[CONV27]], i8* [[Y]], align 8
// CHECK1-NEXT:    [[CALL:%.*]] = call nonnull align 8 dereferenceable(8) i64* @_ZN2TTIxcEixEi(%struct.TT* nonnull dereferenceable(16) [[TMP7]], i32 0) #[[ATTR7:[0-9]+]]
// CHECK1-NEXT:    [[TMP21:%.*]] = load i64, i64* [[CALL]], align 8
// CHECK1-NEXT:    [[ADD28:%.*]] = add nsw i64 [[TMP21]], 1
// CHECK1-NEXT:    store i64 [[ADD28]], i64* [[CALL]], align 8
// CHECK1-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK1:       .termination.notifier:
// CHECK1-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTEXIT]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2TTIxcEixEi
// CHECK1-SAME: (%struct.TT* nonnull dereferenceable(16) [[THIS:%.*]], i32 [[I:%.*]]) #[[ATTR5:[0-9]+]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.TT*, align 8
// CHECK1-NEXT:    [[I_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    store %struct.TT* [[THIS]], %struct.TT** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i32 [[I]], i32* [[I_ADDR]], align 4
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.TT*, %struct.TT** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], %struct.TT* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    ret i64* [[X]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90_worker
// CHECK1-SAME: () #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    store i8* null, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK1:       .await.work:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK1-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK1-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK1-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK1:       .select.workers:
// CHECK1-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK1:       .execute.parallel:
// CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK1-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK1-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK1-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK1:       .terminate.parallel:
// CHECK1-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK1-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK1:       .barrier.parallel:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90
// CHECK1-SAME: (i64 [[A:%.*]], i64 [[AA:%.*]], i64 [[AAA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// 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 [10 x i32]*, align 8
// CHECK1-NEXT:    store i64 [[A]], i64* [[A_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AA]], i64* [[AA_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AAA]], i64* [[AAA_ADDR]], align 8
// CHECK1-NEXT:    store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 8
// CHECK1-NEXT:    [[CONV:%.*]] = bitcast i64* [[A_ADDR]] to i32*
// CHECK1-NEXT:    [[CONV1:%.*]] = bitcast i64* [[AA_ADDR]] to i16*
// CHECK1-NEXT:    [[CONV2:%.*]] = bitcast i64* [[AAA_ADDR]] to i8*
// CHECK1-NEXT:    [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 8
// CHECK1-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK1-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK1-NEXT:    br i1 [[TMP1]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK1:       .worker:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90_worker() #[[ATTR2]]
// CHECK1-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK1:       .mastercheck:
// CHECK1-NEXT:    [[NVPTX_TID3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE5]], 1
// CHECK1-NEXT:    [[TMP3:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], 1
// CHECK1-NEXT:    [[TMP4:%.*]] = xor i32 [[TMP2]], -1
// CHECK1-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP3]], [[TMP4]]
// CHECK1-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[NVPTX_TID3]], [[MASTER_TID]]
// CHECK1-NEXT:    br i1 [[TMP5]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK1:       .master:
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE7:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT8:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS6]], [[NVPTX_WARP_SIZE7]]
// CHECK1-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT8]], i16 1)
// CHECK1-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP6]], 1
// CHECK1-NEXT:    store i32 [[ADD]], i32* [[CONV]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = load i16, i16* [[CONV1]], align 8
// CHECK1-NEXT:    [[CONV9:%.*]] = sext i16 [[TMP7]] to i32
// CHECK1-NEXT:    [[ADD10:%.*]] = add nsw i32 [[CONV9]], 1
// CHECK1-NEXT:    [[CONV11:%.*]] = trunc i32 [[ADD10]] to i16
// CHECK1-NEXT:    store i16 [[CONV11]], i16* [[CONV1]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = load i8, i8* [[CONV2]], align 8
// CHECK1-NEXT:    [[CONV12:%.*]] = sext i8 [[TMP8]] to i32
// CHECK1-NEXT:    [[ADD13:%.*]] = add nsw i32 [[CONV12]], 1
// CHECK1-NEXT:    [[CONV14:%.*]] = trunc i32 [[ADD13]] to i8
// CHECK1-NEXT:    store i8 [[CONV14]], i8* [[CONV2]], align 8
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i64 0, i64 2
// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK1-NEXT:    [[ADD15:%.*]] = add nsw i32 [[TMP9]], 1
// CHECK1-NEXT:    store i32 [[ADD15]], i32* [[ARRAYIDX]], align 4
// CHECK1-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK1:       .termination.notifier:
// CHECK1-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTEXIT]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108_worker
// CHECK1-SAME: () #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    store i8* null, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK1:       .await.work:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK1-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK1-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK1-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK1:       .select.workers:
// CHECK1-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK1:       .execute.parallel:
// CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK1-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK1-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK1-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK1:       .terminate.parallel:
// CHECK1-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK1-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK1:       .barrier.parallel:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108
// CHECK1-SAME: (%struct.S1* [[THIS:%.*]], i64 [[B:%.*]], i64 [[VLA:%.*]], i64 [[VLA1:%.*]], i16* nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, 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 i16*, align 8
// CHECK1-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[B]], i64* [[B_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA]], i64* [[VLA_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[VLA1]], i64* [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    store i16* [[C]], i16** [[C_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[CONV:%.*]] = bitcast i64* [[B_ADDR]] to i32*
// CHECK1-NEXT:    [[TMP1:%.*]] = load i64, i64* [[VLA_ADDR]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i64, i64* [[VLA_ADDR2]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load i16*, i16** [[C_ADDR]], align 8
// CHECK1-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK1-NEXT:    [[TMP4:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK1-NEXT:    br i1 [[TMP4]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK1:       .worker:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108_worker() #[[ATTR2]]
// CHECK1-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK1:       .mastercheck:
// CHECK1-NEXT:    [[NVPTX_TID3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[TMP5:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE5]], 1
// CHECK1-NEXT:    [[TMP6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], 1
// CHECK1-NEXT:    [[TMP7:%.*]] = xor i32 [[TMP5]], -1
// CHECK1-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP6]], [[TMP7]]
// CHECK1-NEXT:    [[TMP8:%.*]] = icmp eq i32 [[NVPTX_TID3]], [[MASTER_TID]]
// CHECK1-NEXT:    br i1 [[TMP8]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK1:       .master:
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE7:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT8:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS6]], [[NVPTX_WARP_SIZE7]]
// CHECK1-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT8]], i16 1)
// CHECK1-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK1-NEXT:    [[CONV9:%.*]] = sitofp i32 [[TMP9]] to double
// CHECK1-NEXT:    [[ADD:%.*]] = fadd double [[CONV9]], 1.500000e+00
// CHECK1-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK1-NEXT:    store double [[ADD]], double* [[A]], align 8
// CHECK1-NEXT:    [[A10:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP10:%.*]] = load double, double* [[A10]], align 8
// CHECK1-NEXT:    [[INC:%.*]] = fadd double [[TMP10]], 1.000000e+00
// CHECK1-NEXT:    store double [[INC]], double* [[A10]], align 8
// CHECK1-NEXT:    [[CONV11:%.*]] = fptosi double [[INC]] to i16
// CHECK1-NEXT:    [[TMP11:%.*]] = mul nsw i64 1, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, i16* [[TMP3]], i64 [[TMP11]]
// CHECK1-NEXT:    [[ARRAYIDX12:%.*]] = getelementptr inbounds i16, i16* [[ARRAYIDX]], i64 1
// CHECK1-NEXT:    store i16 [[CONV11]], i16* [[ARRAYIDX12]], align 2
// CHECK1-NEXT:    [[A13:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP12:%.*]] = load double, double* [[A13]], align 8
// CHECK1-NEXT:    [[CONV14:%.*]] = fptosi double [[TMP12]] to i32
// CHECK1-NEXT:    [[A15:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK1-NEXT:    [[CALL:%.*]] = call i32 @_Z3baziRd(i32 [[CONV14]], double* nonnull align 8 dereferenceable(8) [[A15]]) #[[ATTR7]]
// CHECK1-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK1:       .termination.notifier:
// CHECK1-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTEXIT]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z3baziRd
// CHECK1-SAME: (i32 [[F3:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR5]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[F2:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca double*, align 8
// CHECK1-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [2 x i8*], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3:[0-9]+]])
// CHECK1-NEXT:    [[TMP1:%.*]] = call i16 @__kmpc_parallel_level(%struct.ident_t* @[[GLOB3]], i32 [[TMP0]])
// CHECK1-NEXT:    [[TMP2:%.*]] = icmp eq i16 [[TMP1]], 0
// CHECK1-NEXT:    [[TMP3:%.*]] = call i8 @__kmpc_is_spmd_exec_mode() #[[ATTR2]]
// CHECK1-NEXT:    [[TMP4:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[TMP4]], label [[DOTSPMD:%.*]], label [[DOTNON_SPMD:%.*]]
// CHECK1:       .spmd:
// CHECK1-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK1:       .non-spmd:
// CHECK1-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], i64 4, i64 128
// CHECK1-NEXT:    [[TMP6:%.*]] = call i8* @__kmpc_data_sharing_coalesced_push_stack(i64 [[TMP5]], i16 0)
// CHECK1-NEXT:    [[TMP7:%.*]] = bitcast i8* [[TMP6]] to %struct._globalized_locals_ty*
// CHECK1-NEXT:    br label [[DOTEXIT]]
// CHECK1:       .exit:
// CHECK1-NEXT:    [[_SELECT_STACK:%.*]] = phi %struct._globalized_locals_ty* [ null, [[DOTSPMD]] ], [ [[TMP7]], [[DOTNON_SPMD]] ]
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast %struct._globalized_locals_ty* [[_SELECT_STACK]] to %struct._globalized_locals_ty.0*
// CHECK1-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT__GLOBALIZED_LOCALS_TY:%.*]], %struct._globalized_locals_ty* [[_SELECT_STACK]], i32 0, i32 0
// CHECK1-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_LANE_ID:%.*]] = and i32 [[NVPTX_TID]], 31
// CHECK1-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [32 x i32], [32 x i32]* [[F]], i32 0, i32 [[NVPTX_LANE_ID]]
// CHECK1-NEXT:    [[F1:%.*]] = getelementptr inbounds [[STRUCT__GLOBALIZED_LOCALS_TY_0:%.*]], %struct._globalized_locals_ty.0* [[TMP8]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP10:%.*]] = select i1 [[TMP2]], i32* [[F1]], i32* [[TMP9]]
// CHECK1-NEXT:    [[TMP11:%.*]] = select i1 [[TMP4]], i32* [[F2]], i32* [[TMP10]]
// CHECK1-NEXT:    store i32 [[F3]], i32* [[TMP11]], align 4
