Merge remote-tracking branch 'rosenrodt/gemm-standalone-bench' into wavelet_model

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/CMakeLists.txt

@@ -17,7 +17,6 @@ IF(IS_DIRECTORY "${subdir_path}")
 ENDIF()
 ENDFOREACH()
 
-
 add_library(device_operations STATIC ${CK_DEVICE_INSTANCES})
 add_library(composablekernels::device_operations ALIAS device_operations)
 

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 {

library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f32_f32_f32_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_int8_int8_int8_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_int8_int8_int8_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_int8_int8_int8_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_int8_int8_int8_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 {