Lines Matching refs:DP
61 DP("Warning: Attempting to assign hostrpc to device %u, but hostrpc library " in hostrpc_assign_buffer()
77 DP(#msg " failed\n"); \
79 DP(#msg " succeeded\n"); \
132 DP("hsa_amd_memory_pool_free failed: %s\n", get_error_string(R)); in ~KernelArgPool()
153 DP("hsa_amd_memory_pool_allocate failed: %s\n", get_error_string(Err)); in KernelArgPool()
160 DP("hsa allow_access_to_all_gpu_agents failed: %s\n", in KernelArgPool()
165 DP("hsa memory poll free failed: %s\n", get_error_string(Err)); in KernelArgPool()
230 DP("Construct kernelinfo: ExecMode %d\n", ExecutionMode); in KernelTy()
256 DP("rtl.cpp: err %s\n", get_error_string(Err)); in findAgents()
267 DP("rtl.cpp: err %s\n", get_error_string(Err)); in findAgents()
280 DP("[%s:%d] GPU error in queue %p %d (%s)\n", __FILE__, __LINE__, Source, in callbackQueue()
315 DP("Alloc allowed in memory pool check failed: %s\n", in isValidMemoryPool()
324 DP("Get memory pool size failed: %s\n", get_error_string(Err)); in isValidMemoryPool()
374 DP("Shutting down HSA failed: %d\n", Err); in ~HSALifetime()
404 DP("Failed to create HSA queue %d\n", I); in createQueues()
417 DP("Error destroying HSA queue"); in ~HSAQueueScheduler()
444 DP("Error destroying hsa queue: %s\n", get_error_string(Err)); in operator ()()
891 DP("Alloc allowed in memory pool check failed: %s\n", in setupDevicePools()
899 DP("[%s:%d] %s failed: %s\n", __FILE__, __LINE__, in setupDevicePools()
915 DP("addMemoryPool returned %s, continuing\n", get_error_string(Err)); in setupHostMemoryPools()
930 DP("Get memory pool info failed: %s\n", get_error_string(Err)); in setupHostMemoryPools()
965 DP("Parsed %s=%d\n", Env, Res); in readEnv()
971 DP("Start initializing " GETNAME(TARGET_NAME) "\n"); in RTLDeviceInfoTy()
980 DP("Error when initializing HSA in " GETNAME(TARGET_NAME) "\n"); in RTLDeviceInfoTy()
991 DP("Error when initializing " GETNAME(TARGET_NAME) "\n"); in RTLDeviceInfoTy()
1011 DP("There are no devices supporting HSA.\n"); in RTLDeviceInfoTy()
1014 DP("There are %d devices supporting HSA.\n", NumberOfDevices); in RTLDeviceInfoTy()
1034 DP("Setup for Device Memory Pools failed\n"); in RTLDeviceInfoTy()
1040 DP("Setup for Host Memory Pools failed\n"); in RTLDeviceInfoTy()
1050 DP("HSA query QUEUE_MAX_SIZE failed for agent %d\n", I); in RTLDeviceInfoTy()
1073 DP("Device %d: Initial groupsPerDevice %d & threadsPerGroup %d\n", I, in RTLDeviceInfoTy()
1091 DP("Finalizing the " GETNAME(TARGET_NAME) " DeviceInfo.\n"); in ~RTLDeviceInfoTy()
1107 DP("[%s:%d] %s failed: %s\n", __FILE__, __LINE__, in ~RTLDeviceInfoTy()
1131 DP("Retrieve data %ld bytes, (tgt:%016llx) -> (hst:%016llx).\n", Size, in dataRetrieve()
1139 DP("Error when copying data from device to host. Pointers: " in dataRetrieve()
1144 DP("DONE Retrieve data %ld bytes, (tgt:%016llx) -> (hst:%016llx).\n", Size, in dataRetrieve()
1159 DP("Submit data %ld bytes, (hst:%016llx) -> (tgt:%016llx).\n", Size, in dataSubmit()
1165 DP("Error when copying data from host to device. Pointers: " in dataSubmit()
1220 DP("RTLDeviceInfoTy::Max_Teams: %d\n", RTLDeviceInfoTy::MaxTeams); in getLaunchVals()
1221 DP("Max_Teams: %d\n", MaxTeams); in getLaunchVals()
1222 DP("RTLDeviceInfoTy::Warp_Size: %d\n", WarpSize); in getLaunchVals()
1223 DP("RTLDeviceInfoTy::Max_WG_Size: %d\n", RTLDeviceInfoTy::MaxWgSize); in getLaunchVals()
1224 DP("RTLDeviceInfoTy::Default_WG_Size: %d\n", in getLaunchVals()
1226 DP("thread_limit: %d\n", ThreadLimit); in getLaunchVals()