// CHECK1-NEXT:    store double* [[A]], double** [[A_ADDR]], align 8
// CHECK1-NEXT:    [[TMP12:%.*]] = load double*, double** [[A_ADDR]], align 8
// CHECK1-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP14:%.*]] = bitcast i32* [[TMP11]] to i8*
// CHECK1-NEXT:    store i8* [[TMP14]], i8** [[TMP13]], align 8
// CHECK1-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 1
// CHECK1-NEXT:    [[TMP16:%.*]] = bitcast double* [[TMP12]] to i8*
// CHECK1-NEXT:    store i8* [[TMP16]], i8** [[TMP15]], align 8
// CHECK1-NEXT:    [[TMP17:%.*]] = bitcast [2 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK1-NEXT:    call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB3]], i32 [[TMP0]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*, double*)* @__omp_outlined__1 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__1_wrapper to i8*), i8** [[TMP17]], i64 2)
// CHECK1-NEXT:    [[TMP18:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK1-NEXT:    store i32 [[TMP18]], i32* [[RETVAL]], align 4
// CHECK1-NEXT:    br i1 [[TMP4]], label [[DOTEXIT5:%.*]], label [[DOTNON_SPMD4:%.*]]
// CHECK1:       .non-spmd4:
// CHECK1-NEXT:    [[TMP19:%.*]] = bitcast %struct._globalized_locals_ty* [[_SELECT_STACK]] to i8*
// CHECK1-NEXT:    call void @__kmpc_data_sharing_pop_stack(i8* [[TMP19]])
// CHECK1-NEXT:    br label [[DOTEXIT5]]
// CHECK1:       .exit5:
// CHECK1-NEXT:    [[TMP20:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK1-NEXT:    ret i32 [[TMP20]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142_worker
// CHECK1-SAME: () #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    store i8* null, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK1:       .await.work:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK1-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK1-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK1-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK1:       .select.workers:
// CHECK1-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK1:       .execute.parallel:
// CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK1-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK1-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK1-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK1:       .terminate.parallel:
// CHECK1-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK1-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK1:       .barrier.parallel:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142
// CHECK1-SAME: () #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK1-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK1-NEXT:    br i1 [[TMP0]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK1:       .worker:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142_worker() #[[ATTR2]]
// CHECK1-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK1:       .mastercheck:
// CHECK1-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[TMP1:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK1-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK1-NEXT:    [[TMP3:%.*]] = xor i32 [[TMP1]], -1
// CHECK1-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP2]], [[TMP3]]
// CHECK1-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK1-NEXT:    br i1 [[TMP4]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK1:       .master:
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK1-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK1-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK1-NEXT:    call void @_Z6asserti(i32 0) #[[ATTR8:[0-9]+]]
// CHECK1-NEXT:    unreachable
// CHECK1:       5:
// CHECK1-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK1:       .termination.notifier:
// CHECK1-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTEXIT]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74_worker
// CHECK1-SAME: () #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    store i8* null, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK1:       .await.work:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK1-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK1-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 8
// CHECK1-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK1-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK1:       .select.workers:
// CHECK1-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK1-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK1:       .execute.parallel:
// CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK1-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK1-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK1-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK1:       .terminate.parallel:
// CHECK1-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK1-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK1:       .barrier.parallel:
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74
// CHECK1-SAME: (i64 [[A:%.*]], i64 [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[B_ADDR:%.*]] = alloca [10 x i32]*, align 8
// CHECK1-NEXT:    store i64 [[A]], i64* [[A_ADDR]], align 8
// CHECK1-NEXT:    store i64 [[AA]], i64* [[AA_ADDR]], align 8
// CHECK1-NEXT:    store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 8
// CHECK1-NEXT:    [[CONV:%.*]] = bitcast i64* [[A_ADDR]] to i32*
// CHECK1-NEXT:    [[CONV1:%.*]] = bitcast i64* [[AA_ADDR]] to i16*
// CHECK1-NEXT:    [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 8
// CHECK1-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK1-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK1-NEXT:    br i1 [[TMP1]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK1:       .worker:
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74_worker() #[[ATTR2]]
// CHECK1-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK1:       .mastercheck:
// CHECK1-NEXT:    [[NVPTX_TID2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE4]], 1
// CHECK1-NEXT:    [[TMP3:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS3]], 1
// CHECK1-NEXT:    [[TMP4:%.*]] = xor i32 [[TMP2]], -1
// CHECK1-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP3]], [[TMP4]]
// CHECK1-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[NVPTX_TID2]], [[MASTER_TID]]
// CHECK1-NEXT:    br i1 [[TMP5]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK1:       .master:
// CHECK1-NEXT:    [[NVPTX_NUM_THREADS5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT:    [[NVPTX_WARP_SIZE6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK1-NEXT:    [[THREAD_LIMIT7:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS5]], [[NVPTX_WARP_SIZE6]]
// CHECK1-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT7]], i16 1)
// CHECK1-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP6]], 1
// CHECK1-NEXT:    store i32 [[ADD]], i32* [[CONV]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = load i16, i16* [[CONV1]], align 8
// CHECK1-NEXT:    [[CONV8:%.*]] = sext i16 [[TMP7]] to i32
// CHECK1-NEXT:    [[ADD9:%.*]] = add nsw i32 [[CONV8]], 1
// CHECK1-NEXT:    [[CONV10:%.*]] = trunc i32 [[ADD9]] to i16
// CHECK1-NEXT:    store i16 [[CONV10]], i16* [[CONV1]], align 8
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i64 0, i64 2
// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK1-NEXT:    [[ADD11:%.*]] = add nsw i32 [[TMP8]], 1
// CHECK1-NEXT:    store i32 [[ADD11]], i32* [[ARRAYIDX]], align 4
// CHECK1-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK1:       .termination.notifier:
// CHECK1-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK1-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK1-NEXT:    br label [[DOTEXIT]]
// CHECK1:       .exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__1
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[F:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[F_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca double*, align 8
// CHECK1-NEXT:    [[TMP:%.*]] = alloca double*, align 8
// CHECK1-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store i32* [[F]], i32** [[F_ADDR]], align 8
// CHECK1-NEXT:    store double* [[A]], double** [[A_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[F_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load double*, double** [[A_ADDR]], align 8
// CHECK1-NEXT:    store double* [[TMP1]], double** [[TMP]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load double*, double** [[TMP]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load double, double* [[TMP2]], align 8
// CHECK1-NEXT:    [[ADD:%.*]] = fadd double 2.000000e+00, [[TMP3]]
// CHECK1-NEXT:    [[CONV:%.*]] = fptosi double [[ADD]] to i32
// CHECK1-NEXT:    store i32 [[CONV]], i32* [[TMP0]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper
// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[GLOBAL_ARGS:%.*]] = alloca i8**, align 8
// CHECK1-NEXT:    store i32 0, i32* [[DOTZERO_ADDR]], align 4
// CHECK1-NEXT:    store i16 [[TMP0]], i16* [[DOTADDR]], align 2
// CHECK1-NEXT:    store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
// CHECK1-NEXT:    call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
// CHECK1-NEXT:    [[TMP2:%.*]] = load i8**, i8*** [[GLOBAL_ARGS]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i64 0
// CHECK1-NEXT:    [[TMP4:%.*]] = bitcast i8** [[TMP3]] to i32**
// CHECK1-NEXT:    [[TMP5:%.*]] = load i32*, i32** [[TMP4]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i64 1
// CHECK1-NEXT:    [[TMP7:%.*]] = bitcast i8** [[TMP6]] to double**
// CHECK1-NEXT:    [[TMP8:%.*]] = load double*, double** [[TMP7]], align 8
// CHECK1-NEXT:    call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]], i32* [[TMP5]], double* [[TMP8]]) #[[ATTR2]]
// CHECK1-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9targetBarPiS__l25
// CHECK2-SAME: (i32* [[PTR1:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR2:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[PTR1_ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT:    [[PTR2_ADDR:%.*]] = alloca i32**, align 4
// CHECK2-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [2 x i8*], align 4
// CHECK2-NEXT:    store i32* [[PTR1]], i32** [[PTR1_ADDR]], align 4
// CHECK2-NEXT:    store i32** [[PTR2]], i32*** [[PTR2_ADDR]], align 4
// CHECK2-NEXT:    [[TMP0:%.*]] = load i32**, i32*** [[PTR2_ADDR]], align 4
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK2-NEXT:    call void @__kmpc_data_sharing_init_stack_spmd()
// CHECK2-NEXT:    br label [[DOTEXECUTE:%.*]]
// CHECK2:       .execute:
// CHECK2-NEXT:    [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP3:%.*]] = bitcast i32** [[PTR1_ADDR]] to i8*
// CHECK2-NEXT:    store i8* [[TMP3]], i8** [[TMP2]], align 4
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 1
// CHECK2-NEXT:    [[TMP5:%.*]] = bitcast i32** [[TMP0]] to i8*
// CHECK2-NEXT:    store i8* [[TMP5]], i8** [[TMP4]], align 4
// CHECK2-NEXT:    [[TMP6:%.*]] = bitcast [2 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK2-NEXT:    call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32**, i32**)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP6]], i32 2)
// CHECK2-NEXT:    br label [[DOTOMP_DEINIT:%.*]]
// CHECK2:       .omp.deinit:
// CHECK2-NEXT:    call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK2-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR1:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR2:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT:    [[PTR1_ADDR:%.*]] = alloca i32**, align 4
// CHECK2-NEXT:    [[PTR2_ADDR:%.*]] = alloca i32**, align 4
// CHECK2-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK2-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK2-NEXT:    store i32** [[PTR1]], i32*** [[PTR1_ADDR]], align 4
// CHECK2-NEXT:    store i32** [[PTR2]], i32*** [[PTR2_ADDR]], align 4
// CHECK2-NEXT:    [[TMP0:%.*]] = load i32**, i32*** [[PTR1_ADDR]], align 4
// CHECK2-NEXT:    [[TMP1:%.*]] = load i32**, i32*** [[PTR2_ADDR]], align 4
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32*, i32** [[TMP1]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
// CHECK2-NEXT:    [[TMP4:%.*]] = load i32*, i32** [[TMP0]], align 4
