ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 21:21:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Misc fixes (#994)

Browse Source 
* reinterpret_cast to const char* in dumpBufferToFile to be compatible with both const and non-const input pointers

* Add seed input to GeneratorTensor_4 for normal_distribution generator

* Add GetTypeString() for DeviceElementwiseImpl

* Add HIP_CHECK_ERROR macro
This commit is contained in:
Qianfeng
2023-10-20 00:26:04 +08:00
committed by GitHub
parent 82f3a835d5
commit b4fc4d0b8d
4 changed files with 41 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
include/ck/tensor_operation/gpu/device/impl/device_elementwise_impl.hpp
View File

@@ -296,6 +296,28 @@ struct DeviceElementwiseImpl
{
return std::make_unique<Invoker>();
};
std::string GetTypeString() const override
{
auto str = std::stringstream();
// clang-format off
str << "DeviceElementwiseImpl<" ;
str << "NumDim_" << NumDim << ",";
str << "MPerThread_" << MPerThread << ",";
str << "InScalarPerVector";
static_for<0, InScalarPerVectorSeq::Size(), 1>{}([&](auto i) { str << "_" << InScalarPerVectorSeq::At(i).value; });
str << ",";
str << "OutScalarPerVector";
static_for<0, OutScalarPerVectorSeq::Size(), 1>{}([&](auto i) { str << "_" << OutScalarPerVectorSeq::At(i).value; });
str << ">";
// clang-format on
return str.str();
}
}; // namespace device
} // namespace device