llvm/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp

// 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 _
// RUN: %clang_cc1 -no-enable-noundef-analysis -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -no-enable-noundef-analysis -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown  -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -no-enable-noundef-analysis -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -no-enable-noundef-analysis -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -no-enable-noundef-analysis -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fexceptions -fcxx-exceptions -aux-triple powerpc64le-unknown-unknown -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix=CHECK1
// expected-no-diagnostics
#ifndef HEADER
#define HEADER

#include <complex>

// Verify we do not add tbaa metadata to type punned memory operations:
template <typename T>
void complex_reduction() {
#pragma omp target teams distribute
  for (int ib = 0; ib < 100; ib++) {
    std::complex<T> partial_sum;
    const int istart = ib * 4;
    const int iend = (ib + 1) * 4;
#pragma omp parallel for reduction(+ \
                                   : partial_sum)
    for (int i = istart; i < iend; i++)
      partial_sum += std::complex<T>(i, i);
  }
}

void test() {
  complex_reduction<float>();
  complex_reduction<double>();
}
#endif
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16
// CHECK1-SAME: (ptr noalias [[DYN_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DYN_PTR_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    store ptr [[DYN_PTR]], ptr [[DYN_PTR_ADDR]], align 8, !tbaa [[TBAA10:![0-9]+]]
// CHECK1-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_target_init(ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_kernel_environment, ptr [[DYN_PTR]])
// CHECK1-NEXT:    [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
// CHECK1-NEXT:    br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
// CHECK1:       user_code.entry:
// CHECK1-NEXT:    [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
// CHECK1-NEXT:    store i32 0, ptr [[DOTZERO_ADDR]], align 4
// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTTHREADID_TEMP_]], align 4, !tbaa [[TBAA14:![0-9]+]]
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined(ptr [[DOTTHREADID_TEMP_]], ptr [[DOTZERO_ADDR]]) #[[ATTR4:[0-9]+]]
// CHECK1-NEXT:    call void @__kmpc_target_deinit()
// CHECK1-NEXT:    ret void
// CHECK1:       worker.exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined
// CHECK1-SAME: (ptr noalias [[DOTGLOBAL_TID_:%.*]], ptr noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[TMP:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[IB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[REF_TMP:%.*]] = alloca float, align 4
// CHECK1-NEXT:    [[REF_TMP2:%.*]] = alloca float, align 4
// CHECK1-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x ptr], align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[ISTART:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 4)
// CHECK1-NEXT:    [[IEND:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 4)
// CHECK1-NEXT:    [[PARTIAL_SUM:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 8)
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 99, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[IB]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @__kmpc_distribute_static_init_4(ptr @[[GLOB2:[0-9]+]], i32 [[TMP1]], i32 92, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_LB]], ptr [[DOTOMP_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP2]], 99
// CHECK1-NEXT:    br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK1:       cond.true:
// CHECK1-NEXT:    br label [[COND_END:%.*]]
// CHECK1:       cond.false:
// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[COND_END]]
// CHECK1:       cond.end:
// CHECK1-NEXT:    [[COND:%.*]] = phi i32 [ 99, [[COND_TRUE]] ], [ [[TMP3]], [[COND_FALSE]] ]
// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK1:       omp.inner.for.cond:
// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CMP1:%.*]] = icmp sle i32 [[TMP5]], [[TMP6]]
// CHECK1-NEXT:    br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK1:       omp.inner.for.cond.cleanup:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_END:%.*]]
// CHECK1:       omp.inner.for.body:
// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP7]], 1
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK1-NEXT:    store i32 [[ADD]], ptr [[IB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP]]) #[[ATTR4]]
// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP]], align 4, !tbaa [[TBAA16:![0-9]+]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP2]]) #[[ATTR4]]
// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP2]], align 4, !tbaa [[TBAA16]]
// CHECK1-NEXT:    call void @_ZNSt7complexIfEC1ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP2]]) #[[ATTR11:[0-9]+]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP2]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[MUL3:%.*]] = mul nsw i32 [[TMP8]], 4
// CHECK1-NEXT:    store i32 [[MUL3]], ptr [[ISTART]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD4:%.*]] = add nsw i32 [[TMP9]], 1
// CHECK1-NEXT:    [[MUL5:%.*]] = mul nsw i32 [[ADD4]], 4
// CHECK1-NEXT:    store i32 [[MUL5]], ptr [[IEND]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[TMP10]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 1
// CHECK1-NEXT:    store ptr [[IEND]], ptr [[TMP11]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 2
// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[TMP12]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    call void @__kmpc_parallel_51(ptr @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined_wrapper, ptr [[CAPTURED_VARS_ADDRS]], i64 3)
// CHECK1-NEXT:    br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK1:       omp.body.continue:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK1:       omp.inner.for.inc:
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP13]], 1
// CHECK1-NEXT:    store i32 [[ADD6]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND]]
// CHECK1:       omp.inner.for.end:
// CHECK1-NEXT:    br label [[OMP_LOOP_EXIT:%.*]]
// CHECK1:       omp.loop.exit:
// CHECK1-NEXT:    call void @__kmpc_distribute_static_fini(ptr @[[GLOB2]], i32 [[TMP1]])
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[IB]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @__kmpc_free_shared(ptr [[PARTIAL_SUM]], i64 8)
// CHECK1-NEXT:    call void @__kmpc_free_shared(ptr [[IEND]], i64 4)
// CHECK1-NEXT:    call void @__kmpc_free_shared(ptr [[ISTART]], i64 4)
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNSt7complexIfEC1ERKfS2_
// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]], ptr nonnull align 4 dereferenceable(4) [[__RE:%.*]], ptr nonnull align 4 dereferenceable(4) [[__IM:%.*]]) unnamed_addr #[[ATTR5:[0-9]+]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__RE_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__IM_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZNSt7complexIfEC2ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[THIS1]], ptr nonnull align 4 dereferenceable(4) [[TMP0]], ptr nonnull align 4 dereferenceable(4) [[TMP1]]) #[[ATTR11]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined
// CHECK1-SAME: (ptr noalias [[DOTGLOBAL_TID_:%.*]], ptr noalias [[DOTBOUND_TID_:%.*]], ptr nonnull align 4 dereferenceable(4) [[ISTART:%.*]], ptr nonnull align 4 dereferenceable(4) [[IEND:%.*]], ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[ISTART_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[IEND_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[PARTIAL_SUM_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[TMP:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTCAPTURE_EXPR_2:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[PARTIAL_SUM5:%.*]] = alloca %"class.std::complex", align 4
// CHECK1-NEXT:    [[REF_TMP:%.*]] = alloca float, align 4
// CHECK1-NEXT:    [[REF_TMP6:%.*]] = alloca float, align 4
// CHECK1-NEXT:    [[I7:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[REF_TMP14:%.*]] = alloca %"class.std::complex", align 4
// CHECK1-NEXT:    [[REF_TMP15:%.*]] = alloca float, align 4
// CHECK1-NEXT:    [[REF_TMP16:%.*]] = alloca float, align 4
// CHECK1-NEXT:    [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x ptr], align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[IEND]], ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP3]], ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_1]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[TMP1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_2]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[SUB:%.*]] = sub i32 [[TMP5]], [[TMP6]]
// CHECK1-NEXT:    [[SUB3:%.*]] = sub i32 [[SUB]], 1
// CHECK1-NEXT:    [[ADD:%.*]] = add i32 [[SUB3]], 1
// CHECK1-NEXT:    [[DIV:%.*]] = udiv i32 [[ADD]], 1
// CHECK1-NEXT:    [[SUB4:%.*]] = sub i32 [[DIV]], 1
// CHECK1-NEXT:    store i32 [[SUB4]], ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP7]], ptr [[I]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CMP:%.*]] = icmp slt i32 [[TMP8]], [[TMP9]]
// CHECK1-NEXT:    br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]]
// CHECK1:       omp.precond.then:
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP10:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP10]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[PARTIAL_SUM5]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP]]) #[[ATTR4]]
// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP]], align 4, !tbaa [[TBAA16]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP6]]) #[[ATTR4]]
// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP6]], align 4, !tbaa [[TBAA16]]
// CHECK1-NEXT:    call void @_ZNSt7complexIfEC1ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP6]]) #[[ATTR11]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP6]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I7]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP11:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, ptr [[TMP11]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @__kmpc_for_static_init_4u(ptr @[[GLOB3:[0-9]+]], i32 [[TMP12]], i32 33, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_LB]], ptr [[DOTOMP_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK1-NEXT:    br label [[OMP_DISPATCH_COND:%.*]]
// CHECK1:       omp.dispatch.cond:
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CMP8:%.*]] = icmp ugt i32 [[TMP13]], [[TMP14]]
// CHECK1-NEXT:    br i1 [[CMP8]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK1:       cond.true:
// CHECK1-NEXT:    [[TMP15:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[COND_END:%.*]]
// CHECK1:       cond.false:
// CHECK1-NEXT:    [[TMP16:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[COND_END]]
// CHECK1:       cond.end:
// CHECK1-NEXT:    [[COND:%.*]] = phi i32 [ [[TMP15]], [[COND_TRUE]] ], [ [[TMP16]], [[COND_FALSE]] ]
// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP17:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP17]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP18:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP19:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD9:%.*]] = add i32 [[TMP19]], 1
// CHECK1-NEXT:    [[CMP10:%.*]] = icmp ult i32 [[TMP18]], [[ADD9]]
// CHECK1-NEXT:    br i1 [[CMP10]], label [[OMP_DISPATCH_BODY:%.*]], label [[OMP_DISPATCH_CLEANUP:%.*]]
// CHECK1:       omp.dispatch.cleanup:
// CHECK1-NEXT:    br label [[OMP_DISPATCH_END:%.*]]
// CHECK1:       omp.dispatch.body:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK1:       omp.inner.for.cond:
// CHECK1-NEXT:    [[TMP20:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP21:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD11:%.*]] = add i32 [[TMP21]], 1
// CHECK1-NEXT:    [[CMP12:%.*]] = icmp ult i32 [[TMP20]], [[ADD11]]
// CHECK1-NEXT:    br i1 [[CMP12]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK1:       omp.inner.for.cond.cleanup:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_END:%.*]]
// CHECK1:       omp.inner.for.body:
// CHECK1-NEXT:    [[TMP22:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP23:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[MUL:%.*]] = mul i32 [[TMP23]], 1
// CHECK1-NEXT:    [[ADD13:%.*]] = add i32 [[TMP22]], [[MUL]]
// CHECK1-NEXT:    store i32 [[ADD13]], ptr [[I7]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP14]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP15]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP24:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP24]] to float
// CHECK1-NEXT:    store float [[CONV]], ptr [[REF_TMP15]], align 4, !tbaa [[TBAA16]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP16]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP25:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CONV17:%.*]] = sitofp i32 [[TMP25]] to float
// CHECK1-NEXT:    store float [[CONV17]], ptr [[REF_TMP16]], align 4, !tbaa [[TBAA16]]
// CHECK1-NEXT:    call void @_ZNSt7complexIfEC1ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[REF_TMP14]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP15]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP16]]) #[[ATTR11]]
// CHECK1-NEXT:    [[CALL:%.*]] = call nonnull align 4 dereferenceable(8) ptr @_ZNSt7complexIfEpLIfEERS0_RKS_IT_E(ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]], ptr nonnull align 4 dereferenceable(8) [[REF_TMP14]]) #[[ATTR11]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP16]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP15]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP14]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK1:       omp.body.continue:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK1:       omp.inner.for.inc:
// CHECK1-NEXT:    [[TMP26:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD18:%.*]] = add i32 [[TMP26]], 1
// CHECK1-NEXT:    store i32 [[ADD18]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND]]
// CHECK1:       omp.inner.for.end:
// CHECK1-NEXT:    br label [[OMP_DISPATCH_INC:%.*]]
// CHECK1:       omp.dispatch.inc:
// CHECK1-NEXT:    [[TMP27:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP28:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD19:%.*]] = add i32 [[TMP27]], [[TMP28]]
// CHECK1-NEXT:    store i32 [[ADD19]], ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP29:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP30:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD20:%.*]] = add i32 [[TMP29]], [[TMP30]]
// CHECK1-NEXT:    store i32 [[ADD20]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[OMP_DISPATCH_COND]]
// CHECK1:       omp.dispatch.end:
// CHECK1-NEXT:    [[TMP31:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @__kmpc_for_static_fini(ptr @[[GLOB3]], i32 [[TMP32]])
// CHECK1-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK1-NEXT:    store ptr [[PARTIAL_SUM5]], ptr [[TMP33]], align 8
// CHECK1-NEXT:    [[TMP34:%.*]] = call i32 @__kmpc_nvptx_parallel_reduce_nowait_v2(ptr @[[GLOB1]], i64 8, ptr [[DOTOMP_REDUCTION_RED_LIST]], ptr @_omp_reduction_shuffle_and_reduce_func, ptr @_omp_reduction_inter_warp_copy_func)
// CHECK1-NEXT:    [[TMP35:%.*]] = icmp eq i32 [[TMP34]], 1
// CHECK1-NEXT:    br i1 [[TMP35]], label [[DOTOMP_REDUCTION_THEN:%.*]], label [[DOTOMP_REDUCTION_DONE:%.*]]
// CHECK1:       .omp.reduction.then:
// CHECK1-NEXT:    [[CALL21:%.*]] = call nonnull align 4 dereferenceable(8) ptr @_ZNSt7complexIfEpLIfEERS0_RKS_IT_E(ptr nonnull align 4 dereferenceable(8) [[TMP2]], ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]]) #[[ATTR11]]
// CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
// CHECK1:       .omp.reduction.done:
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I7]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[PARTIAL_SUM5]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_PRECOND_END]]
// CHECK1:       omp.precond.end:
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTCAPTURE_EXPR_2]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTCAPTURE_EXPR_1]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTCAPTURE_EXPR_]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNSt7complexIfEpLIfEERS0_RKS_IT_E
// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]], ptr nonnull align 4 dereferenceable(8) [[__C:%.*]]) #[[ATTR5]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__C_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__C]], ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[CALL:%.*]] = call float @_ZNKSt7complexIfE4realEv(ptr nonnull align 4 dereferenceable(8) [[TMP0]]) #[[ATTR11]]
// CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds nuw %"class.std::complex", ptr [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP1:%.*]] = load float, ptr [[__RE_]], align 4, !tbaa [[TBAA18:![0-9]+]]
// CHECK1-NEXT:    [[ADD:%.*]] = fadd float [[TMP1]], [[CALL]]
// CHECK1-NEXT:    store float [[ADD]], ptr [[__RE_]], align 4, !tbaa [[TBAA18]]
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[CALL2:%.*]] = call float @_ZNKSt7complexIfE4imagEv(ptr nonnull align 4 dereferenceable(8) [[TMP2]]) #[[ATTR11]]
// CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds nuw %"class.std::complex", ptr [[THIS1]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP3:%.*]] = load float, ptr [[__IM_]], align 4, !tbaa [[TBAA20:![0-9]+]]
// CHECK1-NEXT:    [[ADD3:%.*]] = fadd float [[TMP3]], [[CALL2]]
// CHECK1-NEXT:    store float [[ADD3]], ptr [[__IM_]], align 4, !tbaa [[TBAA20]]
// CHECK1-NEXT:    ret ptr [[THIS1]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_omp_reduction_shuffle_and_reduce_func
// CHECK1-SAME: (ptr noundef [[TMP0:%.*]], i16 noundef signext [[TMP1:%.*]], i16 noundef signext [[TMP2:%.*]], i16 noundef signext [[TMP3:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[DOTADDR2:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[DOTADDR3:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST:%.*]] = alloca [1 x ptr], align 8
// CHECK1-NEXT:    [[DOTOMP_REDUCTION_ELEMENT:%.*]] = alloca %"class.std::complex", align 8
// CHECK1-NEXT:    store ptr [[TMP0]], ptr [[DOTADDR]], align 8
// CHECK1-NEXT:    store i16 [[TMP1]], ptr [[DOTADDR1]], align 2
// CHECK1-NEXT:    store i16 [[TMP2]], ptr [[DOTADDR2]], align 2
// CHECK1-NEXT:    store i16 [[TMP3]], ptr [[DOTADDR3]], align 2
// CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[DOTADDR]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = load i16, ptr [[DOTADDR1]], align 2
// CHECK1-NEXT:    [[TMP6:%.*]] = load i16, ptr [[DOTADDR2]], align 2
// CHECK1-NEXT:    [[TMP7:%.*]] = load i16, ptr [[DOTADDR3]], align 2
// CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP4]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP9:%.*]] = load ptr, ptr [[TMP8]], align 8
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr %"class.std::complex", ptr [[TMP9]], i64 1
// CHECK1-NEXT:    [[TMP12:%.*]] = load i64, ptr [[TMP9]], align 8
// CHECK1-NEXT:    [[TMP13:%.*]] = call i32 @__kmpc_get_warp_size()
// CHECK1-NEXT:    [[TMP14:%.*]] = trunc i32 [[TMP13]] to i16
// CHECK1-NEXT:    [[TMP15:%.*]] = call i64 @__kmpc_shuffle_int64(i64 [[TMP12]], i16 [[TMP6]], i16 [[TMP14]])
// CHECK1-NEXT:    store i64 [[TMP15]], ptr [[DOTOMP_REDUCTION_ELEMENT]], align 8
// CHECK1-NEXT:    [[TMP16:%.*]] = getelementptr i64, ptr [[TMP9]], i64 1
// CHECK1-NEXT:    [[TMP17:%.*]] = getelementptr i64, ptr [[DOTOMP_REDUCTION_ELEMENT]], i64 1
// CHECK1-NEXT:    store ptr [[DOTOMP_REDUCTION_ELEMENT]], ptr [[TMP10]], align 8
// CHECK1-NEXT:    [[TMP18:%.*]] = icmp eq i16 [[TMP7]], 0
// CHECK1-NEXT:    [[TMP19:%.*]] = icmp eq i16 [[TMP7]], 1
// CHECK1-NEXT:    [[TMP20:%.*]] = icmp ult i16 [[TMP5]], [[TMP6]]
// CHECK1-NEXT:    [[TMP21:%.*]] = and i1 [[TMP19]], [[TMP20]]
// CHECK1-NEXT:    [[TMP22:%.*]] = icmp eq i16 [[TMP7]], 2
// CHECK1-NEXT:    [[TMP23:%.*]] = and i16 [[TMP5]], 1
// CHECK1-NEXT:    [[TMP24:%.*]] = icmp eq i16 [[TMP23]], 0
// CHECK1-NEXT:    [[TMP25:%.*]] = and i1 [[TMP22]], [[TMP24]]
// CHECK1-NEXT:    [[TMP26:%.*]] = icmp sgt i16 [[TMP6]], 0
// CHECK1-NEXT:    [[TMP27:%.*]] = and i1 [[TMP25]], [[TMP26]]
// CHECK1-NEXT:    [[TMP28:%.*]] = or i1 [[TMP18]], [[TMP21]]
// CHECK1-NEXT:    [[TMP29:%.*]] = or i1 [[TMP28]], [[TMP27]]
// CHECK1-NEXT:    br i1 [[TMP29]], label [[THEN:%.*]], label [[ELSE:%.*]]
// CHECK1:       then:
// CHECK1-NEXT:    call void @"{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined_omp$reduction$reduction_func"(ptr [[TMP4]], ptr [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[IFCONT:%.*]]
// CHECK1:       else:
// CHECK1-NEXT:    br label [[IFCONT]]
// CHECK1:       ifcont:
// CHECK1-NEXT:    [[TMP30:%.*]] = icmp eq i16 [[TMP7]], 1
// CHECK1-NEXT:    [[TMP31:%.*]] = icmp uge i16 [[TMP5]], [[TMP6]]
// CHECK1-NEXT:    [[TMP32:%.*]] = and i1 [[TMP30]], [[TMP31]]
// CHECK1-NEXT:    br i1 [[TMP32]], label [[THEN4:%.*]], label [[ELSE5:%.*]]
// CHECK1:       then4:
// CHECK1-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP34:%.*]] = load ptr, ptr [[TMP33]], align 8
// CHECK1-NEXT:    [[TMP35:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP4]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP36:%.*]] = load ptr, ptr [[TMP35]], align 8
// CHECK1-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[TMP36]], ptr align 8 [[TMP34]], i64 8, i1 false)
// CHECK1-NEXT:    br label [[IFCONT6:%.*]]
// CHECK1:       else5:
// CHECK1-NEXT:    br label [[IFCONT6]]
// CHECK1:       ifcont6:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_omp_reduction_inter_warp_copy_func
// CHECK1-SAME: (ptr noundef [[TMP0:%.*]], i32 noundef [[TMP1:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTCNT_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    store ptr [[TMP0]], ptr [[DOTADDR]], align 8
// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
// CHECK1-NEXT:    [[TMP3:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
// CHECK1-NEXT:    [[NVPTX_LANE_ID:%.*]] = and i32 [[TMP3]], 31
// CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
// CHECK1-NEXT:    [[NVPTX_WARP_ID:%.*]] = ashr i32 [[TMP4]], 5
// CHECK1-NEXT:    [[TMP5:%.*]] = load ptr, ptr [[DOTADDR]], align 8
// CHECK1-NEXT:    store i32 0, ptr [[DOTCNT_ADDR]], align 4
// CHECK1-NEXT:    br label [[PRECOND:%.*]]
// CHECK1:       precond:
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTCNT_ADDR]], align 4
// CHECK1-NEXT:    [[TMP7:%.*]] = icmp ult i32 [[TMP6]], 2
// CHECK1-NEXT:    br i1 [[TMP7]], label [[BODY:%.*]], label [[EXIT:%.*]]
// CHECK1:       body:
// CHECK1-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK1-NEXT:    call void @__kmpc_barrier(ptr @[[GLOB4:[0-9]+]], i32 [[OMP_GLOBAL_THREAD_NUM]])
// CHECK1-NEXT:    [[WARP_MASTER:%.*]] = icmp eq i32 [[NVPTX_LANE_ID]], 0
// CHECK1-NEXT:    br i1 [[WARP_MASTER]], label [[THEN:%.*]], label [[ELSE:%.*]]
// CHECK1:       then:
// CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP5]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP9:%.*]] = load ptr, ptr [[TMP8]], align 8
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr i32, ptr [[TMP9]], i32 [[TMP6]]
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [32 x i32], ptr addrspace(3) @__openmp_nvptx_data_transfer_temporary_storage, i64 0, i32 [[NVPTX_WARP_ID]]
// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, ptr [[TMP10]], align 4
// CHECK1-NEXT:    store volatile i32 [[TMP12]], ptr addrspace(3) [[TMP11]], align 4
// CHECK1-NEXT:    br label [[IFCONT:%.*]]
// CHECK1:       else:
// CHECK1-NEXT:    br label [[IFCONT]]
// CHECK1:       ifcont:
// CHECK1-NEXT:    [[OMP_GLOBAL_THREAD_NUM2:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK1-NEXT:    call void @__kmpc_barrier(ptr @[[GLOB4]], i32 [[OMP_GLOBAL_THREAD_NUM2]])
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTADDR1]], align 4
// CHECK1-NEXT:    [[IS_ACTIVE_THREAD:%.*]] = icmp ult i32 [[TMP2]], [[TMP13]]
// CHECK1-NEXT:    br i1 [[IS_ACTIVE_THREAD]], label [[THEN3:%.*]], label [[ELSE4:%.*]]
// CHECK1:       then3:
// CHECK1-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [32 x i32], ptr addrspace(3) @__openmp_nvptx_data_transfer_temporary_storage, i64 0, i32 [[TMP2]]
// CHECK1-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP5]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP16:%.*]] = load ptr, ptr [[TMP15]], align 8
// CHECK1-NEXT:    [[TMP17:%.*]] = getelementptr i32, ptr [[TMP16]], i32 [[TMP6]]
// CHECK1-NEXT:    [[TMP18:%.*]] = load volatile i32, ptr addrspace(3) [[TMP14]], align 4
// CHECK1-NEXT:    store i32 [[TMP18]], ptr [[TMP17]], align 4
// CHECK1-NEXT:    br label [[IFCONT5:%.*]]
// CHECK1:       else4:
// CHECK1-NEXT:    br label [[IFCONT5]]
// CHECK1:       ifcont5:
// CHECK1-NEXT:    [[TMP19:%.*]] = add nsw i32 [[TMP6]], 1
// CHECK1-NEXT:    store i32 [[TMP19]], ptr [[DOTCNT_ADDR]], align 4
// CHECK1-NEXT:    br label [[PRECOND]]
// CHECK1:       exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined_wrapper
// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR8:[0-9]+]] {
// 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 ptr, align 8
// CHECK1-NEXT:    store i16 [[TMP0]], ptr [[DOTADDR]], align 2, !tbaa [[TBAA21:![0-9]+]]
// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTZERO_ADDR]], align 4
// CHECK1-NEXT:    call void @__kmpc_get_shared_variables(ptr [[GLOBAL_ARGS]])
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[GLOBAL_ARGS]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 0
// CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[TMP3]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 1
// CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[TMP5]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 2
// CHECK1-NEXT:    [[TMP8:%.*]] = load ptr, ptr [[TMP7]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined(ptr [[DOTADDR1]], ptr [[DOTZERO_ADDR]], ptr [[TMP4]], ptr [[TMP6]], ptr [[TMP8]]) #[[ATTR4]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16
// CHECK1-SAME: (ptr noalias [[DYN_PTR:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DYN_PTR_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    store ptr [[DYN_PTR]], ptr [[DYN_PTR_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_target_init(ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_kernel_environment, ptr [[DYN_PTR]])
// CHECK1-NEXT:    [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
// CHECK1-NEXT:    br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
// CHECK1:       user_code.entry:
// CHECK1-NEXT:    [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK1-NEXT:    store i32 0, ptr [[DOTZERO_ADDR]], align 4
// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTTHREADID_TEMP_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined(ptr [[DOTTHREADID_TEMP_]], ptr [[DOTZERO_ADDR]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @__kmpc_target_deinit()
// CHECK1-NEXT:    ret void
// CHECK1:       worker.exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined
// CHECK1-SAME: (ptr noalias [[DOTGLOBAL_TID_:%.*]], ptr noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[TMP:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[IB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[REF_TMP:%.*]] = alloca double, align 8
// CHECK1-NEXT:    [[REF_TMP2:%.*]] = alloca double, align 8
// CHECK1-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x ptr], align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[ISTART:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 4)