// CHECK2-NEXT:    store i32 [[TMP3]], i32* [[TMP4]], align 4
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39_worker
// CHECK2-SAME: () #[[ATTR3:[0-9]+]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK2-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK2-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK2:       .await.work:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK2-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK2-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK2-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK2:       .select.workers:
// CHECK2-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK2-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK2:       .execute.parallel:
// CHECK2-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2:[0-9]+]])
// CHECK2-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK2-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK2-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK2:       .terminate.parallel:
// CHECK2-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK2-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK2:       .barrier.parallel:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39
// CHECK2-SAME: () #[[ATTR0]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK2-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK2-NEXT:    br i1 [[TMP0]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK2:       .worker:
// CHECK2-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39_worker() #[[ATTR2:[0-9]+]]
// CHECK2-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK2:       .mastercheck:
// CHECK2-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[TMP1:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK2-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK2-NEXT:    [[TMP3:%.*]] = xor i32 [[TMP1]], -1
// CHECK2-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP2]], [[TMP3]]
// CHECK2-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK2-NEXT:    br i1 [[TMP4]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK2:       .master:
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK2-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK2-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK2-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK2:       .termination.notifier:
// CHECK2-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTEXIT]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47_worker
// CHECK2-SAME: () #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK2-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK2-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK2:       .await.work:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK2-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK2-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK2-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK2:       .select.workers:
// CHECK2-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK2-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK2:       .execute.parallel:
// CHECK2-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK2-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK2-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK2-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK2:       .terminate.parallel:
// CHECK2-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK2-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK2:       .barrier.parallel:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47
// CHECK2-SAME: (i32 [[AA:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    store i32 [[AA]], i32* [[AA_ADDR]], align 4
// CHECK2-NEXT:    [[CONV:%.*]] = bitcast i32* [[AA_ADDR]] to i16*
// CHECK2-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK2-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK2-NEXT:    br i1 [[TMP0]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK2:       .worker:
// CHECK2-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47_worker() #[[ATTR2]]
// CHECK2-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK2:       .mastercheck:
// CHECK2-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[TMP1:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK2-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK2-NEXT:    [[TMP3:%.*]] = xor i32 [[TMP1]], -1
// CHECK2-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP2]], [[TMP3]]
// CHECK2-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK2-NEXT:    br i1 [[TMP4]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK2:       .master:
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK2-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK2-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK2-NEXT:    [[TMP5:%.*]] = load i16, i16* [[CONV]], align 4
// CHECK2-NEXT:    [[CONV7:%.*]] = sext i16 [[TMP5]] to i32
// CHECK2-NEXT:    [[ADD:%.*]] = add nsw i32 [[CONV7]], 1
// CHECK2-NEXT:    [[CONV8:%.*]] = trunc i32 [[ADD]] to i16
// CHECK2-NEXT:    store i16 [[CONV8]], i16* [[CONV]], align 4
// CHECK2-NEXT:    [[TMP6:%.*]] = load i16, i16* [[CONV]], align 4
// CHECK2-NEXT:    [[CONV9:%.*]] = sext i16 [[TMP6]] to i32
// CHECK2-NEXT:    [[ADD10:%.*]] = add nsw i32 [[CONV9]], 2
// CHECK2-NEXT:    [[CONV11:%.*]] = trunc i32 [[ADD10]] to i16
// CHECK2-NEXT:    store i16 [[CONV11]], i16* [[CONV]], align 4
// CHECK2-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK2:       .termination.notifier:
// CHECK2-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTEXIT]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53_worker
// CHECK2-SAME: () #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK2-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK2-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK2:       .await.work:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK2-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK2-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK2-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK2:       .select.workers:
// CHECK2-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK2-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK2:       .execute.parallel:
// CHECK2-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK2-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK2-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK2-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK2:       .terminate.parallel:
// CHECK2-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK2-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK2:       .barrier.parallel:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53
// CHECK2-SAME: (i32 [[A:%.*]], [10 x float]* nonnull align 4 dereferenceable(40) [[B:%.*]], i32 [[VLA:%.*]], float* nonnull align 4 dereferenceable(4) [[BN:%.*]], [5 x [10 x double]]* nonnull align 8 dereferenceable(400) [[C:%.*]], i32 [[VLA1:%.*]], i32 [[VLA3:%.*]], double* nonnull align 8 dereferenceable(8) [[CN:%.*]], %struct.TT* nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[B_ADDR:%.*]] = alloca [10 x float]*, align 4
// CHECK2-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[BN_ADDR:%.*]] = alloca float*, align 4
// CHECK2-NEXT:    [[C_ADDR:%.*]] = alloca [5 x [10 x double]]*, align 4
// CHECK2-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[VLA_ADDR4:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[CN_ADDR:%.*]] = alloca double*, align 4
// CHECK2-NEXT:    [[D_ADDR:%.*]] = alloca %struct.TT*, align 4
// CHECK2-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    store [10 x float]* [[B]], [10 x float]** [[B_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[VLA]], i32* [[VLA_ADDR]], align 4
// CHECK2-NEXT:    store float* [[BN]], float** [[BN_ADDR]], align 4
// CHECK2-NEXT:    store [5 x [10 x double]]* [[C]], [5 x [10 x double]]** [[C_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[VLA1]], i32* [[VLA_ADDR2]], align 4
// CHECK2-NEXT:    store i32 [[VLA3]], i32* [[VLA_ADDR4]], align 4
// CHECK2-NEXT:    store double* [[CN]], double** [[CN_ADDR]], align 4
// CHECK2-NEXT:    store %struct.TT* [[D]], %struct.TT** [[D_ADDR]], align 4
// CHECK2-NEXT:    [[TMP0:%.*]] = load [10 x float]*, [10 x float]** [[B_ADDR]], align 4
// CHECK2-NEXT:    [[TMP1:%.*]] = load i32, i32* [[VLA_ADDR]], align 4
// CHECK2-NEXT:    [[TMP2:%.*]] = load float*, float** [[BN_ADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load [5 x [10 x double]]*, [5 x [10 x double]]** [[C_ADDR]], align 4
// CHECK2-NEXT:    [[TMP4:%.*]] = load i32, i32* [[VLA_ADDR2]], align 4
// CHECK2-NEXT:    [[TMP5:%.*]] = load i32, i32* [[VLA_ADDR4]], align 4
// CHECK2-NEXT:    [[TMP6:%.*]] = load double*, double** [[CN_ADDR]], align 4
// CHECK2-NEXT:    [[TMP7:%.*]] = load %struct.TT*, %struct.TT** [[D_ADDR]], align 4
// CHECK2-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK2-NEXT:    [[TMP8:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK2-NEXT:    br i1 [[TMP8]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK2:       .worker:
// CHECK2-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53_worker() #[[ATTR2]]
// CHECK2-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK2:       .mastercheck:
// CHECK2-NEXT:    [[NVPTX_TID5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE7:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[TMP9:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE7]], 1
// CHECK2-NEXT:    [[TMP10:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS6]], 1
// CHECK2-NEXT:    [[TMP11:%.*]] = xor i32 [[TMP9]], -1
// CHECK2-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP10]], [[TMP11]]
// CHECK2-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[NVPTX_TID5]], [[MASTER_TID]]
// CHECK2-NEXT:    br i1 [[TMP12]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK2:       .master:
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS8:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE9:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT10:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS8]], [[NVPTX_WARP_SIZE9]]
// CHECK2-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT10]], i16 1)
// CHECK2-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK2-NEXT:    [[TMP13:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP13]], 1
// CHECK2-NEXT:    store i32 [[ADD]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x float], [10 x float]* [[TMP0]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP14:%.*]] = load float, float* [[ARRAYIDX]], align 4
// CHECK2-NEXT:    [[CONV:%.*]] = fpext float [[TMP14]] to double
// CHECK2-NEXT:    [[ADD11:%.*]] = fadd double [[CONV]], 1.000000e+00
// CHECK2-NEXT:    [[CONV12:%.*]] = fptrunc double [[ADD11]] to float
// CHECK2-NEXT:    store float [[CONV12]], float* [[ARRAYIDX]], align 4
// CHECK2-NEXT:    [[ARRAYIDX13:%.*]] = getelementptr inbounds float, float* [[TMP2]], i32 3
// CHECK2-NEXT:    [[TMP15:%.*]] = load float, float* [[ARRAYIDX13]], align 4
// CHECK2-NEXT:    [[CONV14:%.*]] = fpext float [[TMP15]] to double
// CHECK2-NEXT:    [[ADD15:%.*]] = fadd double [[CONV14]], 1.000000e+00
// CHECK2-NEXT:    [[CONV16:%.*]] = fptrunc double [[ADD15]] to float
// CHECK2-NEXT:    store float [[CONV16]], float* [[ARRAYIDX13]], align 4
// CHECK2-NEXT:    [[ARRAYIDX17:%.*]] = getelementptr inbounds [5 x [10 x double]], [5 x [10 x double]]* [[TMP3]], i32 0, i32 1
// CHECK2-NEXT:    [[ARRAYIDX18:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYIDX17]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP16:%.*]] = load double, double* [[ARRAYIDX18]], align 8
// CHECK2-NEXT:    [[ADD19:%.*]] = fadd double [[TMP16]], 1.000000e+00
// CHECK2-NEXT:    store double [[ADD19]], double* [[ARRAYIDX18]], align 8
// CHECK2-NEXT:    [[TMP17:%.*]] = mul nsw i32 1, [[TMP5]]
// CHECK2-NEXT:    [[ARRAYIDX20:%.*]] = getelementptr inbounds double, double* [[TMP6]], i32 [[TMP17]]
// CHECK2-NEXT:    [[ARRAYIDX21:%.*]] = getelementptr inbounds double, double* [[ARRAYIDX20]], i32 3
// CHECK2-NEXT:    [[TMP18:%.*]] = load double, double* [[ARRAYIDX21]], align 8
// CHECK2-NEXT:    [[ADD22:%.*]] = fadd double [[TMP18]], 1.000000e+00
// CHECK2-NEXT:    store double [[ADD22]], double* [[ARRAYIDX21]], align 8
