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

test/gemm/gemm_dl_int8.cpp

 #include <algorithm>
 #include <cstdlib>
-#include <half.hpp>
 #include <iostream>
 #include <numeric>
 #include <tuple>
 #include <vector>
 
-#include "../gemm/gemm_util.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_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"
+
+#include "test/gemm/gemm_util.hpp"
 
 using PassThrough = ck::tensor_operation::element_wise::PassThrough;
 

test/gemm/gemm_util.hpp

-#ifndef GEMM_UTILS_HPP
-#define GEMM_UTILS_HPP
+#pragma once
 
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "reference_gemm.hpp"
-#include "tensor_layout.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.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"
 
 namespace ck {
 namespace gemm_util {
@@ -350,4 +349,3 @@ struct TestGemmBF16
 
 } // namespace gemm_util
 } // namespace ck
-#endif

test/gemm/gemm_xdl_bf16.cpp

 #include <algorithm>
 #include <cstdlib>
-#include <half.hpp>
 #include <iostream>
 #include <numeric>
 #include <tuple>
 #include <vector>
 
-#include "gemm_util.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.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.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"
+
+#include "test/gemm/gemm_util.hpp"
 
 using PassThrough = ck::tensor_operation::element_wise::PassThrough;
 

test/gemm/gemm_xdl_fp16.cpp

 #include <algorithm>
 #include <cstdlib>
-#include <half.hpp>
 #include <iostream>
 #include <numeric>
 #include <tuple>
 #include <vector>
 
-#include "gemm_util.hpp"
-#include "config.hpp"
-#include "print.hpp"
-#include "device.hpp"
-#include "host_gemm.hpp"
-#include "device_tensor.hpp"
-#include "device_gemm_xdl.hpp"
-#include "device_gemm_xdl_cshuffle.hpp"
-#include "element_wise_operation.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.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"
+
+#include "test/gemm/gemm_util.hpp"
 
 using PassThrough = ck::tensor_operation::element_wise::PassThrough;
 

test/gemm/gemm_xdl_fp32.cpp

 #include <algorithm>
 #include <cstdlib>
-#include <half.hpp>
 #include <iostream>
 #include <numeric>
 #include <tuple>
 #include <vector>
 
-#include "gemm_util.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.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.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"
+
+#include "test/gemm/gemm_util.hpp"
 
 using PassThrough = ck::tensor_operation::element_wise::PassThrough;
 

test/gemm/gemm_xdl_fp64.cpp

 #include <algorithm>
 #include <cstdlib>
-#include <half.hpp>
 #include <iostream>
 #include <numeric>
 #include <tuple>
 #include <vector>
 
-#include "gemm_util.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.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.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"
+
+#include "test/gemm/gemm_util.hpp"
 
 using PassThrough = ck::tensor_operation::element_wise::PassThrough;
 

test/gemm/gemm_xdl_int8.cpp

 #include <algorithm>
 #include <cstdlib>
-#include <half.hpp>
 #include <iostream>
 #include <numeric>
 #include <tuple>
 #include <vector>
 
-#include "gemm_util.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.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.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"
+
+#include "test/gemm/gemm_util.hpp"
 
 using PassThrough = ck::tensor_operation::element_wise::PassThrough;
 

test/gemm_reduce/CMakeLists.txt

-include_directories(BEFORE
-    ${PROJECT_SOURCE_DIR}/profiler/include
-    ${PROJECT_SOURCE_DIR}/test/include
-    ${PROJECT_SOURCE_DIR}/external/include/half
-)
-
 add_test_executable(test_gemm_reduce_fp16 gemm_reduce_fp16.cpp)
 target_link_libraries(test_gemm_reduce_fp16 PRIVATE host_tensor)
 target_link_libraries(test_gemm_reduce_fp16 PRIVATE device_gemm_reduce_instance)

test/gemm_reduce/gemm_reduce_fp16.cpp

 #include <iostream>
 
-#include "profile_gemm_reduce_impl.hpp"
+#include "profiler/include/profile_gemm_reduce_impl.hpp"
 
 int main()
 {

test/gemm_split_k/gemm_split_k.cpp

 #include <iostream>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include "config.hpp"
-#include "print.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
-#include "host_gemm.hpp"
-#include "tensor_layout.hpp"
-#include "device_gemm_xdl_splitk.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_splitk.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/host_tensor/device_memory.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
+
+#include "ck/library/host_tensor/host_gemm.hpp"
 
 enum struct GemmMatrixLayout
 {

test/grouped_gemm/grouped_gemm_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"
 
 using PassThrough = ck::tensor_operation::element_wise::PassThrough;
 

test/magic_number_division/magic_number_division.cpp

@@ -2,16 +2,13 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-
-#include "check_err.hpp"
-#include "config.hpp"
-#include "magic_division.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "device_tensor.hpp"
+
+#include "ck/ck.hpp"
+#include "ck/utility/magic_division.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"
 
 __global__ void gpu_magic_number_division(uint32_t magic_multiplier,
                                           uint32_t magic_shift,

test/reduce/reduce_no_index.cpp

-#include "getopt.h"
+#include <getopt.h>
 
-#include "host_common_util.hpp"
-#include "profile_reduce_impl.hpp"
+#include "ck/library/host_tensor/host_common_util.hpp"
+#include "profiler/include/profile_reduce_impl.hpp"
 
 using namespace ck;
 

test/reduce/reduce_with_index.cpp

-#include "getopt.h"
+#include <getopt.h>
 
-#include "host_common_util.hpp"
-#include "profile_reduce_impl.hpp"
+#include "ck/library/host_tensor/host_common_util.hpp"
+#include "profiler/include/profile_reduce_impl.hpp"
 
 using namespace ck;
 

test/reference_conv_fwd/reference_conv_fwd.cpp

 #include <cmath>
 #include <cstdlib>
-#include <half.hpp>
 #include <numeric>
 #include <type_traits>
 #include <vector>
-#include "gtest/gtest.h"
+#include <gtest/gtest.h>
 
-#include "check_err.hpp"
-#include "config.hpp"
-#include "conv_util.hpp"
-#include "element_wise_operation.hpp"
-#include "fill.hpp"
-#include "host_tensor.hpp"
-#include "reference_conv_fwd.hpp"
-#include "tensor_layout.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/utility/fill.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp"
 
 namespace {
 using InElementOp  = ck::tensor_operation::element_wise::PassThrough;

test/softmax/test_softmax_util.hpp

 #include <vector>
 #include <iostream>
-#include "gtest/gtest.h"
-
-#include "config.hpp"
-#include "host_tensor.hpp"
-#include "check_err.hpp"
-#include "number.hpp"
-#include "reference_softmax.hpp"
-#include "device_softmax.hpp"
+#include <gtest/gtest.h>
+
+#include "ck/ck.hpp"
+#include "ck/utility/number.hpp"
+#include "ck/tensor_operation/gpu/device/device_softmax.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/host_tensor/host_tensor.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/reference_tensor_operation/cpu/reference_softmax.hpp"
 
 namespace ck {
 

test/space_filling_curve/space_filling_curve.cpp

@@ -3,7 +3,9 @@
 #include <numeric>
 #include <cassert>
 
-#include "tensor_space_filling_curve.hpp"
+#include "ck/ck.hpp"
+#include "ck/utility/common_header.hpp"
+#include "ck/tensor_description/tensor_space_filling_curve.hpp"
 
 using namespace ck;