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

profiler/include/profile_gemm_reduce_impl.hpp

 #pragma once
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "host_conv.hpp"
-#include "tensor_layout.hpp"
-#include "device_tensor.hpp"
-#include "element_wise_operation.hpp"
-#include "reduction_operator.hpp"
-#include "device_gemm_reduce.hpp"
-#include "reference_gemm.hpp"
+
+#include "ck/ck.hpp"
+#include "ck/utility/reduction_operator.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_gemm_reduce.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_gemm.hpp"
 
 namespace ck {
 namespace tensor_operation {

profiler/include/profile_grouped_gemm_impl.hpp

 #pragma once
+
 #include <iomanip>
 
-#include "check_err.hpp"
-#include "config.hpp"
-#include "device.hpp"
-#include "host_tensor.hpp"
-#include "host_tensor_generator.hpp"
-#include "host_conv.hpp"
-#include "tensor_layout.hpp"
-#include "device_tensor.hpp"
-#include "element_wise_operation.hpp"
-#include "device_gemm.hpp"
-#include "reference_gemm.hpp"
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.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/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_gemm.hpp"
 
 namespace ck {
 namespace tensor_operation {

profiler/include/profile_reduce_impl.hpp

 #pragma once
 
-#include "check_err.hpp"
-#include "device_reduce.hpp"
-#include "device_reduce_instance.hpp"
-#include "reduction_enums.hpp"
-#include "host_reduction.hpp"
-#include "host_common_util.hpp"
-#include "host_tensor_generator.hpp"
+#include "ck/utility/reduction_enums.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce.hpp"
+
+#include "ck/library/utility/check_err.hpp"
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp"
+#include "ck/library/host_tensor/device_memory.hpp"
+#include "ck/library/host_tensor/host_reduction.hpp"
+#include "ck/library/host_tensor/host_common_util.hpp"
+#include "ck/library/host_tensor/host_tensor_generator.hpp"
 
 namespace ck {
 namespace tensor_operation {

profiler/src/profile_batched_gemm.cpp

@@ -3,18 +3,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.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_batched_gemm_xdl.hpp"
-#include "profile_batched_gemm_impl.hpp"
+
+#include "profiler/include/profile_batched_gemm_impl.hpp"
 
 enum struct GemmMatrixLayout
 {

profiler/src/profile_batched_gemm_reduce.cpp

@@ -2,10 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
 
-#include "profile_batched_gemm_reduce_impl.hpp"
+#include "profiler/include/profile_batched_gemm_reduce_impl.hpp"
 
 int profile_batched_gemm_reduce(int argc, char* argv[])
 {

profiler/src/profile_conv_bwd_weight.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_conv_bwd_weight_impl.hpp"
+
+#include "profiler/include/profile_conv_bwd_weight_impl.hpp"
 
 enum struct ConvDataType
 {

profiler/src/profile_conv_fwd_bias_relu.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_conv_fwd_bias_relu_impl.hpp"
+
+#include "profiler/include/profile_conv_fwd_bias_relu_impl.hpp"
 
 enum struct ConvDataType
 {

profiler/src/profile_conv_fwd_bias_relu_add.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_conv_fwd_bias_relu_add_impl.hpp"
+
+#include "profiler/include/profile_conv_fwd_bias_relu_add_impl.hpp"
 
