Index: openmp/trunk/libomptarget/include/omptargetplugin.h =================================================================== --- openmp/trunk/libomptarget/include/omptargetplugin.h +++ openmp/trunk/libomptarget/include/omptargetplugin.h @@ -31,6 +31,9 @@ // having to load the library, which can be expensive. int32_t __tgt_rtl_is_valid_binary(__tgt_device_image *Image); +// Initialize the requires flags for the device. +int64_t __tgt_rtl_init_requires(int64_t RequiresFlags); + // Initialize the specified device. In case of success return 0; otherwise // return an error code. int32_t __tgt_rtl_init_device(int32_t ID); Index: openmp/trunk/libomptarget/plugins/cuda/src/rtl.cpp =================================================================== --- openmp/trunk/libomptarget/plugins/cuda/src/rtl.cpp +++ openmp/trunk/libomptarget/plugins/cuda/src/rtl.cpp @@ -111,6 +111,9 @@ int EnvNumTeams; int EnvTeamLimit; + // OpenMP Requires Flags + int64_t RequiresFlags; + //static int EnvNumThreads; static const int HardTeamLimit = 1<<16; // 64k static const int HardThreadLimit = 1024; @@ -227,6 +230,9 @@ } else { EnvNumTeams = -1; } + + // Default state. + RequiresFlags = OMP_REQ_UNDEFINED; } ~RTLDeviceInfoTy() { @@ -264,6 +270,12 @@ int32_t __tgt_rtl_number_of_devices() { return DeviceInfo.NumberOfDevices; } +int64_t __tgt_rtl_init_requires(int64_t RequiresFlags) { + DP("Init requires flags to %ld\n", RequiresFlags); + DeviceInfo.RequiresFlags = RequiresFlags; + return RequiresFlags; +} + int32_t __tgt_rtl_init_device(int32_t device_id) { CUdevice cuDevice; @@ -436,6 +448,17 @@ DPxPTR(e - HostBegin), e->name, DPxPTR(cuptr)); entry.addr = (void *)cuptr; + if (DeviceInfo.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY && + e->flags & OMP_DECLARE_TARGET_LINK) { + // If unified memory is present any target link variables + // can access host addresses directly. There is no longer a + // need for device copies. + cuMemcpyHtoD(cuptr, e->addr, sizeof(void *)); + DP("Copy linked variable host address (" DPxMOD ")" + "to device address (" DPxMOD ")\n", + DPxPTR(*((void**)e->addr)), DPxPTR(cuptr)); + } + DeviceInfo.addOffloadEntry(device_id, entry); continue; Index: openmp/trunk/libomptarget/plugins/exports =================================================================== --- openmp/trunk/libomptarget/plugins/exports +++ openmp/trunk/libomptarget/plugins/exports @@ -2,6 +2,7 @@ global: __tgt_rtl_is_valid_binary; __tgt_rtl_number_of_devices; + __tgt_rtl_init_requires; __tgt_rtl_init_device; __tgt_rtl_load_binary; __tgt_rtl_data_alloc; Index: openmp/trunk/libomptarget/src/device.cpp =================================================================== --- openmp/trunk/libomptarget/src/device.cpp +++ openmp/trunk/libomptarget/src/device.cpp @@ -275,6 +275,9 @@ /// Init device, should not be called directly. void DeviceTy::init() { + // Make call to init_requires if it exists for this plugin. + if (RTL->init_requires) + RTL->init_requires(RTLRequiresFlags); int32_t rc = RTL->init_device(RTLDeviceID); if (rc == OFFLOAD_SUCCESS) { IsInit = true; Index: openmp/trunk/libomptarget/src/rtl.h =================================================================== --- openmp/trunk/libomptarget/src/rtl.h +++ openmp/trunk/libomptarget/src/rtl.h @@ -36,6 +36,7 @@ int32_t); typedef int32_t(run_team_region_ty)(int32_t, void *, void **, ptrdiff_t *, int32_t, int32_t, int32_t, uint64_t); + typedef int64_t(init_requires_ty)(int64_t); int32_t Idx; // RTL index, index is the number of devices // of other RTLs that were registered before, @@ -60,6 +61,7 @@ data_delete_ty *data_delete; run_region_ty *run_region; run_team_region_ty *run_team_region; + init_requires_ty *init_requires; // Are there images associated with this RTL. bool isUsed; @@ -78,8 +80,8 @@ #endif is_valid_binary(0), number_of_devices(0), init_device(0), load_binary(0), data_alloc(0), data_submit(0), data_retrieve(0), - data_delete(0), run_region(0), run_team_region(0), isUsed(false), - Mtx() {} + data_delete(0), run_region(0), run_team_region(0), + init_requires(0), isUsed(false), Mtx() {} RTLInfoTy(const RTLInfoTy &r) : Mtx() { Idx = r.Idx; @@ -98,6 +100,7 @@ data_delete = r.data_delete; run_region = r.run_region; run_team_region = r.run_team_region; + init_requires = r.init_requires; isUsed = r.isUsed; } }; Index: openmp/trunk/libomptarget/src/rtl.cpp =================================================================== --- openmp/trunk/libomptarget/src/rtl.cpp +++ openmp/trunk/libomptarget/src/rtl.cpp @@ -107,6 +107,10 @@ dynlib_handle, "__tgt_rtl_run_target_team_region"))) continue; + // Optional functions + *((void**) &R.init_requires) = dlsym( + dynlib_handle, "__tgt_rtl_init_requires"); + // No devices are supported by this RTL? if (!(R.NumberOfDevices = R.number_of_devices())) { DP("No devices supported in this RTL\n");