Merge branch 'develop' into bnorm_bwd_pr

example/13_pool2d_fwd/pool2d_fwd_common.hpp

@@ -9,7 +9,7 @@
 #include "ck/utility/reduction_enums.hpp"
 #include "ck/utility/reduction_functions_accumulate.hpp"
 #include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
-#include "ck/tensor_operation/gpu/device/device_pool2d_fwd_nhwc_nhwc.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/14_gemm_xdl_requant_relu_requant/gemm_xdl_requant_relu_requant_int8.cpp

@@ -9,7 +9,7 @@
 #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_gemm_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/device_memory.hpp"

example/15_grouped_gemm/grouped_gemm_xdl_bfp16.cpp

@@ -9,7 +9,7 @@
 #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_grouped_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp

@@ -9,7 +9,7 @@
 #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_grouped_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp

@@ -9,7 +9,7 @@
 #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_grouped_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp

@@ -9,7 +9,7 @@
 #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_grouped_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp

@@ -9,7 +9,7 @@
 #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_grouped_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp

@@ -9,7 +9,7 @@
 #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_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/device_memory.hpp"

example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
 #include "ck/library/utility/literals.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 // DataType

example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp

@@ -4,7 +4,7 @@
 #include "gemm_reduce_xdl_common.hpp"
 
 #include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 // DataType

example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp

@@ -4,7 +4,7 @@
 #include "gemm_reduce_xdl_common.hpp"
 
 #include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 // DataType

example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp

@@ -4,7 +4,7 @@
 #include "gemm_reduce_xdl_common.hpp"
 
 #include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 // DataType

example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp

@@ -4,7 +4,7 @@
 #include "gemm_reduce_xdl_common.hpp"
 
 #include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 using ADataType         = INT4;

example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp

@@ -4,7 +4,7 @@
 #include "gemm_reduce_xdl_common.hpp"
 
 #include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 using ADataType         = INT8;

example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_bf16.cpp

@@ -4,7 +4,7 @@
 #include "gemm_reduce_xdl_common.hpp"
 
 #include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 // DataType

example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp16.cpp

@@ -4,7 +4,7 @@
 #include "gemm_reduce_xdl_common.hpp"
 
 #include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 // DataType

example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp32.cpp

@@ -4,7 +4,7 @@
 #include "gemm_reduce_xdl_common.hpp"
 
 #include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 // DataType

example/17_convnd_bwd_data/convnd_bwd_data_xdl_fp16.cpp

@@ -3,7 +3,7 @@
 
 #include "convnd_bwd_data_common.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"
 
 using InDataType  = ck::half_t;
 using WeiDataType = ck::half_t;

example/18_batched_gemm_reduce/batched_gemm_reduce_xdl_fp16.cpp

@@ -9,7 +9,7 @@
 #include "ck/ck.hpp"
 #include "ck/utility/reduction_operator.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/tensor_operation/gpu/device/device_batched_gemm_reduce_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/19_binary_elementwise/broadcast_add_2d_amn_bn.cpp

@@ -6,7 +6,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp"
-#include "ck/tensor_operation/gpu/device/device_elementwise.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_elementwise.hpp"
 
 #include "ck/library/utility/check_err.hpp"
 #include "ck/library/utility/device_memory.hpp"