 enum struct ConvDataType
 {

profiler/src/profile_conv_fwd_bias_relu_atomic_add.cpp

-#include <iostream>
-#include <numeric>
-#include <initializer_list>
-#include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_conv_fwd_bias_relu_atomic_add_impl.hpp"
-
-enum struct ConvDataType
-{
-    F32_F32_F32, // 0
-    F16_F16_F16, // 1
-};
-
-enum struct ConvInputLayout
-{
-    NCHW, // 0
-    NHWC, // 1
-};
-
-enum struct ConvWeightLayout
-{
-    KCYX, // 0
-    KYXC, // 1
-};
-
-enum struct ConvOutputLayout
-{
-    NKHW, // 0
-    NHWK, // 1
-};
-
-int profile_conv_fwd_bias_relu_atomic_add(int argc, char* argv[])
-{
-    if(argc != 25)
-    {
-        printf("arg1: tensor operation (conv_fwd_bias_relu_atomic_add: "
-               "ForwardConvolution+Bias+ReLu+AtomicAdd)\n");
-        printf("arg2: data type (0: fp32; 1: fp16)\n");
-        printf("arg3: input tensor layout (0: NCHW; 1: NHWC)\n");
-        printf("arg4: weight tensor layout (0: KCYX; 1: KYXC)\n");
-        printf("arg5: output tensor layout (0: NKHW; 1: NHWK)\n");
-        printf("arg6: verification (0: no; 1: yes)\n");
-        printf("arg7: initialization (0: no init; 1: integer value; 2: decimal value)\n");
-        printf("arg8: print tensor value (0: no; 1: yes)\n");
-        printf("arg9: time kernel (0=n0, 1=yes)\n");
-        printf("arg10 to 24: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, "
-               "RightPx\n");
-        exit(1);
-    }
-
-    const auto data_type       = static_cast<ConvDataType>(std::stoi(argv[2]));
-    const auto in_layout       = static_cast<ConvInputLayout>(std::stoi(argv[3]));
-    const auto wei_layout      = static_cast<ConvWeightLayout>(std::stoi(argv[4]));
-    const auto out_layout      = static_cast<ConvOutputLayout>(std::stoi(argv[5]));
-    const bool do_verification = std::stoi(argv[6]);
-    const int init_method      = std::stoi(argv[7]);
-    const bool do_log          = std::stoi(argv[8]);
-    const bool time_kernel     = std::stoi(argv[9]);
-
-    const ck::index_t N  = std::stoi(argv[10]);
-    const ck::index_t K  = std::stoi(argv[11]);
-    const ck::index_t C  = std::stoi(argv[12]);
-    const ck::index_t Y  = std::stoi(argv[13]);
-    const ck::index_t X  = std::stoi(argv[14]);
-    const ck::index_t Hi = std::stoi(argv[15]);
-    const ck::index_t Wi = std::stoi(argv[16]);
-
-    const ck::index_t conv_stride_h   = std::stoi(argv[17]);
-    const ck::index_t conv_stride_w   = std::stoi(argv[18]);
-    const ck::index_t conv_dilation_h = std::stoi(argv[19]);
-    const ck::index_t conv_dilation_w = std::stoi(argv[20]);
-    const ck::index_t in_left_pad_h   = std::stoi(argv[21]);
-    const ck::index_t in_left_pad_w   = std::stoi(argv[22]);
-    const ck::index_t in_right_pad_h  = std::stoi(argv[23]);
-    const ck::index_t in_right_pad_w  = std::stoi(argv[24]);
-
-    const ck::index_t YEff = (Y - 1) * conv_dilation_h + 1;
-    const ck::index_t XEff = (X - 1) * conv_dilation_w + 1;
-
-    const ck::index_t Ho = (Hi + in_left_pad_h + in_right_pad_h - YEff) / conv_stride_h + 1;
-    const ck::index_t Wo = (Wi + in_left_pad_w + in_right_pad_w - XEff) / conv_stride_w + 1;
-
-    if(data_type == ConvDataType::F16_F16_F16 && in_layout == ConvInputLayout::NHWC &&
-       wei_layout == ConvWeightLayout::KYXC && out_layout == ConvOutputLayout::NHWK)
-    {
-        ck::profiler::profile_conv_fwd_bias_relu_atomic_add_impl<
-            2,
-            ck::half_t,
-            ck::half_t,
-            ck::half_t,
-            ck::tensor_layout::convolution::NHWC,
-            ck::tensor_layout::convolution::KYXC,
-            ck::tensor_layout::convolution::NHWK>(
-            do_verification,
-            init_method,
-            do_log,
-            time_kernel,
-            N,
-            K,
-            C,
-            std::vector<ck::index_t>{Hi, Wi},
-            std::vector<ck::index_t>{Y, X},
-            std::vector<ck::index_t>{Ho, Wo},
-            std::vector<ck::index_t>{conv_stride_h, conv_stride_w},
-            std::vector<ck::index_t>{conv_dilation_h, conv_dilation_w},
-            std::vector<ck::index_t>{in_left_pad_h, in_left_pad_w},
-            std::vector<ck::index_t>{in_right_pad_h, in_right_pad_w});
-    }
-    else
-    {
-        throw std::runtime_error("wrong! data_type & layout for this operator is not implemented");
-    }
-
-    return 0;
-}