1227 DP("threadsPerGroup: %d\n", ThreadsPerGroup); in getLaunchVals()
1228 DP("ConstWGSize: %d\n", ConstWGSize); in getLaunchVals()
1233 DP("Setting threads per block to requested %d\n", ThreadLimit); in getLaunchVals()
1238 DP("Adding master wavefront: +%d threads\n", WarpSize); in getLaunchVals()
1242 DP("Setting threads per block to maximum %d\n", ThreadsPerGroup); in getLaunchVals()
1248 DP("Reduced threadsPerGroup to flat-attr-group-size limit %d\n", in getLaunchVals()
1252 DP("threadsPerGroup: %d\n", ThreadsPerGroup); in getLaunchVals()
1253 DP("Preparing %d threads\n", ThreadsPerGroup); in getLaunchVals()
1260 DP("Set default num of groups %d\n", NumGroups); in getLaunchVals()
1263 DP("num_groups: %d\n", NumGroups); in getLaunchVals()
1264 DP("num_teams: %d\n", NumTeams); in getLaunchVals()
1283 DP("num_groups: %d\n", NumGroups); in getLaunchVals()
1284 DP("Env.NumTeams %d\n", Env.NumTeams); in getLaunchVals()
1285 DP("Env.TeamLimit %d\n", Env.TeamLimit); in getLaunchVals()
1290 DP("Modifying teams based on Env.NumTeams %d\n", Env.NumTeams); in getLaunchVals()
1293 DP("Modifying teams based on Env.TeamLimit%d\n", Env.TeamLimit); in getLaunchVals()
1309 DP("Using %d teams due to loop trip count %" PRIu64 " and number of " in getLaunchVals()
1319 DP("Limiting num_groups %d to Max_Teams %d \n", NumGroups, MaxTeams); in getLaunchVals()
1324 DP("Limiting num_groups %d to clause num_teams %d \n", NumGroups, in getLaunchVals()
1337 DP("threadsPerGroup: %d\n", ThreadsPerGroup); in getLaunchVals()
1338 DP("num_groups: %d\n", NumGroups); in getLaunchVals()
1339 DP("loop_tripcount: %ld\n", LoopTripcount); in getLaunchVals()
1341 DP("Final %d num_groups and %d threadsPerGroup\n", NumGroups, in getLaunchVals()
1367 DP("Run target team region thread_limit %d\n", ThreadLimit); in runRegionLocked()
1373 DP("Arg_num: %d\n", ArgNum); in runRegionLocked()
1377 DP("Offseted base: arg[%d]:" DPxMOD "\n", I, DPxPTR(Ptrs[I])); in runRegionLocked()
1386 DP("Kernel %s not found\n", KernelName.c_str()); in runRegionLocked()
1466 DP("Warning: No ArgPool for %s on device %d\n", KernelInfo->Name, in runRegionLocked()
1475 DP("Allocate kernarg failed\n"); in runRegionLocked()
1503 DP("hostrpc_assign_buffer failed, gpu would dereference null and " in runRegionLocked()
1508 DP("Implicit argument count: %d\n", in runRegionLocked()
1518 DP("Bad offset of hostcall: %lu, exceeds kernarg size w/ implicit " in runRegionLocked()
1535 DP("Failed to get signal instance\n"); in runRegionLocked()
1558 DP("Kernel completed\n"); in runRegionLocked()
1566 DP("Supported machine ID not found\n"); in elfMachineIdIsAmdgcn()
1577 DP("Unable to get ELF handle: %s!\n", elf_errmsg(-1)); in elfEFlags()
1584 DP("Unable to get machine ID from ELF file!\n"); in elfEFlags()
1592 DP("ELF Flags: 0x%x\n", Flags); in elfEFlags()
1763 DP("Found device_State_size variable with wrong size\n"); in getDeviceStateBytes()
1811 DP("Finding global device environment '%s' - symbol missing.\n", sym()); in DeviceEnvironment()
1816 DP("Symbol '%s' has size %u, expected at most %zu.\n", sym(), SI.Size, in DeviceEnvironment()
1829 DP("Setting global device environment before load (%u bytes)\n", in beforeLoading()
1842 DP("Setting global device environment after load (%u bytes)\n", in afterLoading()
1851 DP("failed to find %s in loaded image\n", sym()); in afterLoading()
1856 DP("Symbol had size %u before loading, %u after\n", StatePtrSize, in afterLoading()
