Dear, I compile gcc 6 r231616, for offloading and host, When i compile a simple example with -fopenacc -foffload=nvptx-none The compilation process finish o.k, but when i Run the code in a machine with cuda device, obtain the following problem libgomp: cuModuleLoadData error: device kernel image is invalid . i compile the same code with the pgiCompiler and the code running fine. When i review with cuobdump -ptx miCode.x obtaint the following error The file don't have a ptx code Someone can help me please, ??? -- Sincerely Esteban Hernandez B. HPC specialist
