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

upgrade from clang-format-12 to clang-format-18 (#2568)

Browse Source 
* upgrade to clang-format-18

* update to clang-format-18 in pre-commit-config
This commit is contained in:
Illia Silin
2025-07-28 11:34:07 -07:00
committed by GitHub
parent 9786087010
commit 504b101da3
373 changed files with 3351 additions and 3760 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
profiler/include/profiler/profile_conv_bwd_data_impl.hpp
View File

@@ -260,9 +260,9 @@ bool profile_conv_bwd_data_impl(int do_verification,
}
}
std::cout << "Best configuration parameters:"
<< "\nname: " << best_op_name << "\navg_time: " << best_avg_time
<< "\ntflops: " << best_tflops << "\nGB/s: " << best_gb_per_sec << std::endl;
std::cout << "Best configuration parameters:" << "\nname: " << best_op_name
<< "\navg_time: " << best_avg_time << "\ntflops: " << best_tflops
<< "\nGB/s: " << best_gb_per_sec << std::endl;
return pass;
}

6
profiler/include/profiler/profile_conv_fwd_impl.hpp
View File

@@ -233,9 +233,9 @@ bool profile_conv_fwd_impl(int do_verification,
}
}
std::cout << "Best configuration parameters:"
<< "\nname: " << best_op_name << "\navg_time: " << best_avg_time
<< "\ntflops: " << best_tflops << "\nGB/s: " << best_gb_per_sec << std::endl;
std::cout << "Best configuration parameters:" << "\nname: " << best_op_name
<< "\navg_time: " << best_avg_time << "\ntflops: " << best_tflops
<< "\nGB/s: " << best_gb_per_sec << std::endl;
return pass;
}

5
profiler/include/profiler/profile_conv_tensor_rearrange_impl.hpp
View File

@@ -288,9 +288,8 @@ bool profile_conv_tensor_rearrange_impl(int do_verification,
}
}
std::cout << "Best configuration parameters:"
<< "\nname: " << best_op_name << "\navg_time: " << best_avg_time
<< "\nGB/s: " << best_gb_per_sec << std::endl;
std::cout << "Best configuration parameters:" << "\nname: " << best_op_name
<< "\navg_time: " << best_avg_time << "\nGB/s: " << best_gb_per_sec << std::endl;
return is_supporting_instance && pass;
}

7
profiler/include/profiler/profile_grouped_conv_bwd_data_impl.hpp
View File

@@ -287,10 +287,9 @@ bool profile_grouped_conv_bwd_data_impl(int do_verification,
}
}
std::cout << "Best configuration parameters:"
<< "\nname: " << best_op_name << "\navg_time: " << best_avg_time
<< "\ntflops: " << best_tflops << "\nGB/s: " << best_gb_per_sec << ", SplitK "
<< best_split_k << std::endl;
std::cout << "Best configuration parameters:" << "\nname: " << best_op_name
<< "\navg_time: " << best_avg_time << "\ntflops: " << best_tflops
<< "\nGB/s: " << best_gb_per_sec << ", SplitK " << best_split_k << std::endl;
return pass;
}

19
profiler/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp
View File

@@ -92,12 +92,12 @@ bool profile_grouped_conv_bwd_weight_impl(int do_verification,
if(do_verification)
{
auto ref_conv = ck::tensor_operation::host::ReferenceConvBwdWeight<NDimSpatial,
InDataType,
WeiDataType,
OutDataType,
InElementOp,
WeiElementOp,
OutElementOp>{};
InDataType,
WeiDataType,
OutDataType,
InElementOp,
WeiElementOp,
OutElementOp>{};
auto ref_invoker = ref_conv.MakeInvoker();
auto ref_argument = ref_conv.MakeArgument(input,
weight_host_result,
@@ -302,10 +302,9 @@ bool profile_grouped_conv_bwd_weight_impl(int do_verification,
}
}
std::cout << "Best configuration parameters:"
<< "\nname: " << best_op_name << "\navg_time: " << best_avg_time
<< "\ntflops: " << best_tflops << "\nGB/s: " << best_gb_per_sec << ", SplitK "
<< best_split_k << std::endl;
std::cout << "Best configuration parameters:" << "\nname: " << best_op_name
<< "\navg_time: " << best_avg_time << "\ntflops: " << best_tflops
<< "\nGB/s: " << best_gb_per_sec << ", SplitK " << best_split_k << std::endl;
return all_pass;
}

10
profiler/include/profiler/profile_grouped_conv_fwd_bias_clamp_impl.hpp
View File

