Merge commit '30480288' into conv_quant_int8

library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance.cpp

@@ -11,7 +11,7 @@
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/device_contraction_multiple_d_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance.cpp

@@ -11,7 +11,7 @@
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/device_contraction_multiple_d_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance.cpp

@@ -11,7 +11,7 @@
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/device_contraction_multiple_d_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_bf16_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f16_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f32_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv1d_bwd_data/device_conv1d_bwd_data_xdl_nwc_kxc_nwk_int8_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv1d_bwd_weight/device_conv1d_bwd_weight_xdl_nwc_kxc_nwk_bf16_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv1d_bwd_weight/device_conv1d_bwd_weight_xdl_nwc_kxc_nwk_f16_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv1d_bwd_weight/device_conv1d_bwd_weight_xdl_nwc_kxc_nwk_f32_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp

@@ -5,9 +5,9 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
 // FIXME: retire dedicated 2D version
-#include "ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f16_instance.cpp

@@ -5,9 +5,9 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
 // FIXME: retire dedicated 2D version
-#include "ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp

@@ -5,9 +5,9 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
 // FIXME: retire dedicated 2D version
-#include "ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_int8_instance.cpp

@@ -5,9 +5,9 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp"
 // FIXME: retire dedicated 2D version
-#include "ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv2d_bwd_weight/device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv2d_bwd_weight/device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f16_instance.cpp

@@ -5,9 +5,9 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
 // TODO: retire dedicated 2d version
-#include "ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv2d_bwd_weight/device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f32_instance.cpp

@@ -5,9 +5,9 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp"
 // TODO: retire dedicated 2d version
-#include "ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"

library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_f16_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 

library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 

library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"