// CHECK2-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], %struct.TT* [[TMP7]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP19:%.*]] = load i64, i64* [[X]], align 8
// CHECK2-NEXT:    [[ADD23:%.*]] = add nsw i64 [[TMP19]], 1
// CHECK2-NEXT:    store i64 [[ADD23]], i64* [[X]], align 8
// CHECK2-NEXT:    [[Y:%.*]] = getelementptr inbounds [[STRUCT_TT]], %struct.TT* [[TMP7]], i32 0, i32 1
// CHECK2-NEXT:    [[TMP20:%.*]] = load i8, i8* [[Y]], align 8
// CHECK2-NEXT:    [[CONV24:%.*]] = sext i8 [[TMP20]] to i32
// CHECK2-NEXT:    [[ADD25:%.*]] = add nsw i32 [[CONV24]], 1
// CHECK2-NEXT:    [[CONV26:%.*]] = trunc i32 [[ADD25]] to i8
// CHECK2-NEXT:    store i8 [[CONV26]], i8* [[Y]], align 8
// CHECK2-NEXT:    [[CALL:%.*]] = call nonnull align 8 dereferenceable(8) i64* @_ZN2TTIxcEixEi(%struct.TT* nonnull dereferenceable(16) [[TMP7]], i32 0) #[[ATTR7:[0-9]+]]
// CHECK2-NEXT:    [[TMP21:%.*]] = load i64, i64* [[CALL]], align 8
// CHECK2-NEXT:    [[ADD27:%.*]] = add nsw i64 [[TMP21]], 1
// CHECK2-NEXT:    store i64 [[ADD27]], i64* [[CALL]], align 8
// CHECK2-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK2:       .termination.notifier:
// CHECK2-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTEXIT]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2TTIxcEixEi
// CHECK2-SAME: (%struct.TT* nonnull dereferenceable(16) [[THIS:%.*]], i32 [[I:%.*]]) #[[ATTR5:[0-9]+]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.TT*, align 4
// CHECK2-NEXT:    [[I_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    store %struct.TT* [[THIS]], %struct.TT** [[THIS_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[I]], i32* [[I_ADDR]], align 4
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.TT*, %struct.TT** [[THIS_ADDR]], align 4
// CHECK2-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], %struct.TT* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT:    ret i64* [[X]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90_worker
// CHECK2-SAME: () #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK2-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK2-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK2:       .await.work:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK2-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK2-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK2-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK2:       .select.workers:
// CHECK2-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK2-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK2:       .execute.parallel:
// CHECK2-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK2-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK2-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK2-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK2:       .terminate.parallel:
// CHECK2-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK2-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK2:       .barrier.parallel:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90
// CHECK2-SAME: (i32 [[A:%.*]], i32 [[AA:%.*]], i32 [[AAA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[AAA_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK2-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[AA]], i32* [[AA_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[AAA]], i32* [[AAA_ADDR]], align 4
// CHECK2-NEXT:    store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK2-NEXT:    [[CONV:%.*]] = bitcast i32* [[AA_ADDR]] to i16*
// CHECK2-NEXT:    [[CONV1:%.*]] = bitcast i32* [[AAA_ADDR]] to i8*
// CHECK2-NEXT:    [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK2-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK2-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK2-NEXT:    br i1 [[TMP1]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK2:       .worker:
// CHECK2-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90_worker() #[[ATTR2]]
// CHECK2-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK2:       .mastercheck:
// CHECK2-NEXT:    [[NVPTX_TID2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE4]], 1
// CHECK2-NEXT:    [[TMP3:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS3]], 1
// CHECK2-NEXT:    [[TMP4:%.*]] = xor i32 [[TMP2]], -1
// CHECK2-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP3]], [[TMP4]]
// CHECK2-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[NVPTX_TID2]], [[MASTER_TID]]
// CHECK2-NEXT:    br i1 [[TMP5]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK2:       .master:
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT7:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS5]], [[NVPTX_WARP_SIZE6]]
// CHECK2-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT7]], i16 1)
// CHECK2-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK2-NEXT:    [[TMP6:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP6]], 1
// CHECK2-NEXT:    store i32 [[ADD]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[TMP7:%.*]] = load i16, i16* [[CONV]], align 4
// CHECK2-NEXT:    [[CONV8:%.*]] = sext i16 [[TMP7]] to i32
// CHECK2-NEXT:    [[ADD9:%.*]] = add nsw i32 [[CONV8]], 1
// CHECK2-NEXT:    [[CONV10:%.*]] = trunc i32 [[ADD9]] to i16
// CHECK2-NEXT:    store i16 [[CONV10]], i16* [[CONV]], align 4
// CHECK2-NEXT:    [[TMP8:%.*]] = load i8, i8* [[CONV1]], align 4
// CHECK2-NEXT:    [[CONV11:%.*]] = sext i8 [[TMP8]] to i32
// CHECK2-NEXT:    [[ADD12:%.*]] = add nsw i32 [[CONV11]], 1
// CHECK2-NEXT:    [[CONV13:%.*]] = trunc i32 [[ADD12]] to i8
// CHECK2-NEXT:    store i8 [[CONV13]], i8* [[CONV1]], align 4
// CHECK2-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP9:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK2-NEXT:    [[ADD14:%.*]] = add nsw i32 [[TMP9]], 1
// CHECK2-NEXT:    store i32 [[ADD14]], i32* [[ARRAYIDX]], align 4
// CHECK2-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK2:       .termination.notifier:
// CHECK2-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTEXIT]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108_worker
// CHECK2-SAME: () #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK2-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK2-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK2:       .await.work:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK2-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK2-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK2-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK2:       .select.workers:
// CHECK2-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK2-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK2:       .execute.parallel:
// CHECK2-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK2-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK2-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK2-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK2:       .terminate.parallel:
// CHECK2-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK2-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK2:       .barrier.parallel:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108
// CHECK2-SAME: (%struct.S1* [[THIS:%.*]], i32 [[B:%.*]], i32 [[VLA:%.*]], i32 [[VLA1:%.*]], i16* nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 4
// CHECK2-NEXT:    [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[C_ADDR:%.*]] = alloca i16*, align 4
// CHECK2-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[B]], i32* [[B_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[VLA]], i32* [[VLA_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[VLA1]], i32* [[VLA_ADDR2]], align 4
// CHECK2-NEXT:    store i16* [[C]], i16** [[C_ADDR]], align 4
// CHECK2-NEXT:    [[TMP0:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 4
// CHECK2-NEXT:    [[TMP1:%.*]] = load i32, i32* [[VLA_ADDR]], align 4
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[VLA_ADDR2]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load i16*, i16** [[C_ADDR]], align 4
// CHECK2-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK2-NEXT:    [[TMP4:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK2-NEXT:    br i1 [[TMP4]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK2:       .worker:
// CHECK2-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108_worker() #[[ATTR2]]
// CHECK2-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK2:       .mastercheck:
// CHECK2-NEXT:    [[NVPTX_TID3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[TMP5:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE5]], 1
// CHECK2-NEXT:    [[TMP6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], 1
// CHECK2-NEXT:    [[TMP7:%.*]] = xor i32 [[TMP5]], -1
// CHECK2-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP6]], [[TMP7]]
// CHECK2-NEXT:    [[TMP8:%.*]] = icmp eq i32 [[NVPTX_TID3]], [[MASTER_TID]]
// CHECK2-NEXT:    br i1 [[TMP8]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK2:       .master:
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE7:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT8:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS6]], [[NVPTX_WARP_SIZE7]]
// CHECK2-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT8]], i16 1)
// CHECK2-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK2-NEXT:    [[TMP9:%.*]] = load i32, i32* [[B_ADDR]], align 4
// CHECK2-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP9]] to double
// CHECK2-NEXT:    [[ADD:%.*]] = fadd double [[CONV]], 1.500000e+00
// CHECK2-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK2-NEXT:    store double [[ADD]], double* [[A]], align 8
// CHECK2-NEXT:    [[A9:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP10:%.*]] = load double, double* [[A9]], align 8
// CHECK2-NEXT:    [[INC:%.*]] = fadd double [[TMP10]], 1.000000e+00
// CHECK2-NEXT:    store double [[INC]], double* [[A9]], align 8
// CHECK2-NEXT:    [[CONV10:%.*]] = fptosi double [[INC]] to i16
// CHECK2-NEXT:    [[TMP11:%.*]] = mul nsw i32 1, [[TMP2]]
// CHECK2-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, i16* [[TMP3]], i32 [[TMP11]]
// CHECK2-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds i16, i16* [[ARRAYIDX]], i32 1
// CHECK2-NEXT:    store i16 [[CONV10]], i16* [[ARRAYIDX11]], align 2
// CHECK2-NEXT:    [[A12:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP12:%.*]] = load double, double* [[A12]], align 8
// CHECK2-NEXT:    [[CONV13:%.*]] = fptosi double [[TMP12]] to i32
// CHECK2-NEXT:    [[A14:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK2-NEXT:    [[CALL:%.*]] = call i32 @_Z3baziRd(i32 [[CONV13]], double* nonnull align 8 dereferenceable(8) [[A14]]) #[[ATTR7]]
// CHECK2-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK2:       .termination.notifier:
// CHECK2-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTEXIT]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z3baziRd
// CHECK2-SAME: (i32 [[F3:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR5]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[F2:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[A_ADDR:%.*]] = alloca double*, align 4
// CHECK2-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [2 x i8*], align 4
// CHECK2-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3:[0-9]+]])
// CHECK2-NEXT:    [[TMP1:%.*]] = call i16 @__kmpc_parallel_level(%struct.ident_t* @[[GLOB3]], i32 [[TMP0]])
// CHECK2-NEXT:    [[TMP2:%.*]] = icmp eq i16 [[TMP1]], 0
// CHECK2-NEXT:    [[TMP3:%.*]] = call i8 @__kmpc_is_spmd_exec_mode() #[[ATTR2]]
// CHECK2-NEXT:    [[TMP4:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK2-NEXT:    br i1 [[TMP4]], label [[DOTSPMD:%.*]], label [[DOTNON_SPMD:%.*]]
// CHECK2:       .spmd:
// CHECK2-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK2:       .non-spmd:
// CHECK2-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], i32 4, i32 128
// CHECK2-NEXT:    [[TMP6:%.*]] = call i8* @__kmpc_data_sharing_coalesced_push_stack(i32 [[TMP5]], i16 0)
// CHECK2-NEXT:    [[TMP7:%.*]] = bitcast i8* [[TMP6]] to %struct._globalized_locals_ty*
// CHECK2-NEXT:    br label [[DOTEXIT]]
// CHECK2:       .exit:
