mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
* Turning compare warnings on
* Cleaning part I
* Cleaning part II
* Explicit static_cast to ck::type_convert
* Resolving large tensor size issue.
* format
* revert change to tensor descriptor; promote lementSpaceSize to 64bit
* use integer value for GEMM test
* Review remarks
* Review remarks + issues with (un)signed arithmetic
* Format fix
* Format
* Clang-format.
* fix 2gb limit issue
Co-authored-by: Chao Liu <chao.liu2@amd.com>
Co-authored-by: Adam Osewski <aosewski@amd.com>
[ROCm/composable_kernel commit: f03a1738d9]
This commit is contained in:
@@ -25,7 +25,7 @@ std::size_t HostTensorDescriptor::GetElementSize() const
|
||||
std::size_t HostTensorDescriptor::GetElementSpace() const
|
||||
{
|
||||
std::size_t space = 1;
|
||||
for(int i = 0; i < mLens.size(); ++i)
|
||||
for(std::size_t i = 0; i < mLens.size(); ++i)
|
||||
{
|
||||
space += (mLens[i] - 1) * mStrides[i];
|
||||
}
|
||||
@@ -68,7 +68,7 @@ void ostream_HostTensorDescriptor(const HostTensorDescriptor& desc, std::ostream
|
||||
// FIXME: remove
|
||||
void bf16_to_f32_(const Tensor<ck::bhalf_t>& src, Tensor<float>& dst)
|
||||
{
|
||||
for(int i = 0; i < src.mData.size(); ++i)
|
||||
for(std::size_t i = 0; i < src.mData.size(); ++i)
|
||||
dst.mData[i] = ck::type_convert<float>(src.mData[i]);
|
||||
}
|
||||
#endif
|
||||
|
||||
Reference in New Issue
Block a user