@@ -178,8 +178,8 @@ bool profile_grouped_conv_fwd_bias_clamp_impl(int do_verification,
in_element_op,
wei_element_op,
out_element_op,
{},
{},
{},
{},
d_tensors);
// init host output to zero
@@ -312,9 +312,9 @@ bool profile_grouped_conv_fwd_bias_clamp_impl(int do_verification,
run_impl(op_ptr, argument_ptr);
}
std::cout << "Best configuration parameters:"
<< "\nname: " << best_op_name << "\navg_time: " << best_avg_time
<< "\ntflops: " << best_tflops << "\nGB/s: " << best_gb_per_sec << std::endl;
std::cout << "Best configuration parameters:" << "\nname: " << best_op_name
<< "\navg_time: " << best_avg_time << "\ntflops: " << best_tflops
<< "\nGB/s: " << best_gb_per_sec << std::endl;
return pass;
}

6
profiler/include/profiler/profile_grouped_conv_fwd_impl.hpp
View File

@@ -250,9 +250,9 @@ bool profile_grouped_conv_fwd_impl(int do_verification,
run_impl(op_ptr, argument_ptr);
}
std::cout << "Best configuration parameters:"
<< "\nname: " << best_op_name << "\navg_time: " << best_avg_time
<< "\ntflops: " << best_tflops << "\nGB/s: " << best_gb_per_sec << std::endl;
std::cout << "Best configuration parameters:" << "\nname: " << best_op_name
<< "\navg_time: " << best_avg_time << "\ntflops: " << best_tflops
<< "\nGB/s: " << best_gb_per_sec << std::endl;
return pass;
}

6
profiler/include/profiler/profile_grouped_conv_fwd_outelementop_impl.hpp
View File

@@ -342,9 +342,9 @@ bool profile_grouped_conv_fwd_outelementop_impl(int do_verification,
run_impl(op_ptr, argument_ptr);
}
std::cout << "Best configuration parameters:"
<< "\nname: " << best_op_name << "\navg_time: " << best_avg_time
<< "\ntflops: " << best_tflops << "\nGB/s: " << best_gb_per_sec << std::endl;
std::cout << "Best configuration parameters:" << "\nname: " << best_op_name
<< "\navg_time: " << best_avg_time << "\ntflops: " << best_tflops
<< "\nGB/s: " << best_gb_per_sec << std::endl;
return pass;
}

23
profiler/include/profiler/profile_softmax_impl.hpp
View File

@@ -103,12 +103,12 @@ bool profile_softmax_impl(int do_verification,
// add device softmax instances
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
using DeviceOp = tensor_operation::device::DeviceSoftmax<InDataType,
AccDataType,
OutDataType,
PassThrough,
PassThrough,
Rank,
NumReduceDim>;
AccDataType,
OutDataType,
PassThrough,
PassThrough,
Rank,
NumReduceDim>;
// get device op instances
const auto instances = tensor_operation::device::instance::DeviceOperationInstanceFactory<
@@ -141,8 +141,7 @@ bool profile_softmax_impl(int do_verification,
{
std::cout << inst_ptr->GetTypeString() << " skipped due to unsupported argument: ";
LogRange(std::cout << "input lengths = [", in_length, ", ")
<< "], "
<< "scaler = [" << alpha << ", " << beta << "]";
<< "], " << "scaler = [" << alpha << ", " << beta << "]";
LogRange(std::cout << ", reduce dims = [", reduce_dims, ", ") << "]." << std::endl;
instance_pass.push_back(true);
continue;
@@ -202,8 +201,7 @@ bool profile_softmax_impl(int do_verification,
{
std::cout << inst_ptr->GetTypeString() << " failed verification: ";
LogRange(std::cout << "input lengths = [", in_length, ", ")
<< "], "
<< "scaler = [" << alpha << ", " << beta << "]." << std::endl;
<< "], " << "scaler = [" << alpha << ", " << beta << "]." << std::endl;
}
instance_pass.push_back(pass);
}
@@ -215,9 +213,8 @@ bool profile_softmax_impl(int do_verification,
LogRange(std::cout << "length = ", in_tensor_lengths, ",") << ", ";
LogRange(std::cout << "stride = ", in_tensor_strides, ",") << ", ";
LogRange(std::cout << "reduce dims ", reduce_dims, ",") << ", ";
std::cout << "alpha = " << alpha << ", "
<< "beta = " << beta << ", " << best_avg_time << " ms, " << best_gb_per_sec
<< " GB/s, " << best_instance_name << std::endl;
std::cout << "alpha = " << alpha << ", " << "beta = " << beta << ", " << best_avg_time
<< " ms, " << best_gb_per_sec << " GB/s, " << best_instance_name << std::endl;
}
return std::all_of(
std::begin(instance_pass), std::end(instance_pass), [](bool p) { return p; });