Merge commit '30480288' into conv_quant_int8

include/ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp → include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp

@@ -11,7 +11,7 @@
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/device_reduce.hpp"
-#include "ck/tensor_operation/gpu/device/device_reduce_common.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp"
 #include "ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp"
 #include "ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp"
 #include "ck/host_utility/device_prop.hpp"

include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp → include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp

@@ -9,7 +9,7 @@
 #include "ck/host_utility/device_prop.hpp"
 #include "ck/host_utility/kernel_launch.hpp"
 #include "ck/tensor_operation/gpu/device/device_reduce.hpp"
-#include "ck/tensor_operation/gpu/device/device_reduce_common.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp"
 #include "ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp"
 #include "ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp"
 

include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp

@@ -10,8 +10,8 @@
 #include "ck/tensor_operation/gpu/device/device_base.hpp"
 #include "ck/tensor_operation/gpu/device/device_reduce.hpp"
 #include "ck/tensor_operation/gpu/device/device_softmax.hpp"
-#include "ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp"
-#include "ck/tensor_operation/gpu/device/device_reduce_common.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp"
 #include "ck/tensor_operation/gpu/grid/gridwise_softmax.hpp"
 #include "ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp"
 #include "ck/host_utility/device_prop.hpp"

library/include/ck/library/tensor_operation_instance/gpu/device_elementwise_instance.hpp

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

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp

@@ -4,7 +4,7 @@
 #pragma once
 
 #include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
-#include "ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp"
 #include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp"
 
 namespace ck {

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp

@@ -4,7 +4,7 @@
 #pragma once
 
 #include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
-#include "ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp"
 
 #include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp"
 

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp

@@ -4,7 +4,7 @@
 #pragma once
 
 #include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
-#include "ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp"
 #include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gkn_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gnk_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gkn_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gnk_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gkn_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gmk_gnk_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gkn_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gkm_gnk_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_gmk_gkn_gmn_instance.cpp

@@ -6,7 +6,7 @@
 #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_batched_gemm_xdl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {