// RUN: %clang_cc1 -verify=host -Rpass=openmp-opt -Rpass-analysis=openmp-opt -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 -Rpass=openmp-opt -Rpass-analysis=openmp-opt -fopenmp -O2 -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t.out
// host-no-diagnostics
[[omp::assume("omp_no_openmp")]] void baz(void);
void bar(void) {
#pragma omp parallel // #1 \
// expected-remark@#1 {{Parallel region is used in unknown ways. Will not attempt to rewrite the state machine. [OMP101]}}
{
}
}
void foo(void) {
#pragma omp target teams // #2
// expected-remark@#2 {{Rewriting generic-mode kernel with a customized state machine. [OMP131]}}
{
baz(); // expected-remark {{Value has potential side effects preventing SPMD-mode execution. Add `[[omp::assume("ompx_spmd_amenable")]]` to the called function to override. [OMP121]}}
#pragma omp parallel
{
}
bar();
#pragma omp parallel
{
}
}
}
void spmd(void) {
// Verify we do not emit the remarks above for "SPMD" regions.
#pragma omp target teams
#pragma omp parallel
{
}
#pragma omp target teams distribute parallel for
for (int i = 0; i < 100; ++i) {
}
}
#pragma omp begin declare target device_type(nohost)
struct KernelEnvironmentTy;
struct KernelLaunchEnvironmentTy;
__attribute__((weak))
extern "C" int __kmpc_target_init(struct KernelEnvironmentTy *, struct KernelLaunchEnvironmentTy *) { // expected-remark {{Could not internalize function. Some optimizations may not be possible. [OMP140]}}
return 0;
}
#pragma omp end declare target
// expected-remark@* {{OpenMP runtime call __kmpc_global_thread_num deduplicated. [OMP170]}}