diff options
Diffstat (limited to 'offload/plugins-nextgen/cuda/src/rtl.cpp')
| -rw-r--r-- | offload/plugins-nextgen/cuda/src/rtl.cpp | 12 |
1 files changed, 7 insertions, 5 deletions
diff --git a/offload/plugins-nextgen/cuda/src/rtl.cpp b/offload/plugins-nextgen/cuda/src/rtl.cpp index 15193de6ae43..728bf07c572b 100644 --- a/offload/plugins-nextgen/cuda/src/rtl.cpp +++ b/offload/plugins-nextgen/cuda/src/rtl.cpp @@ -935,15 +935,16 @@ struct CUDADeviceTy : public GenericDeviceTy { if (Res == CUDA_SUCCESS) // For consistency with other drivers, store the version as a string // rather than an integer - Info.add("CUDA Driver Version", std::to_string(TmpInt)); + Info.add("CUDA Driver Version", std::to_string(TmpInt), "", + DeviceInfo::DRIVER_VERSION); Info.add("CUDA OpenMP Device Number", DeviceId); Res = cuDeviceGetName(TmpChar, 1000, Device); if (Res == CUDA_SUCCESS) - Info.add("Device Name", TmpChar); + Info.add("Device Name", TmpChar, "", DeviceInfo::NAME); - Info.add("Vendor Name", "NVIDIA"); + Info.add("Vendor Name", "NVIDIA", "", DeviceInfo::VENDOR); Res = cuDeviceTotalMem(&TmpSt, Device); if (Res == CUDA_SUCCESS) @@ -978,7 +979,8 @@ struct CUDADeviceTy : public GenericDeviceTy { if (Res == CUDA_SUCCESS) Info.add("Maximum Threads per Block", TmpInt); - auto &MaxBlock = *Info.add("Maximum Block Dimensions", ""); + auto &MaxBlock = *Info.add("Maximum Block Dimensions", std::monostate{}, "", + DeviceInfo::MAX_WORK_GROUP_SIZE); Res = getDeviceAttrRaw(CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X, TmpInt); if (Res == CUDA_SUCCESS) MaxBlock.add("x", TmpInt); @@ -1311,7 +1313,7 @@ Error CUDAKernelTy::launchImpl(GenericDeviceTy &GenericDevice, if (MaxDynCGroupMem >= MaxDynCGroupMemLimit) { CUresult AttrResult = cuFuncSetAttribute( Func, CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES, MaxDynCGroupMem); - Plugin::check( + return Plugin::check( AttrResult, "Error in cuLaunchKernel while setting the memory limits: %s"); MaxDynCGroupMemLimit = MaxDynCGroupMem; |