Merge branch 'feature/integrage-karg-simplification-pr' into feature/test

24672339 · Po-Yen, Chen · f2c5ca5a · 853e797e · 24672339 · f2c5ca5a
Commit 24672339 authored May 25, 2023 by Po-Yen, Chen
20 changed files
--- a/library/include/ck/library/utility/host_tensor.hpp
+++ b/library/include/ck/library/utility/host_tensor.hpp
--- a/library/include/ck/library/utility/op_instance_engine.hpp
+++ b/library/include/ck/library/utility/op_instance_engine.hpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/pool_fwd_instance_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/pool_fwd_instance_common.hpp
--- a/profiler/include/profiler/data_type_enum_helper.hpp
+++ b/profiler/include/profiler/data_type_enum_helper.hpp
--- a/profiler/include/profiler/profile_convnd_bwd_data_impl.hpp
+++ b/profiler/include/profiler/profile_convnd_bwd_data_impl.hpp
--- a/profiler/include/profiler/profile_convnd_bwd_weight_impl.hpp
+++ b/profiler/include/profiler/profile_convnd_bwd_weight_impl.hpp
--- a/profiler/include/profiler/profile_pool2d_fwd_impl.hpp
+++ b/profiler/include/profiler/profile_pool2d_fwd_impl.hpp
--- a/profiler/include/profiler/profile_pool3d_fwd_impl.hpp
+++ b/profiler/include/profiler/profile_pool3d_fwd_impl.hpp
--- a/profiler/src/CMakeLists.txt
+++ b/profiler/src/CMakeLists.txt
--- a/profiler/src/profile_avg_pool2d_fwd.cpp
+++ b/profiler/src/profile_avg_pool2d_fwd.cpp
--- a/profiler/src/profile_groupnorm.cpp
+++ b/profiler/src/profile_groupnorm.cpp