ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-19 22:39:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Rangify constructor of HostTensorDescriptor & Tensor<> (#445)

Browse Source 
* Rangify STL algorithms

This commit adapts rangified std::copy(), std::fill() & std::transform()

* Rangify check_err()

By rangifying check_err(), we can not only compare values between
std::vector<>s, but also compare any ranges which have same value
type.

* Allow constructing Tensor<> like a HostTensorDescriptor

* Simplify Tensor<> object construction logics

* Remove more unnecessary 'HostTensorDescriptor' objects

* Re-format example code

* Re-write more HostTensorDescriptor ctor call
This commit is contained in:
Po Yen Chen
2022-11-12 01:36:01 +08:00
committed by GitHub
parent 37f2e91832
commit 4a2a56c22f
103 changed files with 657 additions and 649 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
example/23_softmax/softmax_blockwise.cpp
View File

@@ -246,7 +246,7 @@ int main(int argc, char* argv[])
invoker_ptr->Run(argument_ptr.get(), StreamConfig{nullptr, false});
out_dev.FromDevice(out.mData.data());
// LogRangeAsType<float>(std::cout << "tensor out: " , out.mData, ",") << std::endl;
pass = pass && ck::utils::check_err(out.mData, out_ref.mData);
pass = pass && ck::utils::check_err(out, out_ref);
};
float avg_time = invoker_ptr->Run(argument_ptr.get(), StreamConfig{nullptr, args.time_kernel});