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

CMakeLists.txt

@@ -78,10 +78,6 @@ rocm_create_package(
     LDCONFIG
 )
 
-## half
-set(HALF_INCLUDE_DIR "${PROJECT_SOURCE_DIR}/external/include/half")
-message("HALF_INCLUDE_DIR: ${HALF_INCLUDE_DIR}")
-
 ## tidy
 include(EnableCompilerWarnings)
 set(CK_TIDY_ERRORS ERRORS * -readability-inconsistent-declaration-parameter-name)
@@ -229,7 +225,6 @@ set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/bin)
 
 include_directories(BEFORE
     ${PROJECT_SOURCE_DIR}/include
-    ${PROJECT_BINARY_DIR}/include
     ${PROJECT_SOURCE_DIR}/library/include
 )
 

Jenkinsfile

@@ -379,23 +379,23 @@ pipeline {
                 }
             }
         }
-        stage("Client App")
-        {
-            parallel
-            {
-                stage("Run Client App")
-                {
-                    agent{ label rocmnode("gfx908")}
-                    environment{
-                        setup_args = """ -D  -DBUILD_DEV=Off -DCMAKE_INSTALL_PREFIX=../install CMAKE_CXX_FLAGS="--offload-arch=gfx908 -O3 " """
-                        execute_args = """ cd ../test/client_app && rm -rf build && mkdir build && cd build && cmake -DCMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" .. && make  """ 
-                    }
-                    steps{
-                        buildHipClangJobAndReboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
-                    }
-                }
-            }
-        }
+      //stage("Client App")
+      //{
+      //    parallel
+      //    {
+      //        stage("Run Client App")
+      //        {
+      //            agent{ label rocmnode("gfx908")}
+      //            environment{
+      //                setup_args = """ -D  -DBUILD_DEV=Off -DCMAKE_INSTALL_PREFIX=../install CMAKE_CXX_FLAGS="--offload-arch=gfx908 -O3 " """
+      //                execute_args = """ cd ../test/client_app && rm -rf build && mkdir build && cd build && cmake -DCMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" .. && make  """ 
+      //            }
+      //            steps{
+      //                buildHipClangJobAndReboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
+      //            }
+      //        }
+      //    }
+      //}
         stage("Performance Tests")
         {
             parallel

example/01_gemm/gemm_dl_fp16.cpp

@@ -2,19 +2,17 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/device_gemm_dl.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/01_gemm/gemm_dl_fp32.cpp

@@ -2,19 +2,17 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/device_gemm_dl.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/01_gemm/gemm_dl_int8.cpp

@@ -2,19 +2,17 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "device_gemm_dl.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/device_gemm_dl.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/01_gemm/gemm_xdl_bf16.cpp

@@ -2,19 +2,17 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/device_gemm_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
+#include "ck/library/utility/check_err.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/01_gemm/gemm_xdl_fp16.cpp

@@ -2,19 +2,17 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "device_gemm_xdl.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
+
+#include "ck/ck.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/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/01_gemm/gemm_xdl_fp64.cpp

@@ -2,20 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "device_gemm_xdl.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
+
+#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/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
+#include "ck/library/utility/check_err.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/01_gemm/gemm_xdl_int8.cpp

@@ -2,19 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
+
+#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/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/02_gemm_alpha_beta/gemm_xdl_alpha_beta.cpp

@@ -2,21 +2,17 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "print.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "host_gemm.hpp"
-#include "device_tensor.hpp"
-#include "device_base.hpp"
-#include "device_gemm_xdl_c_shuffle_bias_2d.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm_bias_2d.hpp"
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/device_gemm_xdl_c_shuffle_bias_2d.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm_bias_2d.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/03_gemm_bias_relu/gemm_xdl_bias_relu.cpp

@@ -2,18 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
-#include "device_gemm_multiple_d_xdl_cshuffle.hpp"
+
+#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_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
+#include "ck/library/utility/check_err.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp16.cpp

@@ -2,18 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
-#include "device_gemm_multiple_d_xdl_cshuffle.hpp"
+
+#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_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
+#include "ck/library/utility/check_err.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/06_conv2d_fwd_bias_relu/conv2d_fwd_xdl_bias_relu.cpp

@@ -2,20 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "conv_util.hpp"
-#include "device.hpp"
-#include "device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp"
-#include "device_tensor.hpp"
-#include "element_wise_operation.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "reference_conv_fwd_bias_activation.hpp"
-#include "tensor_layout.hpp"
+
+#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_bias_activation_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation.hpp"
 
 namespace {
 

example/07_conv2d_fwd_bias_relu_add/conv2d_fwd_xdl_bias_relu_add.cpp

@@ -2,20 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "conv_util.hpp"
-#include "device.hpp"
-#include "device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp"
-#include "device_tensor.hpp"
-#include "element_wise_operation.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "reference_conv_fwd_bias_activation_add.hpp"
-#include "tensor_layout.hpp"
+
+#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_bias_activation_add_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation_add.hpp"
 
 namespace {
 

example/09_convnd_fwd/convnd_fwd_xdl_fp16.cpp

@@ -3,17 +3,17 @@
 #include <numeric>
 #include <type_traits>
 
-#include "check_err.hpp"
-#include "config.hpp"
-#include "conv_util.hpp"
-#include "device.hpp"
-#include "device_tensor.hpp"
-#include "device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
-#include "element_wise_operation.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "reference_conv_fwd.hpp"
-#include "tensor_layout.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp"
 
 namespace {
 

example/09_convnd_fwd/convnd_fwd_xdl_fp32.cpp

@@ -3,17 +3,17 @@
 #include <numeric>
 #include <type_traits>
 
-#include "check_err.hpp"
-#include "config.hpp"
-#include "conv_util.hpp"
-#include "device.hpp"
-#include "device_tensor.hpp"
-#include "device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
-#include "element_wise_operation.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "reference_conv_fwd.hpp"
-#include "tensor_layout.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp"
 
 namespace {
 

example/09_convnd_fwd/convnd_fwd_xdl_fp64.cpp

@@ -3,17 +3,17 @@
 #include <numeric>
 #include <type_traits>
 
-#include "check_err.hpp"
-#include "config.hpp"
-#include "conv_util.hpp"
-#include "device.hpp"
-#include "device_tensor.hpp"
-#include "device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
-#include "element_wise_operation.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "reference_conv_fwd.hpp"
-#include "tensor_layout.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp"
 
 namespace {
 

example/09_convnd_fwd/convnd_fwd_xdl_int8.cpp

@@ -3,17 +3,17 @@
 #include <numeric>
 #include <type_traits>
 
-#include "check_err.hpp"
-#include "config.hpp"
-#include "conv_util.hpp"
-#include "device.hpp"
-#include "device_tensor.hpp"
-#include "device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
-#include "element_wise_operation.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "reference_conv_fwd.hpp"
-#include "tensor_layout.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp"
 
 namespace {
 

example/10_conv2d_bwd_data/conv2d_bwd_data_xdl.cpp

@@ -2,20 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "print.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "tensor_layout.hpp"
-#include "element_wise_operation.hpp"
-#include "device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
-#include "reference_conv_bwd_data.hpp"
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp"
 
 using InDataType  = ck::half_t;
 using WeiDataType = ck::half_t;

example/11_conv2d_bwd_weight/conv2d_bwd_weight_xdl.cpp

@@ -2,20 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "print.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "tensor_layout.hpp"
-#include "element_wise_operation.hpp"
-#include "device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
-#include "reference_conv_backward_weight.hpp"
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_conv_backward_weight.hpp"
 
 using InDataType  = ck::half_t;
 using WeiDataType = ck::half_t;