// CHECK1-NEXT:    [[IEND:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 4)
// CHECK1-NEXT:    [[PARTIAL_SUM:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 16)
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 99, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[IB]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @__kmpc_distribute_static_init_4(ptr @[[GLOB2]], i32 [[TMP1]], i32 92, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_LB]], ptr [[DOTOMP_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP2]], 99
// CHECK1-NEXT:    br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK1:       cond.true:
// CHECK1-NEXT:    br label [[COND_END:%.*]]
// CHECK1:       cond.false:
// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[COND_END]]
// CHECK1:       cond.end:
// CHECK1-NEXT:    [[COND:%.*]] = phi i32 [ 99, [[COND_TRUE]] ], [ [[TMP3]], [[COND_FALSE]] ]
// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK1:       omp.inner.for.cond:
// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CMP1:%.*]] = icmp sle i32 [[TMP5]], [[TMP6]]
// CHECK1-NEXT:    br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK1:       omp.inner.for.cond.cleanup:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_END:%.*]]
// CHECK1:       omp.inner.for.body:
// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP7]], 1
// CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK1-NEXT:    store i32 [[ADD]], ptr [[IB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP]]) #[[ATTR4]]
// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP]], align 8, !tbaa [[TBAA23:![0-9]+]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP2]]) #[[ATTR4]]
// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP2]], align 8, !tbaa [[TBAA23]]
// CHECK1-NEXT:    call void @_ZNSt7complexIdEC1ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP2]]) #[[ATTR11]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP2]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[MUL3:%.*]] = mul nsw i32 [[TMP8]], 4
// CHECK1-NEXT:    store i32 [[MUL3]], ptr [[ISTART]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD4:%.*]] = add nsw i32 [[TMP9]], 1
// CHECK1-NEXT:    [[MUL5:%.*]] = mul nsw i32 [[ADD4]], 4
// CHECK1-NEXT:    store i32 [[MUL5]], ptr [[IEND]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[TMP10]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 1
// CHECK1-NEXT:    store ptr [[IEND]], ptr [[TMP11]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 2
// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[TMP12]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    call void @__kmpc_parallel_51(ptr @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined_wrapper, ptr [[CAPTURED_VARS_ADDRS]], i64 3)
// CHECK1-NEXT:    br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK1:       omp.body.continue:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK1:       omp.inner.for.inc:
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP13]], 1
// CHECK1-NEXT:    store i32 [[ADD6]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND]]
// CHECK1:       omp.inner.for.end:
// CHECK1-NEXT:    br label [[OMP_LOOP_EXIT:%.*]]
// CHECK1:       omp.loop.exit:
// CHECK1-NEXT:    call void @__kmpc_distribute_static_fini(ptr @[[GLOB2]], i32 [[TMP1]])
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[IB]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @__kmpc_free_shared(ptr [[PARTIAL_SUM]], i64 16)
// CHECK1-NEXT:    call void @__kmpc_free_shared(ptr [[IEND]], i64 4)
// CHECK1-NEXT:    call void @__kmpc_free_shared(ptr [[ISTART]], i64 4)
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNSt7complexIdEC1ERKdS2_
// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]], ptr nonnull align 8 dereferenceable(8) [[__RE:%.*]], ptr nonnull align 8 dereferenceable(8) [[__IM:%.*]]) unnamed_addr #[[ATTR5]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__RE_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__IM_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZNSt7complexIdEC2ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[THIS1]], ptr nonnull align 8 dereferenceable(8) [[TMP0]], ptr nonnull align 8 dereferenceable(8) [[TMP1]]) #[[ATTR11]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined
// CHECK1-SAME: (ptr noalias [[DOTGLOBAL_TID_:%.*]], ptr noalias [[DOTBOUND_TID_:%.*]], ptr nonnull align 4 dereferenceable(4) [[ISTART:%.*]], ptr nonnull align 4 dereferenceable(4) [[IEND:%.*]], ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[ISTART_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[IEND_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[PARTIAL_SUM_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[TMP:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTCAPTURE_EXPR_2:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[PARTIAL_SUM5:%.*]] = alloca %"class.std::complex.0", align 8
// CHECK1-NEXT:    [[REF_TMP:%.*]] = alloca double, align 8
// CHECK1-NEXT:    [[REF_TMP6:%.*]] = alloca double, align 8
// CHECK1-NEXT:    [[I7:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[REF_TMP14:%.*]] = alloca %"class.std::complex.0", align 8
// CHECK1-NEXT:    [[REF_TMP15:%.*]] = alloca double, align 8
// CHECK1-NEXT:    [[REF_TMP16:%.*]] = alloca double, align 8
// CHECK1-NEXT:    [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x ptr], align 8
// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[IEND]], ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP3]], ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_1]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[TMP1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_2]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[SUB:%.*]] = sub i32 [[TMP5]], [[TMP6]]
// CHECK1-NEXT:    [[SUB3:%.*]] = sub i32 [[SUB]], 1
// CHECK1-NEXT:    [[ADD:%.*]] = add i32 [[SUB3]], 1
// CHECK1-NEXT:    [[DIV:%.*]] = udiv i32 [[ADD]], 1
// CHECK1-NEXT:    [[SUB4:%.*]] = sub i32 [[DIV]], 1
// CHECK1-NEXT:    store i32 [[SUB4]], ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP7]], ptr [[I]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CMP:%.*]] = icmp slt i32 [[TMP8]], [[TMP9]]
// CHECK1-NEXT:    br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]]
// CHECK1:       omp.precond.then:
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP10:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP10]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 16, ptr [[PARTIAL_SUM5]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP]]) #[[ATTR4]]
// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP]], align 8, !tbaa [[TBAA23]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP6]]) #[[ATTR4]]
// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP6]], align 8, !tbaa [[TBAA23]]
