Absolute include path (#281)

* ad gelu and fast_gelu

* added GeLU and fast GeLU

* clean up

* add gemm+fastgelu example

* add gemm+gelu instances

* update profiler

* clean up

* clean up

* adding gemm+bias+activation

* clean

* adding bias

* clean

* adding gemm multiple d

* debugging

* add gemm bias add fastgelu

* rename, clean

* refactoring; add readme

* refactor

* refactor

* refactor

* refactor

* refactor

* refactor

* fix

* fix

* update example

* update example

* rename

* update example

* add ckProfiler

* clean

* clean

* clean

* clean

* add client app example

* update readme

* delete obselete files

* remove old client app

* delete old file

* cleaning

* clean

* remove half

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path for all examples

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* revert client app example

* clean build

* fix build

* temporary disable client test on Jenkins

* clean

* clean

* clean

[ROCm/composable_kernel commit: d1db6a0c3e]

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_dl.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f32_f32_f32_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_i8_i8_i8_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f32_f32_f32_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_splitk_c_shuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_splitk_c_shuffle.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_splitk_c_shuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_splitk_c_shuffle.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_splitk_c_shuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_splitk_c_shuffle.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_splitk_c_shuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_splitk_c_shuffle.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_splitk.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_splitk.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_splitk.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_splitk.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_splitk.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_splitk.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp

@@ -1,8 +1,10 @@
-#include <stdlib.h>
-#include "config.hpp"
-#include "device_gemm_xdl_splitk.hpp"
-#include "element_wise_operation.hpp"
-#include "device_operation_instance.hpp"
+#include <cstdlib>
+
+#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_splitk.hpp"
+#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {