Files
composable_kernel/library/src/host_tensor/host_tensor.cpp
Chao Liu 4a27f120ea Absolute include path (#281)
* ad gelu and fast_gelu

* added GeLU and fast GeLU

* clean up

* add gemm+fastgelu example

* add gemm+gelu instances

* update profiler

* clean up

* clean up

* adding gemm+bias+activation

* clean

* adding bias

* clean

* adding gemm multiple d

* debugging

* add gemm bias add fastgelu

* rename, clean

* refactoring; add readme

* refactor

* refactor

* refactor

* refactor

* refactor

* refactor

* fix

* fix

* update example

* update example

* rename

* update example

* add ckProfiler

* clean

* clean

* clean

* clean

* add client app example

* update readme

* delete obselete files

* remove old client app

* delete old file

* cleaning

* clean

* remove half

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path for all examples

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* revert client app example

* clean build

* fix build

* temporary disable client test on Jenkins

* clean

* clean

* clean

[ROCm/composable_kernel commit: d1db6a0c3e]
2022-06-24 20:51:04 -05:00

76 lines
1.9 KiB
C++

#include <cassert>
#include "ck/library/host_tensor/host_tensor.hpp"
void HostTensorDescriptor::CalculateStrides()
{
mStrides.clear();
mStrides.resize(mLens.size(), 0);
if(mStrides.empty())
return;
mStrides.back() = 1;
std::partial_sum(
mLens.rbegin(), mLens.rend() - 1, mStrides.rbegin() + 1, std::multiplies<std::size_t>());
}
std::size_t HostTensorDescriptor::GetNumOfDimension() const { return mLens.size(); }
std::size_t HostTensorDescriptor::GetElementSize() const
{
assert(mLens.size() == mStrides.size());
return std::accumulate(
mLens.begin(), mLens.end(), std::size_t{1}, std::multiplies<std::size_t>());
}
std::size_t HostTensorDescriptor::GetElementSpace() const
{
std::size_t space = 1;
for(std::size_t i = 0; i < mLens.size(); ++i)
{
space += (mLens[i] - 1) * mStrides[i];
}
return space;
}
const std::vector<std::size_t>& HostTensorDescriptor::GetLengths() const { return mLens; }
const std::vector<std::size_t>& HostTensorDescriptor::GetStrides() const { return mStrides; }
std::ostream& operator<<(std::ostream& os, const HostTensorDescriptor& desc)
{
os << "dim " << desc.GetNumOfDimension() << ", ";
os << "lengths {";
LogRange(os, desc.GetLengths(), ", ");
os << "}, ";
os << "strides {";
LogRange(os, desc.GetStrides(), ", ");
os << "}";
return os;
}
void ostream_HostTensorDescriptor(const HostTensorDescriptor& desc, std::ostream& os)
{
os << "dim " << desc.GetNumOfDimension() << ", ";
os << "lengths {";
LogRange(os, desc.GetLengths(), ", ");
os << "}, ";
os << "strides {";
LogRange(os, desc.GetStrides(), ", ");
os << "}" << std::endl;
}
#if 1
// FIXME: remove
void bf16_to_f32_(const Tensor<ck::bhalf_t>& src, Tensor<float>& dst)
{
for(std::size_t i = 0; i < src.mData.size(); ++i)
dst.mData[i] = ck::type_convert<float>(src.mData[i]);
}
#endif