// CHECK2-NEXT:    [[_SELECT_STACK:%.*]] = phi %struct._globalized_locals_ty* [ null, [[DOTSPMD]] ], [ [[TMP7]], [[DOTNON_SPMD]] ]
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast %struct._globalized_locals_ty* [[_SELECT_STACK]] to %struct._globalized_locals_ty.0*
// CHECK2-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT__GLOBALIZED_LOCALS_TY:%.*]], %struct._globalized_locals_ty* [[_SELECT_STACK]], i32 0, i32 0
// CHECK2-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_LANE_ID:%.*]] = and i32 [[NVPTX_TID]], 31
// CHECK2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [32 x i32], [32 x i32]* [[F]], i32 0, i32 [[NVPTX_LANE_ID]]
// CHECK2-NEXT:    [[F1:%.*]] = getelementptr inbounds [[STRUCT__GLOBALIZED_LOCALS_TY_0:%.*]], %struct._globalized_locals_ty.0* [[TMP8]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP10:%.*]] = select i1 [[TMP2]], i32* [[F1]], i32* [[TMP9]]
// CHECK2-NEXT:    [[TMP11:%.*]] = select i1 [[TMP4]], i32* [[F2]], i32* [[TMP10]]
// CHECK2-NEXT:    store i32 [[F3]], i32* [[TMP11]], align 4
// CHECK2-NEXT:    store double* [[A]], double** [[A_ADDR]], align 4
// CHECK2-NEXT:    [[TMP12:%.*]] = load double*, double** [[A_ADDR]], align 4
// CHECK2-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP14:%.*]] = bitcast i32* [[TMP11]] to i8*
// CHECK2-NEXT:    store i8* [[TMP14]], i8** [[TMP13]], align 4
// CHECK2-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 1
// CHECK2-NEXT:    [[TMP16:%.*]] = bitcast double* [[TMP12]] to i8*
// CHECK2-NEXT:    store i8* [[TMP16]], i8** [[TMP15]], align 4
// CHECK2-NEXT:    [[TMP17:%.*]] = bitcast [2 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK2-NEXT:    call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB3]], i32 [[TMP0]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*, double*)* @__omp_outlined__1 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__1_wrapper to i8*), i8** [[TMP17]], i32 2)
// CHECK2-NEXT:    [[TMP18:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK2-NEXT:    store i32 [[TMP18]], i32* [[RETVAL]], align 4
// CHECK2-NEXT:    br i1 [[TMP4]], label [[DOTEXIT5:%.*]], label [[DOTNON_SPMD4:%.*]]
// CHECK2:       .non-spmd4:
// CHECK2-NEXT:    [[TMP19:%.*]] = bitcast %struct._globalized_locals_ty* [[_SELECT_STACK]] to i8*
// CHECK2-NEXT:    call void @__kmpc_data_sharing_pop_stack(i8* [[TMP19]])
// CHECK2-NEXT:    br label [[DOTEXIT5]]
// CHECK2:       .exit5:
// CHECK2-NEXT:    [[TMP20:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK2-NEXT:    ret i32 [[TMP20]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142_worker
// CHECK2-SAME: () #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK2-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK2-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK2:       .await.work:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK2-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK2-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK2-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK2:       .select.workers:
// CHECK2-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK2-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK2:       .execute.parallel:
// CHECK2-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK2-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK2-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK2-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK2:       .terminate.parallel:
// CHECK2-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK2-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK2:       .barrier.parallel:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142
// CHECK2-SAME: () #[[ATTR0]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK2-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK2-NEXT:    br i1 [[TMP0]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK2:       .worker:
// CHECK2-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142_worker() #[[ATTR2]]
// CHECK2-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK2:       .mastercheck:
// CHECK2-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[TMP1:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK2-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK2-NEXT:    [[TMP3:%.*]] = xor i32 [[TMP1]], -1
// CHECK2-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP2]], [[TMP3]]
// CHECK2-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK2-NEXT:    br i1 [[TMP4]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK2:       .master:
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK2-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK2-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK2-NEXT:    call void @_Z6asserti(i32 0) #[[ATTR8:[0-9]+]]
// CHECK2-NEXT:    unreachable
// CHECK2:       5:
// CHECK2-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK2:       .termination.notifier:
// CHECK2-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTEXIT]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74_worker
// CHECK2-SAME: () #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK2-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK2-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK2:       .await.work:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK2-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK2-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK2-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK2-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK2:       .select.workers:
// CHECK2-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK2-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK2-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK2:       .execute.parallel:
// CHECK2-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK2-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK2-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK2-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK2:       .terminate.parallel:
// CHECK2-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK2-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK2:       .barrier.parallel:
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74
// CHECK2-SAME: (i32 [[A:%.*]], i32 [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK2-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[AA]], i32* [[AA_ADDR]], align 4
// CHECK2-NEXT:    store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK2-NEXT:    [[CONV:%.*]] = bitcast i32* [[AA_ADDR]] to i16*
// CHECK2-NEXT:    [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK2-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK2-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK2-NEXT:    br i1 [[TMP1]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK2:       .worker:
// CHECK2-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74_worker() #[[ATTR2]]
// CHECK2-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK2:       .mastercheck:
// CHECK2-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK2-NEXT:    [[TMP3:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK2-NEXT:    [[TMP4:%.*]] = xor i32 [[TMP2]], -1
// CHECK2-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP3]], [[TMP4]]
// CHECK2-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK2-NEXT:    br i1 [[TMP5]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK2:       .master:
// CHECK2-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK2-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK2-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK2-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK2-NEXT:    [[TMP6:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP6]], 1
// CHECK2-NEXT:    store i32 [[ADD]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[TMP7:%.*]] = load i16, i16* [[CONV]], align 4
// CHECK2-NEXT:    [[CONV7:%.*]] = sext i16 [[TMP7]] to i32
// CHECK2-NEXT:    [[ADD8:%.*]] = add nsw i32 [[CONV7]], 1
// CHECK2-NEXT:    [[CONV9:%.*]] = trunc i32 [[ADD8]] to i16
// CHECK2-NEXT:    store i16 [[CONV9]], i16* [[CONV]], align 4
// CHECK2-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK2-NEXT:    [[ADD10:%.*]] = add nsw i32 [[TMP8]], 1
// CHECK2-NEXT:    store i32 [[ADD10]], i32* [[ARRAYIDX]], align 4
// CHECK2-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK2:       .termination.notifier:
// CHECK2-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK2-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK2-NEXT:    br label [[DOTEXIT]]
// CHECK2:       .exit:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__omp_outlined__1
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[F:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT:    [[F_ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT:    [[A_ADDR:%.*]] = alloca double*, align 4
// CHECK2-NEXT:    [[TMP:%.*]] = alloca double*, align 4
// CHECK2-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK2-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK2-NEXT:    store i32* [[F]], i32** [[F_ADDR]], align 4
// CHECK2-NEXT:    store double* [[A]], double** [[A_ADDR]], align 4
// CHECK2-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[F_ADDR]], align 4
// CHECK2-NEXT:    [[TMP1:%.*]] = load double*, double** [[A_ADDR]], align 4
// CHECK2-NEXT:    store double* [[TMP1]], double** [[TMP]], align 4
// CHECK2-NEXT:    [[TMP2:%.*]] = load double*, double** [[TMP]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load double, double* [[TMP2]], align 8
// CHECK2-NEXT:    [[ADD:%.*]] = fadd double 2.000000e+00, [[TMP3]]
// CHECK2-NEXT:    [[CONV:%.*]] = fptosi double [[ADD]] to i32
// CHECK2-NEXT:    store i32 [[CONV]], i32* [[TMP0]], align 4
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper
// CHECK2-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[GLOBAL_ARGS:%.*]] = alloca i8**, align 4
// CHECK2-NEXT:    store i32 0, i32* [[DOTZERO_ADDR]], align 4
// CHECK2-NEXT:    store i16 [[TMP0]], i16* [[DOTADDR]], align 2
// CHECK2-NEXT:    store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
// CHECK2-NEXT:    call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
// CHECK2-NEXT:    [[TMP2:%.*]] = load i8**, i8*** [[GLOBAL_ARGS]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i32 0
// CHECK2-NEXT:    [[TMP4:%.*]] = bitcast i8** [[TMP3]] to i32**
// CHECK2-NEXT:    [[TMP5:%.*]] = load i32*, i32** [[TMP4]], align 4
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i32 1
// CHECK2-NEXT:    [[TMP7:%.*]] = bitcast i8** [[TMP6]] to double**
// CHECK2-NEXT:    [[TMP8:%.*]] = load double*, double** [[TMP7]], align 4
// CHECK2-NEXT:    call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]], i32* [[TMP5]], double* [[TMP8]]) #[[ATTR2]]
// CHECK2-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9targetBarPiS__l25
// CHECK3-SAME: (i32* [[PTR1:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR2:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[PTR1_ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT:    [[PTR2_ADDR:%.*]] = alloca i32**, align 4
// CHECK3-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [2 x i8*], align 4
// CHECK3-NEXT:    store i32* [[PTR1]], i32** [[PTR1_ADDR]], align 4
// CHECK3-NEXT:    store i32** [[PTR2]], i32*** [[PTR2_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32**, i32*** [[PTR2_ADDR]], align 4
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK3-NEXT:    call void @__kmpc_data_sharing_init_stack_spmd()
// CHECK3-NEXT:    br label [[DOTEXECUTE:%.*]]
// CHECK3:       .execute:
// CHECK3-NEXT:    [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK3-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP3:%.*]] = bitcast i32** [[PTR1_ADDR]] to i8*
// CHECK3-NEXT:    store i8* [[TMP3]], i8** [[TMP2]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 1
// CHECK3-NEXT:    [[TMP5:%.*]] = bitcast i32** [[TMP0]] to i8*
// CHECK3-NEXT:    store i8* [[TMP5]], i8** [[TMP4]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = bitcast [2 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK3-NEXT:    call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32**, i32**)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP6]], i32 2)
// CHECK3-NEXT:    br label [[DOTOMP_DEINIT:%.*]]