// CHECK1-NEXT:    call void @_ZNSt7complexIdEC1ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP6]]) #[[ATTR11]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP6]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I7]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP11:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, ptr [[TMP11]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @__kmpc_for_static_init_4u(ptr @[[GLOB3]], i32 [[TMP12]], i32 33, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_LB]], ptr [[DOTOMP_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK1-NEXT:    br label [[OMP_DISPATCH_COND:%.*]]
// CHECK1:       omp.dispatch.cond:
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CMP8:%.*]] = icmp ugt i32 [[TMP13]], [[TMP14]]
// CHECK1-NEXT:    br i1 [[CMP8]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK1:       cond.true:
// CHECK1-NEXT:    [[TMP15:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[COND_END:%.*]]
// CHECK1:       cond.false:
// CHECK1-NEXT:    [[TMP16:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[COND_END]]
// CHECK1:       cond.end:
// CHECK1-NEXT:    [[COND:%.*]] = phi i32 [ [[TMP15]], [[COND_TRUE]] ], [ [[TMP16]], [[COND_FALSE]] ]
// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP17:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 [[TMP17]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP18:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP19:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD9:%.*]] = add i32 [[TMP19]], 1
// CHECK1-NEXT:    [[CMP10:%.*]] = icmp ult i32 [[TMP18]], [[ADD9]]
// CHECK1-NEXT:    br i1 [[CMP10]], label [[OMP_DISPATCH_BODY:%.*]], label [[OMP_DISPATCH_CLEANUP:%.*]]
// CHECK1:       omp.dispatch.cleanup:
// CHECK1-NEXT:    br label [[OMP_DISPATCH_END:%.*]]
// CHECK1:       omp.dispatch.body:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK1:       omp.inner.for.cond:
// CHECK1-NEXT:    [[TMP20:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP21:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD11:%.*]] = add i32 [[TMP21]], 1
// CHECK1-NEXT:    [[CMP12:%.*]] = icmp ult i32 [[TMP20]], [[ADD11]]
// CHECK1-NEXT:    br i1 [[CMP12]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK1:       omp.inner.for.cond.cleanup:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_END:%.*]]
// CHECK1:       omp.inner.for.body:
// CHECK1-NEXT:    [[TMP22:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP23:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[MUL:%.*]] = mul i32 [[TMP23]], 1
// CHECK1-NEXT:    [[ADD13:%.*]] = add i32 [[TMP22]], [[MUL]]
// CHECK1-NEXT:    store i32 [[ADD13]], ptr [[I7]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 16, ptr [[REF_TMP14]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP15]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP24:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP24]] to double
// CHECK1-NEXT:    store double [[CONV]], ptr [[REF_TMP15]], align 8, !tbaa [[TBAA23]]
// CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP16]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP25:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[CONV17:%.*]] = sitofp i32 [[TMP25]] to double
// CHECK1-NEXT:    store double [[CONV17]], ptr [[REF_TMP16]], align 8, !tbaa [[TBAA23]]
// CHECK1-NEXT:    call void @_ZNSt7complexIdEC1ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[REF_TMP14]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP15]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP16]]) #[[ATTR11]]
// CHECK1-NEXT:    [[CALL:%.*]] = call nonnull align 8 dereferenceable(16) ptr @_ZNSt7complexIdEpLIdEERS0_RKS_IT_E(ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]], ptr nonnull align 8 dereferenceable(16) [[REF_TMP14]]) #[[ATTR11]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP16]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP15]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 16, ptr [[REF_TMP14]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK1:       omp.body.continue:
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK1:       omp.inner.for.inc:
// CHECK1-NEXT:    [[TMP26:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD18:%.*]] = add i32 [[TMP26]], 1
// CHECK1-NEXT:    store i32 [[ADD18]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND]]
// CHECK1:       omp.inner.for.end:
// CHECK1-NEXT:    br label [[OMP_DISPATCH_INC:%.*]]
// CHECK1:       omp.dispatch.inc:
// CHECK1-NEXT:    [[TMP27:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP28:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD19:%.*]] = add i32 [[TMP27]], [[TMP28]]
// CHECK1-NEXT:    store i32 [[ADD19]], ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP29:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[TMP30:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    [[ADD20:%.*]] = add i32 [[TMP29]], [[TMP30]]
// CHECK1-NEXT:    store i32 [[ADD20]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    br label [[OMP_DISPATCH_COND]]
// CHECK1:       omp.dispatch.end:
// CHECK1-NEXT:    [[TMP31:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    call void @__kmpc_for_static_fini(ptr @[[GLOB3]], i32 [[TMP32]])
// CHECK1-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK1-NEXT:    store ptr [[PARTIAL_SUM5]], ptr [[TMP33]], align 8
// CHECK1-NEXT:    [[TMP34:%.*]] = call i32 @__kmpc_nvptx_parallel_reduce_nowait_v2(ptr @[[GLOB1]], i64 16, ptr [[DOTOMP_REDUCTION_RED_LIST]], ptr @_omp_reduction_shuffle_and_reduce_func1, ptr @_omp_reduction_inter_warp_copy_func2)
// CHECK1-NEXT:    [[TMP35:%.*]] = icmp eq i32 [[TMP34]], 1
// CHECK1-NEXT:    br i1 [[TMP35]], label [[DOTOMP_REDUCTION_THEN:%.*]], label [[DOTOMP_REDUCTION_DONE:%.*]]
// CHECK1:       .omp.reduction.then:
// CHECK1-NEXT:    [[CALL21:%.*]] = call nonnull align 8 dereferenceable(16) ptr @_ZNSt7complexIdEpLIdEERS0_RKS_IT_E(ptr nonnull align 8 dereferenceable(16) [[TMP2]], ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]]) #[[ATTR11]]
// CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
// CHECK1:       .omp.reduction.done:
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I7]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 16, ptr [[PARTIAL_SUM5]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[OMP_PRECOND_END]]
// CHECK1:       omp.precond.end:
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTCAPTURE_EXPR_2]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTCAPTURE_EXPR_1]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTCAPTURE_EXPR_]]) #[[ATTR4]]
// CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNSt7complexIdEpLIdEERS0_RKS_IT_E
// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]], ptr nonnull align 8 dereferenceable(16) [[__C:%.*]]) #[[ATTR5]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__C_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__C]], ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[CALL:%.*]] = call double @_ZNKSt7complexIdE4realEv(ptr nonnull align 8 dereferenceable(16) [[TMP0]]) #[[ATTR11]]
// CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds nuw %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP1:%.*]] = load double, ptr [[__RE_]], align 8, !tbaa [[TBAA25:![0-9]+]]
// CHECK1-NEXT:    [[ADD:%.*]] = fadd double [[TMP1]], [[CALL]]
// CHECK1-NEXT:    store double [[ADD]], ptr [[__RE_]], align 8, !tbaa [[TBAA25]]
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[CALL2:%.*]] = call double @_ZNKSt7complexIdE4imagEv(ptr nonnull align 8 dereferenceable(16) [[TMP2]]) #[[ATTR11]]
// CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds nuw %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP3:%.*]] = load double, ptr [[__IM_]], align 8, !tbaa [[TBAA27:![0-9]+]]
// CHECK1-NEXT:    [[ADD3:%.*]] = fadd double [[TMP3]], [[CALL2]]
// CHECK1-NEXT:    store double [[ADD3]], ptr [[__IM_]], align 8, !tbaa [[TBAA27]]
// CHECK1-NEXT:    ret ptr [[THIS1]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_omp_reduction_shuffle_and_reduce_func1
// CHECK1-SAME: (ptr noundef [[TMP0:%.*]], i16 noundef signext [[TMP1:%.*]], i16 noundef signext [[TMP2:%.*]], i16 noundef signext [[TMP3:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[DOTADDR2:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[DOTADDR3:%.*]] = alloca i16, align 2
// CHECK1-NEXT:    [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST:%.*]] = alloca [1 x ptr], align 8
// CHECK1-NEXT:    [[DOTOMP_REDUCTION_ELEMENT:%.*]] = alloca %"class.std::complex.0", align 8
// CHECK1-NEXT:    store ptr [[TMP0]], ptr [[DOTADDR]], align 8
// CHECK1-NEXT:    store i16 [[TMP1]], ptr [[DOTADDR1]], align 2
// CHECK1-NEXT:    store i16 [[TMP2]], ptr [[DOTADDR2]], align 2
// CHECK1-NEXT:    store i16 [[TMP3]], ptr [[DOTADDR3]], align 2
// CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[DOTADDR]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = load i16, ptr [[DOTADDR1]], align 2
// CHECK1-NEXT:    [[TMP6:%.*]] = load i16, ptr [[DOTADDR2]], align 2
// CHECK1-NEXT:    [[TMP7:%.*]] = load i16, ptr [[DOTADDR3]], align 2
// CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP4]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP9:%.*]] = load ptr, ptr [[TMP8]], align 8
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr %"class.std::complex.0", ptr [[TMP9]], i64 1
// CHECK1-NEXT:    br label [[DOTSHUFFLE_PRE_COND:%.*]]
// CHECK1:       .shuffle.pre_cond:
// CHECK1-NEXT:    [[TMP12:%.*]] = phi ptr [ [[TMP9]], [[ENTRY:%.*]] ], [ [[TMP23:%.*]], [[DOTSHUFFLE_THEN:%.*]] ]
// CHECK1-NEXT:    [[TMP13:%.*]] = phi ptr [ [[DOTOMP_REDUCTION_ELEMENT]], [[ENTRY]] ], [ [[TMP24:%.*]], [[DOTSHUFFLE_THEN]] ]
// CHECK1-NEXT:    [[TMP14:%.*]] = ptrtoint ptr [[TMP11]] to i64
// CHECK1-NEXT:    [[TMP15:%.*]] = ptrtoint ptr [[TMP12]] to i64
// CHECK1-NEXT:    [[TMP16:%.*]] = sub i64 [[TMP14]], [[TMP15]]
// CHECK1-NEXT:    [[TMP17:%.*]] = sdiv exact i64 [[TMP16]], ptrtoint (ptr getelementptr (i8, ptr null, i32 1) to i64)
// CHECK1-NEXT:    [[TMP18:%.*]] = icmp sgt i64 [[TMP17]], 7
// CHECK1-NEXT:    br i1 [[TMP18]], label [[DOTSHUFFLE_THEN]], label [[DOTSHUFFLE_EXIT:%.*]]
// CHECK1:       .shuffle.then:
// CHECK1-NEXT:    [[TMP19:%.*]] = load i64, ptr [[TMP12]], align 8
// CHECK1-NEXT:    [[TMP20:%.*]] = call i32 @__kmpc_get_warp_size()
// CHECK1-NEXT:    [[TMP21:%.*]] = trunc i32 [[TMP20]] to i16
// CHECK1-NEXT:    [[TMP22:%.*]] = call i64 @__kmpc_shuffle_int64(i64 [[TMP19]], i16 [[TMP6]], i16 [[TMP21]])
// CHECK1-NEXT:    store i64 [[TMP22]], ptr [[TMP13]], align 8
// CHECK1-NEXT:    [[TMP23]] = getelementptr i64, ptr [[TMP12]], i64 1
// CHECK1-NEXT:    [[TMP24]] = getelementptr i64, ptr [[TMP13]], i64 1
// CHECK1-NEXT:    br label [[DOTSHUFFLE_PRE_COND]]
// CHECK1:       .shuffle.exit:
// CHECK1-NEXT:    store ptr [[DOTOMP_REDUCTION_ELEMENT]], ptr [[TMP10]], align 8
// CHECK1-NEXT:    [[TMP25:%.*]] = icmp eq i16 [[TMP7]], 0
// CHECK1-NEXT:    [[TMP26:%.*]] = icmp eq i16 [[TMP7]], 1
// CHECK1-NEXT:    [[TMP27:%.*]] = icmp ult i16 [[TMP5]], [[TMP6]]
// CHECK1-NEXT:    [[TMP28:%.*]] = and i1 [[TMP26]], [[TMP27]]
// CHECK1-NEXT:    [[TMP29:%.*]] = icmp eq i16 [[TMP7]], 2
// CHECK1-NEXT:    [[TMP30:%.*]] = and i16 [[TMP5]], 1
// CHECK1-NEXT:    [[TMP31:%.*]] = icmp eq i16 [[TMP30]], 0
// CHECK1-NEXT:    [[TMP32:%.*]] = and i1 [[TMP29]], [[TMP31]]
// CHECK1-NEXT:    [[TMP33:%.*]] = icmp sgt i16 [[TMP6]], 0
// CHECK1-NEXT:    [[TMP34:%.*]] = and i1 [[TMP32]], [[TMP33]]
// CHECK1-NEXT:    [[TMP35:%.*]] = or i1 [[TMP25]], [[TMP28]]
// CHECK1-NEXT:    [[TMP36:%.*]] = or i1 [[TMP35]], [[TMP34]]
// CHECK1-NEXT:    br i1 [[TMP36]], label [[THEN:%.*]], label [[ELSE:%.*]]
// CHECK1:       then:
// CHECK1-NEXT:    call void @"{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined_omp$reduction$reduction_func"(ptr [[TMP4]], ptr [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[IFCONT:%.*]]
// CHECK1:       else:
// CHECK1-NEXT:    br label [[IFCONT]]
// CHECK1:       ifcont:
// CHECK1-NEXT:    [[TMP37:%.*]] = icmp eq i16 [[TMP7]], 1
// CHECK1-NEXT:    [[TMP38:%.*]] = icmp uge i16 [[TMP5]], [[TMP6]]
// CHECK1-NEXT:    [[TMP39:%.*]] = and i1 [[TMP37]], [[TMP38]]
// CHECK1-NEXT:    br i1 [[TMP39]], label [[THEN4:%.*]], label [[ELSE5:%.*]]
// CHECK1:       then4:
// CHECK1-NEXT:    [[TMP40:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP41:%.*]] = load ptr, ptr [[TMP40]], align 8
// CHECK1-NEXT:    [[TMP42:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP4]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP43:%.*]] = load ptr, ptr [[TMP42]], align 8
// CHECK1-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[TMP43]], ptr align 8 [[TMP41]], i64 16, i1 false)
// CHECK1-NEXT:    br label [[IFCONT6:%.*]]
// CHECK1:       else5:
// CHECK1-NEXT:    br label [[IFCONT6]]
// CHECK1:       ifcont6:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_omp_reduction_inter_warp_copy_func2
// CHECK1-SAME: (ptr noundef [[TMP0:%.*]], i32 noundef [[TMP1:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTCNT_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    store ptr [[TMP0]], ptr [[DOTADDR]], align 8
// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
// CHECK1-NEXT:    [[TMP3:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
// CHECK1-NEXT:    [[NVPTX_LANE_ID:%.*]] = and i32 [[TMP3]], 31
// CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
// CHECK1-NEXT:    [[NVPTX_WARP_ID:%.*]] = ashr i32 [[TMP4]], 5
// CHECK1-NEXT:    [[TMP5:%.*]] = load ptr, ptr [[DOTADDR]], align 8
// CHECK1-NEXT:    store i32 0, ptr [[DOTCNT_ADDR]], align 4
// CHECK1-NEXT:    br label [[PRECOND:%.*]]
// CHECK1:       precond:
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTCNT_ADDR]], align 4
// CHECK1-NEXT:    [[TMP7:%.*]] = icmp ult i32 [[TMP6]], 4
