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]

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;

example/12_reduce/reduce_blockwise.cpp

@@ -4,20 +4,17 @@
 #include <cstdlib>
 #include <getopt.h>
 
-#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 "device_base.hpp"
-#include "device_reduce_multiblock.hpp"
-#include "host_common_util.hpp"
-#include "host_reduction.hpp"
+#include "ck/ck.hpp"
+#include "ck/utility/reduction_enums.hpp"
+#include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp"
 
-#include "reduction_enums.hpp"
-#include "reduction_operator_mapping.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/host_tensor/host_common_util.hpp"
+#include "ck/library/host_tensor/host_reduction.hpp"
 
 using namespace ck;
 using namespace ck::tensor_operation::device;

example/12_reduce/reduce_blockwise_two_call.cpp

@@ -5,20 +5,17 @@
 #include <cstdlib>
 #include <getopt.h>
 
-#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 "device_base.hpp"
-#include "device_reduce_multiblock.hpp"
-#include "host_common_util.hpp"
-#include "host_reduction.hpp"
+#include "ck/ck.hpp"
+#include "ck/utility/reduction_enums.hpp"
+#include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp"
 
-#include "reduction_enums.hpp"
-#include "reduction_operator_mapping.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/host_tensor/host_common_util.hpp"
+#include "ck/library/host_tensor/host_reduction.hpp"
 
 using namespace ck;
 using namespace ck::tensor_operation::device;

example/13_pool2d_fwd/pool2d_fwd_common.hpp

@@ -2,19 +2,17 @@
 
 #include <iostream>
 
-#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 "reduction_enums.hpp"
-#include "reduction_operator_mapping.hpp"
-#include "reduction_functions_accumulate.hpp"
+#include "ck/ck.hpp"
+#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/element/element_wise_operation.hpp"
 
-#include "device_pool2d_fwd_nhwc_nhwc.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"
 
 template <typename InDataType,
           typename OutDataType,

example/13_pool2d_fwd/pool2d_fwd_fp16.cpp

@@ -1,9 +1,9 @@
 #include <iostream>
 #include <cstdlib>
 
-#include "config.hpp"
-#include "tensor_layout.hpp"
-#include "reduction_enums.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/utility/reduction_enums.hpp"
 
 #include "pool2d_fwd_common.hpp"
 

example/13_pool2d_fwd/pool2d_fwd_fp32.cpp

@@ -1,9 +1,9 @@
 #include <iostream>
 #include <cstdlib>
 
-#include "config.hpp"
-#include "tensor_layout.hpp"
-#include "reduction_enums.hpp"
+#include "ck/ck.hpp"
+#include "ck/utility/reduction_enums.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 
 #include "pool2d_fwd_common.hpp"
 

example/14_gemm_xdl_requant_relu_requant/gemm_xdl_requant_relu_requant_int8.cpp

@@ -2,21 +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 "host_gemm.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/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"
 
 struct RequantReluRequant
 {

example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp

@@ -2,21 +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 "host_gemm.hpp"
-#include "device_tensor.hpp"
-#include "device_grouped_gemm_xdl.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_grouped_gemm_xdl.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/16_gemm_reduce/gemm_reduce_xdl_max_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 "device_gemm_reduce_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_reduce_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/16_gemm_reduce/gemm_reduce_xdl_mean_squaremean_fp16.cpp

@@ -2,20 +2,19 @@
 #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 "device_gemm_reduce_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "reduction_operator.hpp"
-#include "reference_gemm.hpp"
-#include "gemm_specialization.hpp"
-#include "reduction_operator.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_reduce_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/utility/reduction_operator.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/17_convnd_bwd_data_xdl/convnd_bwd_data_xdl.cpp

@@ -2,20 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
 
-#include "config.hpp"
-#include "conv_util.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_convnd_bwd_data_xdl_ndhwc_kzyxc_ndhwk.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_convnd_bwd_data_xdl_ndhwc_kzyxc_ndhwk.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/18_batched_gemm_reduce/batched_gemm_reduce_xdl_fp16.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_batched_gemm_reduce_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "reduction_operator.hpp"
-#include "reference_batched_gemm.hpp"
-#include "gemm_specialization.hpp"
+
+#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/gemm_specialization.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_batched_gemm.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/19_binary_elementwise/broadcast_add_2d_amn_bn.cpp

@@ -1,39 +1,14 @@
-/*******************************************************************************
- *
- * MIT License
- *
- * Copyright (c) 2022 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- *******************************************************************************/
 #include <iostream>
 #include <cstdlib>
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
 
-#include "device_tensor.hpp"
-#include "binary_element_wise_operation.hpp"
-#include "device_binary_elementwise.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/device/device_binary_elementwise.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"
 
 using F16 = ck::half_t;
 using F32 = float;

example/19_binary_elementwise/broadcast_add_3d_am_bmnk.cpp

@@ -1,14 +1,14 @@
 #include <iostream>
 #include <cstdlib>
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
 
-#include "device_tensor.hpp"
-#include "binary_element_wise_operation.hpp"
-#include "device_binary_elementwise.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/device/device_binary_elementwise.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"
 
 using F16 = ck::half_t;
 using F32 = float;

example/19_binary_elementwise/elementwise_add_1d.cpp

@@ -1,39 +1,13 @@
-/*******************************************************************************
- *
- * MIT License
- *
- * Copyright (c) 2022 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- *******************************************************************************/
 #include <iostream>
 #include <cstdlib>
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
 
-#include "device_tensor.hpp"
-#include "binary_element_wise_operation.hpp"
-#include "device_binary_elementwise.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/device_binary_elementwise.hpp"
+#include "ck/tensor_operation/gpu/element/binary_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"
 
 using F16 = ck::half_t;
 using F32 = float;

example/19_binary_elementwise/elementwise_add_4d.cpp

@@ -1,39 +1,14 @@
-/*******************************************************************************
- *
- * MIT License
- *
- * Copyright (c) 2020 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- *******************************************************************************/
 #include <iostream>
 #include <cstdlib>
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
 
-#include "device_tensor.hpp"
-#include "binary_element_wise_operation.hpp"
-#include "device_binary_elementwise.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/device/device_binary_elementwise.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"
 
 using F16 = ck::half_t;
 using F32 = float;

example/20_convnd_bwd_weight_xdl/convnd_bwd_weight_xdl.cpp

@@ -2,21 +2,18 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
 
-#include "check_err.hpp"
-#include "conv_util.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_convnd_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_convnd_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;

example/20_convnd_bwd_weight_xdl/convnd_bwd_weight_xdl_bf16_splitk.cpp

@@ -2,22 +2,19 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
 
-#include "check_err.hpp"
-#include "conv_util.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_unary_elementwise.hpp"
-#include "device_convnd_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_convnd_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/device_unary_elementwise.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::bhalf_t;
 using WeiDataType = ck::bhalf_t;

example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_fp16.cpp

@@ -3,17 +3,18 @@
 #include <initializer_list>
 #include <cstdlib>
 
-#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_5ary_elementwise.hpp"
-#include "device_gemm_bias_add_reduce_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_bias_add_reduce_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/device_5ary_elementwise.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/21_gemm_layernorm/gemm_layernorm_xdl_fp16.cpp

@@ -3,17 +3,18 @@
 #include <initializer_list>
 #include <cstdlib>
 
-#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_5ary_elementwise.hpp"
-#include "device_gemm_reduce_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_reduce_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/device_5ary_elementwise.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/22_cgemm/cgemm_xdl_fp16.cpp

@@ -1,45 +1,18 @@
-/*******************************************************************************
- *
- * MIT License
- *
- * Copyright (c) 2022 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in all
- * copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- *******************************************************************************/
 #include <iostream>
 #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_cgemm_4gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.hpp"
-#include "reference_cgemm.hpp"
-#include "gemm_specialization.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/device_cgemm_4gemm_xdl_cshuffle.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_cgemm.hpp"
 
 template <ck::index_t... Is>
 using S = ck::Sequence<Is...>;

example/23_softmax/softmax_blockwise.cpp

@@ -4,20 +4,15 @@
 #include <cstdlib>
 #include <getopt.h>
 
-#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 "device_base.hpp"
-#include "device_softmax.hpp"
-#include "host_common_util.hpp"
-#include "reference_softmax.hpp"
+#include "ck/ck.hpp"
+#include "ck/utility/reduction_enums.hpp"
+#include "ck/tensor_operation/gpu/device/device_softmax.hpp"
+#include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
 
-#include "reduction_enums.hpp"
-#include "reduction_operator_mapping.hpp"
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_common_util.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_softmax.hpp"
 
 using namespace ck;
 using namespace ck::tensor_operation::device;

example/CMakeLists.txt

@@ -1,21 +1,6 @@
 include_directories(BEFORE
-    ${PROJECT_SOURCE_DIR}/include/ck
-    ${PROJECT_SOURCE_DIR}/include/ck/utility
-    ${PROJECT_SOURCE_DIR}/include/ck/host_utility
-    ${PROJECT_SOURCE_DIR}/include/ck/tensor_description
-    ${PROJECT_SOURCE_DIR}/include/ck/tensor
-    ${PROJECT_SOURCE_DIR}/include/ck/problem_transform
-    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/device
-    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/grid
-    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/block
-    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/warp
-    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/thread
-    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/element
-    ${PROJECT_SOURCE_DIR}/library/include/ck/library/host_tensor
-    ${PROJECT_SOURCE_DIR}/library/include/ck/library/reference_tensor_operation/cpu
-    ${PROJECT_SOURCE_DIR}/library/include/ck/library/reference_tensor_operation/gpu
-    ${PROJECT_SOURCE_DIR}/library/include/ck/library/utility
-    ${PROJECT_SOURCE_DIR}/external/include/half
+    ${PROJECT_SOURCE_DIR}/include
+    ${PROJECT_SOURCE_DIR}/library/include
 )
 
 add_custom_target(examples)