Merge branch 'develop' into amd-develop

39002e9e · Jun Liu · b26bdd61 · d52ec016 · 39002e9e · 39002e9e
Commit 39002e9e authored Aug 18, 2023 by Jun Liu
20 changed files
--- a/library/src/tensor_operation_instance/gpu/normalization/normalization_instance_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/normalization_instance_common.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_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_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/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_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/profiler/include/profiler/profile_groupnorm_impl.hpp
+++ b/profiler/include/profiler/profile_groupnorm_impl.hpp
--- a/profiler/include/profiler/profile_layernorm_impl.hpp
+++ b/profiler/include/profiler/profile_layernorm_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_max_pool3d_fwd.cpp
+++ b/profiler/src/profile_max_pool3d_fwd.cpp
--- a/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp
+++ b/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp
--- a/test/grouped_convnd_fwd/grouped_convnd_fwd.cpp
+++ b/test/grouped_convnd_fwd/grouped_convnd_fwd.cpp
--- a/test/pool_fwd/CMakeLists.txt
+++ b/test/pool_fwd/CMakeLists.txt