// CHECK3:       .omp.deinit:
// CHECK3-NEXT:    call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK3-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR1:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR2:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT:    [[PTR1_ADDR:%.*]] = alloca i32**, align 4
// CHECK3-NEXT:    [[PTR2_ADDR:%.*]] = alloca i32**, align 4
// CHECK3-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32** [[PTR1]], i32*** [[PTR1_ADDR]], align 4
// CHECK3-NEXT:    store i32** [[PTR2]], i32*** [[PTR2_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32**, i32*** [[PTR1_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32**, i32*** [[PTR2_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32*, i32** [[TMP1]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32*, i32** [[TMP0]], align 4
// CHECK3-NEXT:    store i32 [[TMP3]], i32* [[TMP4]], align 4
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39_worker
// CHECK3-SAME: () #[[ATTR3:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK3-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK3:       .await.work:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK3-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK3-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK3-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK3:       .select.workers:
// CHECK3-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK3-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK3:       .execute.parallel:
// CHECK3-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2:[0-9]+]])
// CHECK3-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK3-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK3-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK3:       .terminate.parallel:
// CHECK3-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK3-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK3:       .barrier.parallel:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39
// CHECK3-SAME: () #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK3-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK3-NEXT:    br i1 [[TMP0]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK3:       .worker:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39_worker() #[[ATTR2:[0-9]+]]
// CHECK3-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK3:       .mastercheck:
// CHECK3-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[TMP1:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK3-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK3-NEXT:    [[TMP3:%.*]] = xor i32 [[TMP1]], -1
// CHECK3-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP2]], [[TMP3]]
// CHECK3-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK3-NEXT:    br i1 [[TMP4]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK3:       .master:
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK3-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK3-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK3-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK3:       .termination.notifier:
// CHECK3-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTEXIT]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47_worker
// CHECK3-SAME: () #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK3-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK3:       .await.work:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK3-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK3-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK3-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK3:       .select.workers:
// CHECK3-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK3-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK3:       .execute.parallel:
// CHECK3-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK3-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK3-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK3-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK3:       .terminate.parallel:
// CHECK3-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK3-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK3:       .barrier.parallel:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47
// CHECK3-SAME: (i32 [[AA:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store i32 [[AA]], i32* [[AA_ADDR]], align 4
// CHECK3-NEXT:    [[CONV:%.*]] = bitcast i32* [[AA_ADDR]] to i16*
// CHECK3-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK3-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK3-NEXT:    br i1 [[TMP0]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK3:       .worker:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47_worker() #[[ATTR2]]
// CHECK3-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK3:       .mastercheck:
// CHECK3-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[TMP1:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK3-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK3-NEXT:    [[TMP3:%.*]] = xor i32 [[TMP1]], -1
// CHECK3-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP2]], [[TMP3]]
// CHECK3-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK3-NEXT:    br i1 [[TMP4]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK3:       .master:
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK3-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK3-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK3-NEXT:    [[TMP5:%.*]] = load i16, i16* [[CONV]], align 4
// CHECK3-NEXT:    [[CONV7:%.*]] = sext i16 [[TMP5]] to i32
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[CONV7]], 1
// CHECK3-NEXT:    [[CONV8:%.*]] = trunc i32 [[ADD]] to i16
// CHECK3-NEXT:    store i16 [[CONV8]], i16* [[CONV]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = load i16, i16* [[CONV]], align 4
// CHECK3-NEXT:    [[CONV9:%.*]] = sext i16 [[TMP6]] to i32
// CHECK3-NEXT:    [[ADD10:%.*]] = add nsw i32 [[CONV9]], 2
// CHECK3-NEXT:    [[CONV11:%.*]] = trunc i32 [[ADD10]] to i16
// CHECK3-NEXT:    store i16 [[CONV11]], i16* [[CONV]], align 4
// CHECK3-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK3:       .termination.notifier:
// CHECK3-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTEXIT]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53_worker
// CHECK3-SAME: () #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK3-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK3:       .await.work:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK3-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK3-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK3-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK3:       .select.workers:
// CHECK3-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK3-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK3:       .execute.parallel:
// CHECK3-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK3-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK3-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK3-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK3:       .terminate.parallel:
// CHECK3-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK3-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK3:       .barrier.parallel:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53
// CHECK3-SAME: (i32 [[A:%.*]], [10 x float]* nonnull align 4 dereferenceable(40) [[B:%.*]], i32 [[VLA:%.*]], float* nonnull align 4 dereferenceable(4) [[BN:%.*]], [5 x [10 x double]]* nonnull align 8 dereferenceable(400) [[C:%.*]], i32 [[VLA1:%.*]], i32 [[VLA3:%.*]], double* nonnull align 8 dereferenceable(8) [[CN:%.*]], %struct.TT* nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca [10 x float]*, align 4
// CHECK3-NEXT:    [[VLA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[BN_ADDR:%.*]] = alloca float*, align 4
// CHECK3-NEXT:    [[C_ADDR:%.*]] = alloca [5 x [10 x double]]*, align 4
// CHECK3-NEXT:    [[VLA_ADDR2:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[VLA_ADDR4:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[CN_ADDR:%.*]] = alloca double*, align 4
// CHECK3-NEXT:    [[D_ADDR:%.*]] = alloca %struct.TT*, align 4
// CHECK3-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK3-NEXT:    store [10 x float]* [[B]], [10 x float]** [[B_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA]], i32* [[VLA_ADDR]], align 4
// CHECK3-NEXT:    store float* [[BN]], float** [[BN_ADDR]], align 4
// CHECK3-NEXT:    store [5 x [10 x double]]* [[C]], [5 x [10 x double]]** [[C_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA1]], i32* [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    store i32 [[VLA3]], i32* [[VLA_ADDR4]], align 4
// CHECK3-NEXT:    store double* [[CN]], double** [[CN_ADDR]], align 4
// CHECK3-NEXT:    store %struct.TT* [[D]], %struct.TT** [[D_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load [10 x float]*, [10 x float]** [[B_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, i32* [[VLA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load float*, float** [[BN_ADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load [5 x [10 x double]]*, [5 x [10 x double]]** [[C_ADDR]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, i32* [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    [[TMP5:%.*]] = load i32, i32* [[VLA_ADDR4]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = load double*, double** [[CN_ADDR]], align 4
// CHECK3-NEXT:    [[TMP7:%.*]] = load %struct.TT*, %struct.TT** [[D_ADDR]], align 4
// CHECK3-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK3-NEXT:    [[TMP8:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK3-NEXT:    br i1 [[TMP8]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK3:       .worker:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53_worker() #[[ATTR2]]
// CHECK3-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK3:       .mastercheck:
// CHECK3-NEXT:    [[NVPTX_TID5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE7:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[TMP9:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE7]], 1
// CHECK3-NEXT:    [[TMP10:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS6]], 1
// CHECK3-NEXT:    [[TMP11:%.*]] = xor i32 [[TMP9]], -1
// CHECK3-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP10]], [[TMP11]]
// CHECK3-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[NVPTX_TID5]], [[MASTER_TID]]
// CHECK3-NEXT:    br i1 [[TMP12]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK3:       .master:
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS8:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE9:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT10:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS8]], [[NVPTX_WARP_SIZE9]]
// CHECK3-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT10]], i16 1)
// CHECK3-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK3-NEXT:    [[TMP13:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP13]], 1
// CHECK3-NEXT:    store i32 [[ADD]], i32* [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x float], [10 x float]* [[TMP0]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP14:%.*]] = load float, float* [[ARRAYIDX]], align 4
// CHECK3-NEXT:    [[CONV:%.*]] = fpext float [[TMP14]] to double
// CHECK3-NEXT:    [[ADD11:%.*]] = fadd double [[CONV]], 1.000000e+00
// CHECK3-NEXT:    [[CONV12:%.*]] = fptrunc double [[ADD11]] to float
// CHECK3-NEXT:    store float [[CONV12]], float* [[ARRAYIDX]], align 4
// CHECK3-NEXT:    [[ARRAYIDX13:%.*]] = getelementptr inbounds float, float* [[TMP2]], i32 3
// CHECK3-NEXT:    [[TMP15:%.*]] = load float, float* [[ARRAYIDX13]], align 4
// CHECK3-NEXT:    [[CONV14:%.*]] = fpext float [[TMP15]] to double
// CHECK3-NEXT:    [[ADD15:%.*]] = fadd double [[CONV14]], 1.000000e+00
// CHECK3-NEXT:    [[CONV16:%.*]] = fptrunc double [[ADD15]] to float
// CHECK3-NEXT:    store float [[CONV16]], float* [[ARRAYIDX13]], align 4
// CHECK3-NEXT:    [[ARRAYIDX17:%.*]] = getelementptr inbounds [5 x [10 x double]], [5 x [10 x double]]* [[TMP3]], i32 0, i32 1
