https://gcc.gnu.org/bugzilla/show_bug.cgi?id=122281
--- Comment #21 from Benjamin Schulz <schulz.benjamin at googlemail dot com> --- also that one ========= Program hit CUDA_ERROR_NOT_FOUND (error 500) due to "named symbol not found" on CUDA API call to cuModuleGetGlobal_v2. very strange... Does omp_target_alloc or map work at all on my system? If omp_target_alloc would not work, then the memory could of course not be accessed by an index on gpu...
