Reorganize files, Part 1 (#119)

* delete obselete files * move files * build * update cmake * update cmake * fix build * reorg examples * update cmake for example and test [ROCm/composable_kernel commit: 5d37d7bff4]
2026-05-16 19:09:59 +00:00 · 2022-03-08 21:46:36 -06:00
parent 2466420db6
commit 6203866064
422 changed files with 388 additions and 3326 deletions
--- a/library/src/host_tensor/host_tensor.cpp
+++ b/library/src/host_tensor/host_tensor.cpp
@@ -0,0 +1,81 @@
+#include <cassert>
+#include "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(int 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;
+}
+
+float bf16_to_f32_(ck::bhalf_t src_val)
+{
+    union
+    {
+        uint32_t int32;
+        float fp32;
+    } u = {uint32_t(src_val) << 16};
+    return u.fp32;
+}
+
+void bf16_to_f32_(const Tensor<ck::bhalf_t>& src, Tensor<float>& dst)
+{
+    for(int i = 0; i < src.mData.size(); ++i)
+        dst.mData[i] = bf16_to_f32_(src.mData[i]);
+}