// CHECK3-NEXT:    [[ARRAYIDX18:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYIDX17]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP16:%.*]] = load double, double* [[ARRAYIDX18]], align 8
// CHECK3-NEXT:    [[ADD19:%.*]] = fadd double [[TMP16]], 1.000000e+00
// CHECK3-NEXT:    store double [[ADD19]], double* [[ARRAYIDX18]], align 8
// CHECK3-NEXT:    [[TMP17:%.*]] = mul nsw i32 1, [[TMP5]]
// CHECK3-NEXT:    [[ARRAYIDX20:%.*]] = getelementptr inbounds double, double* [[TMP6]], i32 [[TMP17]]
// CHECK3-NEXT:    [[ARRAYIDX21:%.*]] = getelementptr inbounds double, double* [[ARRAYIDX20]], i32 3
// CHECK3-NEXT:    [[TMP18:%.*]] = load double, double* [[ARRAYIDX21]], align 8
// CHECK3-NEXT:    [[ADD22:%.*]] = fadd double [[TMP18]], 1.000000e+00
// CHECK3-NEXT:    store double [[ADD22]], double* [[ARRAYIDX21]], align 8
// CHECK3-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], %struct.TT* [[TMP7]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP19:%.*]] = load i64, i64* [[X]], align 8
// CHECK3-NEXT:    [[ADD23:%.*]] = add nsw i64 [[TMP19]], 1
// CHECK3-NEXT:    store i64 [[ADD23]], i64* [[X]], align 8
// CHECK3-NEXT:    [[Y:%.*]] = getelementptr inbounds [[STRUCT_TT]], %struct.TT* [[TMP7]], i32 0, i32 1
// CHECK3-NEXT:    [[TMP20:%.*]] = load i8, i8* [[Y]], align 8
// CHECK3-NEXT:    [[CONV24:%.*]] = sext i8 [[TMP20]] to i32
// CHECK3-NEXT:    [[ADD25:%.*]] = add nsw i32 [[CONV24]], 1
// CHECK3-NEXT:    [[CONV26:%.*]] = trunc i32 [[ADD25]] to i8
// CHECK3-NEXT:    store i8 [[CONV26]], i8* [[Y]], align 8
// CHECK3-NEXT:    [[CALL:%.*]] = call nonnull align 8 dereferenceable(8) i64* @_ZN2TTIxcEixEi(%struct.TT* nonnull dereferenceable(16) [[TMP7]], i32 0) #[[ATTR7:[0-9]+]]
// CHECK3-NEXT:    [[TMP21:%.*]] = load i64, i64* [[CALL]], align 8
// CHECK3-NEXT:    [[ADD27:%.*]] = add nsw i64 [[TMP21]], 1
// CHECK3-NEXT:    store i64 [[ADD27]], i64* [[CALL]], align 8
// CHECK3-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK3:       .termination.notifier:
// CHECK3-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTEXIT]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2TTIxcEixEi
// CHECK3-SAME: (%struct.TT* nonnull dereferenceable(16) [[THIS:%.*]], i32 [[I:%.*]]) #[[ATTR5:[0-9]+]] comdat align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.TT*, align 4
// CHECK3-NEXT:    [[I_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    store %struct.TT* [[THIS]], %struct.TT** [[THIS_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[I]], i32* [[I_ADDR]], align 4
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.TT*, %struct.TT** [[THIS_ADDR]], align 4
// CHECK3-NEXT:    [[X:%.*]] = getelementptr inbounds [[STRUCT_TT:%.*]], %struct.TT* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT:    ret i64* [[X]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90_worker
// CHECK3-SAME: () #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK3-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK3:       .await.work:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK3-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK3-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK3-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK3:       .select.workers:
// CHECK3-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK3-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK3:       .execute.parallel:
// CHECK3-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK3-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK3-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK3-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK3:       .terminate.parallel:
// CHECK3-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK3-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK3:       .barrier.parallel:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90
// CHECK3-SAME: (i32 [[A:%.*]], i32 [[AA:%.*]], i32 [[AAA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// 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 [10 x i32]*, align 4
// CHECK3-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AA]], i32* [[AA_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AAA]], i32* [[AAA_ADDR]], align 4
// CHECK3-NEXT:    store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK3-NEXT:    [[CONV:%.*]] = bitcast i32* [[AA_ADDR]] to i16*
// CHECK3-NEXT:    [[CONV1:%.*]] = bitcast i32* [[AAA_ADDR]] to i8*
// CHECK3-NEXT:    [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK3-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK3-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK3-NEXT:    br i1 [[TMP1]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK3:       .worker:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90_worker() #[[ATTR2]]
// CHECK3-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK3:       .mastercheck:
// CHECK3-NEXT:    [[NVPTX_TID2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE4]], 1
// CHECK3-NEXT:    [[TMP3:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS3]], 1
// CHECK3-NEXT:    [[TMP4:%.*]] = xor i32 [[TMP2]], -1
// CHECK3-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP3]], [[TMP4]]
// CHECK3-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[NVPTX_TID2]], [[MASTER_TID]]
// CHECK3-NEXT:    br i1 [[TMP5]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK3:       .master:
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT7:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS5]], [[NVPTX_WARP_SIZE6]]
// CHECK3-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT7]], i16 1)
// CHECK3-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK3-NEXT:    [[TMP6:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP6]], 1
// CHECK3-NEXT:    store i32 [[ADD]], i32* [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP7:%.*]] = load i16, i16* [[CONV]], align 4
// CHECK3-NEXT:    [[CONV8:%.*]] = sext i16 [[TMP7]] to i32
// CHECK3-NEXT:    [[ADD9:%.*]] = add nsw i32 [[CONV8]], 1
// CHECK3-NEXT:    [[CONV10:%.*]] = trunc i32 [[ADD9]] to i16
// CHECK3-NEXT:    store i16 [[CONV10]], i16* [[CONV]], align 4
// CHECK3-NEXT:    [[TMP8:%.*]] = load i8, i8* [[CONV1]], align 4
// CHECK3-NEXT:    [[CONV11:%.*]] = sext i8 [[TMP8]] to i32
// CHECK3-NEXT:    [[ADD12:%.*]] = add nsw i32 [[CONV11]], 1
// CHECK3-NEXT:    [[CONV13:%.*]] = trunc i32 [[ADD12]] to i8
// CHECK3-NEXT:    store i8 [[CONV13]], i8* [[CONV1]], align 4
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP9:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK3-NEXT:    [[ADD14:%.*]] = add nsw i32 [[TMP9]], 1
// CHECK3-NEXT:    store i32 [[ADD14]], i32* [[ARRAYIDX]], align 4
// CHECK3-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK3:       .termination.notifier:
// CHECK3-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTEXIT]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108_worker
// CHECK3-SAME: () #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK3-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK3:       .await.work:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK3-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK3-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK3-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK3:       .select.workers:
// CHECK3-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK3-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK3:       .execute.parallel:
// CHECK3-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK3-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK3-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK3-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK3:       .terminate.parallel:
// CHECK3-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK3-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK3:       .barrier.parallel:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108
// CHECK3-SAME: (%struct.S1* [[THIS:%.*]], i32 [[B:%.*]], i32 [[VLA:%.*]], i32 [[VLA1:%.*]], i16* nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, 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 i16*, align 4
// CHECK3-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[B]], i32* [[B_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA]], i32* [[VLA_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[VLA1]], i32* [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    store i16* [[C]], i16** [[C_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32, i32* [[VLA_ADDR]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[VLA_ADDR2]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load i16*, i16** [[C_ADDR]], align 4
// CHECK3-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK3-NEXT:    [[TMP4:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK3-NEXT:    br i1 [[TMP4]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK3:       .worker:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108_worker() #[[ATTR2]]
// CHECK3-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK3:       .mastercheck:
// CHECK3-NEXT:    [[NVPTX_TID3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[TMP5:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE5]], 1
// CHECK3-NEXT:    [[TMP6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], 1
// CHECK3-NEXT:    [[TMP7:%.*]] = xor i32 [[TMP5]], -1
// CHECK3-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP6]], [[TMP7]]
// CHECK3-NEXT:    [[TMP8:%.*]] = icmp eq i32 [[NVPTX_TID3]], [[MASTER_TID]]
// CHECK3-NEXT:    br i1 [[TMP8]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK3:       .master:
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS6:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE7:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT8:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS6]], [[NVPTX_WARP_SIZE7]]
// CHECK3-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT8]], i16 1)
// CHECK3-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK3-NEXT:    [[TMP9:%.*]] = load i32, i32* [[B_ADDR]], align 4
// CHECK3-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP9]] to double
// CHECK3-NEXT:    [[ADD:%.*]] = fadd double [[CONV]], 1.500000e+00
// CHECK3-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK3-NEXT:    store double [[ADD]], double* [[A]], align 8
// CHECK3-NEXT:    [[A9:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP10:%.*]] = load double, double* [[A9]], align 8
// CHECK3-NEXT:    [[INC:%.*]] = fadd double [[TMP10]], 1.000000e+00
// CHECK3-NEXT:    store double [[INC]], double* [[A9]], align 8
// CHECK3-NEXT:    [[CONV10:%.*]] = fptosi double [[INC]] to i16
// CHECK3-NEXT:    [[TMP11:%.*]] = mul nsw i32 1, [[TMP2]]
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, i16* [[TMP3]], i32 [[TMP11]]
// CHECK3-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds i16, i16* [[ARRAYIDX]], i32 1
// CHECK3-NEXT:    store i16 [[CONV10]], i16* [[ARRAYIDX11]], align 2
// CHECK3-NEXT:    [[A12:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP12:%.*]] = load double, double* [[A12]], align 8
// CHECK3-NEXT:    [[CONV13:%.*]] = fptosi double [[TMP12]] to i32
// CHECK3-NEXT:    [[A14:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
// CHECK3-NEXT:    [[CALL:%.*]] = call i32 @_Z3baziRd(i32 [[CONV13]], double* nonnull align 8 dereferenceable(8) [[A14]]) #[[ATTR7]]
// CHECK3-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK3:       .termination.notifier:
// CHECK3-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTEXIT]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z3baziRd
// CHECK3-SAME: (i32 [[F3:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR5]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[F2:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca double*, align 4
// CHECK3-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [2 x i8*], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3:[0-9]+]])
// CHECK3-NEXT:    [[TMP1:%.*]] = call i16 @__kmpc_parallel_level(%struct.ident_t* @[[GLOB3]], i32 [[TMP0]])
// CHECK3-NEXT:    [[TMP2:%.*]] = icmp eq i16 [[TMP1]], 0
// CHECK3-NEXT:    [[TMP3:%.*]] = call i8 @__kmpc_is_spmd_exec_mode() #[[ATTR2]]
// CHECK3-NEXT:    [[TMP4:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK3-NEXT:    br i1 [[TMP4]], label [[DOTSPMD:%.*]], label [[DOTNON_SPMD:%.*]]