profiler/src/profile_convnd_bwd_data.cpp

@@ -2,10 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
 
-#include "profile_convnd_bwd_data_impl.hpp"
+#include "profiler/include/profile_convnd_bwd_data_impl.hpp"
 
 namespace {
 

profiler/src/profile_convnd_fwd.cpp

@@ -4,13 +4,13 @@
 #include <memory>
 #include <string>
 #include <vector>
-#include <half.hpp>
 
-#include "conv_util.hpp"
-#include "element_wise_operation.hpp"
-#include "fill.hpp"
-#include "profile_convnd_fwd.hpp"
-#include "tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/library/utility/conv_util.hpp"
+#include "ck/library/utility/fill.hpp"
+
+#include "profiler/include/profile_convnd_fwd.hpp"
 
 namespace {
 

profiler/src/profile_gemm.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_gemm_impl.hpp"
+
+#include "profiler/include/profile_gemm_impl.hpp"
 
 enum struct GemmMatrixLayout
 {

profiler/src/profile_gemm_add_add_fastgelu.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
 
-#include "profile_gemm_add_add_fastgelu_impl.hpp"
+#include "profiler/include/profile_gemm_add_add_fastgelu_impl.hpp"
 
 int profile_gemm_add_add_fastgelu(int argc, char* argv[])
 {

profiler/src/profile_gemm_bias_2d.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_gemm_bias_2d_impl.hpp"
+
+#include "profiler/include/profile_gemm_bias_2d_impl.hpp"
 
 enum struct GemmMatrixLayout
 {

profiler/src/profile_gemm_bias_add_reduce.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_gemm_bias_add_reduce_impl.hpp"
+
+#include "profiler/include/profile_gemm_bias_add_reduce_impl.hpp"
 
 int profile_gemm_bias_add_reduce(int argc, char* argv[])
 {

profiler/src/profile_gemm_bias_relu.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_gemm_bias_relu_impl.hpp"
+
+#include "profiler/include/profile_gemm_bias_relu_impl.hpp"
 
 enum struct GemmMatrixLayout
 {

profiler/src/profile_gemm_bias_relu_add.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_gemm_bias_relu_add_impl.hpp"
+
+#include "profiler/include/profile_gemm_bias_relu_add_impl.hpp"
 
 enum struct GemmMatrixLayout
 {

profiler/src/profile_gemm_reduce.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_gemm_reduce_impl.hpp"
+
+#include "profiler/include/profile_gemm_reduce_impl.hpp"
 
 int profile_gemm_reduce(int argc, char* argv[])
 {

profiler/src/profile_grouped_gemm.cpp

@@ -2,9 +2,8 @@
 #include <numeric>
 #include <initializer_list>
 #include <cstdlib>
-#include <stdlib.h>
-#include <half.hpp>
-#include "profile_grouped_gemm_impl.hpp"
+
+#include "profiler/include/profile_grouped_gemm_impl.hpp"
 
 enum struct GemmMatrixLayout
 {

profiler/src/profile_reduce.cpp

@@ -6,11 +6,12 @@
 #include <sstream>
 #include <getopt.h>
 
-#include "data_type_enum.hpp"
-#include "reduction_enums.hpp"
+#include "ck/utility/reduction_enums.hpp"
 
-#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"
+#include "profiler/include/data_type_enum.hpp"
 
 using namespace std;