Merge pull request #33 from ROCm/lwpck-1292

Merge from the public repo.

Merge pull request #33 from ROCm/lwpck-1292
Merge from the public repo.
29dcb956 · Illia Silin · GitHub · 29deceb6 · cbcc844e · 29dcb956
Unverified Commit 29dcb956 authored Feb 08, 2024 by Illia Silin Committed by GitHub Feb 08, 2024
20 changed files
--- a/library/src/tensor_operation_instance/gpu/normalization_fwd/device_groupnorm_fwd_swish_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization_fwd/device_groupnorm_fwd_swish_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization_fwd/device_layernorm2d_fwd_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization_fwd/device_layernorm2d_fwd_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization_fwd/device_layernorm4d_fwd_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization_fwd/device_layernorm4d_fwd_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization_fwd/normalization_fwd_instance_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/normalization_fwd/normalization_fwd_instance_common.hpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp
--- a/library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/transpose/device_transpose_instances_3d.cpp
+++ b/library/src/tensor_operation_instance/gpu/transpose/device_transpose_instances_3d.cpp
--- a/library/src/utility/CMakeLists.txt
+++ b/library/src/utility/CMakeLists.txt
--- a/profiler/include/profiler/profile_gemm_add_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_add_impl.hpp
--- a/profiler/include/profiler/profile_gemm_add_relu_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_add_relu_impl.hpp
--- a/profiler/include/profiler/profile_gemm_add_silu_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_add_silu_impl.hpp
--- a/profiler/include/profiler/profile_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_impl.hpp
--- a/profiler/include/profiler/profile_gemm_splitk_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_splitk_impl.hpp
--- a/profiler/include/profiler/profile_grouped_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_gemm_impl.hpp
--- a/profiler/include/profiler/profile_groupnorm_bwd_data_impl.hpp
+++ b/profiler/include/profiler/profile_groupnorm_bwd_data_impl.hpp
--- a/profiler/include/profiler/profile_groupnorm_bwd_gamma_beta_impl.hpp
+++ b/profiler/include/profiler/profile_groupnorm_bwd_gamma_beta_impl.hpp
--- a/profiler/include/profiler/profile_layernorm_bwd_data_impl.hpp
+++ b/profiler/include/profiler/profile_layernorm_bwd_data_impl.hpp
--- a/profiler/include/profiler/profile_layernorm_bwd_gamma_beta_impl.hpp
+++ b/profiler/include/profiler/profile_layernorm_bwd_gamma_beta_impl.hpp