// CHECK3:       .spmd:
// CHECK3-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK3:       .non-spmd:
// CHECK3-NEXT:    [[TMP5:%.*]] = select i1 [[TMP2]], i32 4, i32 128
// CHECK3-NEXT:    [[TMP6:%.*]] = call i8* @__kmpc_data_sharing_coalesced_push_stack(i32 [[TMP5]], i16 0)
// CHECK3-NEXT:    [[TMP7:%.*]] = bitcast i8* [[TMP6]] to %struct._globalized_locals_ty*
// CHECK3-NEXT:    br label [[DOTEXIT]]
// CHECK3:       .exit:
// CHECK3-NEXT:    [[_SELECT_STACK:%.*]] = phi %struct._globalized_locals_ty* [ null, [[DOTSPMD]] ], [ [[TMP7]], [[DOTNON_SPMD]] ]
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast %struct._globalized_locals_ty* [[_SELECT_STACK]] to %struct._globalized_locals_ty.0*
// CHECK3-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT__GLOBALIZED_LOCALS_TY:%.*]], %struct._globalized_locals_ty* [[_SELECT_STACK]], i32 0, i32 0
// CHECK3-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_LANE_ID:%.*]] = and i32 [[NVPTX_TID]], 31
// CHECK3-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [32 x i32], [32 x i32]* [[F]], i32 0, i32 [[NVPTX_LANE_ID]]
// CHECK3-NEXT:    [[F1:%.*]] = getelementptr inbounds [[STRUCT__GLOBALIZED_LOCALS_TY_0:%.*]], %struct._globalized_locals_ty.0* [[TMP8]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP10:%.*]] = select i1 [[TMP2]], i32* [[F1]], i32* [[TMP9]]
// CHECK3-NEXT:    [[TMP11:%.*]] = select i1 [[TMP4]], i32* [[F2]], i32* [[TMP10]]
// CHECK3-NEXT:    store i32 [[F3]], i32* [[TMP11]], align 4
// CHECK3-NEXT:    store double* [[A]], double** [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP12:%.*]] = load double*, double** [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP14:%.*]] = bitcast i32* [[TMP11]] to i8*
// CHECK3-NEXT:    store i8* [[TMP14]], i8** [[TMP13]], align 4
// CHECK3-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 1
// CHECK3-NEXT:    [[TMP16:%.*]] = bitcast double* [[TMP12]] to i8*
// CHECK3-NEXT:    store i8* [[TMP16]], i8** [[TMP15]], align 4
// CHECK3-NEXT:    [[TMP17:%.*]] = bitcast [2 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK3-NEXT:    call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB3]], i32 [[TMP0]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*, double*)* @__omp_outlined__1 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__1_wrapper to i8*), i8** [[TMP17]], i32 2)
// CHECK3-NEXT:    [[TMP18:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK3-NEXT:    store i32 [[TMP18]], i32* [[RETVAL]], align 4
// CHECK3-NEXT:    br i1 [[TMP4]], label [[DOTEXIT5:%.*]], label [[DOTNON_SPMD4:%.*]]
// CHECK3:       .non-spmd4:
// CHECK3-NEXT:    [[TMP19:%.*]] = bitcast %struct._globalized_locals_ty* [[_SELECT_STACK]] to i8*
// CHECK3-NEXT:    call void @__kmpc_data_sharing_pop_stack(i8* [[TMP19]])
// CHECK3-NEXT:    br label [[DOTEXIT5]]
// CHECK3:       .exit5:
// CHECK3-NEXT:    [[TMP20:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK3-NEXT:    ret i32 [[TMP20]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142_worker
// CHECK3-SAME: () #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK3-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK3:       .await.work:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK3-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK3-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK3-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK3:       .select.workers:
// CHECK3-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK3-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK3:       .execute.parallel:
// CHECK3-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK3-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK3-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK3-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK3:       .terminate.parallel:
// CHECK3-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK3-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK3:       .barrier.parallel:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142
// CHECK3-SAME: () #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK3-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK3-NEXT:    br i1 [[TMP0]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK3:       .worker:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142_worker() #[[ATTR2]]
// CHECK3-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK3:       .mastercheck:
// CHECK3-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[TMP1:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK3-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK3-NEXT:    [[TMP3:%.*]] = xor i32 [[TMP1]], -1
// CHECK3-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP2]], [[TMP3]]
// CHECK3-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK3-NEXT:    br i1 [[TMP4]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK3:       .master:
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK3-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK3-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK3-NEXT:    call void @_Z6asserti(i32 0) #[[ATTR8:[0-9]+]]
// CHECK3-NEXT:    unreachable
// CHECK3:       5:
// CHECK3-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK3:       .termination.notifier:
// CHECK3-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTEXIT]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74_worker
// CHECK3-SAME: () #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[WORK_FN:%.*]] = alloca i8*, align 4
// CHECK3-NEXT:    [[EXEC_STATUS:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    store i8* null, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    store i8 0, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK:%.*]]
// CHECK3:       .await.work:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    [[TMP0:%.*]] = call i1 @__kmpc_kernel_parallel(i8** [[WORK_FN]])
// CHECK3-NEXT:    [[TMP1:%.*]] = zext i1 [[TMP0]] to i8
// CHECK3-NEXT:    store i8 [[TMP1]], i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[WORK_FN]], align 4
// CHECK3-NEXT:    [[SHOULD_TERMINATE:%.*]] = icmp eq i8* [[TMP2]], null
// CHECK3-NEXT:    br i1 [[SHOULD_TERMINATE]], label [[DOTEXIT:%.*]], label [[DOTSELECT_WORKERS:%.*]]
// CHECK3:       .select.workers:
// CHECK3-NEXT:    [[TMP3:%.*]] = load i8, i8* [[EXEC_STATUS]], align 1
// CHECK3-NEXT:    [[IS_ACTIVE:%.*]] = icmp ne i8 [[TMP3]], 0
// CHECK3-NEXT:    br i1 [[IS_ACTIVE]], label [[DOTEXECUTE_PARALLEL:%.*]], label [[DOTBARRIER_PARALLEL:%.*]]
// CHECK3:       .execute.parallel:
// CHECK3-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
// CHECK3-NEXT:    [[TMP5:%.*]] = bitcast i8* [[TMP2]] to void (i16, i32)*
// CHECK3-NEXT:    call void [[TMP5]](i16 0, i32 [[TMP4]])
// CHECK3-NEXT:    br label [[DOTTERMINATE_PARALLEL:%.*]]
// CHECK3:       .terminate.parallel:
// CHECK3-NEXT:    call void @__kmpc_kernel_end_parallel()
// CHECK3-NEXT:    br label [[DOTBARRIER_PARALLEL]]
// CHECK3:       .barrier.parallel:
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTAWAIT_WORK]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74
// CHECK3-SAME: (i32 [[A:%.*]], i32 [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK3-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK3-NEXT:    store i32 [[AA]], i32* [[AA_ADDR]], align 4
// CHECK3-NEXT:    store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK3-NEXT:    [[CONV:%.*]] = bitcast i32* [[AA_ADDR]] to i16*
// CHECK3-NEXT:    [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK3-NEXT:    [[NVPTX_TID:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS]], [[NVPTX_WARP_SIZE]]
// CHECK3-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[NVPTX_TID]], [[THREAD_LIMIT]]
// CHECK3-NEXT:    br i1 [[TMP1]], label [[DOTWORKER:%.*]], label [[DOTMASTERCHECK:%.*]]
// CHECK3:       .worker:
// CHECK3-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74_worker() #[[ATTR2]]
// CHECK3-NEXT:    br label [[DOTEXIT:%.*]]
// CHECK3:       .mastercheck:
// CHECK3-NEXT:    [[NVPTX_TID1:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS2:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE3:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[TMP2:%.*]] = sub nuw i32 [[NVPTX_WARP_SIZE3]], 1
// CHECK3-NEXT:    [[TMP3:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS2]], 1
// CHECK3-NEXT:    [[TMP4:%.*]] = xor i32 [[TMP2]], -1
// CHECK3-NEXT:    [[MASTER_TID:%.*]] = and i32 [[TMP3]], [[TMP4]]
// CHECK3-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[NVPTX_TID1]], [[MASTER_TID]]
// CHECK3-NEXT:    br i1 [[TMP5]], label [[DOTMASTER:%.*]], label [[DOTEXIT]]
// CHECK3:       .master:
// CHECK3-NEXT:    [[NVPTX_NUM_THREADS4:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT:    [[NVPTX_WARP_SIZE5:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK3-NEXT:    [[THREAD_LIMIT6:%.*]] = sub nuw i32 [[NVPTX_NUM_THREADS4]], [[NVPTX_WARP_SIZE5]]
// CHECK3-NEXT:    call void @__kmpc_kernel_init(i32 [[THREAD_LIMIT6]], i16 1)
// CHECK3-NEXT:    call void @__kmpc_data_sharing_init_stack()
// CHECK3-NEXT:    [[TMP6:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK3-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP6]], 1
// CHECK3-NEXT:    store i32 [[ADD]], i32* [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP7:%.*]] = load i16, i16* [[CONV]], align 4
// CHECK3-NEXT:    [[CONV7:%.*]] = sext i16 [[TMP7]] to i32
// CHECK3-NEXT:    [[ADD8:%.*]] = add nsw i32 [[CONV7]], 1
// CHECK3-NEXT:    [[CONV9:%.*]] = trunc i32 [[ADD8]] to i16
// CHECK3-NEXT:    store i16 [[CONV9]], i16* [[CONV]], align 4
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK3-NEXT:    [[ADD10:%.*]] = add nsw i32 [[TMP8]], 1
// CHECK3-NEXT:    store i32 [[ADD10]], i32* [[ARRAYIDX]], align 4
// CHECK3-NEXT:    br label [[DOTTERMINATION_NOTIFIER:%.*]]
// CHECK3:       .termination.notifier:
// CHECK3-NEXT:    call void @__kmpc_kernel_deinit(i16 1)
// CHECK3-NEXT:    call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK3-NEXT:    br label [[DOTEXIT]]
// CHECK3:       .exit:
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__omp_outlined__1
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[F:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT:    [[F_ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT:    [[A_ADDR:%.*]] = alloca double*, align 4
// CHECK3-NEXT:    [[TMP:%.*]] = alloca double*, align 4
// CHECK3-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT:    store i32* [[F]], i32** [[F_ADDR]], align 4
// CHECK3-NEXT:    store double* [[A]], double** [[A_ADDR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[F_ADDR]], align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = load double*, double** [[A_ADDR]], align 4
// CHECK3-NEXT:    store double* [[TMP1]], double** [[TMP]], align 4
// CHECK3-NEXT:    [[TMP2:%.*]] = load double*, double** [[TMP]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load double, double* [[TMP2]], align 8
// CHECK3-NEXT:    [[ADD:%.*]] = fadd double 2.000000e+00, [[TMP3]]
// CHECK3-NEXT:    [[CONV:%.*]] = fptosi double [[ADD]] to i32
// CHECK3-NEXT:    store i32 [[CONV]], i32* [[TMP0]], align 4
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper
// CHECK3-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[GLOBAL_ARGS:%.*]] = alloca i8**, align 4
// CHECK3-NEXT:    store i32 0, i32* [[DOTZERO_ADDR]], align 4
// CHECK3-NEXT:    store i16 [[TMP0]], i16* [[DOTADDR]], align 2
// CHECK3-NEXT:    store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
// CHECK3-NEXT:    call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
// CHECK3-NEXT:    [[TMP2:%.*]] = load i8**, i8*** [[GLOBAL_ARGS]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i32 0
// CHECK3-NEXT:    [[TMP4:%.*]] = bitcast i8** [[TMP3]] to i32**
// CHECK3-NEXT:    [[TMP5:%.*]] = load i32*, i32** [[TMP4]], align 4
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i32 1
// CHECK3-NEXT:    [[TMP7:%.*]] = bitcast i8** [[TMP6]] to double**
// CHECK3-NEXT:    [[TMP8:%.*]] = load double*, double** [[TMP7]], align 4
// CHECK3-NEXT:    call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]], i32* [[TMP5]], double* [[TMP8]]) #[[ATTR2]]
// CHECK3-NEXT:    ret void
//