1880 DP("zero fill device_state failed with %u\n", Rc); in implCalloc()
1909 DP("Error getting ISA info length\n"); in GetIsaInfo()
1916 DP("Error getting ISA info name\n"); in GetIsaInfo()
1964 DP("Compatible: Exact match \t[Image: %s]\t:\t[Environment: %s]\n", in IsImageCompatibleWithEnv()
1976 DP("Incompatible: Processor mismatch \t[Image: %s]\t:\t[Environment: %s]\n", in IsImageCompatibleWithEnv()
1984 DP("Incompatible: Image has more features than the environment \t[Image: " in IsImageCompatibleWithEnv()
1997 DP("Incompatible: Value of Image's non-ANY feature is not matching with " in IsImageCompatibleWithEnv()
2004 DP("Incompatible: Value of Image's non-ANY feature is not matching with " in IsImageCompatibleWithEnv()
2016 DP("Compatible: Target IDs are compatible \t[Image: %s]\t:\t[Environment: " in IsImageCompatibleWithEnv()
2043 DP("Error iterating ISAs\n"); in __tgt_rtl_is_valid_binary_info()
2049 DP("Image has Target ID compatible with the current environment: %s\n", in __tgt_rtl_is_valid_binary_info()
2062 DP("AMDGPU plugin construction failed. Zero devices available\n"); in __tgt_rtl_number_of_devices()
2067 DP("Init requires flags to %ld\n", RequiresFlags); in __tgt_rtl_init_requires()
2075 DP("HSA Initialization Failed.\n"); in __tgt_rtl_init_device()
2079 DP("Initialize the device id: %d\n", DeviceId); in __tgt_rtl_init_device()
2090 DP("Error getting compute units : settiing to 1\n"); in __tgt_rtl_init_device()
2093 DP("Using %d compute unis per grid\n", DeviceInfo().ComputeUnits[DeviceId]); in __tgt_rtl_init_device()
2106 DP("Device#%-2d CU's: %2d %s\n", DeviceId, in __tgt_rtl_init_device()
2115 DP("Error getting grid dims: num groups : %d\n", in __tgt_rtl_init_device()
2119 DP("Using %d ROCm blocks per grid\n", DeviceInfo().GroupsPerDevice[DeviceId]); in __tgt_rtl_init_device()
2122 DP("Max ROCm blocks per grid %d exceeds the hard team limit %d, capping " in __tgt_rtl_init_device()
2137 DP("Default thread limit: %d\n", RTLDeviceInfoTy::MaxWgSize); in __tgt_rtl_init_device()
2140 DP("Capped thread limit: %d\n", RTLDeviceInfoTy::MaxWgSize); in __tgt_rtl_init_device()
2142 DP("Using ROCm Queried thread limit: %d\n", in __tgt_rtl_init_device()
2147 DP("Error getting max block dimension, use default:%d \n", in __tgt_rtl_init_device()
2156 DP("Queried wavefront size: %d\n", WavefrontSize); in __tgt_rtl_init_device()
2160 DP("Warning: Unknown wavefront size, assuming 64\n"); in __tgt_rtl_init_device()
2169 DP("Capping max groups per device to OMP_TEAM_LIMIT=%d\n", in __tgt_rtl_init_device()
2176 DP("Default number of teams set according to environment %d\n", in __tgt_rtl_init_device()
2187 DP("Default number of teams = %d * number of compute units %d\n", in __tgt_rtl_init_device()
2193 DP("Default number of teams exceeds device limit, capping at %d\n", in __tgt_rtl_init_device()
2201 DP("Capping max number of threads to OMP_TEAMS_THREAD_LIMIT=%d\n", in __tgt_rtl_init_device()
2207 DP("Default number of threads set according to library's default %d\n", in __tgt_rtl_init_device()
2211 DP("Default number of threads exceeds device limit, capping at %d\n", in __tgt_rtl_init_device()
2215 DP("Device %d: default limit for groupsPerDevice %d & threadsPerGroup %d\n", in __tgt_rtl_init_device()
2219 DP("Device %d: wavefront size %d, total threads %d x %d = %d\n", DeviceId, in __tgt_rtl_init_device()
2296 DP("Possible gpu arch mismatch: device:%s, image:%s please check" in __tgt_rtl_load_binary_locked()
