diff --git a/openmp/libomptarget/src/interface.cpp b/openmp/libomptarget/src/interface.cpp --- a/openmp/libomptarget/src/interface.cpp +++ b/openmp/libomptarget/src/interface.cpp @@ -82,7 +82,7 @@ static_assert(std::is_convertible_v, "TargetAsyncInfoTy must be convertible to AsyncInfoTy."); - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); DP("Entering data %s region for device %" PRId64 " with %d mappings\n", RegionName, DeviceId, ArgNum); @@ -128,7 +128,7 @@ int64_t *ArgTypes, map_var_info_t *ArgNames, void **ArgMappers) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); /// RAII to establish tool anchors before and after data begin OMPT_IF_BUILT(InterfaceRAII TargetDataEnterRAII( RegionInterface.getCallbacks(), @@ -145,7 +145,7 @@ void **Args, int64_t *ArgSizes, int64_t *ArgTypes, map_var_info_t *ArgNames, void **ArgMappers, int32_t DepNum, void *DepList, int32_t NoAliasDepNum, void *NoAliasDepList) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); targetDataMapper( Loc, DeviceId, ArgNum, ArgsBase, Args, ArgSizes, ArgTypes, ArgNames, ArgMappers, targetDataBegin, "Entering OpenMP data region", "begin"); @@ -160,7 +160,7 @@ int64_t *ArgTypes, map_var_info_t *ArgNames, void **ArgMappers) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); /// RAII to establish tool anchors before and after data end OMPT_IF_BUILT(InterfaceRAII TargetDataExitRAII( RegionInterface.getCallbacks(), @@ -177,7 +177,7 @@ void **Args, int64_t *ArgSizes, int64_t *ArgTypes, map_var_info_t *ArgNames, void **ArgMappers, int32_t DepNum, void *DepList, int32_t NoAliasDepNum, void *NoAliasDepList) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); targetDataMapper( Loc, DeviceId, ArgNum, ArgsBase, Args, ArgSizes, ArgTypes, ArgNames, ArgMappers, targetDataEnd, "Exiting OpenMP data region", "end"); @@ -189,7 +189,7 @@ int64_t *ArgTypes, map_var_info_t *ArgNames, void **ArgMappers) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); /// RAII to establish tool anchors before and after data update OMPT_IF_BUILT(InterfaceRAII TargetDataUpdateRAII( RegionInterface.getCallbacks(), @@ -206,7 +206,7 @@ void **Args, int64_t *ArgSizes, int64_t *ArgTypes, map_var_info_t *ArgNames, void **ArgMappers, int32_t DepNum, void *DepList, int32_t NoAliasDepNum, void *NoAliasDepList) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); targetDataMapper( Loc, DeviceId, ArgNum, ArgsBase, Args, ArgSizes, ArgTypes, ArgNames, ArgMappers, targetDataUpdate, "Updating OpenMP data", "update"); @@ -249,7 +249,7 @@ static_assert(std::is_convertible_v, "Target AsyncInfoTy must be convertible to AsyncInfoTy."); - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); DP("Entering target region for device %" PRId64 " with entry point " DPxMOD "\n", @@ -299,6 +299,8 @@ RegionInterface.getCallbacks(), DeviceId, /* CodePtr */ OMPT_GET_RETURN_ADDRESS(0));) + TIMESCOPE_WITH_IDENT(Loc); + int Rc = OFFLOAD_SUCCESS; Rc = target(Loc, Device, HostPtr, *KernelArgs, AsyncInfo); @@ -325,7 +327,7 @@ EXTERN int __tgt_target_kernel(ident_t *Loc, int64_t DeviceId, int32_t NumTeams, int32_t ThreadLimit, void *HostPtr, KernelArgsTy *KernelArgs) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); if (KernelArgs->Flags.NoWait) return targetKernel( Loc, DeviceId, NumTeams, ThreadLimit, HostPtr, KernelArgs); diff --git a/openmp/libomptarget/src/omptarget.cpp b/openmp/libomptarget/src/omptarget.cpp --- a/openmp/libomptarget/src/omptarget.cpp +++ b/openmp/libomptarget/src/omptarget.cpp @@ -531,7 +531,7 @@ int64_t ArgSize, int64_t ArgType, map_var_info_t ArgNames, void *ArgMapper, AsyncInfoTy &AsyncInfo, TargetDataFuncPtrTy TargetDataFunction) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); DP("Calling the mapper function " DPxMOD "\n", DPxPTR(ArgMapper)); // The mapper function fills up Components. @@ -1002,7 +1002,7 @@ static int targetDataContiguous(ident_t *Loc, DeviceTy &Device, void *ArgsBase, void *HstPtrBegin, int64_t ArgSize, int64_t ArgType, AsyncInfoTy &AsyncInfo) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); TargetPointerResultTy TPR = Device.getTgtPtrBegin(HstPtrBegin, ArgSize, /*UpdateRefCount=*/false, /*UseHoldRefCount=*/false, /*MustContain=*/true); @@ -1096,7 +1096,7 @@ uint64_t Size, int64_t ArgType, int CurrentDim, int DimSize, uint64_t Offset, AsyncInfoTy &AsyncInfo) { - TIMESCOPE_WITH_IDENT(Loc); + //TIMESCOPE_WITH_IDENT(Loc); int Ret = OFFLOAD_SUCCESS; if (CurrentDim < DimSize) { for (unsigned int I = 0; I < NonContig[CurrentDim].Count; ++I) { @@ -1140,6 +1140,9 @@ void **ArgsBase, void **Args, int64_t *ArgSizes, int64_t *ArgTypes, map_var_info_t *ArgNames, void **ArgMappers, AsyncInfoTy &AsyncInfo, bool) { + + TIMESCOPE_WITH_IDNET(Loc); + // process each input. for (int32_t I = 0; I < ArgNum; ++I) { if ((ArgTypes[I] & OMP_TGT_MAPTYPE_LITERAL) ||