113     DP("Error when copying data from device to device. Pointers: src "  in memcpyDtoD()
129     DP("Error when recording event. stream = " DPxMOD ", event = " DPxMOD "\n",  in recordEvent()
143     DP("Error when syncing event = " DPxMOD "\n", DPxPTR(Event));  in syncEvent()
506     DP("Start initializing CUDA\n");  in DeviceRTLTy()
511       DP("Failed to load CUDA shared library\n");  in DeviceRTLTy()
515       DP("There are no devices supporting CUDA.\n");  in DeviceRTLTy()
527       DP("There are no devices supporting CUDA.\n");  in DeviceRTLTy()
543       DP("Parsed OMP_TEAM_LIMIT=%d\n", EnvTeamLimit);  in DeviceRTLTy()
548       DP("Parsed OMP_TEAMS_THREAD_LIMIT=%d\n", EnvTeamThreadLimit);  in DeviceRTLTy()
553       DP("Parsed OMP_NUM_TEAMS=%d\n", EnvNumTeams);  in DeviceRTLTy()
558       DP("Parsed LIBOMPTARGET_SHARED_MEMORY_SIZE = %" PRIu64 "\n",  in DeviceRTLTy()
564       DP("Parsed LIBOMPTARGET_NUM_INITIAL_STREAMS=%d\n", NumInitialStreams);  in DeviceRTLTy()
601     DP("Getting device %d\n", DeviceId);  in initDevice()
619       DP("The primary context is active, no change to its flags\n");  in initDevice()
622         DP("Warning the current flags are not CU_CTX_SCHED_BLOCKING_SYNC\n");  in initDevice()
624       DP("The primary context is inactive, set its flags to "  in initDevice()
656       DP("Error getting max grid dimension, use default value %d\n",  in initDevice()
660       DP("Using %d CUDA blocks per grid\n", MaxGridDimX);  in initDevice()
669       DP("Error getting max block dimension, use default value %d\n",  in initDevice()
673       DP("Using %d CUDA threads per block\n", MaxBlockDimX);  in initDevice()
678         DP("Max CUDA threads per block %d exceeds the thread limit %d set by "  in initDevice()
684         DP("Max CUDA threads per block %d exceeds the hard thread limit %d, "  in initDevice()
696       DP("Error getting warp size, assume default value 32\n");  in initDevice()
699       DP("Using warp size %d\n", WarpSize);  in initDevice()
705       DP("Capping max CUDA blocks per grid to OMP_TEAM_LIMIT=%d\n",  in initDevice()
741       DP("Default number of teams set according to environment %d\n",  in initDevice()
746       DP("Default number of teams set according to library's default %d\n",  in initDevice()
751       DP("Default number of teams exceeds device limit, capping at %d\n",  in initDevice()
758     DP("Default number of threads set according to library's default %d\n",  in initDevice()
762       DP("Default number of threads exceeds device limit, capping at %d\n",  in initDevice()
813     DP("Load data from image " DPxMOD "\n", DPxPTR(Image->ImageStart));  in loadBinary()
819     DP("CUDA module successfully loaded!\n");  in loadBinary()
833         DP("Invalid binary: host entry '<null>' (size = %zd)...\n", E->size);  in loadBinary()
850           DP("Loading global '%s' - size mismatch (%zd != %zd)\n", E->name,  in loadBinary()
855         DP("Entry point " DPxMOD " maps to global %s (" DPxMOD ")\n",  in loadBinary()
874           DP("Copy linked variable host address (" DPxMOD  in loadBinary()
893       DP("Entry point " DPxMOD " maps to %s (" DPxMOD ")\n",  in loadBinary()
907           DP("Loading global exec_mode '%s' - size mismatch (%zd != %zd)\n",  in loadBinary()
921         DP("Loading global exec_mode '%s' - symbol missing, using default "  in loadBinary()
966         DP("Sending global device environment data %zu bytes\n", CUSize);  in loadBinary()
968         DP("Finding global device environment '%s' - symbol missing.\n",  in loadBinary()
970         DP("Continue, considering this is a device RTL which does not accept "  in loadBinary()
1005       DP("Error when copying data from host to device. Pointers: host "  in dataSubmit()
1022       DP("Error when copying data from device to host. Pointers: host "  in dataRetrieve()
1091         DP("Error returned from cuMemcpyPeerAsync. src_ptr = " DPxMOD  in dataExchange()
1137       DP("Setting CUDA threads per block to requested %d\n", ThreadLimit);  in runTargetTeamRegion()
1141         DP("Adding master warp: +%d threads\n", DeviceData[DeviceId].WarpSize);  in runTargetTeamRegion()
1145       DP("Setting CUDA threads per block to default %d\n",  in runTargetTeamRegion()
1151       DP("Threads per block capped at device limit %d\n",  in runTargetTeamRegion()
1166       DP("Threads per block capped at kernel limit %d\n",  in runTargetTeamRegion()
1207         DP("Using %d teams due to loop trip count %" PRIu32  in runTargetTeamRegion()
1211         DP("Using default number of teams %d\n", DeviceData[DeviceId].NumTeams);  in runTargetTeamRegion()
1215       DP("Using requested number of teams %d\n", TeamNum);  in runTargetTeamRegion()
1220       DP("Capping number of teams to team limit %d\n",  in runTargetTeamRegion()
1241     DP("Launch of entry point at " DPxMOD " successful!\n",  in runTargetTeamRegion()
1258       DP("Error when synchronizing stream. stream = " DPxMOD  in synchronize()
1463       DP("Error when waiting event. stream = " DPxMOD ", event = " DPxMOD "\n",  in waitEvent()
1567   DP("Image has compatible compute capability: %s\n", info->Arch);  in __tgt_rtl_is_valid_binary_info()
1574   DP("Init requires flags to %" PRId64 "\n", RequiresFlags);  in __tgt_rtl_init_requires()