2300 DP("Error loading image onto GPU: %s\n", get_error_string(Err)); in __tgt_rtl_load_binary_locked()
2312 DP("AMDGPU module successfully loaded!\n"); in __tgt_rtl_load_binary_locked()
2327 DP("No device_state symbol found, skipping initialization\n"); in __tgt_rtl_load_binary_locked()
2330 DP("unexpected size of state_ptr %u != %zu\n", StatePtrSize, in __tgt_rtl_load_binary_locked()
2342 DP("Can't initialize device_State, missing size information\n"); in __tgt_rtl_load_binary_locked()
2352 DP("Failed to allocate device_state array\n"); in __tgt_rtl_load_binary_locked()
2363 DP("Inconsistent sizes of device_State unsupported\n"); in __tgt_rtl_load_binary_locked()
2371 DP("memcpy install of state_ptr failed\n"); in __tgt_rtl_load_binary_locked()
2394 DP("Analyzing host entry '<null>' (size = %lld)...\n", in __tgt_rtl_load_binary_locked()
2411 DP("Loading global '%s' (Failed)\n", E->name); in __tgt_rtl_load_binary_locked()
2416 DP("Loading global '%s' - size mismatch (%u != %lu)\n", E->name, in __tgt_rtl_load_binary_locked()
2421 DP("Entry point " DPxMOD " maps to global %s (" DPxMOD ")\n", in __tgt_rtl_load_binary_locked()
2435 DP("Error when copying USM\n"); in __tgt_rtl_load_binary_locked()
2436 DP("Copy linked variable host address (" DPxMOD ")" in __tgt_rtl_load_binary_locked()
2444 DP("to find the kernel name: %s size: %lu\n", E->name, strlen(E->name)); in __tgt_rtl_load_binary_locked()
2490 DP("Loading global computation properties '%s' - size mismatch (%u != " in __tgt_rtl_load_binary_locked()
2498 DP("KernDescVal size %lu does not match advertized size %d for '%s'\n", in __tgt_rtl_load_binary_locked()
2501 DP("After loading global for %s KernDesc \n", KernDescName); in __tgt_rtl_load_binary_locked()
2502 DP("KernDesc: Version: %d\n", KernDescVal.Version); in __tgt_rtl_load_binary_locked()
2503 DP("KernDesc: TSize: %d\n", KernDescVal.TSize); in __tgt_rtl_load_binary_locked()
2504 DP("KernDesc: WG_Size: %d\n", KernDescVal.WGSize); in __tgt_rtl_load_binary_locked()
2508 DP("Setting KernDescVal.WG_Size to default %d\n", KernDescVal.WGSize); in __tgt_rtl_load_binary_locked()
2511 DP("WGSizeVal %d\n", WGSizeVal); in __tgt_rtl_load_binary_locked()
2514 DP("Warning: Loading KernDesc '%s' - symbol not found, ", KernDescName); in __tgt_rtl_load_binary_locked()
2528 DP("Loading global computation properties '%s' - size mismatch (%u " in __tgt_rtl_load_binary_locked()
2537 DP("After loading global for %s WGSize = %d\n", WGSizeName, WGSizeVal); in __tgt_rtl_load_binary_locked()
2541 DP("Error wrong WGSize value specified in HSA code object file: " in __tgt_rtl_load_binary_locked()
2547 DP("Warning: Loading WGSize '%s' - symbol not found, " in __tgt_rtl_load_binary_locked()
2567 DP("Loading global computation properties '%s' - size mismatch(%u != " in __tgt_rtl_load_binary_locked()
2575 DP("After loading global for %s ExecMode = %d\n", ExecModeName, in __tgt_rtl_load_binary_locked()
2580 DP("Error wrong exec_mode value specified in HSA code object file: " in __tgt_rtl_load_binary_locked()
2586 DP("Loading global exec_mode '%s' - symbol missing, using default " in __tgt_rtl_load_binary_locked()
2599 DP("Entry point %ld maps to %s\n", E - HostBegin, E->name); in __tgt_rtl_load_binary_locked()
2617 DP("Tgt alloc data %ld bytes, (tgt:%016llx).\n", Size, in __tgt_rtl_data_alloc()
2667 DP("Tgt free data (tgt:%016llx).\n", (long long unsigned)(Elf64_Addr)TgtPtr); in __tgt_rtl_data_delete()
2670 DP("Error when freeing CUDA memory\n"); in __tgt_rtl_data_delete()