Merge branch 'develop' into lwpck-756

8c4897d1 · Rostyslav Geyyer · GitHub · 9ba9ebec · 9e86ebd6 · 8c4897d1
Unverified Commit 8c4897d1 authored Aug 30, 2023 by Rostyslav Geyyer Committed by GitHub Aug 30, 2023
20 changed files
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp
--- 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/pool3d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/pool3d_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/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_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/library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_int8_instance.hpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_int8_instance.hpp
--- a/library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt
--- a/library/src/utility/device_memory.cpp
+++ b/library/src/utility/device_memory.cpp
--- a/profiler/README.md
+++ b/profiler/README.md
--- a/profiler/include/profiler/profile_gemm_multiply_add_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_multiply_add_impl.hpp