// CHECK1-NEXT:    br i1 [[TMP7]], label [[BODY:%.*]], label [[EXIT:%.*]]
// CHECK1:       body:
// CHECK1-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK1-NEXT:    call void @__kmpc_barrier(ptr @[[GLOB4]], i32 [[OMP_GLOBAL_THREAD_NUM]])
// CHECK1-NEXT:    [[WARP_MASTER:%.*]] = icmp eq i32 [[NVPTX_LANE_ID]], 0
// CHECK1-NEXT:    br i1 [[WARP_MASTER]], label [[THEN:%.*]], label [[ELSE:%.*]]
// CHECK1:       then:
// CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP5]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP9:%.*]] = load ptr, ptr [[TMP8]], align 8
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr i32, ptr [[TMP9]], i32 [[TMP6]]
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [32 x i32], ptr addrspace(3) @__openmp_nvptx_data_transfer_temporary_storage, i64 0, i32 [[NVPTX_WARP_ID]]
// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, ptr [[TMP10]], align 4
// CHECK1-NEXT:    store volatile i32 [[TMP12]], ptr addrspace(3) [[TMP11]], align 4
// CHECK1-NEXT:    br label [[IFCONT:%.*]]
// CHECK1:       else:
// CHECK1-NEXT:    br label [[IFCONT]]
// CHECK1:       ifcont:
// CHECK1-NEXT:    [[OMP_GLOBAL_THREAD_NUM2:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK1-NEXT:    call void @__kmpc_barrier(ptr @[[GLOB4]], i32 [[OMP_GLOBAL_THREAD_NUM2]])
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTADDR1]], align 4
// CHECK1-NEXT:    [[IS_ACTIVE_THREAD:%.*]] = icmp ult i32 [[TMP2]], [[TMP13]]
// CHECK1-NEXT:    br i1 [[IS_ACTIVE_THREAD]], label [[THEN3:%.*]], label [[ELSE4:%.*]]
// CHECK1:       then3:
// CHECK1-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [32 x i32], ptr addrspace(3) @__openmp_nvptx_data_transfer_temporary_storage, i64 0, i32 [[TMP2]]
// CHECK1-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP5]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP16:%.*]] = load ptr, ptr [[TMP15]], align 8
// CHECK1-NEXT:    [[TMP17:%.*]] = getelementptr i32, ptr [[TMP16]], i32 [[TMP6]]
// CHECK1-NEXT:    [[TMP18:%.*]] = load volatile i32, ptr addrspace(3) [[TMP14]], align 4
// CHECK1-NEXT:    store i32 [[TMP18]], ptr [[TMP17]], align 4
// CHECK1-NEXT:    br label [[IFCONT5:%.*]]
// CHECK1:       else4:
// CHECK1-NEXT:    br label [[IFCONT5]]
// CHECK1:       ifcont5:
// CHECK1-NEXT:    [[TMP19:%.*]] = add nsw i32 [[TMP6]], 1
// CHECK1-NEXT:    store i32 [[TMP19]], ptr [[DOTCNT_ADDR]], align 4
// CHECK1-NEXT:    br label [[PRECOND]]
// CHECK1:       exit:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined_wrapper
// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR8]] {
// 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 ptr, align 8
// CHECK1-NEXT:    store i16 [[TMP0]], ptr [[DOTADDR]], align 2, !tbaa [[TBAA21]]
// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA14]]
// CHECK1-NEXT:    store i32 0, ptr [[DOTZERO_ADDR]], align 4
// CHECK1-NEXT:    call void @__kmpc_get_shared_variables(ptr [[GLOBAL_ARGS]])
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[GLOBAL_ARGS]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 0
// CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[TMP3]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 1
// CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[TMP5]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 2
// CHECK1-NEXT:    [[TMP8:%.*]] = load ptr, ptr [[TMP7]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined(ptr [[DOTADDR1]], ptr [[DOTZERO_ADDR]], ptr [[TMP4]], ptr [[TMP6]], ptr [[TMP8]]) #[[ATTR4]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNSt7complexIfEC2ERKfS2_
// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]], ptr nonnull align 4 dereferenceable(4) [[__RE:%.*]], ptr nonnull align 4 dereferenceable(4) [[__IM:%.*]]) unnamed_addr #[[ATTR5]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__RE_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__IM_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds nuw %"class.std::complex", ptr [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP1:%.*]] = load float, ptr [[TMP0]], align 4, !tbaa [[TBAA16]]
// CHECK1-NEXT:    store float [[TMP1]], ptr [[__RE_]], align 4, !tbaa [[TBAA18]]
// CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds nuw %"class.std::complex", ptr [[THIS1]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP3:%.*]] = load float, ptr [[TMP2]], align 4, !tbaa [[TBAA16]]
// CHECK1-NEXT:    store float [[TMP3]], ptr [[__IM_]], align 4, !tbaa [[TBAA20]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNKSt7complexIfE4realEv
// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]]) #[[ATTR5]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds nuw %"class.std::complex", ptr [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP0:%.*]] = load float, ptr [[__RE_]], align 4, !tbaa [[TBAA18]]
// CHECK1-NEXT:    ret float [[TMP0]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNKSt7complexIfE4imagEv
// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]]) #[[ATTR5]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds nuw %"class.std::complex", ptr [[THIS1]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP0:%.*]] = load float, ptr [[__IM_]], align 4, !tbaa [[TBAA20]]
// CHECK1-NEXT:    ret float [[TMP0]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNSt7complexIdEC2ERKdS2_
// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]], ptr nonnull align 8 dereferenceable(8) [[__RE:%.*]], ptr nonnull align 8 dereferenceable(8) [[__IM:%.*]]) unnamed_addr #[[ATTR5]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__RE_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    [[__IM_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds nuw %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP1:%.*]] = load double, ptr [[TMP0]], align 8, !tbaa [[TBAA23]]
// CHECK1-NEXT:    store double [[TMP1]], ptr [[__RE_]], align 8, !tbaa [[TBAA25]]
// CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds nuw %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[TMP3:%.*]] = load double, ptr [[TMP2]], align 8, !tbaa [[TBAA23]]
// CHECK1-NEXT:    store double [[TMP3]], ptr [[__IM_]], align 8, !tbaa [[TBAA27]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNKSt7complexIdE4realEv
// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]]) #[[ATTR5]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds nuw %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP0:%.*]] = load double, ptr [[__RE_]], align 8, !tbaa [[TBAA25]]
// CHECK1-NEXT:    ret double [[TMP0]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZNKSt7complexIdE4imagEv
// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]]) #[[ATTR5]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
// CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds nuw %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP0:%.*]] = load double, ptr [[__IM_]], align 8, !tbaa [[TBAA27]]
// CHECK1-NEXT:    ret double [[TMP0]]
//